AMD Bulldozer News and Discussion

Well MSI has shown the AMD's latest Scorpius platform or 9XX series chipset for the upcoming AM3+ CPUs.
Check here
For detail information regarding the upcoming motherboards, check here

Nice piece of info. cilus. So they will support upcoming bulldozer and llano cores?

i wish they launch something like:
"change ur old AM3 mobo and cpu and get x% discount on AM3+ stuff"

^^

...nice sense of humour!!!
Don't we all want that!!!

Hey come on guys.......... I don't have any amd stuff. What will i do? :))

vickybat said:
Hey come on guys.......... I don't have any amd stuff. What will i do?

"change ur old ~~AM3~~ LGA1156 mobo and cpu and get x% discount on ~~AM3+~~ LGA1155 stuff" :-D

Piyush said:
i wish they launch something like:
"change ur old AM3 mobo and cpu and get x% discount on AM3+ stuff"

what will you call it? AMD summer bonanza? or Fusion Xchange offer?

A

^^bulldozer bargain

Sam.Shab said:
what will you call it? AMD summer bonanza? or Fusion Xchange offer?

Fusion Xchange Offer sounds more catchy

Piyush said:
Fusion Xchange Offer sounds more catchy

but it may have some ill effects. some super minds from Bhabha ARC may come there to Xchange their old Fission reactors for a new Fusion one :razz:

aby geek said:
^^bulldozer bargain

Change it to bulldozar bonanza....

So 9xx and Zambezi is going to compete with x78 and LGA 2011.

This is just great for us that the AM3+ mobos will be backward compatible with AM3 cpus.

@ cilus - thanks for sharing the news.

^^Zambezi will compete not only with socket 2011 but also 1155 sandybridge processors. Some more powerful 1155 cpu's are also due for launch and might show up in more than 4 cores avatar.

Zambezi has to be really good because it has two tough competitions to beat.

Early previews show 8 cores zambezi to be some 50% powerful than i7 950.
Source - This and This

Any news on the motherboard specification for am3+ because a lot has been talked about the zambezi processors but no critical detail about the motherboards such as
1.will it support pci-e 3.0(in the future,they are still supporting 2.0 duh)
2.will it have a usb 3.0 native support
3.overclocking potential
4.form factor
5.i hope the mobo/proccy combination doesnt cost a bomb.(price point)

as when intel was about to launch sb they had all the configs ready 3~4 months back.

vickybat said:
Early previews show 8 cores zambezi to be some 50% powerful than i7 950.
Source - This and This

Too good to be true.

One thing is certain this time around though. Am3+ boards + bulldozer cpu's won't be competing for value and definitely won't be cheap. They will fight with intel right through the top end.

Zambezi processors are going to be expensive.

If this time amd is able to bring the price point to current ph ii x6 top end level(12~15K) then the zambezi will be killer processor this year.
i'll get one right away if the price is right.
lets see at what price point mobos for am3+ are launched...a long wait(>3months).

^^ Thats highly unlikely dude. Zambezi will be much more expensive than current x6. Maybe more than 20k for the slowest processor and top end will exceed 30k or maybe more.

Amd themselves had said that this time around they will eye the top end market and wont play the value game anymore.

^^^ lets see dude amd has till now not mentioned the price point of zambezi lineup..they are first launching desktop processors in Q2 so lets hope for the best!
previously u mentioned they are competing against lga 2011 & lga 1155. so they will keep that in mind when selecting the price range.
then too if they are able keep below 18k price range wats the problem have fun.
still its too early to speculate.

Cool.. good thing about amd is that buyers can be sure that these mobos will support proccys for atleast another 3 yrs! unlike intel who believe in changing the processor sockets for breakfast lunch and dinner!

topgear said:
This is just great for us that the AM3+ mobos will be backward compatible with AM3 cpus.

does it mean that our athlon II/phenom II AM3 CPUs can be run on AM3+ boards?

^^ Yes.... you got that right

yipeeeee

but what will be featured in new boards?
i have gone through the articles yet

vickybat said:
^^ Thats highly unlikely dude. Zambezi will be much more expensive than current x6. Maybe more than 20k for the slowest processor and top end will exceed 30k or maybe more.

Amd themselves had said that this time around they will eye the top end market and wont play the value game anymore.

They haven't said this anywhere.

20K for a slowest Zambezi cpu wuld be just an overkill.

I think AMD will release some 10-15K Zambezi CPUs for sure to compete with SB cpus.

like i said before...8k+ will be sweet spot for zambezi cpu's for desktop.still its just a speculation theres still plenty of time.no site has even got any sample to provide any information,even linus techtips(youtube guy) has been reviewing just a result of a undisclosed amd processor 3.6 ghz 6mb cache.but its surely a am3 cpu.
how likely it will be that a 8-core cpu would be that helpful in day to day computing
however it will be more helpful in compression/decompression,animation/rendering.
i doubt that it will be useful in gaming because games hardly use 4 cores to the max.

^^ I can gurantee that zambezi 8 cores wont be anywhere near 8k. They will be much higher. It will cost $300 and upwards for the cheapest zambezi. Check THIS

Anyway, check more info on bulldozer here and here.

^^ buddy thanks for links.I'm still not convinced it will bring brilliant performance as compared to intel SB.For a gaming system it'll work but for real work it will be second to intel.and BTW i said 8k+ i meant the prices will be always greater then 8k.

it will be ~12k
guaranteed

^^

Piyush, its $300 for the slowest zambezi in US. In india, launch prices are going to be more than 15k for sure.

The stars based cores will be priced around 10 -12k imo.

stars based cores?
whats that?

successor of Zambezi or in short the Lynx platform if i am not wrong.

^^

No no stars is not successor of zambezi and is not even bulldozer. :grin:

Its the upcoming llano based fusion apu's which will have existing phenom 2 based dual & quadcores along with llano apu.Amd calls them stars.

Bulldozer based fusion apu's will launch next year.

^^ Nice way to put those phenom II chips in good use IMO.

BTW, I agree with you that 8 core Bulldozers will be priced around ~$300 for sure and if they can perform well AMD might be able hold the price point for long enough.

From Vicky bat:
"Piyush, its $300 for the slowest zambezi in US. In india, launch prices are going to be more than 15k for sure.

The stars based cores will be priced around 10 -12k imo. "

Can u explain from where did you get that information about zambezi prices?
It will be helpful if u provide that link.And what is stars based cores?
In India after the prices settle down,and a good stockup the prices of hardware are almost equal to the prices in US. so thats not a problem.for that u can check out the prices of 6-core amd lineup.

Hardly anyone can claim ANYTHING, I mean no one can talk anything about the prices. No one has a clue.

vickybat said:
^^

No no stars is not successor of zambezi and is not even bulldozer.

Its the upcoming llano based fusion apu's which will have existing phenom 2 based quadcores along with llano apu.Amd calls them stars.

Bulldozer based fusion apu's will launch next year.

won't they run hot. cause they'll be manufactured in 45nm node.

ico said:
Hardly anyone can claim ANYTHING, I mean no one can talk anything about the prices. No one has a clue.

It was mentioned in the xbit website in case you didn't notice. That was the clue. Check here Second paragraph last line.

Though prices can't be confirmed as of now, newer articles are leading that way. But its certain that an 8 core zambezi cpu won't come cheap cause they will be amd's true flagship this time and may have the power to topple intel's flagship at that time or atleast perform neck to neck.

Sam.Shab said:
won't they run hot. cause they'll be manufactured in 45nm node.

Well that won't be an issue imo. They would be 3rd generation stars and amd must have tweaked them a bit to incorporate the apu.

It will be seen after launch , how thermally cool stars based llano really is.

This news is not old but interesting about the amd am3+ zambezi are to be named after the flag ship models of 2003~2004 the "fx" series.Amd plans to rename it as the "Vision Black FX" for the 8-core and "Ultimate Vision FX" for the 6-core/4-core processors.
the whole topic could be read *internalcomputer.com/amd-resurrect...ulldozer-variants-as-vison-fx-series.computer

@ max_snyper

Thanks for the link buddy.Cleared some air giving us more clues.

M

@vickybat , u cann't tell the predicted zambezi, a 8core processors accurately.an integer and a core is not the same thing.we can tell them ,4moduled processor.
As two integer share same instruction fetch and hardware decoding and also their is only one shared floating point scheduler in one module.so, an integer and a core ,a lot difference.
And please note that, it is highly enhanced interconnection in bulldozer, that is expected to enhance the gme fps performance.

.
And also, as it is too early to predict the price, don't be so confident to tell those rumor price.

mohiuddin said:
@vickybat , u cann't tell the predicted zambezi, a 8core processors accurately.an integer and a core is not the same thing.we can tell them ,4moduled processor.
As two integer share same instruction fetch and hardware decoding and also their is only one shared floating point scheduler in one module.so, an integer and a core ,a lot difference.
And please note that, it is highly enhanced interconnection in bulldozer, that is expected to enhance the gme fps performance..
And also, as it is too early to predict the price, don't be so confident to tell those rumor price.

Zambezi is an eight core processor and thats how amd will market them and not as 4 modules. Amd in the design level addresses two cores as a single module.And a processor not only computes integers but also floating point instructions.

AMD is addressing a dual core design as a single module which can work on two threads separately and not like smt.They share multiple resources like fetch, decode, floating point scheduler and integer point scheduler which are separate entities in a dual core. Amd claims this to achieve 80% of the performance of a true dual core.

This design will give more performance per watt but by what degree has to be seen. In this design, they are more biased towards integer math performance due to two integer scheduler in a module.

Neverthless, amd will still call its single module as two cores and will market them as such. And for the price, its definitely not gonna come cheap this time.

i think AMD did it right. Intel have Hyper Threading & most noobs (a few of my friends who thinks they know a lot about computing) counts the virtual cores into the total number of cores. so AMD countered with modules. but how will these processors fight the Intel i7 army on single threaded apps? i hope these ship with Turbo Core 2.0

M

vickybat said:
Zambezi is an eight core processor and thats how amd will market them and not as 4 modules. Amd in the design level addresses two cores as a single module.And a processor not only computes integers but also floating point instructions.

AMD is addressing a dual core design as a single module which can work on two threads separately and not like smt.They share multiple resources like fetch, decode, floating point scheduler and integer point scheduler which are separate entities in a dual core. Amd claims this to achieve 80% of the performance of a true dual core.

This design will give more performance per watt but by what degree has to be seen. In this design, they are more biased towards integer math performance due to two integer scheduler in a module.

Neverthless, amd will still call its single module as two cores and will market them as such. And for the price, its definitely not gonna come cheap this time.

your post proves that an integer and cpu, not same..yea, amd gonna selling it as 8core.but, still,same fact.in accurate they r not that cores.
Whatever, just hoping for a good fight.

Mohiuddin, I'll explain you this in a much simpler way which is completely my interpretation and it might be wrong too.

Think like this. 2 normal cores are taking 2 sq. units of area or 1 core is taking 1 sq. unit of area. [die size]

1 bulldozer module or 2 bulldozer cores are taking only something around 1.2 sq. units (arbitrary) of die size and still performing 80% of a standard 2 core.

Now limit the die size to 10 sq. units. You get 10 standard cores whereas in Bulldozer, you get 10/0.6 = 16.66 bulldozer cores.

If 10 standard cores get 10 marks on some benchmark, 16.66 bulldozer cores will get 0.8*16.66 = 13.33.

[just a simple interpretation]

*images.anandtech.com/reviews/cpu/amd/hotchips2010/bulldozerefficient.jpg
^ this thing actually says that compared to a single core, a bulldozer module aka two bulldozer cores only take 12% more die size. [information in the box] (the first bulleted statement is sort of incorrectly framed, I think)

And here's why it is their answer to hyperthreading.
*media.bestofmicro.com/bulldozer-bobcat-hot-chips,L-M-258682-13.jpg
By just adding mere 12% more and sharing resources, they are achieving 80% performance of a dual core. Whereas in HyperThreading, performance gains are only 10-20%.

nice explanation. but i think the 1st bullet point is true. take the whole module size at 100sq units & so adding the 2nd integer core increased the module size by 12% i.e. total size now is 112 eq units. now if size of each circuitry is 1sq unit (LET) than the total extra circuitry needed is indeed 12sq unit more. cause size directly proportional to the amount of circuits used.

& lastly i hope AMD at least don't follow Intel's footstep of locking their chips. at least not the clock generator.

See, you are saying what I have said.

AMD provides two cores in 1.12 sq units which perform 80% of standard two cores in 2 sq units. If you read the statement in the first point and in the box, you'll find the first point "sort of" incorrectly framed.

"Amount of circuitry needed for a second integer core is only 12% of the total module"

Replace the word "module" with "single core", then it makes sense to me because AMD never really called "single core" as "single module" before in their lives. Just poor choice of words though. I'm just being picky.

They should have said it rather this way:

"Amount of circuitry needed for a second integer core is only 12% of today's single core giving us a module."

I'm just criticizing their choice of words, nothing else.

J

good informative post...
die efficiency is another aspect of chip design. like amd's cpus at the moment suck compared to intel. i hope bulldozer turns out to be their "core" architecture and does to Intel what Intel did to them 4 years ago.

for eg, HD 6970 is like 73% of gtx 580. so, gtx 580 should naturally be faster. profit margins for amd are still hight. having said, gtx 470/80 series were complete failures. They were as big as gtx 580, so you can see.

ico said:
See, you are saying what I have said.

AMD provides two cores in 1.12 sq units which perform 80% of standard two cores in 2 sq units. If you read the statement in the first point and in the box, you'll find the first point "sort of" incorrectly framed.

"Amount of circuitry needed for a second integer core is only 12% of the total module"

Replace the word "module" with "single core", then it makes sense to me because AMD never really called "single core" as "single module" before in their lives. Just poor choice of words though. I'm just being picky.

They should have said it rather this way:

"Amount of circuitry needed for a second integer core is only 12% of today's single core giving us a module."

I'm just criticizing their choice of words, nothing else.

yes. you corrected the term technically but i think the choice of using words that doesn't highlight the complete scenario was deliberate.

cause if AMD says they added a 2nd core by using just 12% more circuitry, most may start saying that their platform is slow or weak even before it enters the market.

M

ico said:
Replace the word "module" with "single core", then it makes sense to me because AMD never really called "single core" as "single module" before in their lives. Just poor choice of words though.

thats a great poin of view.

...
and thats what i was talking about.
we can tell modules a super-threaded core

..as there is much hardware dedication unlike those disgusting-chemoflexing hyperthreading in intel-cpus.

bulldozer ftw.lets bulldoze intels' sandy bridge and also ivy bridge

^^ Well buddy its not that easy to bulldoze sandybridge, the upcoming socket 2011 and ivy bridge. But if that happens it will be a major win for amd since its k8 architecture. And i am sure there's much more with upcoming intel cpu's than hyperthreading.

Remember that the sandybridge cpu's launched are mid to low end parts. They are even competing and beating intel's previous flagship i.e i7 980x gulftown.

And intel is completely silent about socket 2011 as of now.

Early previews from xbit labs suggest that zambezi 8 core processor is around 50% faster than an i7 950 and the thubans. So beating intels new highend and to be launched 6 and 8 core sandybridge cpu's is going to be an extremely tough job.

But amd cannot be counted out at all and has the potential for a strong showing.

Bulldozer has an excellent design taking power efficiency to a new level and is more biased towards integer operations rather than floating point operations.

>>There is a lot of gaga going on the 8-core zambezi from couple week has any body got the news on the 6-core,4-core processors that are going to be launched at the same day as the 8-core?
Are they going to follow the same architecture of the zambezi like the module with two cores or same architechture as the thuban?
Its a gamble for AMD this time on the 8-core architecture,i hope amd gets all the betting right this time(ps. icing on the cake would be lower price on the 8-core for us.lets hope it happens.)

^^ The fusion apu's will have a thuban like architecture for the cpu and amd calls them stars.

But zambezi based quads and hex cores when launched will be bulldozers i.e the above architecture discussed.

But that lower price thingy is highly unlikely imo. So lets see what happens.

If lower price is unlikely, then it only translates into excellent performance.

Yeah thats for sure bulldozer based cpu's will perform brilliantly and they have to in order to take the fight to intel's high end.

I'm also hoping for it. Wish those times will come back when AMD released their 1st 64 bit processors, Athlon 64 bit 3000+.

^^ their first 64 bit cpu were Athlon FX-51 and Athlon 64 3200+

Still no word about the zambezi 6-core,4-core proccy's on the internet.If they are gonna be based on the same architecture as the 8-core.then how they are gonna perform against any of the sb 4 core proccys.as amd said its a module 80% performance of the real dual core architecture.If they perform as their old ph ii x6 architecture,then only difference would be new memory support 1800+ mhz.though it will be good buy as something new but it will be as same as their old counter parts.
yes im little interested in how will x6 zambezi perform in real world.i hope that amd has taken note of the current intel snb lineup.i wrong move and amd will get seriously bashing from snb(my concerns only regarding the x6 and x4 lineup).
As for the x8 its gonna rock....not for most of the people but some enthusiast for whom budget is not a issue.
ps.any news for x6 x4 zambezi is appreciated.

^^ you have actually missed everything which I talked about.

They are performing 80% while taking approximately 45% less die space. Read everything which I wrote carefully. AMD can easily compensate for the 20% performance loss by adding more of these modules.

What I'm expecting to see is AMD offering a 4-module processor against a 4-core Intel hyper-threaded processor.

^^i was just curious about what if they could not perform as expected..more than 8-core im anxious to know more about the 6-core that will be economical for desktop users.
and dude why would amd increase core count just to compensate losses,they have already decided to go with 4-6-8 cores(read 2-3-4 modules).For the 4 module architecture i'm eagerly waitin for its real world performance..it is surely gonna rock.
till then we all have to keep our hopes up.
any news for x6 x4 zambezi is still appreciated.
thank you.

PC Perspective - Bulldozer at ISSCC 2011 - The Future of AMD Processors

AMD to Showcase Bulldozer Microprocessors at CeBIT Trade-Show - X-bit labs

---------- Post added at 08:23 AM ---------- Previous post was at 08:22 AM ----------

AMD to showcase Bulldozer at CeBit

here's a little bit about mobos :

MSI and ASRock Present AM3 Bulldozer Motherboards Powered by AMD 800-series Chipsets - Softpedia

beautiful mobos TP. and that msi one shows shipping in april :-D

. and rumors say bulldozer compatible with existing am3. :-D

. cant wait :-D

.
and amd is presenting bulldozer at same place tp: cebit. but when??

R

I just hope we dont end up with low clock Bulls...

^Intel Core i9 hopefully :-D

offtopic: ^^in that case look at saswat23's signature. 100 cores and 400 threadings. imagine if ever it will be available for the price of athlon...... lol

Nah, given AMD's history, I think we will be lucky if the Bulldozer can match the Nehalem in performance. I don't see it surpassing Sandy Bridge..

AMD has always caught up to the previous Gen of Intel CPUs for a while now.. I don't see that trend changing anytime soon.

R

rchi84 said:
Nah, given AMD's history, I think we will be lucky if the Bulldozer can match the Nehalem in performance. I don't see it surpassing Sandy Bridge..

AMD has always caught up to the previous Gen of Intel CPUs for a while now.. I don't see that trend changing anytime soon.

Only if we could actually understand what those architecture charts actually meant, would we be even in a position to comment. We simply cant say that just because AMD has not done it before, they can't do it.

Lets just keep our fingers crossed

AMD Bulldozer, Llano launch dates leaked

The release dates for AMD Bulldozer and
Llano appear to have ended up being leaked
to a Turkish trade mag.
The mag is claiming that Bulldozer will be in
the shops in June 20 and Llano will be ready
in July. AMD UK estimates Llano won't be
available until September, last time we talked
to them, at Distree in Monaco.
The information is attributed to industrial
sources which probably means a supplier
spilt the beans.
The Turkish site has found a leaked slide
and quotes information gathered by
"industrial sources," and various reports are
indicating that AMD plans to launch its
upcoming high-end desktop Bulldozer CPUs
sometime during the week of June 20,
2011.
Looking at it all it
would appear that
Bulldozer will arrive in
quad-core, six-core and eight-core variants
using the FX handle. There will be two
FX4000-series chips, two will be FX6000-
series chips and four will be FX8000s.
Four processors are expected to appear in
Q2 2011 while the other four are planned
for the last quarter.
The Llano A-Series APUs will appear in two-
core, three-core and quad-core flavours just
when the US is celebrating its illegal French-
backed coup against its lawful King. More
than eleven Llamo APUs will be released
throughout the year.
The slides give us a two year view of what
AMD has planned. It looks like over the next
two years all three Llano APUs will support
1,600 MHz DDR3 memory at 45W.
"BeaverCreek" and "WinterPark" integrated
DirectX 11 GPUs will be shoved under the
bonnet.
Llano will be aimed at the mainstream and
performance markets during 2011 whereas
the Zacate will go into the essential market
and Ontario will head for the sub-12-inch
markets respectively.
If the world does not end in 2012, Trinity,
Richland, Wichita will be released to target
the essential, mainstream and performance
markets. A Krishna APU will target the
sub-12-inch devices probably by riding a
horse and killing off sinners with a bow.

J

i wish bulldozer edges sandy bridge in performance.

it will definitely not make a joke of it like athlon 64 vs pentium 4.

[X-bit] Four AMD Bulldozer Chips Incoming: Details Revealed

The initial family of AMD's FX-series microprocessors based on Bulldozer micro-architecture will include four models with eight, six or four cores and 95W or 125W thermal design power (TDP).

The first breed of AMD FX8000, FX6000 and FX4000 currently known under Zambezi code-name will completely support all the advantages that the Bulldozer micro-architecture is supposed to bring, including new Flex FP floating point processing unit. The new chips in maximum eight-core configurations are projected - by AMD's internal documents - to offer roughly 50% performance improvement over Phenom II-series microprocessors in multimedia applications.

*i236.photobucket.com/albums/ff148/Bloodlust28/Forum%20Images/amdbulldozer.png

Source

lets see what exclusive features it brings to the table. in todays world, high clock speed isn't of any use (without a proper efficient architecture).

Source: AMD Zambezi Based FX CPUs Box-Art Leaked > CPUs > Techtree.com

*images.techtree.com/ttimages/story/114779_1.jpg

@ALL: We Indians are very keen when it comes to getting free stuff and exchange bonanzas

And the way you people are bargaining about the upcoming prices of AMD proccys, I strongly believe that AMD has to have a counselling with you people before fixing their price.
:+1:

[XBIT] AMD Aims to Fight Core i7 “Sandy Bridge” with Bulldozer

*www.xbitlabs.com/cms/include/image.php?src=/images/news/2011-03/amd-pos.png&width=550&height=456&cache=1&quality=75&aspect=0&format=png

Among the advantages that are mentioned by the AMD documents that X-bit labs has happened to see are “more overclocked cores”, “more cores dual graphics, OpenCL and GPU” compute and others. By the end of the year the firm expects over 10% of its desktop products to be based on the Bulldozer micro-architecture and be in the AM3+ form-factor.

AMD Orochi design is the company's next-generation processor for high-end desktop (Zambezi) and server (Valencia) markets. The chip will feature eight processing engines, but since it is based on Bulldozer micro-architecture, those cores will be packed into four modules. Every module which will have two independent integer cores (that will share fetch, decode and L2 functionality) with dedicated schedulers, one "Flex FP" floating point unit with two 128-bit FMAC pipes with one FP scheduler. The chip will have shared L3 cache, new dual-channel DDR3 memory controller and will use HyperTransport 3.1 bus. The Zambezi chips will use new AM3+ form-factor and will require brand new platforms.

Source

pauldmps said:
Source: AMD Zambezi Based FX CPUs Box-Art Leaked > CPUs > Techtree.com

*images.techtree.com/ttimages/story/114779_1.jpg

wow man these boxes look real cool. sandy bridge boxes look crap in front of it.

FX will be back! :razz:

---------- Post added at 09:04 PM ---------- Previous post was at 08:56 PM ----------

moreover these 4 are just initial breed.
more will come after that which will be more powerful.

^ Yeah, the number of proccys that will come out will make buying components a HUGE task..

all thats left is some flashy AMD ads. without ads, Indian ppls will believe AMD to be another Chinese chip making company.

If you meet any Intel fanboys anywhere, just tell them that Sandy Bridge is an amd64 processor. :mrgreen:

Had it not been for amd64, we wouldn't have been able to enjoy 32-bit applications without any performance penalty.

ico said:
If you meet any Intel fanboys anywhere, just tell them that Sandy Bridge is an amd64 processor. Had it not been for amd64, we wouldn't have been able to enjoy 32-bit applications without any performance penalty.

really! you mean all 64-bit proccys are amd64 architecture?

utkarsh009 said:
really! you mean all 64-bit proccys are amd64 architecture?

well, Intel developed x86 instruction set which was pre-dominantly used in 16-bit and 32-bit processors by both Intel and AMD.

Then Intel developed a 64-bit processor named "Itanium" which used IA-64 architecture. This was incompatible with old x86 instruction sets which would mean 32-bit applications would have been "emulated" with performance penalty if we wanted to run them. AMD didn't like this.

So, what AMD did, they extended x86 to x86-64 aka amd64 which is a 64-bit architecture backwards compatible with x86 (32-bit) and released Athlon 64. Now we all know Athlon 64 was a huge success and made Pentium 4 look like a joke. And the good thing was, you could run 32-bit OS/softwares on it without any performance penalty and you could also run 64-bit OS/softwares too.

Intel had to give in and instead of using Itanium's IA-64, they implemented x86-64/amd64 with minor changes in Core 2 and called it EM64T/Intel 64.

So, basically this is the reason why you can use Windows 7 32-bit on your Core i3, i5 and i7 processors despite they're 64-bit processors. You can't do this with Itanium processors.

^^nice piece of info dude!

^^ and those kind of people still believe that AMD CPU has heating issues - what an epic misconception ;-)

@ pauldmps - nice post - I really liked those box arts - they are even more good looking than windows 7 box arts and those reminds us of legendary FX series ;-)

K

yeah bro graphics on boxes are killer. Boxes are like this then inside them will be a legend. I think now amd will show intel earth after launching of bulldozer.

Why cant AMD or Intel develop a universal socket? That will save us all from repeatedly upgrading our mobos

^^ really wish there exist an universal socket.

@all, Amd's 8 core price is shown to be 700$+ & it is up against a 250-300$ Core i7 2600. typo?

Sam said:
@all, Amd's 8 core price is shown to be 700$+ & it is up against a 250-300$ Core i7 2600. typo?

They've actually written "System price" in that pic.

i think universal socket is possible by 2013-14, if AMD & Intel integrate SB onto processor die. this looks possible in <20nm architecture.

lordirecto said:
Why cant AMD or Intel develop a universal socket? That will save us all from repeatedly upgrading our mobos

actually un logoke dimag me yeh :idea:

batti nahi jali :grin:

'idea' ke SIM bhej do, jal jayegi!!

J

it wont be possible cuz the future is fusion.

^^yah "its amazing technology"

K

may be amd's fusion will fuse amd and intel

kamal_saran said:
may be amd's fusion will fuse amd and intel

yeah why not
i was just thinking we should ask China to give our Tibet back

haha...this thread owns!!!

K

we can't get back tibet from china. But we can fuse china and india together

^^
yeah,,lol
pakistan will help us in fusing us both

ico said:
They've actually written "System price" in that pic.

oh damn. my bad. should have paid more attention to the pics. thanks for pointing out

but still 1 doubt remains: the 8core processor will be: 4X2 modules or 8X2 modules?

masterkd said:
actually un logoke dimag me yeh batti nahi jali
'idea' ke SIM bhej do, jal jayegi!!

sammy 4 modules.

Sam said:
but still 1 doubt remains: the 8core processor will be: 4X2 modules or 8X2 modules?

4 modules. 4*2 cores.

Piyush said:
^^
yeah,,lol
pakistan will help us in fusing us both

You are forgetting Bangladesh!!

ico said:
4 modules. 4*2 cores.

Jaskanwar Singh said:
sammy 4 modules.

cool way to increase cores. i hope Core Turbo 2 or whatever they call it shuts down the core instead of clocking it down, else these may again fail in single threaded apps.

lordirecto said:
Why cant AMD or Intel develop a universal socket? That will save us all from repeatedly upgrading our mobos

That's a novel concept but it it's implemented board partners will be pissed ;-)

^ Since it has not been implemented, it is us who are getting pissed through out our life.

Some good news coming.

Asustek to Support Future AMD FX "Bulldozer" Chips on Current Mainboards - X-bit labs

^^ good news for the old guys that feel their processor (K10.5) is already aged & needs an upgrade. but it'll surely have more than 1 limitations.

here's a little bit more and the price is just awesome ;-)

ASRock AM3 Bulldozer Motherboard Gets Listed in Japan - Softpedia

^^ IF they are avaliable in India around april and priced similarly to japan then surely gone buy this board....
BTW In cebit 2011 all the manufactures told tha the 8xx series chipset will have full support to the bulldozers when they are launched,Its better to buy tested mobo now with a quad and upgrade later to bulldozers.
The only missing link here is hypertransport 3.1 (6400mhz),as all the 8xx series support hypertransport 3.0,the other features are the same.

But they tell only about 8series AM3 boards.What about 785G AM3 ? Will there be any BD's to support in my board with limited features?

K

so is it good that if i buy a 880 series mobo then i can later upgrade it with bulldozer or llano apu's

hey guys see this

X-bit labs has a (pretty massive) scoop of AMD info to share with us this week, as it has put together the above chart detailing what it expects the company's APU roadmap will look like for the remainder of the year. Published a couple of days ago, this data has now been partially corroborated by the snoops over at DigiTimes, who confirm a couple of the model names and agree that AMD is planning an initial Q3 rollout of five Llano chips, to be followed by even more processors coming in Q4 of 2011. Llano represents AMD's play for the performance crown, coming as it does with dual- or quad-core processing units, DirectX 11-capable Radeon HD 6000-series graphics, and a dual-channel DDR3 memory controller, all bundled up inside the same warm and toasty package. More E-series APUs for power-conscious users are also said to be on the cards, and AMD itself should be making these plans official at Computex in Taipei come early June. It's a bit of a wait, but we've got a feeling it'll be worth it. Source : X-bit labs

ajai5777 said:
But they tell only about 8series AM3 boards.What about 785G AM3 ? Will there be any BD's to support in my board with limited features?

I'm also interested to know about this though my guess is mobo manufacturers will release some bios update to support bulldozers.

It seems like you all are forgetting that there is a chipset that Intel is going to release in early April, called Z68. Makes me wonder if it is going to be a overkill of sorts against AMD.

max_snyper said:
In cebit 2011 all the manufactures told tha the 8xx series chipset will have full support to the bulldozers when they are launched

they told? till AMD themselves doesn't open their mouth, can't take manufacturer's word seriously. though it looks possible. after all its electronics. can be implemented in different ways.

a common example is no ACC on 8series chipsets. but manufacturers released their own core unlockers. if 8series supports Llano (wish 78X & 79X too) it'll shut the mouth of critics for good & hopefully for a long time.

lordirecto said:
It seems like you all are forgetting that there is a chipset that Intel is going to release in early April, called Z68. Makes me wonder if it is going to be a overkill of sorts against AMD.

AMD 9XX vs Intel Z68? can they be compared? direct comparison is not possible & shouldn't be compared until AMD releases or confirms details on their Llano chips & their chipsets. even then, its better to compare platform wise, not individual parts.

^^ There is no news from the amd side,but its upto the manufacturers what and how they want to implement...gigabyte,asrock,msi and somewhat asus have changed their proccy socket from am3 to am3+ on their current lineup of 8-series motherboards.
Guyz with the old chipsets(7xx series) u all are missing the fact that the bulldozer processors have 1 pin more that makes these processor incompatible with am3 sockets...
unless the manufacturers comeup with a release of mobos (7xx series) with am3+ socket.

The only difference between 9xx series mobos and current 8xx series mobos
1.hyper link transport 3.1 present in 9xx series mobos.(not much of the difference as against hyper transport 3.0)
2.uefi bios.
3.better communication between north bridge and following chipset.
4.As for the memory controller its in the processors now-a-days.. ;-)

IMO its better to invest in established technology then to believe in upcoming such as the p67/h67 sata problem.
what a user of amd platform can do is get these 8 series boards,invest in a good hex/quad core processors, as bulldozers establish themselves he can change it to 6~8 core bulldozer later. quite a good upgrade path.

PS. launch date for 8 series motherboards with am3+ socket is in april by most of the manufacturers.Good for people buying amd systems at that point of time.

^ Early adoption has its own benefits as well as pitfalls. Let me point out that established technology will get outdated faster than the upcoming technology. So choose if you want a future proof computer or not. The end decision is yours as the computer belongs to you.

^^ Its not necessary that upcoming technology will always outdate establish technology...and BTW in terms of technology nothing is "future proof"....technology is and always be evolving...it was just i was suggesting a upgrade path for the users who will buy their pc in month of april/may..they cannot wait any longer...coz bulldozer will take time to reach our shores and top of that it will take time for prices to settle down in India...somewhere down to q3~q4 of this year.

IMO, no matter what AMD comes up with Intel will always have an upper hand(performance wise). Only things that can save AMD are fanboys and pricing.

slashragnarok said:
IMO, no matter what AMD comes up with Intel will always have an upper hand(performance wise). Only things that can save AMD are fanboys and pricing.

what was the case of Intel before 2006 i.e. before Core 2 came in?? what was the state of nVidia before from 2008 to late-2010?? ATi before 38xx?? All it takes is a successful redesign and things can get back on track.

@max: True to some extent. But the end decision lies with the buyer. Neither you nor me can make people do what we want to.

@ico: True, I am really hoping that AMD will get the upperhand this time, atleast in India

slashragnarok said:
IMO, no matter what AMD comes up with Intel will always have an upper hand(performance wise). Only things that can save AMD are fanboys and pricing.

Your views are completely biased and seems like you don't know much about pc hardwares ( history ) anyway ;-)

@slashragnarok, duh, who have better price/performance ratio, who rocks in entry level and mid range scenario, and who developed amd64!!

^woohoo...... AMD rocksss......

K

now this thread becomes bulldozer news discussion to upcoming intel vs. Amd's apu's

^ Why would you want that??

R

ico said:
4 modules. 4*2 cores.

Depends on how you define a core, anyways, yea, more or less 2 core/module

How I wish they would come out a month earlier, parents will be in the US in mid may, darn bulldozer coming out mid june. :-x

lordirecto said:
True, I am really hoping that AMD will get the upperhand this time, atleast in India

the end fight is really like Nokia vs the rest. ppls here just know Nokia & SE are the best & should buy it. rest (HTC, Samsung, Motorola, LG, etc) are Chinese. same in case of processor. some even told AMD is a local/chinese processor & will blow up after sometime.

Sam said:
the end fight is really like Nokia vs the rest. ppls here just know Nokia & SE are the best & should buy it. rest (HTC, Samsung, Motorola, LG, etc) are Chinese. same in case of processor. some even told AMD is a local/chinese processor & will blow up after sometime.

WT*? one of my friend says "hamko symbian accha lagta hai" just because it comes with nokia.

did you all see the joke of the year which i posted? let me post it again:
on asking one of the assemblers in ranchi about bringing the athlon II X4 635 proccy this is what he replied, " yeh kaun sa processor hai? intel ka toh nahi lagta hai jarur celeron ka hoga!!!!!!" lolzzz......

K

utkarsh009 said:
WT*? one of my friend says "hamko symbian accha lagta hai" just because it comes with nokia.

did you all see the joke of the year which i posted? let me post it again:
on asking one of the assemblers in ranchi about bringing the athlon II X4 635 proccy this is what he replied, " yeh kaun sa processor hai? intel ka toh nahi lagta hai jarur celeron ka hoga!!!!!!" lolzzz......

most funnist joke i ever heard about pc's :rofl:

utkarsh009 said:
WT*? one of my friend says "hamko symbian accha lagta hai" just because it comes with nokia.

did you all see the joke of the year which i posted? let me post it again:
on asking one of the assemblers in ranchi about bringing the athlon II X4 635 proccy this is what he replied, " yeh kaun sa processor hai? intel ka toh nahi lagta hai jarur celeron ka hoga!!!!!!" lolzzz......

I'm just wondering what he would he call a sempron then - manufacturer of SB cpus ;-)

All right, it's time to be on-topic now.

Asus Claims Certain Boards AM3+ Compatible, Says Zilch About Bulldozer - HotHardware

my question is
will the existing 785g 760g 790 series Mobos be compatible too?
cause there's not much difference between 8 and 7 series, are there?

funkysourav said:
my question is
will the existing 785g 760g 790 series Mobos be compatible too?
cause there's not much difference between 8 and 7 series, are there?

They might be and might not be. No official word. So, better not have any expectations.

Read the article (and comments) which I posted above.

Bulldozer/AM3+ will have one extra pin. So, if you want to use Bulldozer in your present AM3 motherboard, it *might* work after you remove the pin. But consider it unsupported. And motherboard manufacturers will have to release BIOS updates too.

*img862.imageshack.us/img862/7514/am3vsam3plus.jpg

^^
lol
remove the pin?!?!?
really??

am3+ boards -
GIGABYTE - Motherboard - Socket AM3 - GA-890GPA-UD3H (rev. 3.1)
GIGABYTE - Motherboard - Socket AM3 - GA-890FXA-UD5 (rev. 3.1)

these are revision 3.1 of previous am3 boards.

See, if that pin is a "dead pin" in AM3+ processors which AMD has included only to differentiate from AM3, then AM3+ processors might work in AM3.

AM2+ processors with 2 dead pins removed still work in AM2+ sockets. (the ones which differentiate it from AM3)

Jaskanwar Singh said:
am3+ boards -
GIGABYTE - Motherboard - Socket AM3 - GA-890GPA-UD3H (rev. 3.1)
GIGABYTE - Motherboard - Socket AM3 - GA-890FXA-UD5 (rev. 3.1)

these are revision 3.1 of previous am3 boards.

You see that these revised boards have a black colour socket which tells you that the socket is AM3+.

*www.gigabyte.com/fileupload/product/2/3785/4029_big.jpg

*www.gigabyte.com/fileupload/product/2/3756/3894_big.jpg

ico said:
All right, it's time to be on-topic now.

Asus Claims Certain Boards AM3+ Compatible, Says Zilch About Bulldozer - HotHardware

That link is not mentioning bulldozer chip based on am3+ socket clearly..may be asus is refering to just am3+ based boards probably next phenom series based on am3+ and not bulldozer..

bhushan05d251 said:
That link is not mentioning bulldozer chip based on am3+ socket clearly..may be asus is refering to just am3+ based boards probably next phenom series based on am3+ and not bulldozer..

Phenom II will work on AM3+ motherboards without any problem. There will not be any next Phenom series.

Bulldozer is an AM3+ processor and has one extra pin. You can't fit it in AM3 motherboards unless you mess around with that pin.

It *might* work in AM3 motherboards. We'll know in June.

hmmm lets c..

M fan of amd nw..wasn't aware of terms like bulldozer like u all experts are before a week as m planning to upgrade system to amd..so visiting relevant posts n threads continuously n curiously..thanx to all...

I think amd's time has come..amd will capture major market share near future..and intel will have to struggle just like the way what happened with nokia's symbian smartphones against android n ios...

R

i dont trust that news.....AMD themselves said bulldozer will not be supported on AM3.....but if, it is true, it will be awesome for all of us

^ How come not supporting is awesome for all of us? Or am i missing something?

When I bought my 785G board, I boasted to my friends (who use intel) that AMD wont change sockets regularly so that it can even support future processors.But it looks like its ended with phenom II X6.

Will I be able to put a BD in it ? or else its going to be a Phenom II X6.

K

hey guys found this while surfing . It says that asus will give bios update to some of it's current mobo's to be compatible with am3+ processors
*techpowerup.com/img/11-03-15/92a.jpg

thats really nice
wish MSI/Gigabyte too follow this trend

kamal_saran said:
hey guys found this while surfing . It says that asus will give bios update to some of it's current mobo's to be compatible with am3+ processors
*techpowerup.com/img/11-03-15/92a.jpg

See, again the point is - Asus is bringing out revised motherboards with AM3+ socket and offering BIOS updates for older versions with AM3 socket.

But to plug in Bulldozer in AM3 socket, you'll have to take care of that extra processor pin.

Sam said:
a common example is no ACC on 8series chipsets. but manufacturers released their own core unlockers. if 8series supports Llano (wish 78X & 79X too) it'll shut the mouth of critics for good & hopefully for a long time.

Unlikely imho. Llano will be using a new socket named FM1 as it would need extra pin contacts for the built-in GPU.

K

@piyush ,i hope so . . . . . .

Why asus is not mentioning about that extra pin socket?? If they would have mentioned about pin socket, the things could have been more specific till now..

ico said:
Bulldozer/AM3+ will have one extra pin. So, if you want to use Bulldozer in your present AM3 motherboard, it *might* work after you remove the pin. But consider it unsupported. And motherboard manufacturers will have to release BIOS updates too.

ico said:
See, if that pin is a "dead pin" in AM3+ processors which AMD has included only to differentiate from AM3, then AM3+ processors might work in AM3.

WTH. remove a pin from a new processor? thats too much. some may try it out but considering the risk, its not worth it. never will be.

lordirecto said:
^ How come not supporting is awesome for all of us? Or am i missing something?

he mean the otherway round. awesome if it supports. read again.

kamal_saran said:
hey guys found this while surfing . It says that asus will give bios update to some of it's current mobo's to be compatible with am3+ processors

better they mail a plier to remove that pin.

bhushan05d251 said:
Why asus is not mentioning about that extra pin socket?? If they would have mentioned about pin socket, the things could have been more specific till now..

they'll. before launch. 3 months left till June. so, theres time.

Sam said:
WTH. remove a pin from a new processor? thats too much. some may try it out but considering the risk, its not worth it. never will be.

well, AM2+ processors had two less pins than AM3 processors. Tom's hardware tried breaking two pins and plugging the AM2+ processor in an AM3 board. As expected, it didn't work in the AM3 board. (lack of DDR3 controller)

But still, it worked fine without those pins in the AM2+ board just like it should.

@ kamal_saran - thanks for the list - I'm very happy to see 7xx series is supported ;-)

K

@topgear , you are welcome

Old 7xx series isnt supported, they will launch new 7xx series with AM3+ support.If there are no BD's for old 7xx series, I wont suggest an AMD to anyone.If they are switching sockets like this, there is no nood to go for under performing AMD's

Actually AMD's were never better than Intel, Their price to performance ratio and socket compatibility were the advantages, and the later is already gone.

ajai5777 said:
Old 7xx series isnt supported, they will launch new 7xx series with AM3+ support.If there are no BD's for old 7xx series, I wont suggest an AMD to anyone.If they are switching sockets like this, there is no nood to go for under performing AMD's

They have been giving you an upgrade path since 3 generations. It is completely fair if they have to change their socket to compete with Intel.

And yes, I still expect Bulldozer to work if you break that pin and your motherboard manufacturer offers you a BIOS upgrade.

Atleast they have still given you an upgrade path. Get a new AM3+ motherboard this summer (your Phenom/Athlon will work) and get Bulldozer after one year. You still have an upgrade path.

ajai5777 said:
Actually AMD's were never better than Intel, Their price to performance ratio and socket compatibility were the advantages, and the later is already gone.

Forgotten about Athlon XP and 64?

I upgraded from GF615M P33 to 785G.There is no way I am changing my motherboard soon.If there is no BD for my board, I'll be satisfied with 1090T later.

by the way, found a different thing here

To support its claims, AMD has always pointed at the different pin layouts of the two sockets, as AM3+ has one extra pin that makes inserting Bulldozer/Zambezi CPUs in AM3 motherboards impossible.

However, sources cited by the Sweclcokers website claim that the extra pin available on the socket isn't present on Zambezi processors, so the pin layout is identical to that of an ordinary AM3 CPU.

As a result, these can be installed inside regular AM3 boards and all that is required is a BIOS update so that the new processors will be recognized by the board.

From Asus' entire lineup of AM3 motherboards, the company said that only six models are compatible with AMD's upcoming processors, including the company's high-end Crosshair IV Formula and Crosshair IV models.

According to the same website, the limitation could be imposed by the fact that AM3+ CPUs place a higher power demand on the board than their AM3 counterparts.

Source

If its true, no need to remove the extra pin and I wont mind trying 3rd party BIOS update if its not officially supported ;-)

R

^thats awesome news....

Wish AMD makes up for the disadvantage of upgrade path on current generation motherboards with good performance that can take on sandy bridge

K

@ajai bro . Thanx for info.

[Phoronix] AMD Bulldozer Dual-Interlagos Benchmarks On Linux

Lately we have been talking a lot about Intel's latest Sandy Bridge processors under Linux due to their very competitive performance and interesting graphics abilities, but on the AMD side there has not been too much to talk about. On the low-end there is the intriguing Fusion APUs, but on the high-end they don't have an answer to Sandy Bridge until delivering their new "Bulldozer" products closer to the summer. Fortunately, we have the first Linux scoop and performance benchmarks from engineering samples of their 16-core Interlagos server chip.

Source

They have a link where you can dynamically compare. They said though the 8-core Xeon's are better in some tests.

Gaurav Bhattacharjee said:
They have a link where you can dynamically compare. They said though the 8-core Xeon's are better in some tests.

8-core Xeons _will_ be better. But Bulldozer gives you potent 8 cores in approximately 50% less die space compared to Xeon. And with the same die-size of Xeon, Bulldozer will give you 16-cores. That's the whole point of this architecture.

What AMD will be doing is, pitting their 4 modules against Intel's 4 cores i.e. 8 cores vs 4 cores from the price point of view.

M

^yea, thats the main advantage.and don't forget aggressive core clock setting mechanism. It will help for less threaded applications.

any latest news about am3+ support?? gigabyte is showing am3+ support on their site on 890 chipsets..but they haven't mentioned "bulldozer" specifically in d supported processors' list...

bhushan05d251 said:
any latest news about am3+ support?? gigabyte is showing am3+ support on their site on 890 chipsets..but they haven't mentioned "bulldozer" specifically in d supported processors' list...

bulldozer is am3+ socket proccy. they'll update the list when BD actually comes out.

look at this:AMD Wants to “Bulldozer” Intel’s Sandy Bridge | Overclockers now comment on which (out of amd and intel) would be a better choice once BD comes out.

If this happens, I would be so happy. Intel's had a free run on the performance front for way too long now. We need some competition. Just like Australia losing in the WC makes for an exciting final

AMD v. Intel - Wikipedia, the free encyclopedia dark side of intel??????

hey guyz this is just in!!!!!!!!!!!!
specs of flagship bulldozer model fx-8150p black edition:::::::::::::::

CPU-core::::::8
Clock speed::::4.2 GHz
Turbo Core max::::4.7 GHz
L2-cache:::::::8MB
L3-cache:::::::8MB
TDP:::::::::::::140W
Memory contrl::1866 MHz
Black Edition::yes, unlocked multiplier
Socket::::::::::AM3+
Manufacturing::32nm SOI

this i got it from nordichardware not on the english website,the swedish one.
the only part was missing in specification was clock speed and turbo,if its true as given, then its real deal though it may be costly but its worthed.

Exclusive: AMD is investing in excess of 4 GHz with AMD FX-8150P Black Edition

wow - that's some awesome stock speed and AMD just made a new record in the cpu world - by releasing first ever cpu passing 4GHz mark ;-)

show this to vickybat who considers amd to be an underdog!!!!!!

OMG..I badly need any of them to be supported in my board.

gr8..m gonna purchase am3+ board with athlon or phenom..n after a year when prices of bulldozer will drop, will look for it..but no idea of how much the prices will drop after year.. :-(

4Ghz stock speed? WOW :shock:

Wow! 4 ghz stock speed! amazing :shock:

Must be an awesome performer.

utkarsh009 said:
show this to vickybat who considers amd to be an underdog!!!!!!

Amd is still an underdog when compared to intel's sales and revenue. But that does not mean amd cannot release good products.

I am not against amd but always with the side that performs better. Intel has been dominating since "conroe" and its never looking back since. If bulldozer beats sandybridge(socket 2011), then it will indeed be a big victory for amd.

See the whole picture before posting.

umm
i don't think clock speeds do equate to real world performance(i7 920 vs pII X4 1090)
we have to wait and watch for real world benchmarks

^^ yep,that's true but a8 core cpu with 4.2 Ghz stock ( 4.7 Ghz with TB ) has great potential I think but as you have said some benches in the future will make everything crystal clear ;-)

and to what amount we can oc on air cooling. maybe 5.8-6ghz :razz:

thetechfreak said:
I still feel this proccy will just TEAR apart the top end Sandy Bridge i7's.

may. if it cost ~50k, it better do it or else SB will take the fight to AMD's camp.

thetechfreak said:
AMD should take turbo mode even higher to 5 ghz.

future revisions should. but whats more important is how efficient. for now it looks good on paper only.

Jaskanwar Singh said:
and to what amount we can oc on air cooling. maybe 5.8-6ghz

thetechfreak said:
This proccy is going to be an Overclockers DREAM!!!

depends how much OC headroom is left on these processors. as you can see, PII 965 @ 3.4Ghz somehow was able to get past 4Ghz or barely missed 4Ghz mark.

[TheReg]AMD gases up Bulldozers for Intel push back

Advanced Micro Devices is in a number of tight spots at the moment, but the company is hopefully optimistic that its future "Bulldozer" Opteron processors due later this year will let it dig in and grab some desperately needed - and profitable - server market share from archrival Intel.

The first Bulldozer Opteron chips, the 16-core "Interlagos" processors, are still on track for production in the second quarter with a formal launch sometime in the third quarter, Vlad Rozanovich, director of the enterprise and public sector business at AMD, tells El Reg. These chips will be used in servers with two or four processor sockets and will plug into existing machines that use the G34 socket and that currently sport the 12-core "Magny-Cours" Opteron 6100s.

Source

max_snyper said:
Memory contrl::1866

Does that mean it will support main memory with 1866MHz onwards?? If yes then what about old motherboards which are running on lesser frequency already and will need to be available for bulldozer through bios update??

^^ max default ram speed support. for current AMD AM3 board it is 1333Mhz. for SB it is 1333Mhz but old I7 9** its 1066Mhz.

Sam said:
^^ max default ram speed support. for current AMD AM3 board it is 1333Mhz. for SB it is 1333Mhz but old I7 9** its 1066Mhz.

Sorry but not satisfied with ur answer..phenom n athlon r running on am3 even with 1600 frequency of ram..that is why dual channel kits over 1333 are available with supported motherboard na??..n sb proccys might be running over 2000mhz of ram support for sure i guess though haven't experienced it..

^^dude what hes trying to say is previous generation amd proccy had 1333mhz memory controller speed as memory controller is inbuilt the processor now-a-days.
higher speed memory had to be overclocked to run at their prescribed speed from motherboard bios settings.
amd bulldozer will have 1866mhz memory controller in built so that memory with 1866 mhz native speed run but higher than that speed memory will have to be overclocked in mobo bios setting.
*(here overclock means tweaking memory controller speed higher then its prescribed speed)
now u get it.

ok..now i got it..u need to oc MEMORY CONTROLLER to match the speed of higher speed memory right?? but what about lower memory speed?? ..if m using am3 proccy like phenom on 880 or 890 chipset with 1333 memory supported and if i put bulldozer into same mobo and update bios so that proccy should be worked on am3 board..now bulldozer will have 1866 memory controller..so will that 1333 ram stick work with it?? Or will i able to oc tht memory (AFAIK u cann't oc Memory stick but a controller Or will i need to buy memory with higher frequency like 1866 and onwards..?? Got the question??

@bhushan

Please go through this:

*en.wikipedia.org/wiki/Athlon_64#NX_bit

@bhushan
1. u got it wrong...proccy with current generation have memory controller with speed of 1333mhz supported,any memory higher than that will work on default speed of the controller (1333mhz)....u have to tweak bios setting to set the speed of memory that works on higher speeds.
2.in case of amd bulldozer cpu,they have 1866mhz memory controller inbuilt...that means any memory with speed upto 1866mhz will work without any issues with the proccy.
3. there will be no issue with the motherboard compatibility with the memories coz....memories are tied up with proccessors not north bridge as earlier it use to be.
*Bios update for bulldozer proccy will also include all the compatibility between the processors and the motherboard..so no issues with memories.
I think this will clear your doubt.

max,
thanks dude..cleared ur bulldozer n motherboard compatiblity wala point..that means memory with lower speed (1333 or 1600) will have no issue with bulldozer (1866)

Now again new stupid question arose here.. :-D

(extremely sorry for troubling all of u..but need to clear my base)

In ur 1st point u said, proccy with current generation have memory controller with speed of 1333MHz..that means any memory higher than that (like 1600) will run on default speed of the controller (1333) by tweaking bios..that means memory with higher speed (like 1600) than the default speed of controller (1333) won't work at it's actual speed (1600) (assuming here)..so what's the point in buying memory with a speed higher than default speed of controller..??

bhushan05d251 said:
In ur 1st point u said, proccy with current generation have memory controller with speed of 1333MHz..that means any memory higher than that (like 1600) will run on default speed of the controller (1333)

yes. it'll. how fast you use, it'll get clocked down.

bhushan05d251 said:
by tweaking bios..

for what cause?

bhushan05d251 said:
that means memory with higher speed (like 1600) than the default speed of controller (1333) won't work at it's actual speed (1600) (assuming here)..so what's the point in buying memory with a speed higher than default speed of controller..??

will work if you are ready to overclock the processor. though you can achieve higher memory clocks simply by tweaking BIOS or retain original speed (if it was 1333Mhz) by lowering memory multiplier/increasing CPU clock multiplier.

bhushan05d251 said:
Now again new stupid question arose here.. (extremely sorry for troubling all of u..but need to clear my base)

after reading you problem, all i can say is your question was indeed stupid. but i hope this was the last from you :smile:

we have update..check this:
AMD confirms they will support bulldozer on AM3+

Sam said:
after reading you problem, all i can say is your question was indeed stupid. but i hope this was the last from you

LOL

thanx all of u anyways..

[Softpedia] AMD's FX-Series Bulldozer Processors to Launch on June 7, Rumors Say

The release date of AMD's upcoming desktop Zambezi processors, based on the Bulldozer architecture, has been the target of many debates in the last couple of months and these tend to continue as a recently leaked slide seems to suggest that the first FX-series CPUs will be launched on June 7.

Source

^^ that's really

TFS

BTW, anybody has some rumors about prices ??

K

it will be total loot if bulldozer sells like 7k for four cores.

assuming it competes with intel i5 2*** series

^^ It won't come that cheap but won't be expensive as well. Amd is always known for pricing things right. Bulldozer is going to be a performance part this time around and won't be playing the value game.

a 7k, 4core BD chip against a i5 2300/2400. but its still 3months away. so Intel can very easily do a 50$ pricecut & will go head on with AMD. AMD must offer good on-die graphics. that can run modern demanding games with ease. else, its trouble for AMD again.

if AMD at least can offer i3 2100's performance but the graphics power of HD5570 within 7-7.5k it'll be gameover for the i3's. at least till ivy bridge comes to the rescue.

[Softpedia] AMD to Release More Desktop Bulldozer Processors in October-November

*img.donanimhaber.com//images/haber/26064/AMD_Bulldozer_FX_2011rdmp_dh_fx57.jpg

In early Q4 2011, these first Bulldozer CPUs will be joined by four other Zambezi FX processors and Donanim Haber states that the release will closely resemble the initial launch, since AMD plans to introduce two eight-core, one six-core, and one quad-core processor.

Sadly, no other specifications are available at this time, but these CPUs will most probably feature improved operating frequencies to counter Intel's Sandy Bridge-E chips that are also expected to arrive in Q4 2011.

Source

Sam said:
a 7k, 4core BD chip against a i5 2300/2400. but its still 3months away. so Intel can very easily do a 50$ pricecut & will go head on with AMD. AMD must offer good on-die graphics. that can run modern demanding games with ease. else, its trouble for AMD again.

if AMD at least can offer i3 2100's performance but the graphics power of HD5570 within 7-7.5k it'll be gameover for the i3's. at least till ivy bridge comes to the rescue.

Well you are getting confused again buddy.Bulldozer won't have any on-die graphics when launched. The battle will be for ultimate processing power. Llano will have 400 sp's based apu's but will be based on phenom 2 architecture instead of bulldozer. When bulldozer based fusion cpu's will arrive, intel will challenge them with ivybridge which has dx11 graphics, more eu's and multimonitor support.

But i think this on-die graphics won't be a decider because gamers and enthusiasts will always go for a discrete gpu.

The processing and number crunching power is what that matters and surely be a decider.

vickybat said:
Well you are getting confused again buddy.Bulldozer won't have any on-die graphics when launched. The battle will be for ultimate processing power. Llano will have 400 sp's based apu's but will be based on phenom 2 architecture instead of bulldozer. When bulldozer based fusion cpu's will arrive, intel will challenge them with ivybridge which has dx11 graphics, more eu's and multimonitor support.

yup. i meant it for the llano parts that will be launched in 3 months time

vickybat said:
But i think this on-die graphics won't be a decider because gamers and enthusiasts will always go for a discrete gpu.

won't there be any entrylevel bulldozer based proccy with on-die graphics? its simply like replacing the Phenom-II die with a Bulldozer die keeping the mGPU intact.

vickybat said:
The processing and number crunching power is what that matters and surely be a decider.

we gonna have a busy year ahead i feel.

Sam said:
won't there be any entrylevel bulldozer based proccy with on-die graphics? its simply like replacing the Phenom-II die with a Bulldozer die keeping the mGPU intact.

Next year. Currently, Bulldozer is on-board graphics.

ico said:
Next year. Currently, Bulldozer is on-board graphics.

thats what i asked. Bulldozer 2.0 may have it. cause existing K10.5 architecture will ultimately be replaced by bulldozer.

^^ Yes, next year, bulldozer will have fusion apu's. But that won't matter because as i said earlier, discrete graphics will still rule the hearts of multimedia enthusiasts. Pure number crunching performance is all that matters and bulldozer won't dissapoint i hope.

but budget processor have to exist. not everyone can afford a 10k proccy + 15-20k GPU :smile:

^ they will exists along with budget gfx cards under 4-5k range ;-)

what about the socket of next year on-die gfx bulldozer?? Will am3+ (including bios update for current am3) still remain or will it be replaced by am4?

Am3+ is a bridge socket which is designed to support the future AMD processors like Bulldozer while retaining backward compatibility with the current AM3 processors and it is officially confirmed by AMD.

However, whether current AM3 motherboards will support Future AMD processors is splely dependent upon the motherboard manufacturer. Asus and Gigabyte have confirmed that after a BIOS update their motherboards are gonna support Bulldozer processors. But this is yet to be confirmed by other manufacturers like MSI, Biostar or ECS.

A

AMD released info that with 33% more cores (X6's 6 to BD's 8) they achieved a total performance increase of about 50% or about 10-15% more speed compared to current X6's at the same clock.

IMO BD will at best be able to compare with Intel, but it is far from beating it, especially in single threaded apps. But even with multicore apps, at best they will be able to tie or win by an unnoticeable margin.

A

whatever AMD achieves in BULLDOZER beating or going near to sandybridge , one thing is sure , their CPUs will always best bang for the bucks

akrr said:
whatever AMD achieves in BULLDOZER beating or going near to sandybridge , one thing is sure , their CPUs will always best bang for the bucks

can't say for sure. if AMD is able to beat Intel (highly unlikely) then they'll surely price their highend chips at ridiculously high price like 60-70k.

^^ winner always makes the decision ;-)

BTW, I think we going to see some real tough copetetion in cpu market on the upcomiung months and at the end of trhe day we will benifit from this and have more processing power than ever in desktop pcs.

[Softpedia] AMD 900-Series Chipset Required for Bulldozer Power Gating Technology

AMD's upcoming 900-series motherboard chipsets, that the company plans to launch together with its Zamabezi FX processors based on the Bulldozer architecture, will feature an improved power management technology which should decrease the energy consumption of AMD's future CPUs.

Source

AMD is again proving their excellent support for the existing customers. ASUS and Gigabyte has already announced their AM3 mobos is gonna support Bulldozer. Today I've found out that with a BIOS update, my mobo is also gonna support AM3+ processors.

R

i dont get it, how will you get the extra pin with the BIOS update lol...

AFAIK, newer revisions have the new socket,will support AM3+....??

AMD has officially announced that their Zambezi will retain compatibility with AM3 socket. Check the Wikipedia link. ASUS, Gigabyte and MSI have already confirmed that their 8XX series mobos are gonna support AM3+ CPUs. Check their sites also.
I've downloaded the latest BIOS V1.40 which enables compatibility of AM3+ processors in my 890GXM-G65. Obviously they will not support the full feature set of AM3+ processors.

Actually you will still have to mess around with that extra pin in AM3+ CPUs to make them fit in the AM3 socket.

That pin is actually nothing more than a compatibility pin perhaps, not related to the circuit.

^^AMD has neither denied nor accepted the compatibility issue with the am3+ procesors and 8xx series chipset.
Its just the chipset manufacturers are boasting compatibility from thier side,they have just released am3+ socket 8xx series motherboards. ASUS,GIGABYTE,ASROCK these are the companies that will release shortly 8xx series am3+ socket motherboard.
MSI is still relying on bios update(IMO it will not help in case of am3 socket boards.)
you still need to take care of the 1 extra pin...it might be related to the circuitry such as temp sensor,power management,memory controller etc.
Its still risky to run am3+ proccy on the am3 motherboard.
Its fine if the 8xx series motherboard has a am3+ socket to support zambezi.
Doing R & D on the costly proccy is not a good thing to do
We have to still wait for AMD for the conformation about am3 mobo and am3+ proccy compatibility.

R

Cilus said:
AMD has officially announced that their Zambezi will retain compatibility with AM3 socket. Check the Wikipedia link. ASUS, Gigabyte and MSI have already confirmed that their 8XX series mobos are gonna support AM3+ CPUs. Check their sites also.
I've downloaded the latest BIOS V1.40 which enables compatibility of AM3+ processors in my 890GXM-G65. Obviously they will not support the full feature set of AM3+ processors.

guess so....lets wait and see..

can we expect some AM3+ chips with 1 less pin which can readily be used with both AM3 as well as AM3+ boards?

Sam said:
can we expect some AM3+ chips with 1 less pin which can readily be used with both AM3 as well as AM3+ boards?

Beats the point of having a new socket. AM3 chips (Phenom II) can be used in both AM3 and AM3+ motherboards.

ico said:
Beats the point of having a new socket. AM3 chips (Phenom II) can be used in both AM3 and AM3+ motherboards.

2nd part i know but yes. i better stop banging my head on these AM3+ chips. waiting for an official announcement.

Have a look at this

4.1Ghz Turbo on a hexa core :shock:

now only they should make the pricing right.

^^ you'll be amazed more ;-)

see this link : *www.thinkdigit.com/forum/1363813-post168.html - posted by ico

AMD FX-8150P will debut with a clock speed of 4.2 GHz and Turbo Core technology good for over 4.7 GHz.

Does that feels good or great ;-)

it feels awesome.i am waiting to see its real power,lots of hope is there on bulldozer.if it performs as expected then i think Intel will be having tough time for their sandy bridge.

^^let sandy bridge e and ivy bridge release... ;-)

^^ I agree, because AMD is always been superior in the pricing. So if a Bulldozer can even perform very closely to Intel's Sandy Bridge E processors and provide more competitive price point, they will be sold like nothing....even they don't need to beat the Sandy Bridge in performance.

^^but right now looking at the news it seems that bulldozer will surely beat sandy bridge but don't know any thing about sandy bridge e and ivy bridge due to lack of knowledge.but still amd will surely continue to modify their processor in the mean time till the release of ivy bridge.and link in one of the above post also says that amd is trying to make their processors future proof.so lets hope for the best.
i think amd also should think about giving publicity and advertisement to their products,their products need good marketing in this field which intel is too brilliant.

^^true...intel leads in marketing too...i haven't seen any advertising of amd solutions on television yet lol...because of this, many people in india still don't know about amd processors...it has been a definition like "computer = intel"..."kaunsa computer liya? = intel ka" :-D

...and about the above 4 GHz news...intel never concentrated on frequency...rather they produced best resulting chips on their superior architecture only...this is the only area of concern for amd...they always concentrated on clock rates...

bhushan05d251 said:
^^true...intel leads in marketing too...i haven't seen any advertising of amd solutions on television yet lol...because of this, many people in india still don't know about amd processors...it has been a definition like "computer = intel"..."kaunsa computer liya? = intel ka" ...and about the above 4 GHz news...intel never concentrated on frequency...rather they produced best resulting chips on their superior architecture only...this is the only area of concern for amd...they always concentrated on clock rates...

man you need to study history

bhushan05d251 said:
^^true...intel leads in marketing too...i haven't seen any advertising of amd solutions on television yet lol...because of this, many people in india still don't know about amd processors...it has been a definition like "computer = intel"..."kaunsa computer liya? = intel ka" ...and about the above 4 GHz news...intel never concentrated on frequency...rather they produced best resulting chips on their superior architecture only...this is the only area of concern for amd...they always concentrated on clock rates...

their marketing strategy is a most stupid act i've ever seen
they misguide poor consumers by irrelevant info on their ads

lol....AMD have to follow intel?!?!?! :lol:

dont forget it was intel who was left stunned when AMD launched their 64 bit proccys

@jas,

^^yup i may be wrong as m not so expert...but as far as i know and after seeing many benchmarks, i can say that...quad core sandy bridge at stock frequency beats OCed phenom hexa core in many aspects...isn't it?? And why digit experts suggesting sandy bridge config over amd...people prefer i5 2500k instead phenom ii x6 1100 at same price...u also have been suggesting na.aren't u? :-D

Piyush said:
lol....AMD have to follow intel?!?!?!
dont forget it was intel who was left stunned when AMD launched their 64 bit proccys

yeah point..

^^Phenom was made by tweaking the same architecture but bulldozer is a new architecture.bulldozer is in news not only because of its speed but mainly because of its architecture design.

^^yup...lets hope amd will deliver performance up to mark with this new architecture...

bhushan05d251 said:
.intel never concentrated on frequency...rather they produced best resulting chips on their superior architecture only...this is the only area of concern for amd...they always concentrated on clock rates...

Athlon 64 3000+ @ 1.9 Ghz was better than Pentium 4 @ 3.0Ghz.

The fact that clock speed doesn't matter, architecture matters was proven by AMD, not Intel.

sukesh1090 said:
it feels awesome.i am waiting to see its real power,lots of hope is there on bulldozer.if it performs as expected then i think Intel will be having tough time for their sandy bridge.

better yet SLI is also coming for AMD again with AMD’s 990FX, 990X and 970 chipsets and those must have support CF anyway - so bulldozer users can go with any multi gpu setup they want ;-)

sukesh1090 said:
don't know any thing about sandy bridge e and ivy bridge due to lack of knowledge

read these two threads ;-)

*www.thinkdigit.com/forum/cpu-motherboards/139831-intel-sandy-bridge-e-lga2011-discussion.html

*www.thinkdigit.com/forum/cpu-motherboards/139267-intel-ivy-bridge-discussion.html

thank you for the links topgear.so overclocking is the main advantage of sb e processors and i think it won't be a much headache for amd as they got black editions for oc and ivy bridge have got features like 22nm where amd has to work out a lot and direct x 11 2nd generation hd graphics card which i think amd already have.
so,sb e processor i think is not a big rival for bulldozer but ivy bridge can be.performance wise bulldozer gonna rock the only thing amd has to do is good marketing and advertisements.then only a lot of people come to know that there is also another company in the world which produces quality processors and can go head to head with intel.

topgear said:
^^ you'll be amazed more

see this link : *www.thinkdigit.com/forum/1363813-post168.html - posted by ico

Does that feels good or great

thats terrific speed on paper. but in real life, it'll be interesting to know. surely it'll cost a bomb but thats ok if it is able to dethrone Core i7 990X.

bhushan05d251 said:
i haven't seen any advertising of amd solutions on television yet lol

^^ yep, 4.7 Ghz with TB is some serious speed for a cpu ( factory clocked ) but as you have said we have to see some benchmark to know how it really performs with it's rivals.

Some benchmark projections:-

AMD FX Series and A Series First Performance Projections Surface | techPowerUp

*www.techpowerup.com/img/11-05-04/20a.jpg

*www.techpowerup.com/img/11-05-04/20b.jpg

Here's the original link in turkish:-

Ä°ÅŸte AMD'nin 8 Ã§ekirdekli Bulldozer FX iÅŸlemcisi iÃ§in test sonuÃ§larÄ±

looks like an allrounder. hope the final results will be better than this.

^^ Looks like cpu score is on par with 2600k. I don't know if it can keep up with the upcoming sandybridge-E processors.
But fx8130p is going to be one heck of a competitor for sure. The added sli support in the fx platform sweetens the deal even more.

Yeah, finally it looks like AMD can at least match Intel. That will be a very good news for customers.

i7 2600k running on onboard graphics? vs FX 8core with discrete graphics (i know FX got no ondie GPU)? what kind of comparison is this? if they want to show real comparison, provide 2 slide: A6 vs i7 2600k & FX 8-core with a fast GPU vs i7 2600K with the same GPU. then we can talk about performance.

& A4 still slower than entry level i3? thats bad. now only if the A4's come within 3-4k.

Yeah, A4 results are disappointing. But take these figures with a pinch of salt. The final results may actually vary.

no, A4 doesn't disappoint. It still has superior on-die graphics than Core i3-2100 for budget gamers and according to AMD's positioning, it does fine. You can see AMD's positioning below:

*i.imgur.com/cI8Xi.png

Sam said:
i7 2600k running on onboard graphics? vs FX 8core with discrete graphics (i know FX got no ondie GPU)? what kind of comparison is this? if they want to show real comparison, provide 2 slide: A6 vs i7 2600k & FX 8-core with a fast GPU vs i7 2600K with the same GPU. then we can talk about performance.

Just compare the PCMARK Vantage part of the graph.

Lastly, these graphs are rubbish.

WoW! $700 CPu to compete with core i7 26xx and core i5 25xx - that's very steep ! but I'm sure thety will lower the price once it released

It is the "System Price"

Ok, got

but thanks for pointing it out.

ico said:
You can see AMD's positioning below:

*i.imgur.com/cI8Xi.png

this graph is better. the last price chart posted shows the E-series APU competing against the Pentum which they don't stand a chance against. & FX going over i7s.

ico said:
Lastly, these graphs are rubbish.

PS: someone don't sleep.

are those the benchmark results of bulldozer?then why not only processor benchmarks than adding gfx card along with it.if we get only processor ones i think then only we will be able to say which one is better bulldozer or sandy bridge.

Sam said:
i7 2600k running on onboard graphics? vs FX 8core with discrete graphics (i know FX got no ondie GPU)? what kind of comparison is this? if they want to show real comparison, provide 2 slide: A6 vs i7 2600k & FX 8-core with a fast GPU vs i7 2600K with the same GPU. then we can talk about performance.

& A4 still slower than entry level i3? thats bad. now only if the A4's come within 3-4k.

Totally agree...firstly, the comparison has disappointed me..discrete gpu added just with bulldozer and not with sandy bridge..and when we see cpu benchmarks in that graph, 8 core bulldozer just slightly outperforms quad core 8 threaded sandy bridge...some more benchmarks should be come to make statement of either side...

Some ASUS 900 series mobo specifications:-

*www.rumorpedia.net/wp-content/uploads/2011/05/asusam3r2.jpg

things are looking better & better by the days for AMD :smile:

wasn't the news like this: 900-series naively support some 1866Mhz DDR3 ram? if yes, then why the "OC" against the ram speed in the Crosshair V board?

L

Will the current AM3 mobo really support this new line of processors? Am thinking about upgrading so am really confuse at this point, should i just wait? Which i really don't want to. And how long would it take for it to launch in India?

J

lalam said:
Will the current AM3 mobo really support this new line of processors? Am thinking about upgrading so am really confuse at this point, should i just wait? Which i really don't want to. And how long would it take for it to launch in India?

refer to the previous pages on this thread. we had a long discussion on this.

*i1-news.softpedia-static.com/images/news2/AMD-Llano-and-Bulldozer-Pricing-Revealed-Report-3.jpg

Halle luuiahhh

Is the TDP of FX6110 & FX4110 correct?

Skud said:
Is the TDP of FX6110 & FX4110 correct?

Should have been 95W imo...but as the proverbial saying goes 'take all leaks with ample helpings of salt'

If these are the actual prices though, Intel will only be too happy to sit tight on pricing :pullhair:

mukherjee said:
*i1-news.softpedia-static.com/images/news2/AMD-Llano-and-Bulldozer-Pricing-Revealed-Report-3.jpg

Halle luuiahhh

mention the source from next time ;-)

AMD Llano and Bulldozer Pricing Revealed â€“ Report - Softpedia

Looking at the price - they have to pack some serious performance under the hood to compete with intel SB cpus.

BTW, that FX4110 has 3.4 Ghz stock clock speed ( rumored ) - looking forward to some benchmark to see how far it can be OCed and what kind of performance it would provide compared to rival SB cpus.

topgear said:
mention the source from next time

AMD Llano and Bulldozer Pricing Revealed â€“ Report - Softpedia

Looking at the price - they have to pack some serious performance under the hood to compete with intel SB cpus.

BTW, that FX4110 has 3.4 Ghz stock clock speed ( rumored ) - looking forward to some benchmark to see how far it can be OCed and what kind of performance it would provide compared to rival SB cpus.

oops my bad...sorry, I got so carried away,I didnt post the link...

Hoping the FX-8310P would be better than i7-2600K. At 16K it will be simply irresistible.

Skud said:
Hoping the FX-8310P would be better than i7-2600K. At 16K it will be simply irresistible.

U mean the FX 8130P!

Well,if it atleast matches the Core i7 2600K...that will be enough for now...price will surely go down...

oh... silly me!!! I think with 8 physical cores it has to be better than i7 in multi-threaded apps.

J

*wccftech.com/wp-content/uploads/2011/05/11112694.jpg

L

OMG!!! It's so much cheaper than i ever thought it would be, talking about Zambezi. I hope it is backward compatible.

@ joker

Please kindly mention the source. I think you got it from here:-
AMD Bulldozer (Zambezi-FX) CPU Performance Exposed, Beats i7 2600K in CineBench Benchmark

If this holds true then some exciting times are ahead of us.

N

AMD FX-8130P – 8 Core, 3.8Ghz, Max T.C 4.2Ghz, 125W (320$)
AMD FX-8110 – 8 Core, 3.6Ghz, Max T.C 4.0Ghz, 95W (290$)
AMD FX-6110 – 6 Core, Unknown, Max T.C Unknown, 95W (240$)
AMD FX-4110 – 4 Core, Unknown, Max T.C Unknown, 95W (190$)

Read more: AMD Bulldozer (Zambezi-FX) Specifications Leaked by Asus

Bulldozer FX clockspeeds leaked

So far so good. If everything goes right, next year I'll be in for some huge upgrades. :razz:

The fx 8130p will surely beat i7 2600k . Atleast that's my speculation. But it will be no match for sandybridge- E processors for socket 2011.

Let's wait and see how far my predictions stand correct.

Skud said:
So far so good. If everything goes right, next year I'll be in for some huge upgrades.

vickybat said:
The fx 8130p will surely beat i7 2600k . Atleast that's my speculation. But it will be no match for sandybridge- E processors for socket 2011.

Let's wait and see how far my predictions stand correct.

Lets see

vickybat said:
The fx 8130p will surely beat i7 2600k . Atleast that's my speculation. But it will be no match for sandybridge- E processors for socket 2011.

i7 2600k + a highend GPU vs FX8130p (AMD can't find any better name) + a highend GPU. now guess who'll trump whom?

Another Bulldozer sucker punch : courtesy AMD....

AMD Bulldozer Retail Availability Postponed to Q3 2011 – Report

Does AMD want to sell or not?

mukherjee said:
Another Bulldozer sucker punch : courtesy AMD....

AMD Bulldozer Retail Availability Postponed to Q3 2011 – Report

Does AMD want to sell or not?

AFAIR, ATI used to be famous for paper launches. Maybe AMD has got the same disease now.

baccilus said:
AFAIR, ATI used to be famous for paper launches. Maybe AMD has got the same disease now.

May all bad things happen to AMD...I was counting on Bulldozer

mukherjee said:
May all bad things happen to AMD...I was counting on Bulldozer

I still wish it to be a huge success. Intel needs some real competition or their pricing is going to get worse and worse. My guess is that Bulldozer is not performing as well as AMD was hoping and they are trying to improve it's performance before they ship it. Or maybe they are just trying to upscale production since this is their first chip with the new architecture.

baccilus said:
I still wish it to be a huge success. Intel needs some real competition or their pricing is going to get worse and worse. My guess is that Bulldozer is not performing as well as AMD was hoping and they are trying to improve it's performance before they ship it. Or maybe they are just trying to upscale production since this is their first chip with the new architecture.

Or maybe they are plain frightened of their inadequacies in the eve of Sandybridge E launch??

Come on AMD ...we need you to make Intel see reason to price their proccys right!!!

baccilus said:
AFAIR, ATI used to be famous for paper launches. Maybe AMD has got the same disease now.

But after AMD take over ATi that disease have been greatly cured. Almost zero paper launches these days as far as Radeons are concerned. The chipsets are ready, mobos have been pictured, so what's stopping them? But then Q3 starts from July 1, so may not be too late.

On second thought, are they planning to take Sandy Bridge-E head on? Are they going to be that good?

Skud said:
On second thought, are they planning to take Sandy Bridge-E head on? Are they going to be that good?

I was thinking that too. May be it is so awesome that they just want to compete against Sandy Bridge-E.

baccilus said:
I was thinking that too. May be it is so awesome that they just want to compete against Sandy Bridge-E.

Maybe they want to save the blushes??!!! Nobody knows...Wait wait and wait some more...

I think I'm posting these too late
but still have look if you haven't already

AMD ''Interlagos'' Bulldozer Benchmarks Leaked

more new CPUs coming into the family ;-)

The new processors would include Four new FX processors, As detailed in the roadmap Engineering samples are already available so we can expect a few benchmarks to come up shortly. Production would start in August 2011 while Retail availability is expected in Q3 2011. This could also mean that the Launch for the current lineup won’t be delayed much further than the original June-July Launch. The new processors would include AMD FX 8150 , FX 8100 AMD (8 cores), AMD FX 6100 (6-core) and AMD FX 4100 (4-cores) . Detailed specs below:

FX-8150, 8 Core, 125W, 8MB L2 Cache, 32Nm, DDR3 1866+ support
FX-8100, 8 Core, 95W, 8MB L2 Cache, 32Nm, DDR3 1866+ support
FX-6100, 6 Core, 95W, 6MB L2 Cache, 32Nm, DDR3 1866+ support
FX-4100, 4 Core, 95W, 4MB L2 Cache, 32Nm, DDR3 1866+ support

*wccftech.com/wp-content/uploads/2011/05/New_AMD_FX_Roadmap-600x330.png

The new processors are most likely to come with higher clock speeds than the currently FX-8130P (3.8Ghz/T.C 4.2Ghz). Featuring the same amount of TDP, Core count and DDR3 memory support as their respective first gen model, The would be priced same of a bit higher than the current lineup revealed here and would also feature an Exclusive Black Edition Overclock technology.

source

8100 looks good. Hope by the time I would be ready to upgrade, some 8170/8190 would be in the block at 15k range. Hmmm... have they started to name their CPUs just like GPUs - 8130, 8150...

whoa!!!!look at the speed
and whats the deal with Exclusive Black Edition Overclock technology ?

@Piyush

Black Edition in AMD parlance refer to CPU with unlocked multiplier. These must be some beast of CPU!!! Probably we are going to see the first 4GHz processor. Can't wait.

ah....thats the same thing used in deneb and its relatives
i though this time its a little different

When is the Bulldozer initial confirmed launch? Seems to get more confusing than ever

Gigabyte GA-990FXA-UD7

*semiaccurate.com/assets/uploads/2011/05/Gigabyte_GA-990FXA-UD7.jpg

It looks like Bulldozer is close, really close, and the 990FX boards for it look are more or less done. That said, here is a look at the Gigabyte GA-990FXA-UD7.

What you are seeing is the first AMD based UD7 board, the high end line from Gigabyte. It has an AMD 990FX chipset, AM3+ socket, and 6 PCIe 16x slots. To top it off, when was the last time you saw a board with both 4-way CrossfireX and 4-way SLI? It looks like the Nvidia exclusive lockout licenses just went poof. Isn’t that sad?

Gigabyte GA-990FXA-UD7

If 4 GPUs isn’t enough, the UD7 has six PCIe slots, although all do not have the full bandwidth. One chrome-plated-nothing to the first person that does 3-way crossfire AND 3-way SLI on this board at the same time. Yay stupid hardware tricks. Should that not be enough, there is a PCI slot to add something really old to the mix. Depending on where Bulldozer ends up for performance, this could be the basis of a killer gaming system.

On top of that, there are the usual Gigabyte features, 2x copper PCB, dual BIOS, and lots of USB3 ports. The USB3 ports are all 3x power, and coloured red for USB2, blue for USB3. Should you want more, the board has firewire, eSATA, optical audio, and all the usual features.

The last little bit is quite cool, a little connector between just to the left of the SATA ports. It looks like a SATA power plug because it is a SATA power plug. You put an extra SATA power cable in to it, and it feeds power to the GPUs/slots to keep overclocked or power hungry boards nicely fed. The GA-990FXA-UD7 looks like a very interesting enthusiast board if Bulldozer comes through. We will know soon

Source

Some update here:-

AnandTech - Computex 2011: ASRock Llano, 990FX and Z68 Motherboards

AMD originally wanted to launch Bulldozer at Computex but performance issues with its B0 and B1 stepping chips pushed back the launch. Now we're looking at a late July launch with B2 silicon, but performance today is a big unknown. Apparently the performance of B1 stepping silicon doesn't look too good.

Performance problems???

*tech2.in.com/news/motherboards/computex-2011-asus-may-show-amd-bulldozer-in-action/222052
Asus is showing its new motherboard

sunny10 said:
**tech2.in.com/news/motherboards/computex-2011-asus-may-show-amd-bulldozer-in-action/222052
Asus is showing its new motherboard

Edit your link. * has been typed twice.

More bad news:-

AMD May Delay Launch of FX-Series "Zambezi" Microprocessors - X-bit labs

*www.xbitlabs.com/images/news/2011-05/amd_bulldozer_launch.jpg

Image taken from xbitlabs.com.

POST ADDED
Some more update:-

AMD Needs to Boost Clock-Speed of FX "Bulldozer" Chips - Sources - X-bit labs

Check this out :

The 990FX Chipset Arrives: AMD And SLI Rise Again : 990FX: Socket AM3+ Meets SLI

though they have used a Phenom II X4 980 BE cpu the review worth a visit ;-)

^^ i agree with u you topgear....the review is worth a visit but the 990fx chipset not more than a re-badge of 8xx series chipset...no native usb 3.0....no full x16 lanes for dual..triple video configs...wat we are getting is sli qualification,what does it has to do with the scorpius platform???
and couldnt test the motherboard at its best form coz we dont have the BD chips...
"Damn you AMD"....it has been one year since bulldozer has been disclosed.
And how lame is that the reviewer uses quads to review and not using oct core phenoms...
Just my take on the amd business policy...got bored of waiting for the bulldozer platform.

Stay tuned to get bored for another 3-4 months. It won't coming before September.

max_snyper said:
^^ i agree with u you topgear....the review is worth a visit but the 990fx chipset not more than a re-badge of 8xx series chipset...no native usb 3.0....no full x16 lanes for dual..triple video configs...wat we are getting is sli qualification,what does it has to do with the scorpius platform???
and couldnt test the motherboard at its best form coz we dont have the BD chips...
"Damn you AMD"....it has been one year since bulldozer has been disclosed.
And how lame is that the reviewer uses quads to review and not using oct core phenoms...
Just my take on the amd business policy...got bored of waiting for the bulldozer platform.

a correction -
a 990 fx chipset supports 42 pcie lanes.
thus dual card setup get 16 lanes each
and tri setup gets 16 8 8 atleast.

Just missed it... thanks for pointing out, Jas.

Absence of USB 3.0 is bewildering though.

^^ The southbridge lacks the usb 3.0 interfacing but i guess they will incorporate them in production mobos.

It has been incorporated but no native support is there. That's kinda baffling.

ok...may be wrong about the 990fx but im right about 970...990x one has x16 single and other has 8x+8x dual...i mean whose gonna buy 990fx everyday but they are of no use coz they are as same as the 800 series counter part....nothing new in the technology,
8xx series also has now-a-days uefi bios.
grow up intel and amd....stop fooling customers...if got the chance i would tell them.. ;-)

FX-8130P oced to 6GHz using liquid nitrogen
Bulldozer details in CPU-Z

Jaskanwar Singh said:
FX-8130P oced to 6GHz using liquid nitrogen
Bulldozer details in CPU-Z

One of the comments say:

CPUZ 1.57.1 does not support Bulldozer nor Zambezi-FX. Thus, the “FX” logo should not even exist. Check here CPUID - System & hardware benchmark, monitoring, reporting

Read more: AMD Bulldozer "FX-8130P" Overclocked to 6Ghz using Liquid Nitrogen, CPU-z Details inside

But many cpus reached 6 Ghz and beyond with LN2 - so there's nothing surprising.
I'm looking forward for some real review/benchmark test to see how far it can go with air coolers.

R

Phenoms 2 have done 7GHz+ on LN2....so its really sad, cos even with 32nm, BD just reached 6GHz...guess they are clocked low just like the original Phenom series...

Skud said:
POST ADDED
Some more update:-

AMD Needs to Boost Clock-Speed of FX "Bulldozer" Chips - Sources - X-bit labs

rajan1311 said:
Phenoms 2 have done 7GHz+ on LN2....so its really sad, cos even with 32nm, BD just reached 6GHz...guess they are clocked low just like the original Phenom series...

Check the link above.

The 32Nm based AMD FX-8130P comes at a stock clock of 3.8Ghz which can turbo upto 4.2Ghz holding a total of 8Cores/8 Threads with 8Mb L3 Cache, The processor used was an early engineering sample and part of the older revision, AMD announced new Revisions due to performance issues in its current Bulldozer lineup so final clocks of the model would be changed. The clock achieved by the user was 6021.2mhz(223.0×27) on an insane 1.984 VCore, The CPU only consumes 125w TDP while the one in the CPU-z shows 186W.

So its one of the earlier revision chip, I guess. AMD has pushed back retail availability because of lower clock speeds at older revisions. Final version may change the thing.

R

holly s**t 3.8GHz stock on an Octa and still 125W TDP? That too old older revision? I don't think i got that right..can someone explain?

Also, when is Llano launch?

that 6ghz ln2 is fake.

damn it... we are still waiting...

AMD FX 8 Core and 4 Core Processor Systems Seen Running at E3

K

off topic
hey guys sorry for offtopic query. Just don't want to make a thread for small query. See hear the price of phenom x4 955 BE . *www.deltapage.com/list/index.html*deltapage.com/list/index.html
is it really 5600rs. Or just a mistake. Because if it's 5600 rs. Then we have a athlon replacement. . . .

^ yes, its correct. See SMC International site there its priced at 5500rs. Damn...I bought it around 45days back for 6.6k!!!

And the bulldozer is nowhere around

. I guess by the time they do come out we will probably get a Phenom II X6 at 5-6k price! This is madness!!!

BTW, is Llano production ready?

R

the Llano was seen working on an MSI AIO PC..

BD late, but Llano on schedule?

BTW when is Bulldozer gonna come to India..????????

R

we still waiting for global launch dude.....how to tell when in india....say 2 weeks after its readily available on newegg?

Skud said:
BTW, is Llano production ready?

Production ready? It has been shipping to OEMs since over 2 months. Refer to the AMD Llano thread.

You mean the desktop chips???

Well whenever Bulldozer is ready and launched...will take atleast 1month to have supply of both cpus and mobos here...

Skud said:
You mean the desktop chips???

Yes..

K

if i'm right then amd did this price cut due to llano launch. So that it can clear it's old stocks. . . . Then i wish that llano will launch this month .

So when are they coming at retail?

UPDATE:-

Some benchmarks of the the 8-core Zambezi FX:-

AMD Bulldozer 8-Core CPU Benchmark Numbers Leaked - Legit Reviews

Original source:-

æŽ¨åœŸæœºEng Sampleè¯„æµ‹(å¾…æ›´æ–°) - CPU / å†…å˜ / ä¸»æ¿ / è¶…é¢‘ - CHIPHELL - äº†è§£CHH,æ‡‚CHH,çˆ±CHH! - Powered by Discuz!

And some youtube videos:-

AMD FX-8130P ES B0 Processor Benchmarking Video On YouTube! - Legit Reviews

These are all B0 stepping, and performance doesn't look very promising at these clocks.

It is a very very early engineering sample. Athlon II X2 250 would give better 1M SuperPi score than that.

I don't even know why CPU-Z is saying 186w TDP when it shouldn't.

Yeah I know, even my E7400 gives far better result in SuperPi.

Have a look at this Bulldozers Eng Sample evaluation :shock:

Already posted it doc.

look 3-4 posts upward...

Skud said:
Already posted it doc. look 3-4 posts upward...

OOps...my bad...even I went through the Legitreviews link....sorry bro!

Btw..this is an ES chip...dont u think the release SKUs will perform better...with better clocks and stepping and all those stuff?

Arre, its absolutely OK, no probs.

Regarding the benchmarks AMD is already working on the B2 revision AFAIR. The 8130P will probably comes with a default speed of 3.8 GHz and 4.2 GHz on turbo. Apparently these ES and B0 samples couldn't hit the speeds AMD wanted and if we take the benchmark results of these ES samples, they are in dire need for speed.

So far it doesn't look good for the first batch of Bulldozer. Even the 990 chipset is disappointing.

You people might like these.

*2.bp.blogspot.com/-O9u3ev-rc2A/TfJpuSs4DpI/AAAAAAAAAww/AGiyw8fcIuA/s1600/wprime.png

*4.bp.blogspot.com/-Z8My6HK1gu4/TfJpoV3mlTI/AAAAAAAAAwg/OBbx_taU95c/s1600/superpi.png

*4.bp.blogspot.com/-9liSYxb9aUo/TfJpiInzCcI/AAAAAAAAAwY/HNYxGZO2su0/s1600/cine11.png

*1.bp.blogspot.com/-_yJPK97Rybk/TfJpfWWP61I/AAAAAAAAAwQ/DspREe95ymM/s1600/cine10.png

Looks better now. Care to give the source???

^^ here's the source ;-)

thanks

Update:-

AMD new generation Turbo: Bulldozer FX processor with 1GHz speed can increase

^Thanks for the cool update bro!

T

The Delay to the BullDozer coupled with my upgrade bug is making me Move to i5-2400k which I dont want to

Tech_Wiz said:
The Delay to the BullDozer coupled with my upgrade bug is making me Move to i5-2400k which I dont want to

Is the i5 2400K available yet? Price?

First saw it mentioned in the Corsair blog some time ago...

T

I blame the bug haha.. Its 2500K

Theitdepot - Intel Core I5-2500K 6MB 3.30GHz Processor

So the 16-core server CPU is demonstrated by AMD. See here:-

AMD Shows Off Working 16-Core Opteron "Interlagos" - X-bit labs

And here:-

Amd demonstrates a 32 core bulldozer server- The Inquirer

Nothing has been divulged but the chip is cool-running. Lets hope performance would be hot though.

Now, bring on the desktop Bulldozers.

^^ thanks for the news

BTW, can we get a 8 core Bulldozer CPU for desktop ;-)

The top-end model would be 8-core.

^^ glad to hear that - now we only need some really awesome performance from Bulldozer cpus ;-)

Fingers crossed since long!!!

T

AMD is delaying launches so much that by the time BD is out Intel will Launch 3rd gen

Tech_Wiz said:
AMD is delaying launches so much that by the time BD is out Intel will Launch 3rd gen

yeah, so it'll become Sandy Bridge E v/s BD not SB v/s BD.

I'm wondering if they did this purposely, as in, are they confident they can beat the 6 core SB-E with their 8 core?

In another couple of months we will come to know.

So finally some good news, the top-end FX-8130P can be stably OCed to 4.63 GHz at 1.5V. Not a big jump from its base frequency of 3.8 GHz, but still commendable, And here's the Super Pi results:-

*i1-news.softpedia-static.com/images/news2/AMD-Bulldozer-Engineering-Sample-CPU-Overclocked-to-4-63GHz-4.png

And here's the i7 2600k result @ 5.7 GHz (taken from Guru3d SuperPI 1M Records thread)

*www.shrani.si/f/23/13J/2cMFgDQr/pi.png

Of course, taking it with a bucketful of salt, but if it comes true...

Source:-
AMD Bulldozer Engineering Sample CPU Overclocked to 4.63GHz - Softpedia

Not impressive at all, nope, I mean the overclock.

Why? Tubro Core itself goes to 4.2GHz, so, sorry but 4.6GHz is hardly anything.

One positive thing is that AMD is already clocking it very high, so even those who won't OC can get almost the fullest performance out of this CPU. Personally I would like the manufacturer to clock the CPU at its highest possible level without any intervention from my side.

And what about that Super Pi result?

Skud said:
One positive thing is that AMD is already clocking it very high, so even those who won't OC can get almost the fullest performance out of this CPU. Personally I would like the manufacturer to clock the CPU at its highest possible level without any intervention from my side.

And what about that Super Pi result?

But then they will also charge you accordingly. The whole point of overclocking is to get more performance for no extra money in return of some time and risk.

Skud said:
One positive thing is that AMD is already clocking it very high, so even those who won't OC can get almost the fullest performance out of this CPU. Personally I would like the manufacturer to clock the CPU at its highest possible level without any intervention from my side.

And what about that Super Pi result?

Isn't it obvious its a hoax?

Salty

Seems like bulldozer keeps dozing off

I'll take all the benchmarks with a truckload of salt after all you never know if AMD has a surprise up their sleeve

R

Its an ES...generally ES are not good for OCing...so why the fuss? This is the reason BD was postponed, so its kinda expected...

rajan1311 said:
Its an ES...generally ES are not good for OCing...so why the fuss? This is the reason BD was postponed, so its kinda expected...

The top pic is false, if ES reaches 4.6GHz how much will normal editions go? 5GHz? Even sandy does not 5GHz without exotic air/water cooling.

Nothing is known till the final day.

oh btw, I have never understood the common use of SuperPi when it uses the now discarded x87 instruction set. Isn't there anything appropriate available??

^^ yes, no benchmarks and real world applications and ultimate VFM.

T

I am so much missing the AMD on my pc. LAUNCH IT ALREADY!

With the Price Strategy of the two so far I can squeeze in a good GFX for my upgrade as well.

Some more news:-

AMD's Next-Generation Opteron "Bulldozer" Chips to Feature Adjustable TDP - X-bit labs

Will it come to desktops also?

R

tkin said:
The top pic is false, if ES reaches 4.6GHz how much will normal editions go? 5GHz? Even sandy does not 5GHz without exotic air/water cooling.

but then if a processor has a stock speed of 3.8Ghz, maybe, just maybe, it could do 5GHz on air? anyways, SB does reach 4.5GHz+ on a good air cooled setup...lets hope these do better..

And was it stock cooler? No word on that...

Skud said:
And was it stock cooler? No word on that...

No it's some non-reference I read it somewhere there.

AMD Bulldozer 4Ghz (ES) Gets Pitted Against Intel Core i7-990X in Various Gaming Benchmarks

^^ thanks for the link but I'll wait for the benchmark of a final retail product anyway ;-)

And anyway, we will be able to buy it only after the final retail product hit the stores...

But seriously, why SLI? AMD chipsets have only get the support after the recent nVIDIA driver update and not everything has been ironed out. A CFX setup would have been better.

Sandy Bridge-E Delayed to January 2012: Sources | techPowerUp

Guess what, Sandy Bridge E just got DELAYED.

^^ Guess who found out about performance of bulldozer? :lol:

On a side note, good time for an upgrade.

Intel will do what they did with Sandy bridge and Gulftown/Westmere EP.

First launch the highest performing parts for $999 and in a few months launch a newer processor with almost the same performance for half the price(Sandybridge).
Now it will happen with sandybridge and ivybridge.

That's in a nutshell, Intel for you. And within 1.5-2 years, upgrade for the platform would stop. :))

^^ Nope, intels upgrade path is on par with amd this time around. Both sandybridge ( 1155) and sandybridge-e( 2011) will get future ivybridge support for the respective platforms i.e the panther point supported pocessors are totally backward compatible with cougar point chipsets.

tkin said:
^^ Guess who found out about performance of bulldozer?

On a side note, good time for an upgrade.

Man after toady you got a good sense of humour!!!:roll: :rofl:

tkin said:
^^ Guess who found out about performance of bulldozer?

On a side note, good time for an upgrade.

Exactly, when bulldozer launches, intel will quietly unleash a monster. Lets see if amd can bulldoze that! :lol:

vickybat said:
^^ Nope, intels upgrade path is on par with amd this time around. Both sandybridge ( 1155) and sandybridge-e( 2011) will get future ivybridge support for the respective platforms i.e the panther point supported pocessors are totally backward compatible with cougar point chipsets.

Let it happen first.

^^ Its already announced and its obvious. Ivybridge is no new architecture and is simply a tick i.e dieshrink. So current 32nm sandybridge and sandybridge-e ( 32nm) will receive the 22nm treatment. Its bound to happen if you see it this way.

Besides ivybridge will also use intels 3d trigate based transistors which is their patented design. It drastically reduces leakage current thus lowering tdp and churns out more performance than a similar set of normal planar transistors used in a chip. The gate design is actually the key here as they control the current flow now.

Check this buddy. Its pretty interesting. :smile:

vickybat said:
^^ Its already announced and its obvious. Ivybridge is no new architecture and is simply a tick i.e dieshrink. So current 32nm sandybridge and sandybridge-e ( 32nm) will receive the 22nm treatment. Its bound to happen if you see it this way.

Besides ivybridge will also use intels 3d trigate based transistors which is their patented design. It drastically reduces leakage current thus lowering tdp and churns out more performance than a similar set of normal planar transistors used in a chip. The gate design is actually the key here as they control the current flow now.

Check this buddy. Its pretty interesting.

Ok, I think I need to start allocating the budget again.

Sandy Bridge E got delayed to Q1 2012

^^ That means ivy will also be delayed. Maybe intel doesn't need sandybridge-e to compete with bulldozer. They think their socket 1155 cpu's are enough for now.

Maybe we can expect some new launches for socket 1155 this year.

Batman, I am not talking about announcements and all. If Bulldozer becomes a failure, I am damn sure Intel would just change 1-2 pins here and there and force the users to migrate to another platform with Ivy. Socket 1156 got a lifespan of just 2 years, and somehow I feel SNB could have debuted at that platform also. Of course, don't throw me some links and tutorial on electronics, I am naive on this, what I am saying is completely from a user's point of view.

Just ask a cash strapped 785 owner, who with a BIOS update can upgrade to Bulldozer when it will be released and later can change the mobo to a higher chipset.

^^ Okay no prob, i won't throw any such articles if you insist. But what you are saying is your own personal point of view not reality. Btw 785 chipset owners cannot upgrade to bulldozer with a bios update. They have to go for an 8 or 9series motherboard.

In reality, intel has offcourse announced panther point 7 series (Z77) chipsets for its ivybridge processors. But they had also stated that ivybridge will be completely backward compatible with existing 1155 6 series cougar point chipsets that include h61,h67,p67 & z68 motherboards.

Check this link. Its totally written in an end user's point of view.

This one is directly from techpowerup.

vickybat said:
^^ That means ivy will also be delayed. Maybe intel doesn't need sandybridge-e to compete with bulldozer. They think their socket 1155 cpu's are enough for now.

Maybe we can expect some new launches for socket 1155 this year.

Ivy Bridge delay news came out a month ago, it's been delayed from Q1 2012 to Q2 2012.

I have a feeling Ivy Bridge will itself thrash Bulldozer, 4 core v/s 4 module.

Sandy Bridge will become 584-999$ enthusiast processor setup.

I too think INTEL should go LGA 2012 and call it a day

vickybat said:
^^ Okay no prob, i won't throw any such articles if you insist. But what you are saying is your own personal point of view not reality. Btw 785 chipset owners cannot upgrade to bulldozer with a bios update. They have to go for an 8 or 9series motherboard.

In reality, intel has offcourse announced panther point 7 series chipsets for its ivybridge processors. But they had also stated that ivybridge will be completely backward compatible with existing 1155 6 series cougar point chipsets that include h61,h67,p67 & z68 motherboards.

Check this link. Its totally written in an end user's point of view.

This one is directly from techpowerup.

No problem in throwing articles buddy, the forum is full of people who will understand it.

If in reality, Intel makes ivy bridge backward compatible that would be great. And lets hope true >4 core CPUs will be supported.

And regarding the 785 chipset, well not exactly the 785 but the 770 & 760g will support BD. Here's the MSI announcement:-

MSI AM3+ CPU Support

Google Translate

Of course, I do agree this means little but generally AMD supports their platform longer than Intel. And here's one comment from that Techpowerup link you give:-

Not a new Socket ? now thats a first...

let me tell u one thing:
1.This thread is about the amd bulldozer,so discuss on bulldozer only.if u want to fight on intel vs and go make your own thread,DONT SPOIL THIS THREAD.

2.Ivy bridge is for enthusiast platform,come on in India how many ppl are actually gonna buy $.500+ proccy.until intel introduces mainstream ivybridge.

3.In India, mainstream product outside India is high end product (prices),naturally intel proccy gonna be priced higher than amd.

4.Amd is again targetting mainstream user with high performance parts...they just want to make it right first time..remember phenom 1 disaster..though they are targetting high end user but its gonna end up in main stream....a vs sandy bridge 1155 series.
thats why they priced their proccy not more than $.350+

Thats my point of view.

^^

1. If we are comparing BD with SB-E, I see no reason for you to stop us

2. Ivy Bridge is mainstream, a direct replacement for SB, quad cores for quads, duals for duals, price for price, expect highest end IVY BRIDGE to cost under 320$

^^
discussing amd vs sb-e is one thing and thrashing amd is other,intels gonna kick amd's ass...this that,is more like fighting
and that too on the processors that havent been released or their true potential known.
if intel is reasonable it is surely gonna win....im seeing trend for the last 4~5 years,it hasnt been reasonable as compared to other countries.
they have their R&D setup,get their designs cleared here still they sell costly products in India.
competitive pricing is one thing and monopoly is other.
im not taking side of any other company,but wrong business practice is wrong.

K

@max , good saying man

.

MSI and Asus have made announcement of the Am3+ CPU support in their all AM3 boards and already have released BIOS for it. That is the reason I've purchased 890GXM-G65 in the 1st place. With the version 1.A0, it is already ready for Bulldozer. :smile:

But other companies like ECS, Gigabyte, Asrock have not confirmed it yet and only some of the selected models from them are currently officially announced for AM33+ CPU support. That is the reason I've suggested the GIGABYTE GA-880GA-UD3H mobo in the PC Buying guide as it it officially announced to support AM3+

^^ hey cilus i have question for regarding the am3+ socket(am3b socket as we call it),
mobo companies are saying that older mobos like 8xx chipset are supported but they are 941 pins and amd bd are 942 pins..... 1-pin more so do we have to cut that pin form the processor or what?
Or the companies are misleading with info.,,,they are saying about the old chipset with new socket. and ppl are confusing them with old chipset with old am3 socket.

max_snyper said:
^^
discussing amd vs sb-e is one thing and thrashing amd is other,intels gonna kick amd's ass...this that,is more like fighting
and that too on the processors that havent been released or their true potential known.
if intel is reasonable it is surely gonna win....im seeing trend for the last 4~5 years,it hasnt been reasonable as compared to other countries.
they have their R&D setup,get their designs cleared here still they sell costly products in India.
competitive pricing is one thing and monopoly is other.
im not taking side of any other company,but wrong business practice is wrong.

I totally agree with comp@ddict here. We actually didn't do any comparison cause non of the aforementioned products are launched. Besides speculating on an upcoming product's performance is not wrong.

And nobody said intel will thrash amd or any such comments. Check thoroughly and post properly instead of cooked up things that you think someone actually said so.

^^
u read the whole thread first throughly...i'm following this thread since start...i havent seen any post regarding intel...but from last few weeks this thread is only inclined towards the intel side that pisses me off...if want to discuss then do for the amd side only on this thread not intel. make new thread for intel sandy -e.
i finished it earlier and stopped it but u any way want to dig up skeletons from the grave..
and u always like to increase your posts by fighting off with anybody.
thats good thing to do but at some point of time it gets childish.
"Peace Bro" ;-)

A

Eight core Bulldozer overclocked to 4.63GHz

found this

and sandy-e is ivybridge , i.e 2011 is the die shrink of 1155.

new architectures are rockwell and haswell ( is told to be coming march 2013)

Probably AM3+ CPUs will be designed in such a way that the extra 2 pins won't interfere with the current AM3 sockets, having 938 pin. As a result issue might be the use of the sideband temperature sensor interface for reading the temperature from the CPU. Also, certain power-saving features may not work, due to lack of support for rapid VCore switching.
Another probability is there will be several versions of Bulldozer with different type of sockets.

A

cilus is the q3 bully launch confirmed? what pieces will be coming our way?

hey Cilus u mean that we are gonna get BD in two versions one with 942 for am3+ and other for am3 only...then this will be cool thing thing for old chipset users,double the power in same package thing then
BTW as for the end user(read naive) temp sensor,power saver thing doesnt matter much they just need general computing with more efficiency.
till now no exact date is confirmed its just q3 of this year,amd wanted to revise the version of proccys because there was some problem with its performance.
the prices are though confirmed from low end($190) to high end($320).

That was the original plan, but it looks like BD will come for AM3+ only, and with AMD in a hurry to Phase out their 45nm processors and AM3 socket, I think BD will be AM3+ exclusive.

Plus, it's delayed. If it doesn't perform, AMD will have to hide behind another few years of"budget" priced CPUs.

^^ AMD hasnt shine in performance since the athlon64 days
bulldozer is the only chance they have got so they are extra carefull with it...so thats why the delay.
it has also slipped the market share somewhat compared to 2009. In 2010 it was just above 10% of the world. so thats why they dont want to leave any stone unturned.they are trying to make it first time right for bulldozer
lets see how it performs...tired of waiting and bluffed benchmarks of bulldozer!!!!!!!

max_snyper said:
^^
u read the whole thread first throughly...i'm following this thread since start...i havent seen any post regarding intel...but from last few weeks this thread is only inclined towards the intel side that pisses me off...if want to discuss then do for the amd side only on this thread not intel. make new thread for intel sandy -e.
i finished it earlier and stopped it but u any way want to dig up skeletons from the grave..
and u always like to increase your posts by fighting off with anybody.
thats good thing to do but at some point of time it gets childish.
"Peace Bro"

Could you please point me when did i fight in this thread and really dug up any skeletons? Does it really matter if it pi$$es you or not?

The discussions will go on and intel will come to the picture if needed for comparison irrespective of your personal desires.

max_snyper said:
In 2010 it was just above 10% of the world.

well, according to Steam, AMD's market share is 27.5%.

I *easily* expect it to be above 10%.

*mod edit for personal attack*

@ICO oh just wrote it the wrong way,read about the Q1 of 2011 posted as 2010
heres the link for that article:
Intel takes CPU market share from AMD in Q1 â€¢ The Register

5.1 Ghz on air with an Engineering Sample? Good.

^^ Wow that's great. We might have a new overclocking champion.

ico said:
5.1 Ghz on air with an Engineering Sample? Good.

mmmmmm...luving it!
But, those aren't stock coolers, are they?

I would love to have those Noctua as stock coolers!

5.1 Ghz on air for an ES sample looks good but that's not a stock cooler for sure - now coming to the real question - can we manage to get 5.5 on Air and 6 Ghz with H2O cooling with the final product ;-)

ES and 5.1GHz, finally, things are looking up.

Hoping to see final retail chips hit 5.4GHz ish on stock cooler(we can dream right?

)

More important question is: are we going to see the first retail CPU clocked over 4 GHz?

are we going to see the first retail CPU clocked over 4 GHz?

Well, the first line of CPUs will have the highest clocked part at 3.8GHz base, 4 modules, 8 cores, and a TURBO of 4.2GHz.

So 4GHz stock is pretty much 1 quarter away after launch.

BUMP...

And bring out your spoonful of salts

More benchmarks with another ES at 3.2 GHz and if these things are correct, the 8130P is going to best the i7 2600k. Check the following:-

1. AMD's Bulldozer-based FX-8130P benchmarked early - TechSpot News

2. Purported AMD Bulldozer Benchmarks Leaked by VR-Zone.com

Original source:-

Google Translate

Read the comments here:
AMD's Bulldozer-based FX-8130P benchmarked early - TechSpot News :rofl:

All I can say if amd is giving 8 core for the price of intel's 4 core, and intel just delayed ivy the that means bd won't be a big threat, maybe not as cr@p as phenoms were but not good enough to best it anyway.

to best what - snb or ivy?

Skud said:
to best what - snb or ivy?

Of course SNB, ivy is another monster to start with :lol:

I just made a gflops comparison between Faun's 2500k and mukherjee's 2600k at same clock speeds, mukherjee is getting 70% more performance with HT on, so in reality 2600k actually behaves like a 7 core processor, so all amd has to do is beat intel's 7 core with their 8 core with supposedly half avx performance as well(need to do a bit research on this).

tkin said:
All I can say if amd is giving 8 core for the price of intel's 4 core, and intel just delayed ivy the that means bd won't be a big threat, maybe not as cr@p as phenoms were but not good enough to best it anyway.

All some other guy can say if amd is giving 8 cores for the price of intel's 4 core, and intel just delayed ivy means bd has to be a big threat, surely not as cr@p as phenoms were but good enough to best sb anyway.

tkin said:
Of course SNB, ivy is another monster to start with

I just made a gflops comparison between Faun's 2500k and mukherjee's 2600k at same clock speeds, mukherjee is getting 70% more performance with HT on, so in reality 2600k actually behaves like a 7 core processor, so all amd has to do is beat intel's 7 core with their 8 core with supposedly half avx performance as well(need to do a bit research on this).

What you are saying is OK, but in the end its the real life performance that matters. OK, just a couple of months to go to let the dust settled.

And in any case, all the leaked performance figures are more or less consistent, so it will hardly go haywire in the end.

If BD can "just match" Sandy Bridge, then god save AMD because Ivy Bridge will eat it alive, at half the die size and TDP.

ico said:
All some other guy can say if amd is giving 8 cores for the price of intel's 4 core, and intel just delayed ivy means bd has to be a big threat, surely not as cr@p as phenoms were but good enough to best sb anyway.

Didn't get you, how did you make that assumption? If product A is a threat for product B than manufacturer of B cancels new product so that they can be beat black and blue by A?

Ivy taped out months ago, intel can ramp up production anytime they want, sandy launched just in time. And the fact that they pushed both to next year means intel wants to cash on the Sandy platform this year and does not wish to decrease earnings by launching new platform(old inventory clearance etc), clearly BD can't be a serious threat. Most we can see are a bit of price decrease from them.

PS: For the price of a good 2.1 speaker(6k), frontech gives you 5.1 speakers, by your analogy frontech speakers are better.

Read properly again.

tkin said:
Didn't get you, how did you make that assumption? If product A is a threat for product B than manufacturer of B cancels new product so that they can be beat black and blue by A?

Ivy taped out months ago, intel can ramp up production anytime they want, sandy launched just in time. And the fact that they pushed both to next year means intel wants to cash on the Sandy platform this year and does not wish to decrease earnings by launching new platform(old inventory clearance etc), clearly BD can't be a serious threat. Most we can see are a bit of price decrease from them.

PS: For the price of a good 2.1 speaker(6k), frontech gives you 5.1 speakers, by your analogy frontech speakers are better.

It seems like a marketing strategy. Intel has realized that the 8 cored BD's will be a substantial threat to their current flagship SBs. So they halt their ready product -- Ivy Bridge, to combat the market pie when BDs are officially released. For Intel it does not matter how much of sales they do of any product / chip they manufacture. They are an aggressive company. They want 100% of the pie. Monopoly.

Using foresight, they would rather take a hit right now of sales (not releasing Ivy Bridge) and later on capture more market share (which AMD wants) -- by pushing a product a wee bit late.

Right place right time.

ico said:
Read properly again.

Oh, I see, so you are saying BD if possible will beat ivy as well, hmm, like that's ever gonna happen, ivy parts will come with 4Ghz base clock.

Read properly again.

asingh said:
It seems like a marketing strategy. Intel has realized that the 8 cored BD's will be a substantial threat to their current flagship SBs. So they halt their ready product -- Ivy Bridge, to combat the market pie when BDs are officially released. For Intel it does not matter how much of sales they do of any product / chip they manufacture. They are an aggressive company. They want 100% of the pie. Monopoly.

Using foresight, they would rather take a hit right now of sales (not releasing Ivy Bridge) and later on capture more market share (which AMD wants) -- by pushing a product a wee bit late.

Right place right time.

Seems a bit to far fetched, what will they even gain with this? Even if they launch Ivy later the money that amd makes from BD can be used by them to research and release better version of BD next year, plus the publicity, if amd just gets past intel in one generation people will go gaga over it, remember amd 58xx? Amd just managed to beat nvidia once in 3 or 4 gens, and people went crazy over them, a popularity that carried over still today and will likely to continue forward even when now nvidia had released competing products in almost every segment, its like how america created osama, give someone too freedom and he becomes too big a threat to contain any more.

Enough conspiracy theories, hope BD makes it this year, its been too long already, any more and people rather wait for Ivy, I mean if someone can wait 5 months for BD why can't they wait another 5 for Ivy?

Oh, I see, so you are saying BD if possible will beat ivy as well, hmm, like that's ever gonna happen, ivy parts will come with 4Ghz base clock.

I think he said the opposite.

Read again.

comp@ddict said:
I think he said the opposite.

Read again.

Maybe I misread it, full domination? They can do that right now with ivy, why wait for BD to settle?

tkin said:
Seems a bit to far fetched, what will they even gain with this? Even if they launch Ivy later the money that amd makes from BD can be used by them to research and release better version of BD next year, plus the publicity, if amd just gets past intel in one generation people will go gaga over it, remember amd 58xx? Amd just managed to beat nvidia once in 3 or 4 gens, and people went crazy over them, a popularity that carried over still today and will likely to continue forward even when now nvidia had released competing products in almost every segment, its like how america created osama, give someone too freedom and he becomes too big a threat to contain any more.

Enough conspiracy theories, hope BD makes it this year, its been too long already, any more and people rather wait for Ivy, I mean if someone can wait 5 months for BD why can't they wait another 5 for Ivy?

That has happened only once starting from x800 series to HD3xxx series. But before that:-

Radeon 8500> GF3
Radeon 9700> GF4
Radeon 9800> GF5

That's also a loss of 3 generations. So nVIDIA was Osama much earlier than AMD.

Skud said:
That has happened only once starting from x800 series to HD3xxx series. But before that:-

Radeon 8500> GF3
Radeon 9700> GF4
Radeon 9800> GF5

That's also a loss of 3 generations. So nVIDIA was Osama much earlier than AMD.

Upto HD4xxx, cause GT2xx spanked 4xxx hard :wink:

tkin said:
Amd just managed to beat nvidia once in 3 or 4 gens.

Nope.

skud said:
that has happened only once starting from x800 series to hd3xxx series. But before that:-

radeon 8500> gf3
radeon 9700> gf4
radeon 9800> gf5

that's also a loss of 3 generations. So nvidia was osama much earlier than amd.

X1950XTX > gf7.

tkin said:
Upto HD4xxx, cause GT2xx spanked 4xxx hard

GT 2xx couldn't compete with HD 4850/70 price points.

HD 4870 was faster than GTX 260 and Core 216. Then there was GTX 280. HD 4890 was faster than GTX 280. Then GTX 285.

tkin said:
Upto HD4xxx, cause GT2xx spanked 4xxx hard

No way. In that case, even GF 6xxx and 7xxx were spanked hard by their respective AMD counterparts.

ico said:
Nope.

X1950XTX > gf7.

GT 2xx couldn't compete with HD 4850/70 price points.

HD 4870 was faster than GTX 260 and Core 216. Then there was GTX 280. HD 4890 was faster than GTX 280. Then GTX 285.

Just forget about that X19xx. My mind jumps straight to HD 2900 from X1800.

HD 4850 and 4870 sold like crazy. Really crazy. I remember the forum in those days.

Skud said:
No way. In that case, even GF 6xxx and 7xxx were spanked hard by their respective AMD counterparts.

Of course, the 3870x2. Till 8 series came, so its like 8, 9 and gt200.

ico said:
HD 4850 and 4870 sold like crazy. Really crazy. I remember the forum in those days.

I was one of those buyers.

Despite having faster cards, it was nVidia who got spanked in GT 2xx. Following the launch of HD 4850/70, there was like 30-50% reduction in nVidia prices instantly. You don't have to have the fastest product to win.

tkin said:
Maybe I misread it, full domination? They can do that right now with ivy, why wait for BD to settle?

I think they are having problems with 22nm 3D transistors, or maybe they are changing plans a bit (due to Fusion release), that's why Ivy Bridge got delayed 3 months.

ico said:
HD 4850 and 4870 sold like crazy. Really crazy. I remember the forum in those days.

Yups. Everyone got them then. 4850 was like the "normal" pick up card.

I got mine then too..! The 48xx series started end of domination for nVidia. HD4890 was the icing, when it killed the GTX280 and bordered GTX285.

I got a 9800GTX+ when 4850 came up, mostly due to the heat issue **Hides in bushes**

tkin said:
Of course, the 3870x2. Till 8 series came, so its like 8, 9 and gt200.

I think Gefroce 8 series spanked X1950XTX and HD 2000 series. It was even much better than HD 3000 series. HD 3850/70 + dual variants were only a return to competition for ATi. 9 doesn't count as it was a mere re-brand.

ico said:
Despite having faster cards, it was nVidia who got spanked in GT 2xx. Following the launch of HD 4850/70, there was like 30-50% reduction in nVidia prices instantly. You don't have to have the fastest product to win.

Agreed. Intel had tread a similar path during Athlon 64 days. Apparently they were selling overpriced products due to no/less competition. So even for Intel/nVIDIA fanboys, a win for AMD is just as good as an AMD fanboy.

Bottom Line:- Competition is always good for customers.

tkin said:
I got a 9800GTX+ when 4850 came up, mostly due to the heat issue **Hides in bushes**

That heat issue was rectified promptly with dual slot custom coolers. Even my "Palit" never went over 65C under load.

ico said:
I think Gefroce 8 series spanked X1950XTX and HD 2000 series. It was even much better than HD 3000 series. HD 3850/70 + dual variants were only a return to competition for ATi. 9 doesn't count as it was a mere re-brand.

Particularly the 8800GT. It was a darling for a long long time.

asingh said:
Yups. Everyone got them then. 4850 was like the "normal" pick up card.

I got mine then too..! The 48xx series started end of domination for nVidia. HD4890 was the icing, when it killed the GTX280 and bordered GTX285.

yep, same case with HD5850 and HD6850 and HD6950, always the 50s enjoy popularity

Personally speaking, I hated ATi. Absolutely hated ATi. ATi used to be notorious. Drivers never ever worked in Linux. Never. nVidia always worked in Linux.

Real gaming scenario in those old days used to be this - nVidia winning in OpenGL titles whereas ATi winning in Direct3D titles.

Intel and AMD are very open source friendly. AMD's acquisition of ATi transformed ATi from open source enemies to friends. AMD released the GPU instruction set specifications and now pays their open source driver developers. nouveau developers on the other hand receive no support from nVidia.

I have a 5750. Don't know if it was popular or not. :grin:

^^ the older brother HD 5770 has been the largest selling DX 11 card followed by GTX 460, HD 5850 and HD 5870 in succession.

Even I was a nVIDIA fanboy since the 4850/70 comes out. The first review I read was on Anandtech, and instantly knew I was going to get one.

K

don't you guys think that it's bulldozer discussion thread

not about best selling popular graphic card's

ico said:
^^ the older brother HD 5770 has been the largest selling DX 11 card followed by GTX 460, HD 5850 and HD 5870 in succession.

Actually buddy my 5750 is giving 5770 framerates with a 100mhz oc and maybe even surpassing that. I have checked guru3d frames and i'm getting a bit higher than 5770 at stock whereas mine is overclocked to 100mhz i.e 800mhz core clock up from 700mhz stock.

Asus formula coolers are extremely good and the highest temps i get even in gpu intensive games after oc is around 67c.

In crysis2 with everything set to ultra, dx11 & high res textures on @ 1600x900, i'm getting 20-25fps in normal scenes. But during heavy firefights ,it drops to 15-18 fps. Consider my card is a 5750, these numbers aren't that bad. But i have to oc my card to get these numbers to 800mhz core clock and 1250 mhz memory clock. :smile:

I have always been a nvidia guy since XFX 8600 GT, then I bought MSI 9800 GTX & then Palit GTX 260 & again MSI GTX 260 Lightning. I personally started liking AMD since HD 5xxx series, cause it was the very particular time when AMD turned the table. One of my fav card is HD 5870 (I like this card very much) among all AMD cards.

Now, now... enough of Radeons and Geforces. Lets come back to topic.

Check this:-

*www.thinkdigit.com/forum/cpu-motherboards/135848-amd-bulldozer-news-discussion-14.html#post1449779

And post your comments on this.

nVidia winning in OpenGL titles whereas ATi winning in Direct3D titles.

that has changed so much now..

Anyways, ICO please read your PM, I need a few extra blank posts on the thread.

Bulldozer has to come out in this summer, right? When does summer end in US of A?

Bulldozer has to come out in this summer, right? When does summer end in US of A?

Same as it ends here buddy, we are all in the Northern Hemisphere remember?

But here it's monsoons (varsha ritu ;-)

)already and no sign of bulldozer.

D

I Think Bulldozer Will Be Delayed To SNB-E Released.

Why would AMD do that if it can't even match the current Sandy Bridge?

D

baccilus said:
Why would AMD do that if it can't even match the current Sandy Bridge?

Recent Bulldozer Benchmarks Shows AMD Has Something Left To Show. SNB-E will be Priced Higher as it a premium intel thing. If Bulldozer Can Beat 990X & 2600K at a low price during snb-e definately intel market share will drop into AMD Hands.

Example:

300$ Bulldozer Can Defeat 990X & i7 2600K & 10-20% Faster SNB-E Low End Models eg: 300$ SNB-E & if it Can Match Performance In Between The 400$ & 500$ SNB - E Bulldozer will be a steal.

Or if bulldozer even slighlty perform better than sandy bridge i7 2600K Then There Will Be Huge Price Drop In Sandy Bridge 2600K & 2500K as there snb-e will be also available in that period. Extremely Sorry For Very Bad English & Explanation. ;-)

The leaked benches have an ES on B1 stepping, which is never going to see the daylight in retail as AMD is reportedly unhappy with the clocks and already working on B2/B3 stepping. So if a 3.2 GHz 8130P ES can compete with i7 2600k, the reportedly 3.8 GHz 8130P retail chip can be a real threat to 990X.

All these are theoretical right now. We are just couple of months away from reality.

Geek-With-Lens said:
Recent Bulldozer Benchmarks Shows AMD Has Something Left To Show. SNB-E will be Priced Higher as it a premium intel thing. If Bulldozer Can Beat 990X & 2600K at a low price during snb-e definately intel market share will drop into AMD Hands.

Example:

300$ Bulldozer Can Defeat 990X & i7 2600K & 10-20% Faster SNB-E Low End Models eg: 300$ SNB-E & if it Can Match Performance In Between The 400$ & 500$ SNB - E Bulldozer will be a steal.

Or if bulldozer even slighlty perform better than sandy bridge i7 2600K Then There Will Be Huge Price Drop In Sandy Bridge 2600K & 2500K as there snb-e will be also available in that period. Extremely Sorry For Very Bad English & Explanation.

If the highly oc'ed BD(3.8GHz) becomes a threat to 2600k, intel will just release 3.8GHz+ 2700k and be done with it, and do not underestimate intel, the tech intel has is beyond what amd can come up right now, sandy E if 22nm will probably eat BD alive, with some ketchup.

Too much of useless speculation.

Here's some interesting news ( Published about an hour ago ) ;-)

Bulldozer prototype suggests AMD shooting for Sandy Bridge performance

and this ;-)

But to catch market attention AMD have to play with BD pricing to make them attaractive as Intel is preparing to win the cpu battle again with SB-E and only right pricing can make Bulldozer somewhat win the upcoming battle of CPU power and price ;-)

Some interesting read:-

AnandTech - Details on AMD Bulldozer: Opterons to Feature Configurable TDP

POST ADDED:-

And in not so good news, it may be delayed until October:-

InsideHW - AMD Bulldozers set for October release

And there may be no less than 7 FX parts ranging from quad to octa core:-

*www.insidehw.com/images/stories/news/products/AMD/amdfxserieslinel_1.jpg

T

That just sux. Oct is still so far away. AMD just pushing people to Intel by postponing launch like that.

Also 6 & 8 Core Will be practically useless for gamers as of now. I hope the FX 4120 has what it takes to take out i5 2400

More delays, by god, BD will compete with Ivy and Sandy E, back to phenom situation I guess.

Also heard top BD clock will be 3.6Ghz with boost to 4.2GHz, seems amd is having trouble reaching that clock speed, so they are delaying, so BD atleast competes with sandy.

@Tech_Wiz:

More and more games are using 3/4 cores now, and real cores, not HT for that matter. So 6 & 8-core are a bit future-proof provided the CPU is already powerful enough. Just a couple of years back games were utilizing just two cores, not now anymore.

@tkin:

I think you are right. BD has to compete with Ivy and Sandy E, provided AMD doesn't have any surprises in store.

Bulldozer won't be good. I personally have no expectations for desktops. It might sell for servers though.

What was so bad about the "Phenom situation". I would be happy if Bulldozer delivers good performance like Phenom did with less cost. For me it doesn't have to beat intel, it just has to beat all the games releasing in the next 3-4 years.

D

Top End Bulldozer Chip will defeat 2600K or there is no worth releasing bulldozer.

baccilus said:
What was so bad about the "Phenom situation". I would be happy if Bulldozer delivers good performance like Phenom did with less cost. For me it doesn't have to beat intel, it just has to beat all the games releasing in the next 3-4 years.

Agreed. But even that is doubtful.

Geek-With-Lens said:
Top End Bulldozer Chip will defeat 2600K or there is no worth releasing bulldozer.

And defeat by a good margin. Remember it will be very late in the party so there will be no excuses.

^^ I too want that and amd has to do it in order to stay competent in the business. Lots of am3 users are eyeing a bulldozer upgrade. I guess amd won't dissapoint them.

T

Skud said:
@Tech_Wiz:

More and more games are using 3/4 cores now, and real cores, not HT for that matter. So 6 & 8-core are a bit future-proof provided the CPU is already powerful enough. Just a couple of years back games were utilizing just two cores, not now anymore.

Well I agree that more and more are closer to using 4 Cores as of now. But 6 & 8 will take more time. By the time games start supporting those a whole new league of Proccys will be out

I tend to agree with ico.

AMD's "Pure" CPU power is getting over powered by Intel so they are getting the Fusion & APU thing going so as to compensate for that.

AMD = Entry Mid Level (i.e masses) and Mid High + High will go with Intel.

Skud said:
Agreed. But even that is doubtful.

Even Phenom II X4 can max all the games out there. That won't change till the next generation consoles come out. As long as they sell it for cheap and it is better than Phenom II, I will be happy.

baccilus said:
Even Phenom II X4 max all the games out there. That won't change till the next generation consoles come out. As long as they sell it for cheap and it is better than Phenom II, I will be happy.

If it performs anywhere closer as reported by the leaks, then AMD have done a good enough job. It will mean Trinity will become simply irresistible. Coming back to BD, I am a bit disappointed with the 990 FX/X chipset - I was expecting more.

Tech_Wiz said:
Well I agree that more and more are closer to using 4 Cores as of now. But 6 & 8 will take more time. By the time games start supporting those a whole new league of Proccys will be out

I tend to agree with ico.

AMD's "Pure" CPU power is getting over powered by Intel so they are getting the Fusion & APU thing going so as to compensate for that.

AMD = Entry Mid Level (i.e masses) and Mid High + High will go with Intel.

It's not that you upgrade your CPU whenever there are some new releases. So when games will start using more than 4 cores, you "older" 6/8 core CPUs will just delay the inevitable upgrade, saving you some dough. So having more cores, albeit somewhat lower performing, at a similar price point is not bad at all.

^^ It has to be seen how much lower performing bulldozer will be compared to its competition. I think the fight won't even go to socket 2011 based sandybridge-E, but 1155 will be enough.

Remember that more cpu's are going to role out from the 1155 stable. That means 2600k might get a big brother. :wink:

BD will ultimately more or less match SNB. Even if i7 2700/2800 comes, AMD is also keeping the option open for a speed bump. So they looks more or less even. SNB-E would be a different beast altogether, it would be interesting to see how AMD is going to counter that.

baccilus said:
Even Phenom II X4 can max all the games out there. That won't change till the next generation consoles come out. As long as they sell it for cheap and it is better than Phenom II, I will be happy.

Skud said:
If it performs anywhere closer as reported by the leaks, then AMD have done a good enough job. It will mean Trinity will become simply irresistible. Coming back to BD, I am a bit disappointed with the 990 FX/X chipset - I was expecting more.

It's not that you upgrade your CPU whenever there are some new releases. So when games will start using more than 4 cores, you "older" 6/8 core CPUs will just delay the inevitable upgrade, saving you some dough. So having more cores, albeit somewhat lower performing, at a similar price point is not bad at all.

vickybat said:
^^ It has to be seen how much lower performing bulldozer will be compared to its competition. I think the fight won't even go to socket 2011 based sandybridge-E, but 1155 will be enough.

Remember that more cpu's are going to role out from the 1155 stable. That means 2600k might get a big brother.

^^ or 2500k might get a younger brother but I'm sure Intel is delaying it for Final BullDozer cpu release.

For me ( as a gamer's perspective ) IF Bulldozer can give 60-80+ FPS on most current gen games with a decent GPU like say HD6970/GTX580 and if it's reasonably priced then I think it's enough as games are getting more GPU power hungry than CPU it's so good to invest more in a good GPU and if possible in multi gpu config ;-)

If BD did beat 2600k, amd would've released it by now, period.

More wait, more cr@p, eg, Fermi 1st gen aka thermi.

topgear said:
^^ or 2500k might get a younger brother but I'm sure Intel is delaying it for Final BullDozer cpu release.

For me ( as a gamer's perspective ) IF Bulldozer can give 60-80+ FPS on most current gen games with a decent GPU like say HD6970/GTX580 and if it's reasonably priced then I think it's enough as games are getting more GPU power hungry than CPU it's so good to invest more in a good GPU and if possible in multi gpu config

If I am not mistaken, to drive that GPU/s to its optimum potential a powerful CPU is necessary.

tkin said:
If BD did beat 2600k, amd would've released it by now, period.

More wait, more cr@p, eg, Fermi 1st gen aka thermi.

But Fermi(480) did take the single GPU crown from 5870. Only that the temps and noise were unbearable and the gap was not much to warrant any changes.

A

dont know why i feell this way but it appears that something is really rong with intels haswell /rocwell thats why AMD is releasing buldozer wth sandy bridge -E to lurk in the shadows to strike haswell.

AMD's Bulldozer-based FX-8130P benchmarked early - TechSpot News

*en.wikipedia.org/wiki/Bulldozer_(processor)

The release of Bulldozer is due to the performance issue but the general assumption that the performance is below the current generation Sandybridge processor is may not be true. It is highly possible that AMD has set their minimum threshold to a very high level to make everything correct after a long time.
One interesting thing, we were discussing in the ASUS Power user meetup, rather than 8 cores or 6 cores of Bulldozer, just consider the 8 core Bulldozer as 4 modules which is having almost 2 Physical cores, i.e. discrease execution units for most of the cases apart from the FPU and Fetch unit.

Intel 2600K is also a 4 module based design where each of the module has 2 logical cores but only one set of execution units. It has two thread register to hold two threads simultaneously.

Now in a single threaded applications, which has been a very strong point for Intel now, HT won't help and all the instructions present in the thread will be executed by one core with all its execution unit. It may be improved by out of Order execution, Pipelining, superscalar processing, but remember, inside a single core.
Now come to the case of a Bulldozer mudule. Here a single module is having two independent set of execution units. Now if a single thread is assigned to a BD module, the shared double Fetch and Dispatch unit will fetch the istructions present in that thread to the BD module as it is shared by both the cores. So the istructions present inside a single thread can be executed parallelly by two cores of a BD module. Suppose total number of instructions inside Thread T is 2N. just consider each of the core is processing N number of instructions and again N instructions for a core can be benifited rom the OOO, Supersacalar and Pipelining.
So actually even if a single thread is assigned to a BD module it can still use both the cores to implement a ILP which is not in the case of Sandybridge where ILP is possible only inside the one execution core and HT is not gonna help.
That's why in the single threaded Super PI, I guess bulldozer is performing better.

^^ what is ILP??

A

inductive logic programming i believe

or instruction level parallelism

Instruction-level parallelism. Check here:-

Instruction-level parallelism - Wikipedia, the free encyclopedia

Cilus I wanted to rep you for your post but TDF doesn't let me. Say I need to spread some around. So I will just +1 you.
+1

Cilus said:
The release of Bulldozer is due to the performance issue but the general assumption that the performance is below the current generation Sandybridge processor is may not be true. It is highly possible that AMD has set their minimum threshold to a very high level to make everything correct after a long time.
One interesting thing, we were discussing in the ASUS Power user meetup, rather than 8 cores or 6 cores of Bulldozer, just consider the 8 core Bulldozer as 4 modules which is having almost 2 Physical cores, i.e. discrease execution units for most of the cases apart from the FPU and Fetch unit.

Intel 2600K is also a 4 module based design where each of the module has 2 logical cores but only one set of execution units. It has two thread register to hold two threads simultaneously.

Now in a single threaded applications, which has been a very strong point for Intel now, HT won't help and all the instructions present in the thread will be executed by one core with all its execution unit. It may be improved by out of Order execution, Pipelining, superscalar processing, but remember, inside a single core.
Now come to the case of a Bulldozer mudule. Here a single module is having two independent set of execution units. Now if a single thread is assigned to a BD module, the shared double Fetch and Dispatch unit will fetch the istructions present in that thread to the BD module as it is shared by both the cores. So the istructions present inside a single thread can be executed parallelly by two cores of a BD module. Suppose total number of instructions inside Thread T is 2N. just consider each of the core is processing N number of instructions and again N instructions for a core can be benifited rom the OOO, Supersacalar and Pipelining.
So actually even if a single thread is assigned to a BD module it can still use both the cores to implement a ILP which is not in the case of Sandybridge where ILP is possible only inside the one execution core and HT is not gonna help.
That's why in the single threaded Super PI, I guess bulldozer is performing better.

just awesum explanation dude!
*bow down*

can you babysit me? :lol:

J

i will explain in simple words.

a normal core has one integer schedular and one floating point schedular.normally a core handles one thread.

a bulldozer module has two integer schedulars and one floating point schedular.

intel's hyper threading "forces" two threads through a core which has integer schedular and one floating schedular. hyperthreading in real world applications gives u 10-15% boost. synthetic benchmarks may show u 50-60% boost but that doesnt matter.

a bulldozer module will handle two threads and both threads will get their own integer schedular but will share the floating point schedular.

people think, bulldozer will obviously be good in multithreaded performance but are not sure about single threaded performance.

if bulldozer module handles a single thread and somehow the second integer schedular comes into play..then single threaded performance will also have some decent gain.

but this is all paper talk.we need bulldozer launching quickly.

core to core i still expect intel to be faster with their traditional approach but this will be of no practical significance as AMD with their bulldozer module approach will be able to pack in more cores in a limited die space and price compared to intel.

bulldozer also doesnt have to be faster than 2600k to win. history has taught us the fastest and better product doesnt always win. noobs are most likely to be fooled by the core count and insanely high clock speeds. another thing is...enthusiasts like us are a minority. real money is in server and OEM market.

Cilus said:
The release of Bulldozer is due to the performance issue but the general assumption that the performance is below the current generation Sandybridge processor is may not be true. It is highly possible that AMD has set their minimum threshold to a very high level to make everything correct after a long time.
One interesting thing, we were discussing in the ASUS Power user meetup, rather than 8 cores or 6 cores of Bulldozer, just consider the 8 core Bulldozer as 4 modules which is having almost 2 Physical cores, i.e. discrease execution units for most of the cases apart from the FPU and Fetch unit.

Intel 2600K is also a 4 module based design where each of the module has 2 logical cores but only one set of execution units. It has two thread register to hold two threads simultaneously.

Now in a single threaded applications, which has been a very strong point for Intel now, HT won't help and all the instructions present in the thread will be executed by one core with all its execution unit. It may be improved by out of Order execution, Pipelining, superscalar processing, but remember, inside a single core.
Now come to the case of a Bulldozer mudule. Here a single module is having two independent set of execution units. Now if a single thread is assigned to a BD module, the shared double Fetch and Dispatch unit will fetch the istructions present in that thread to the BD module as it is shared by both the cores. So the istructions present inside a single thread can be executed parallelly by two cores of a BD module. Suppose total number of instructions inside Thread T is 2N. just consider each of the core is processing N number of instructions and again N instructions for a core can be benifited rom the OOO, Supersacalar and Pipelining.
So actually even if a single thread is assigned to a BD module it can still use both the cores to implement a ILP which is not in the case of Sandybridge where ILP is possible only inside the one execution core and HT is not gonna help.
That's why in the single threaded Super PI, I guess bulldozer is performing better.

Nice explanation but why AMD is delaying Bulldozer release day by day- are they thinking of competing with SB-E but with what price or performance ;-)

Reportedly AMD is not happy with the clocks of the current stepping. There might be other reasons though.

Ya, Clock speed also plays a significant role in performance as architecture wise both the competitors are strong enough. AMD has faced lot of issues to deliver high clock speed in their previous gen architectures (who can forget the TLB Bug in their 1st series of Phenom Processors?) and their Trubo Core in Thuban is and also in Llano is simply not up to the mark. I guess they are making sure nothing of that kind will happen this time.
Example of Core clock speed is: If you overclock a 1090T or 1100T to 4 to 4.2 GHz, it beats Core i7 975 and perform closer to a i7 980X in most of the benchmarks.
By the way, yesterday, I have reached 3.9 GHz with my 1090T by using just the stock cooler. Idle was 32 degree and in load (while running 3D MArk 2011) it was 57 degree. I just increased the Multiplier to 19.5 and CPU V to 1.41 V. Great Oceing...na.

Joker said:
i will explain in simple words.

a normal core has one integer schedular and one floating point schedular.normally a core handles one thread.

a bulldozer module has two integer schedulars and one floating point schedular.

intel's hyper threading "forces" two threads through a core which has integer schedular and one floating schedular. hyperthreading in real world applications gives u 10-15% boost. synthetic benchmarks may show u 50-60% boost but that doesnt matter.

a bulldozer module will handle two threads and both threads will get their own integer schedular but will share the floating point schedular.

people think, bulldozer will obviously be good in multithreaded performance but are not sure about single threaded performance.

if bulldozer module handles a single thread and somehow the second integer schedular comes into play..then single threaded performance will also have some decent gain.

but this is all paper talk.we need bulldozer launching quickly.

core to core i still expect intel to be faster with their traditional approach but this will be of no practical significance as AMD with their bulldozer module approach will be able to pack in more cores in a limited die space and price compared to intel.

bulldozer also doesnt have to be faster than 2600k to win. history has taught us the fastest and better product doesnt always win. noobs are most likely to be fooled by the core count and insanely high clock speeds. another thing is...enthusiasts like us are a minority. real money is in server and OEM market.

Actually a cpu is more biased towards integer operations than floating point operations. A gpu handles more floating point operations and is in contrast.

Amd after acquiring ATI has now a lot of expertise in gpu manufacturing and they know this fact well. Therefore, they shared the floating point unit and gave an extra integer unit to a single bulldozer module.

Thus not exactly having an extra core as a normal core, it surely has twice the integer units than a generic single core. Since floating point performance does not matter that much in cpu based tasks, amd reffers its modules as two cores because of these two execution units.

Therefore any thread having multiple instructions will be divided between the two units. The integer operations will be executed by the two integer units giving rise to ILP whereas the float operations will be shared by the single unit. Therefore instruction level parallelism will be restricted to integer operations and this is what is required for a cpu.

Thus this is more efficient form of smt (simultaneous multithreading) than intel's hyperthreading.

Some update:-

AMD to Update FX Lineup of Microprocessors in Q1 2012 - Sources - X-bit labs

The initial family of AMD desktop chips based on Bulldozer micro-architecture due in September will include models FX-8150, FX-8100, FX-6100 and FX-4100. The refresh lineup scheduled to arrive in mid-Q1 2012 will contain FX-8170, FX-8120, FX-6120 and FX-4120 models.

Earlier this year it turned out that AMD had to delay commercial launch of its desktop FX-series microprocessors due to insufficient performance of B0 and B1 stepping Zambezi/Bulldozer processors, which could function only at around 2.50GHz/3.50GHz (nominal/turbo) clock-speeds. As a consequence, AMD needed to tune the design of the processor and create B2 stepping of the chip with better clock-speed potential amid similar thermal design power (TDP), which is not a quick process. Looks like the delay of the initial family also made AMD to postpone the refresh.

The first batch is not out and they are already talking about refreshes, does NOT look good.

Everything's OK, if the end product really lives up to the hype.

T

Kinda Off topic but For Gaming guys...I just went through the Anand Tech reviews for CPU & GPU Bottlenecking & it turns out that if you have any QUAD Core with more than 3 GHz Speed then you DO NOT need any CPU Upgrade. Above this point its all GFX Card. So people who already on C2Q & Phenom X4 actually dont need i5 or a BD as it wont give them anything. But if you are on Phenom X2 or C2D then your Proccy will bottleneck & you need a Upgrade. So for gamers atleast BD wont bring anything great but 7xxx will

Tech_Wiz said:
Kinda Off topic but For Gaming guys...I just went through the Anand Tech reviews for CPU & GPU Bottlenecking & it turns out that if you have any QUAD Core with more than 3 GHz Speed then you DO NOT need any CPU Upgrade. Above this point its all GFX Card. So people who already on C2Q & Phenom X4 actually dont need i5 or a BD as it wont give them anything. But if you are on Phenom X2 or C2D then your Proccy will bottleneck & you need a Upgrade. So for gamers atleast BD wont bring anything great but 7xxx will

Even a Q6600 oc'ed to 2.8 or 3GHz has descent gaming performance, we are not talking about gaming, anything over 2400 is overkill for any kind of gaming.

T

Yeah...So I guess a i5 OCed to 4 GHz+ will prevent CPU bottlenecking for 3-4 years at-least.

Coming back to Topic I also dont like the sound of refresh versions coming in so fast.

Tech_Wiz said:
Yeah...So I guess a i5 OCed to 4 GHz+ will prevent CPU bottlenecking for 3-4 years at-least.

Coming back to Topic I also dont like the sound of refresh versions coming in so fast.

Only for gaming and watching movies etc, and bragging as well :lol:

, for video encoding or compressing stuff 2600k helps a lot.

Exactly, a high end CPU is not just targeted for gaming only, it aslo targets the productivity areas. Adobe software like Photoshop, After Effects, Premiere, 3D designing software like 3Ds Max, Maya, Video encoding and decoding applications like Tmpgenc, AVidemux are very much CPU intensive and highly multi-threaded and can have very high level of performance boost with CPU with efficient architecture and more cores.
In this kind of scenarios CPU like 2600K or upcoming Bulldozer will be a great help.

^Yep...people like us should be worried less about benchmarks and more about the real world usage.

At last Intel is gonna have some competition...real competition!!! :))

So bulldozer is coming, meanwhile I'm thinking to buy Crosshair V Formula, will it support Bulldozer for later upgrade?

T

I think it will support after a Bios Upgrade.

Crosshair V Formula is a 990FX based mobo. It already supports BD natively. A BIOS update might be needed later.

AMD has been putting up some weird comics on their website. Either their PR department has gone crazy/consists of kids or they are being pretty confident.

eh, ico, can you post the links?

that's great, cuz according to my upgrade plan right now I've got 15k for the board will go for this one next month and BD CPU after its out.

^^ imho, first wait for BD to come out and then get both - the board and the processor.

VarDOS said:
So bulldozer is coming, meanwhile I'm thinking to buy Crosshair V Formula, will it support Bulldozer for later upgrade?

it will...buy it....and take some time to learn the bios...its all worth it

ico said:
^^ imho, first wait for BD to come out and then get both - the board and the processor.

buying the board now wont be a bad idea...since even an chap athlon II x2 will work on that board...
IMHO he should buy the board first and learn the technicalities of the BIOS

sumonpathak said:
buying the board now wont be a bad idea...since even an chap athlon II x2 will work on that board...
IMHO he should buy the board first and learn the technicalities of the BIOS

he might regret not going for Sandy Bridge if Bulldozer doesn't turn out to be good. That's my point.

from what i have seen the gaming performance that everyone seeks is almost at par....but that's only me....others may beg/desire to differ

ico said:
That's my point.

That's the point!, ROG's supporting SB are damn costly 26k for mobo where as this one is pretty cheap. I'm building this kinda a desk and that's why ROG boards are must.

VarDOS said:
That's the point!, ROG's supporting SB are damn costly 26k for mobo where as this one is pretty cheap. I'm building this kinda a desk and that's why ROG boards are must.

Couldn't get you, why ROG is must for that type of setup?

^^he wants a ROG mobo...but dont want it to cost it too much

sumonpathak said:
^^he wants a ROG mobo...but dont want it to cost it too much

exactly!

I'll be showing off my motherboard through the glass in the desk, ROG boards have performance + beauty which even look cool than other boards and that's why I want ROG board.

OK, Got it.

Latest Update, and with a date:-

AMD hints at September 19 release date for FX-Series APUs - TechSpot News

Here's the video:-

But, APUs... ???

like the blue vs red theme

lol, that's what I was talking about - looks childish. Google more, you'll also find a comic on AMD's website. It says 8-core BD is ~$300. If that is to be believed, then I think it would beat i7-2600k as AMD has always offered better performance per dollar.

They haven't teased Intel at this level during the Athlon 64 days. Don't know from where they are getting the confidence.

maybe they got something....me gettin a bullz....

Have a look at this:

If I was an ~~AMD~~ nVidia fan, I'd be pissed.

ico said:
lol, that's what I was talking about - looks childish. Google more, you'll also find a comic on AMD's website. It says 8-core BD is ~$300. If that is to be believed, then I think it would beat i7-2600k as AMD has always offered better performance per dollar.

I think their hexcore fx 6100 will beat the 2600k. This is why amd is delaying BD, as its optimizing them for a perfect launch.

Amd has to beat i7 2600k handsdown to stay in competition and i think it will do so.

I mean its not bad to be bit optimistic. :wink:

Either AMD is outta their mind or they have something like the S1000RR
BMW also went head on with the comics over the Japanese manufacturers
But they delivered a machine that was the best of the best

Hope this happens with AMD too

Skud said:
eh, ico, can you post the links?

Operation Scorpius

EDIT:
Read the comic, it pretty lame.

Already checked it last night. Guess, they have some aces under their sleeves.

Something better than Bulldozer:-

*fudzilla.com/processors/item/23525-amds-2012-cpu-lineup-detailed

Pics:-

*2f.zol-img.com.cn/product/68_800x600/531/ceWclXQ9CKfg.jpg

*2a.zol-img.com.cn/product/68_800x600/532/cehuMJ7S3Bqy.jpg

And some news for server:-

Server Maker Leaks Clock-Speeds of AMD Opteron "Bulldozer" Chips - X-bit labs

Already had doubts about AMD discontinuing AM3+. Won't blame them if they do so.

lets hope they come out with pinless architecture

ico said:
Already had doubts about AMD discontinuing AM3+. Won't blame them if they do so.

So, we need to wait more???

^^ Just a couple of months i guess. :smile:

Apparently:-

*wccftech.com/wp-content/uploads/2011/07/7-24-2011-1-29-15-AM.jpg

T

That Comic Thing is so lame! I wont even call it funny tbh

seems that amd era is going to come back :-D

sukesh1090 said:
seems that amd era is going to come back

With added asset of ATI, and the revival of processors they may make an excellent combo, which will make intel and nvidia run to reduce costs to lure customers

In this epic battle, consumer will always win :wink:

Guys, for your info.

The first wave of high-performance desktop systems AMD FX processor will make its appearance in stores on September 19 according to sources on the Internet.

Source

T

Yeah I read that. I hope BD lives up to the Hypes and Smoke SBs by a decent margin.

8100 or 8150 for 300$

AMD confirmed that either the FX-8150P or FX-8100 chip will cost approximately $300.

AMD Confirms Pricing of Eight-Core FX Processors: Approximately $300 - X-bit labs

there is some new info/rumors that there will be only a paper launch of BD in Sept!!!!!

hmmm, there was another news that retail availability will be from October... :?:

^^ no matter if it's Sept or oct - we will see that in local markets on nov/dec for sure - guys start ( who are interested ) planning to get it as a Christmas gift ;-)

mostly till now all the AMD release have come at the same time as world wide release!!!
i.e. Thuban, Llano A8(Desktop), HD6000

Not exactly Bulldozer news, but might be interesting read.

1. Maximum PC | Intel to Ship Sandy Bridge-E in November, Prevent Balls to the Wall Overclocking of Ivy Bridge

2. Exclusive: Sandy Bridge-E now expected to launch in November, X79 chipset getting further feature cuts by VR-Zone.com

We're also hearing that Intel is worried about AMD's FX processor refresh which should take place early next year, maybe not in terms of raw performance, but the company needs to have its platform out there to show that the company has yet another high-end platform ready to go. Make what you want of this, but to manage to meet the November deadline, Intel has cut further features from its X79 chipset.

If you remember the article from a couple of weeks ago which had the same diagram as the one above, we told you that Intel had gone from the server level Patsburg-D to the Patsburg-B level chipset for the X79. Well, now we're talking Patsburg-A, i.e. no SAS support at all. In other words, we're looking at a chipset very similar to Intel's current P67 chipset, as it will only sport two SATA 6Gbps ports and four SATA 3Gbps. This is starting to make it look less and less like that Intel will simply be able to "enable" these features by a software upgrade in the future and instead we can either look forward to a chipset revision or a new, more expensive chipset for the Waimea Bay platform.

And it doesn't stop there, we have more bad news with regards to the X79 chipset, but that's another story…

Let's wait and see how strong bulldozer is going to be.

oh boy .. I'm smelling a bull fight ;-)

BTW, one of our forum member ( clear_lot ) is saying :

BD is confirmed to be released on 19 september.

- link

@ Skud - on your pic on post no. 518 - there's two BD cpu is going to be released on 19th sept - where from you get that image ?

can anyone confirm this ...

T

I read that 19th Sept date on some other Forum as well. But I doubt it

topgear said:
@ Skud - on your pic on post no. 518 - there's two BD cpu is going to be released on 19th sept - where from you get that image ?

can anyone confirm this ...

Read post #522

Too bad Bulldozer is coming in mid-September. Most probably I'll be going to USA - late August. Might buy i7-2600k then.

topgear said:
oh boy .. I'm smelling a bull fight

BTW, one of our forum member ( clear_lot ) is saying :

- link

@ Skud - on your pic on post no. 518 - there's two BD cpu is going to be released on 19th sept - where from you get that image ?

can anyone confirm this ...

I got it from here:-

AMD Bulldozer Launch in September Now Official, Two New 8 Core FX Processors to arrive in Q1 2012

D

September Launch is official as stated in terms of condition on amd's contest website.

^^ good to know about the source ;-)

MegaMind said:
Read post #522

^^ thanks for pointing it out ;-)

let's see how a $300 BD ( OCed ) holds up against a core i5 2500k ( Oced ) - getting impatient to see some real benchmark ;-)

Not exact a bulldozer news, but surely a good news for all
Intel lines up 2500k/2600k price cuts to welcome FX | KitGuru

Bulldozer to ship soon, really soon | SemiAccurate

ico said:
Too bad Bulldozer is coming in mid-September. Most probably I'll be going to USA - late August. Might buy i7-2600k then.

lucky you! Those are cheap there (compared to here), but do you have to pay import duties and taxes to bring them with you here???

What AMD is really up to with their first line of Bulldozers? Now they are planning to ship a Antec Kühler H2O 620 or similar water-cooling solution with their octa-core BDs :shock:

:

AMD Considers Equipping FX Chips with Liquid-Cooling Solution - X-bit labs

Guess they are building something seriously good or seriously bad. At the very least, no more headache over RAM heatsink height.

But one line from the article I found pretty funny:

Both Advanced Micro Devices and Intel have been bundling rather powerful air cooling solutions with their chips for a number of years now.

AMD, I understand, but Intel? Powerful air cooling? :rofl:

Skud said:
AMD, I understand, but Intel? Powerful air cooling?

May be their stock air cooling fan is tested at 6C temp.

That's called "tested at lab condition".

Skud said:
That's called "tested at lab condition".

Who knows whether their lab temperature is 6-7C or not. :evil:

T

Seriously My C2D use to idle at 50 and my Quad Phenom Idles at 39. Numbers speak for themselves.

Tech_Wiz said:
Seriously My C2D use to idle at 50 and my Quad Phenom Idles at 39. Numbers speak for themselves.

Are you using your quad phenom with its stock cooler?

Skud said:
What AMD is really up to with their first line of Bulldozers? Now they are planning to ship a Antec Kühler H2O 620 or similar water-cooling solution with their octa-core BDs

it'll be better if they ship their ship some of their highend octacores without any HSF. let customers decide for themselve what they want. H20 or O2 (or LN2) cooling.

Skud said:
AMD, I understand, but Intel? Powerful air cooling?

both makes toy fans.

Tech_Wiz said:
Seriously My C2D use to idle at 50 and my Quad Phenom Idles at 39. Numbers speak for themselves.

half of Phenom II coolers are faulty. they pack heatpipes but with a tiny fan & lowquality heatsink, they will be rejected by scrapmetal works also.

Intel's story is not much different. my P4 used to have a solid aluminum block to take away heat. uncle's core2quad sink became half the size. but at least most of their heatsink works. its different that a good percent suffer from overheating problems but at least the noise level is within limits.

If amd is bundling liquid coolers with BD then guess what the thermals will be, I was right people, Fermi is being reincarnated by amd.

tkin said:
If amd is bundling liquid coolers with BD then guess what the thermals will be, I was right people, Fermi is being reincarnated by amd.

Here you are talking about very good point. But if the thermals are too high then it can't be used with air coolers. :-(

tkin said:
If amd is bundling liquid coolers with BD then guess what the thermals will be, I was right people, Fermi is being reincarnated by amd.

AMD FX = enthusiasts platform. i am not denying what you say but more likely AMD is targeting the overclockers & not solving overheat problems.

^^ I think it's an exciting launch offer to show this cpu is made for Ocers and gamers and this might bump up the sell of enthusiast series mobos anyway - but what AMD is doing is the first in the history of cpu world - bundling a liquid cooler - I would be more happy to see a CM Hyper 212+ or similar cooler with the high end cpus ;-)

T

d6bmg said:
Are you using your quad phenom with its stock cooler?

Yeah Always on Stock and OCed it to 3.6 Ghz and still temp are pretty much under control. Mentioned in my Siggy also :grin:

Sam said:
Re: AMD Bulldozer News and Discussion
half of Phenom II coolers are faulty. they pack heatpipes but with a tiny fan & lowquality heatsink, they will be rejected by scrapmetal works also.

Well I must be pretty lucky then as this is my 3rd AMD and none of there coolers have failed on me so far in spite of moderate OCing for 400-600 MHz) ;-)

And I think the Liquid Cooling is kinda a Enthusiastic Attraction Thing than real life usage issue.
And Intel should implement it first for their i7 Line right now :twisted:

I read in that article that intel too will be providing liquid coolers or good air cooling solutions with its high end sandybridge-E offerings with socket 2011.

And what if that cooler just blows up? Will AMD or Intel pay for all my damaged components?

^^ Never heard of coolers blowing up. Even if it does, i think its warranty will be included along with the processor i.e 3 years.

It's already discussed here a couple of months back. There's one incident (posted most probably in HardOCP forums along with pics) in which a H50/70 of one user was blown up and the coolant destroys his graphics card and mobo among others. In that particular case, Corsair was generous enough to reimburse his total loss.

My point was if something like that happen then whether AMD and Intel would have a similar policy in place. :?:

Skud said:
It's already discussed here a couple of months back. There's one incident (posted most probably in HardOCP forums along with pics) in which a H50/70 of one user was blown up and the coolant destroys his graphics card and mobo among others. In that particular case, Corsair was generous enough to reimburse his total loss.

My point was if something like that happen then whether AMD and Intel would have a similar policy in place.

xactly bro! I don't think that the service centre's in our city are kind enough to replace or reimburse the damaged components. First, they need to strengthen up the service points!

Skud said:
It's already discussed here a couple of months back. There's one incident (posted most probably in HardOCP forums along with pics) in which a H50/70 of one user was blown up and the coolant destroys his graphics card and mobo among others. In that particular case, Corsair was generous enough to reimburse his total loss.

My point was if something like that happen then whether AMD and Intel would have a similar policy in place.

Can you point me to that thread? I want to give it a look.

vickybat said:
I read in that article that intel too will be providing liquid coolers or good air cooling solutions with its high end sandybridge-E offerings with socket 2011.

That's called cat and dog competition.

vickybat said:
Can you point me to that thread? I want to give it a look.

me too.

coolers may leak (extremely rare) but blow up? never heard. link please.

Sam said:
coolers may leak (extremely rare) but blow up? never heard. link please.

He means leaks, not blow up, but either way damage will be catastrophic due to the fluid inside being distilled water which becomes conductive when it comes in contact with impurities present on the pcb of the hardware.

H70 Broke! Coolant Everywhere! Help! - The Corsair Support Forums

My H70 pump has blewn up and caused a major leaked - The Corsair Support Forums

Corsair H70 leaking fluid that smells like anti-freeze from my truck/van!

Corsair H50 Leak! go with the H70

There are plenty more issues like this, but corsair USA replaces all the parts damaged, but no such policies exist elsewhere, the shipping parts to USA part will cost a fortune.

Always go with air coolers, Noctua NH-D14 will rip corsair Hydro apart(the ones that come within same price bracket, like H70).

Basically this is the incident I am talking about:

Pictures of when your H70 pump decides to blow up! - [H]ard|Forum

Sort of blown up, as per the poster. And as tkin has mentioned, there are more issues like this.

^^ Yes, the cooler really gave way. Hats of to corsair though for replacing the 580 as well.
I think in future designs, they'll do away with plastic and use aluminium casings to prevent a complete meltdown.

In amd's case, i think they will cover everything if in case such incident happens. But the poor service in india totally make things unpredictable.

vickybat said:
^^ Yes, the cooler really gave way. Hats of to corsair though for replacing the 580 as well.
I think in future designs, they'll do away with plastic and use aluminium casings to prevent a complete meltdown.

In amd's case, i think they will cover everything if in case such incident happens. But the poor service in india totally make things unpredictable.

AMD support is not as good as corsair(pretty bad actually), corsair has a dedicated forum where all our queries are answered very fast by official forum personnels, if you ever go to AMD Game forum you'll see that none of the questions are ever answered by officials, moreover some raging fanboy trolls ruin every thread there, so using that bundled cooler is like inviting troubles.

Better stick to air.

^^ Haha, rightly said mate. :smile:

tkin said:
AMD support is not as good as corsair(pretty bad actually), corsair has a dedicated forum where all our queries are answered very fast by official forum personnels, if you ever go to AMD Game forum you'll see that none of the questions are ever answered by officials, moreover some raging fanboy trolls ruin every thread there, so using that bundled cooler is like inviting troubles.

Better stick to air.

I wholeheartedly agree with this. I was having some driver related problems with my 4850 during it's initial days. Never get a proper reply. Have left the forums since.

tkin said:
He means leaks, not blow up, but either way damage will be catastrophic due to the fluid inside being distilled water which becomes conductive when it comes in contact with impurities present on the pcb of the hardware.

H70 Broke! Coolant Everywhere! Help! - The Corsair Support Forums

My H70 pump has blewn up and caused a major leaked - The Corsair Support Forums

Corsair H70 leaking fluid that smells like anti-freeze from my truck/van!

Corsair H50 Leak! go with the H70

There are plenty more issues like this, but corsair USA replaces all the parts damaged, but no such policies exist elsewhere, the shipping parts to USA part will cost a fortune.

Always go with air coolers, Noctua NH-D14 will rip corsair Hydro apart(the ones that come within same price bracket, like H70).

Wow!! In USA corsair is so fast!! Hopefully one day they will be here in India selling their products directly rather than via resellers.

tkin said:
He means leaks, not blow up, but either way damage will be catastrophic due to the fluid inside being distilled water which becomes conductive when it comes in contact with impurities present on the pcb of the hardware.

H70 Broke! Coolant Everywhere! Help! - The Corsair Support Forums

My H70 pump has blewn up and caused a major leaked - The Corsair Support Forums

Corsair H70 leaking fluid that smells like anti-freeze from my truck/van!

Corsair H50 Leak! go with the H70

There are plenty more issues like this, but corsair USA replaces all the parts damaged, but no such policies exist elsewhere, the shipping parts to USA part will cost a fortune.

Always go with air coolers, Noctua NH-D14 will rip corsair Hydro apart(the ones that come within same price bracket, like H70).

looking at the incidents I think it's better to stick with air and my hyper 212 might work with BD cpus anyway ;-)

^^ will you buy BD ? which one ?

topgear said:
looking at the incidents I think it's better to stick with air and my hyper 212 might work with BD cpus anyway

As per reports, any cooler working with AM3 CPUs should work with BDs also.

AMD's socket mounting hasn't really changed since Socket 754 days, I think.

yep and it's good IMO - no need to get a new cpu cooler every time if the cooler can perform with new cpus ;-)

nilgtx260 said:
^^ will you buy BD ? which one ?

Skud said:
As per reports, any cooler working with AM3 CPUs should work with BDs also.

let's see the price and performance first ;-)

any best place to buy ASUS Crosshair V Formula (online) ? SMC International just removed that board

. I'll be buying it first week of September.

Just mail them asking for it.

Cybertonic said:
Just mail them asking for it.

just did that, now waiting for their reply

VarDOS said:
any best place to buy ASUS Crosshair V Formula (online) ? SMC International just removed that board . I'll be buying it first week of September.

ur location?

H

VarDOS said:
any best place to buy ASUS Crosshair V Formula (online) ? SMC International just removed that board . I'll be buying it first week of September.

try lynx-india.com

M

SMC will have Crosshair V by Wednesday....I am too wanting this mobo...

monkey said:
SMC will have Crosshair V by Wednesday....I am too wanting this mobo...

Go to lynx-india.

Asus Crosshair V Formula @ 15.1K + Vat is available at MD computers ( Kolkata ) - info given by cilus ;-)

sumonpathak said:
ur location?

Karad, Maharashtra! -can buy from Mumbai.

@hector: Lynx doesn't have the board.

@topgear: that's nice, pretty cheap than SMC. But including shipping it will cost the same.

as Cybertonic said I mailed them and now they have the board in their stock. SMC replied me saying, the board is back in stock and just confirm the product availability before ordering.

any better deals for Crosshair V Formula on streets?

M

topgear said:
Asus Crosshair V Formula @ 15.1K + Vat is available at MD computers ( Kolkata ) - info given by cilus

SMC gave me quote of 14.8k (tax paid) so I will wait.

monkey said:
SMC gave me quote of 14.8k (tax paid) so I will wait.

That's awesome deal, I'll be buying one first week of next month hope the price falls

Has any body came to know about the 990fx chipset from asrock, ecs if yes how is the quality and what would be price in India.

^^^more than the quality you should think bout the brand presence here....from what i have heard they are not so good...

Asrock is somewhat popular amongst OCers, but availability here is a big issue.

monkey said:
SMC gave me quote of 14.8k (tax paid) so I will wait.

that's an awesome deal and thanks for informing this ;-)

BTW, any news on the availability of 990X or 970 mobos ;-)

topgear said:
that's an awesome deal and thanks for informing this

BTW, any news on the availability of 990X or 970 mobos

May be not before BD is actually launched.

POST ADDED
AMD has released some architectural details of the Bulldozer, check here:-

AMD's Bulldozer: More Design Details Surface

You can check the slideshow here:-

Bild Einzelnes â€žBulldozerâ€œ-Modul (1/19) - ComputerBase

Well I was not actually following any CPU but now when I have to purchase a new PC so I need to follow. I hope that Bulldozer what it meant to be. I have high expectations from it.

Thanks for the link Skud that was quite informative for a noob like me.

Guess I am in a situation with SNB, never really followed it.

I had planned a short preview on amd’s new bulldozer architecture but couldn’t find sufficient details on it. The first architectural details that surfaced some months back were vague tbh and were not sufficient for proper interpretation. Now AMD has released some slides which discusses its architectural design in a more finer detail and what exactly bulldozer brings to the table. I have taken help from various sources to write this.

Out of order execution –

We already know that bulldozer has two tightly coupled out of order processing units which it call modules. Talking about out of order, this is where its competitor intel was superior cause in its latest sandybridge microarchitecture , intel had greatly worked on the out of order execution capabilities. Out of order execution is nothing but the new order in which instructions in a thread are executed and not the original order of instructions the program already has.
Lets say a thread has 4 instructions A,B,C & D where A depends on C & B depends on D. Now when a processor’s execution engines process the thread in the original order , there will be a lot of dependencies and a significant delay because A will wait for D’S execution and B will wait for C’s execution.
But lets say we change the order to D ,A ,C & B. Then there will be no dependencies and execution will go smoothly without any halts or delays. This is out of order execution and is handled by the cpu’s frontend which we will discuss more. Bulldozer improves greatly on this part. The instructions in found in today’s apps and programs are far complex than the above example. So out of order execution significantly improves a processor’s efficiency and execution time.

Bulldozer Die –

*i55.tinypic.com/sc98wg.jpg
The standard bulldozer die has a modules or the execution cores which has 128kb L1 cache (32kb/module or 16kb / core). It will have a 64 bytes cacheline which is nothing but data in each location of the cache which has an index, tag and the data. Index is the address and is unique for each cacheline . Tag is the index value of the main memory present in cache. Data hold the value fetched from main memory.
When the cpu needs to read or write a location in main memory, it first checks whether that memory location is in the cache. This is accomplished by comparing the address of the memory location to all tags in the cache that might contain that address. If the processor finds that the memory location is in the cache, we say that a cache hit has occurred; otherwise, we speak of a cache miss. In the case of a cache hit, the processor immediately reads or writes the data in the cache line. The proportion of accesses that result in a cache hit is known as the hit rate, and is a measure of the effectiveness of the cache for a given program or algorithm.
Talking about associativity , it’s the number of times, the copy of main memory goes to a cpu cacheline.
Bulldozer has a 4-way associativity in its L1 cache.

The L2 cache is big and is 8MB in totally or 2mb dedicated per module with same 64 byte cacheline but is 16 way associative.
The die also has the north bridge integrated with 8mb L3 cache which is shared among four modules, 2 72 bit wide memory channels( as seen in the diagram) and 4 16 bit transmit & 16 bit receive hypertransport links for communication with other peripherals.

Bulldozer module –

*i56.tinypic.com/2zj99hz.jpg
The bulldozer module contains the fetch and decode (frontend) which we will discuss later. Each bulldozer module has a fetch and decode unit. The actual execution units consist of two separate integer units that contains a scheduler 4 instruction pipelines and L1 data cache. Scheduling is nothing but the assignment of processes to the cpu execution unit for processing and is a very fundamental aspect in a multitasking environment. We will discuss more in detail. The integer units work only on an integer data set.
Next up is a single floating point execution unit that packs the floating point scheduler , two 128bit FMAC pipelines and the L2 cache. Note that the l2 cache is shared by both integer and floating units but l1 cache is dedicated to integer units only. More details will follow later.

Bulldozer Core ( shared frontend)-

*i53.tinypic.com/es26o0.jpg

Ok now lets delve a bit deeper shall we?

Fetch -

The front-end has been entirely modified and is now responsible for feeding both cores within a module. Bulldozer’s front end includes branch prediction, instruction fetching, instruction decoding and macro-op dispatch. These stages are effectively multi-threaded with single cycle switching between threads.
Since Bulldozer is termed as a high frequency design, branch prediction is critically important. Deeper pipelines tend to have more instruction in-flight at a given time, thus mispredicts can result in mixing of more instructions. The number of instructions mixed of is directly related to the wasted energy and performance.
The branch predictor is shared by the two cores in each module and decoupled from the instruction fetching via a pair of prediction queues (one queue per core). The branch predictor can run-ahead and will continue to predict new relative instruction pointers (RIPs) unless the queues are full.
The first step in branch prediction is determining the direction – whether a branch is taken or not. Once a branch is predicted as taken, the next step is to determine the target. For branches with a single target address, the branch target buffer (BTB) has been substantially expanded and now uses a two level hierarchy, similar to Nehalem. The L1 BTB is a 512 entry, 4-way associative structure that resolves predictions with a single cycle penalty to the pipeline. The L2 BTB is much larger with 5120 entries and 5-way associativity, but the extra capacity will cost additional latency for a L2 BTB hit. The BTBs in Bulldozer are competitively shared by both cores, but provide greater coverage than the 2K entry BTB in Istanbul.
Once a RIP is placed into the prediction queue and passed to the next stage, the fetch unit accesses the dynamically shared ITLBs (Instruction TLB) and L1 I-cache. The L1 ITLB is fully associative with 72 entries for the various page sizes. Tlb or translation lookaside buffer maps the virtual and physical address spaces. So here, the instruction pointer in the prediction queue are mapped with tlb and instruction cache.

Decode –

*i53.tinypic.com/2qjvbt0.jpg
The decode phase of bulldozer has been modified and now consists of a micro code engine and 4 decoders. After taking the fetched instruction from the 32 byte buffer queue, its decoded in 4 instructions per cycle owing to 4 physical decode engines. After examining the instruction window, the decoders translate each x86 instruction into 1 or 2 macro-operations and place them into a queue for dispatching. Microcoded instructions (i.e. those requiring more than 2 macro-operations) are handled by the microcode ROM . In addition to having an extra decoder, Bulldozer is the first AMD CPU with branch fusion, whereby an adjacent arithmetic test or comparison and a jump instruction are decoded into a single macro-op
Then the decoded macro-ops instructions are dispatched and handled by the execution units present in the cores.

Before delving further into decoding, it is useful to discuss some terminology. Intel refers to the variable length x86 instructions as macro-operations. These can be quite complex, with multiple memory and arithmetic operations. Intel refers to their own simpler internal, fixed length operations as micro-ops or uops. AMD’s terminology is subtly (and confusingly) different. In AMD parlance, x86 instructions are referred to as AMD64 instructions – again, variable length and potentially quite complex. An AMD macro-operation is an internal, fixed length operation that may include both an arithmetic operation and a memory operation (e.g. a single macro-op may be a read-modify-write). In some cases, AMD also refers to these macro-ops as complex ops or cops. An AMD uop is an even simpler, fixed length operation that performs a single operation: arithmetic, load or store – but only one, and not a combination. So in theory, an AMD macro-op could translate into 3 AMD uops. The best way to think about AMD’s arrangement is that macro-ops are how the out-of-order microarchitecture tracks work, while uops are executed in execution units.

The bulldozer core –

Integer cores –

*i51.tinypic.com/ejg22e.jpg

*i56.tinypic.com/2gui1au.jpg

Coming down to the execution cores, lets first look at the integer cores. There are two integer cores in a single bulldozer module. Now the decoded instructions from the dispatch queue in the form of macro-ops are stored in the instruction retirement queue. Upto 4 macro-ops can be stored per integer core.The retirement queue also maintains the bookkeeping logic for each macro-op.
Memory operations must also allocate an entry in the appropriate load or store queue, to maintain x86 consistency. However, any FP or SIMD macro-ops will be sent to the floating point cluster to continue execution, although the retirement status is tracked in the integer core. Note that a FP or SIMD memory access will dispatch both a memory macro-operation to the integer core and an execution macro-operation to the FP cluster.
Bulldozer’s physical register file (PRF) based renaming is a fundamental change to the out-of-order microarchitecture. In microarchitectures using a physical register file, there also are two structures to hold the state, but they are divided based on function. One structure is the physical register file, which holds all the data values – both for speculative renamed registers and architectural registers. The other structure is what AMD calls the retirement queue, which holds a pointer to the appropriate entry in the PRF and also status information about each in-flight macro-op and the associated register (e.g. is the register speculative or architectural). This microarchitecture enables lower power retirement and rollback, by manipulating the retirement queue pointers that map into the PRF, rather than copying register values. In Bulldozer, up to 4 macro-ops can be retired each cycle, matching the throughput in the rest of the CPU. Branch mispredicts are handled by a flash clear, which likely reverts the retirement queue to a prior known good state.
Once renamed, macro-operations are placed into the 40 entry unified scheduler where they are held until all the necessary resources, such as source operands are available. When uops are ready, the scheduler will issue up to four of the oldest uops to the appropriate execution units.

Integer execution units –

Bulldozer’s integer execution units can be thought of as two mostly identical groups (0 and 1) and the ALU.The two units (0 and 1) are identical and perform the address calculations that feed into the load-store unit and cache hierarchy. The integer execution units (EX 0 and EX 1) are each a fully featured ALU capable of executing the vast majority of integer operations. Ex 0 is the integer divider whereas EX 1 is the integer multiplier.

Shared Floating Point Cluster –

*i53.tinypic.com/6ss4cj.jpg

*i54.tinypic.com/2nk71fo.jpg

The floating point cluster for Bulldozer has its own four-wide out-of-order execution facilities including renaming, scheduling and register files. We also know that it relies upon the integer cores for handling any loads and stores and also retiring macro-ops.
When a dispatch group is sent to a core, any FP or SIMD macro-ops are allocated an entry in the retirement queue, just like the integer macro-ops. However, the floating point or SIMD macro-ops are then sent to the FP cluster for renaming, scheduling and execution.
The incoming FP and SIMD instructions follow a similar manner as the integer part. The decoded instructions or macro-ops are renamed in a PRF (similar to integer PRF). It is dynamically shared between the two cores and has 160 entries. So that’s a wide PRF.
If the PRF is 128 bits wide, and lets say an instruction is 256 bit, it will decode as two macro-ops and use two entries in the PRF, Scheduler and retirement queue. Then the macro-ops are moved into the scheduler which contains 60 macro-ops. Then these macro-ops are fed to the appropriate pipeline for execution.

Shared Floating Point Execution Units –

All execution units in bulldozer are 128 bits wide because it can execute the new AVX instruction. Thus all 256 bits instructions will be divided into two macro-ops. Like the integer cores, bulldozer does away with a dedicated scheduler and lanes and prefers a flexible unified approach. All the 4 pipelines are fed into the 60 entry scheduler.
The heart of the cluster contains two 128bit FMAC (FLOATING POINT MULTIPLY-ACCUMULATE) units that can also perform division and squareroot with variable latency.
In addition, they also execute FADD & FMUL instructions including AMD’s own XOP instruction set as well for numeric, multimedia and algorithms as well. The first pipeline or first FMAC also converts integer to floating point numbers whereas the second pipeline does permutations, combinations , shifts, shuffles, packing and unpacking operations as well.

** More info on memory and power management will be added shortly. :smile:

Very good article Vicky, waiting for your next one. I think I can add some more contents later.

nice writeup...can you share the source of your info? i mean the details...

Real nice article bat.

nice compilation vicky - waiting for the memory and power management part ;-)

Great article Vickybat. ;-)

Some more news:-

Bulldozer comes on September 19th

AMD's A-list is currently seeing what we know as Bulldozer at a secret presentation in Huston, Texas. They will be showed AMD's much delayed answer to Core i7 and Core i5 processors but our multiple, well informed sources claim that it won’t be able to beat the Core i7 second generation, Sandy Bridge core. However not everything is lost as AMD's six and eight-core CPUs will end up significantly cheaper and will offer pretty good value for money.

The issue is the IPC, instructions per clock don’t perform as well we they should and they cannot do enough calculations fast to beat Intel's current offering. Let’s not even mention that the third generation of Core i7, Ivy Bridge at 22nm will be even faster. And there is Sandy Bridge E coming to take over the crown lead.

AMD at least got its act together and can produce this rather complicated chip in volume, as our sources claim that Bulldozer yields are at good levels, and that they are in much better shape than Llano, AMD’s A-series APU.

The good thing is that this chip is showing its face after a two year delay. Bear in mind that Bulldozer is the first massive change of AMD core after K8 and K10 and that it has to last for a very long time.

2013 Bulldozer successor is 28nm

And apparently, Gigabyte has given out the details of the CPUs:-

GIGABYTE TECHNOLOGY Socket AM3+ - AMD 990FX - GA-990FXA-UD7 (rev. 1.0)

And some more:-

AMD's Highly-Anticipated Bulldozer Chips May Face Further Delay

^^ Sounds quite bad, specially when I read its cpi can't beat i7 2nd gen processors. :-(

J

great article vickey :razz:

D

is bulldozer available now?
I've enquired in Lamington Road shop and they say its available..
So are they providing fake processors or anything like that?
Need help here

They may be confusing with Llano. BD is not yet released.

yes i too felt very bad when i saw it can't beat i7 but still small hope is left in me.

Bulldozer sounds mythical to be honest. I expect it to be a notch below the i7. And AMD will improve it with revisions.

On a basis of single core performance, BD won't be able to touch intel, but with multicore it may pose a healthy competition for 2500k or lower, 2600k will remain on top due to hyperthreading(its gives a monster boost).

Still waiting for price fall of 2600K. But it looks like it will not come soon. :-(

I recon bulldozer's single threaded performance to be higher than 1155 sandybridge cpu's owing to the shared frontend which dispatches dependent instructions simultaneously to two execution units at once.

A thread having lot of dependent instructions will favor bulldozer's modular architecture and its shared frontend.

AMD is utilizing ILP here and not only TLP because not only independent instructions will be executed but the dependent instructions will too be executed in the single module owing to its shared resources. This is very different from hyperthreading that intel employs as it doesn't have a shared frontend like bulldozer. A conventional dual core cpu as individual fetch and decode units for a single core and a dual core bulldozer has a single module with shared fetch and decode. So it can assign multiple instructions from multiple threads to its two execution units whereas in a normal dual core , the frontend of one hyperthreaded core takes up instructions from a single thread. But if there are dependencies with a second thread ,it has to wait until instructions are executed from 2nd thread. Remember they have a single execution unit percore (both integer and floating point units to be considered as one).

Had a long chat with CILUS as he had prepared a terrific article on threading which explains SMT (simultaneous multithreading) and hyperthreading in detail. He explained me the whole thing and will be providing the content to the entire TDF universe.

After reading that, lots of doubts will be cleared on the threading concept including single and multithreading performance of a conventional cpu.

Lemme troll a bit: You guys rock!!!

@vickybat,
then what say will BD beats i7 2600K or not?
waiting for the article.way to get some knowledge which i don't have much.

^^ Yes it will. Things currently are leading that way.

then we can suggest people to wait for BD if they want to buy a new PC. :grin:

TBH waiting is for nobs. Get what is best now, i.e., Intel.

Will think about bulldozer when it releases. That said, I hope AMD gives Intel good competition here.

I'm currently doing the last minute touch to my article where I've explained everything about multi threading...from the single threaded single module to a Hyper-threaded module, about operating system with block diagrams and examples. But it is huge, you guys need to be little patient to read it.

But still some words about HT and Bulldozer cores:-

Actually 1 module of Bulldozer will beat one Hyperthreaded core of Intel i7 but if you consider 1 module as two cores then each of the core's performance is not as good as Intel Sandybridge hyper-threaded core.
There is a misconception that Hyper-threading is TLP, not ILP, which is actually wrong. Holding two threads inside CPU thread registers and switching to one when the other one is busy or waiting for resources...which is the basic concept of Hyperthreading...is actually a misconception. The above mentioned technique is called Superthreading, not Hyper-threading. Hyper-threading improves the Thread level Parallelism by improving ILP. In HT, if the CPU fronted (fetch, decode, Out of Order Logic) can issue 4 instructions and suppose the current thread can issue only two instructions, then a HT enabled processor can issue another two instructions from the 2nd thread. So total 4 instructions will be executed by CPU at any particular cycle where two instructions are coming from Thread 1 and another two from Thread 2. Here some of the instructions from both the threads are being executed simultaneously. In contrast, in Superthreading (which is wrongly thought as Hyper-threading by most of us) can only issue instructions from one of two threads in any particular cycle, not from both. But this is a best case scenario where both the threads are completely independent to each other. HT performance decreases if dependency is present among the threads since it has to wait for the completion of the independent thread to process the dependent one and both of their instructions can't be processed because CPU execution unit is one.

Consider the following example:
Thread 1 or T1: Instructions I1, I2, I3, I4 and I5 are present
Thread 2 or T2: Instructions I6, I7, I8, I9 and I10 are present.
Thread 3: It is in the thread queue waiting to be picked up after the completion of any of the threads T1 and T2. It has instructions I11, 12, I13, I14 and I15. All are independent.

Dependencies: I1 and I2 are independent, I4 is dependent upon I6, i5 is dependent upon both I4 and I10.
I6 is independent, i7 is dependent upon i2, I8 is dependent upon i5. I9 and I10 are independent

Case 1: one Hyper-threaded Core of i7 core with two logical units:

In a HT processor which can issue 4 instructions in a single cycle, I1, I2, I6 and I9 can be issued in the 1st Cycle as they are independent. Now in the 2nd Cycle only I4 (I6 is completed in 1st Cycle), I7(I2 is completed) and I10 can be executed as all the remaining are dependent. So one instruction issue logic is getting wasted.
Cycle 3, only instructions I5(I4 & I10 is done) can be issued as I8 requires I5 to be finished. So three instruction resource is getting wasted. Only in Cycle 4, I8 can be issued. To total 4 cycles are required. At the start of 5th cycle T3 will be fetched. For finishing T3, two more cycles will be required as it has five instructions. So total number of cycles to finish three threads is 7.

Case 2: One Bulldozer module with two cores and shared Frontend
Now Consider a Bulldozer module where two separate execution units are available and they are but the two threads inside a module are shared among all the execution units inside the module which is two here. Consider it has Core 1 and Core 2 which can share all the data, threads and instructions present inside the module.
So in the 1st Cycle Core1 will have I1, I2, I6 and I9 and Core2 will have I10.
In the 2nd Cycle, Core1 will have I4 and I5 and Core2 will have I7 and I8 loaded but waiting for resource.
Now lets devide 2nd Cycle into two different time frame. let's consider 2nd Cycle time span = t1 (timespan to execute 1st instruction) + t2 (timespan to execute 2nd instruction). So both t1 and t2 are less that Clock cycle 2's total time period.
Now at the end of t1, Core1 will finish I4 (I6 is done in Cycle 1) and Core2 will finish I7 (I2 is done is 1st Cycle). At the end of t2, I5 will be executed as I4 and I10 are done and I8 is still in Core2 execution unit
So Now Core 1 is completely free and Core2 has 1 instruction left. So at the beginning of Cycle 3, T3 is fetched and I11, 12, I13, I14 of it will be assigned to Core1 and I15 will be assigned to Core2 as it has still 3 empty slots.
Now at the end of 3rd clock cycle T1, T2 and T3, all are completed.

So advantage over a Ht core is 4 cycles.

J

tkin said:
On a basis of single core performance, BD won't be able to touch intel, but with multicore it may pose a healthy competition for 2500k or lower, 2600k will remain on top due to hyperthreading(its gives a monster boost).

no. that's wrong. in synthetic benchmarks it might give "monster boost" but otherwise hyperthreading is only 20-25% boost. 2 intel cores will be 70-80% faster than 1 hyperthreaded intel core.

@cilus,
nice explanation.4 cycle faster than intel one :shock:

.then BD will rock.

@cilus: nicely explained. Thanks.

Skud said:
Lemme troll a bit: You guys rock!!!

You are trolling? I haz it, cant beat me.

nice explanation Cilus good job.....
So accordingly.....as compared to i7 2600k a bulldozer 8 core will be therotically somewhat 25~30% faster in multithreaded application.....mainly it will help in rendering animation,games....as now a days games are silly ported from consoles.

There is a chance that it may perform well in games which are not that much multi-threaded, too due to its dual core module design. Here even if a single thread is available to a module, all the instructions of it can be issued to both of the cores of the module simultaneously to fasten the execution speed.
But these things are hard to speculate until we can see it performing and the latest architecture design of it.

So long story short...better dayz ahead for AMD
I hope it doesnt turn out to be disaster as the phenom I lineup
Finger crossed...!

^^ That won't last for long thanks to sandybridge-e processors coming out.

^^ but they will be much more higher priced and AMD will win the VFM battle IMO if BD can outperform current gen SB's - but to know for sure we still need to wait for 15 long days ;-)

@ cilus - nice explanation on HT and Bulldozer cores ;-)

BTW, 6 BD cpu is going to hit the market for sure :

FX -8150, FX-8120 (95W and 125W TDP ) ,FX-8100 , FX-6100 and FX-4100

chck this out ;-)

Real nice explanation. I hope beats intel as I am suspending my purchase for this processor b.c.

d6bmg said:
^^ That won't last for long thanks to sandybridge-e processors coming out.

i read somewhere that Intel is cutting the features of SB-E to launch it early to compete with BD.if this is the case then SB-E won't be having much performance boost and there is no meaning in going for it @ very high prices compared to current SB and future BD.

Yes, actually Intel is also facing problems to implement 22 nm fabrication process with their tri-gate Transistor and with the speed of progress, Sandybridge E can't be launched with all the speculated features in the time line they have disclosed earlier. So the processor as well as the new motherboard chipset, both are coming without some of the features which were promised earlier.

a lil update...from the PR division
*twitter.com/#!/AMDphil/status/111469723018993664

On track to ship before the end of September and we are tracking to an expected Q4 launch and availability

^^ Thanks for twitter link.

sukesh1090 said:
i read somewhere that Intel is cutting the features of SB-E to launch it early to compete with BD.if this is the case then SB-E won't be having much performance boost and there is no meaning in going for it @ very high prices compared to current SB and future BD.

At the rumored price range, I'm not sure whether SB-E is going to dominate the market or not. So, we have to wait till Q2,2012 to get some really powerful CPUs.

Engadget

I feel bad for AMD.

SiSoft Leaks AMD FX "Zambezi" Scores: Worse Than Intel Core i7 - Bright Side Of News*

AMD Starts Shipping "Bulldozer" CPUs

Yeah, the server ones...

comp@ddict said:
I feel bad for AMD.

SiSoft Leaks AMD FX "Zambezi" Scores: Worse Than Intel Core i7 - Bright Side Of News*

here is the report of that review :-D

AMD Bulldozer Benchmarks Released by SiSoftware were Fake - Lenzfire

here is another link,
*www.guru3d.com/news/amd-bulldozer-prelaunch-faq/

^^ thanks for the links - much relieved now ;-)

welcome brother.i felt the same. :smile:

sukesh1090 said:
here is the report of that review
AMD Bulldozer Benchmarks Released by SiSoftware were Fake - Lenzfire

Now this sounds better & much more realistic.

Just read Cilus' article. Great one man.

^^ better cross our fingers for the final launch now.

Asus 9 Series BD mobo prices ;-)

Asus M5A97 @ 5.7k
Asus M5A97 PRO @ 6.8k
Asus M5A97 EVO @ 7.1k

Asus SABERTOTH 990FX @ 13k
Asus M5A99X EVO @ 10k

^^source?

^^ All from Delta Peripherals - also they have ASUS Crosshair V Formula 990FX at 14.7k - want to grab one , eh ;-)

Does any one know Bulldozer preorder have started already???
Here are the pricing
FX6100 X6 - $204.99
FX8120 x8 - $236.99
FX8150 x8 - $259.99

As against the top of the line x8 bd price of $320 the 8150 settles at $259.99~$266.99

Currently only three models are up for the pre-order
source:*www.xbitlabs.com/news/cpu/display/..._Orders_on_AMD_s_FX_Series_Zambezi_Chips.html

I hope the 260$ price tag lower than i7 2600k's 299$ doesn't mean lower performance too, cuz that would be a HUGE Bummer!

Therotically...it has to pass 2600k in multithreaded applications.....now lets see the legit benchmarks first before jumping into conclusions...keeping my hopes up for the bulldozer performance.......the delivery will not be given till the first week of october for pre-order.
lets see how the world scenario changes after BD release.

comp@ddict said:
I hope the 260$ price tag lower than i7 2600k's 299$ doesn't mean lower performance too, cuz that would be a HUGE Bummer!

Good. Again, I'm expecting a sharp fall of the price of i5-2400, i5-2500, i5-2500K, i7-2600, i7-2600K. (I'm greedy).

AMD FX-8150 'Bulldozer' Hits 8.4GHz and Breaks Overclocking World Record - AMD FX 'Bulldozer' Extreme Cooling Demonstration Event - Legit Reviews
AMD Bulldozer Breaks CPU Frequency World Record | Overclockers

M

Ishu Gupta said:
AMD FX-8150 'Bulldozer' Hits 8.4GHz and Breaks Overclocking World Record - AMD FX 'Bulldozer' Extreme Cooling Demonstration Event - Legit Reviews
AMD Bulldozer Breaks CPU Frequency World Record | Overclockers

solid find.. go AMD.. now i can peacfully wait for amd

Ishu Gupta said:
AMD FX-8150 'Bulldozer' Hits 8.4GHz and Breaks Overclocking World Record - AMD FX 'Bulldozer' Extreme Cooling Demonstration Event - Legit Reviews
AMD Bulldozer Breaks CPU Frequency World Record | Overclockers

8.4Ghz

WOW

TFS.

hey guys do anyone know the price and release date(india)of BD 8core series will it beat 2600k?? i was planing 2 get i7 this weekend .... totally confused now .......

(srry if this Q was discussed b4)

Hope it will do 5 Ghz on good air coolers with ease. Thanks Ishu for the links.

Skud said:
Hope it will do 5 Ghz on good air coolers with ease. Thanks Ishu for the links.

AMD claims that it will on sub $100 coolers

All that said, results of “well beyond 5GHz” on air were claimed on cooling solutions priced below the $100 mark!

M

8-core FX processor that AMD was able to overclock to 4.8GHz using the Antec Kühler.

from anandtech. if an antec kuhler could do that then a nh d14 will do 5+

Ishu Gupta said:
AMD FX-8150 'Bulldozer' Hits 8.4GHz and Breaks Overclocking World Record - AMD FX 'Bulldozer' Extreme Cooling Demonstration Event - Legit Reviews
AMD Bulldozer Breaks CPU Frequency World Record | Overclockers

(i was just going to share this here, after noticing this terrific news on the feeds

)

Let's see how the market responds to AMD...and how Intel fights back...

Looks like AMD is PITA for Intel and nVidia, both!

market believes more on ads (literally, for the non-techies/geeks).

talking about India, Bulldozer beats Core i7 2600k hands down but without ads, FAIL.
but if AMD can provide a good promo & some good ads, even if bulldozer looses to Intel SB, it'll be a success.

^^i never saw any AMD ads, i swear! :>

@ max_snyper - thanks for the BD cpu prices ;-)

A speed of 8.4 Ghz is great but it's not practical for everybody and most of the enthusiasts users at the same as most of them will either use 3rd party air cpu coolr or some luquid solution ( not LN2 ) - so I'm more interested to see how fair BD cpus can do with good Air Cpu cooler and with 3rd party ready to use liquid cooling kits ;-)

MatchBoxx said:
^^i never saw any AMD ads, i swear! :>

Viswanathan Anand used to do some promos for AMD. Guess that sums it up nicely, AMD=thinking man's choice.

8.4GHz!!!! Its like they have done teh impossible.
Clock speed wise they can easily beat Intel SB cpus.

MatchBoxx said:
^^i never saw any AMD ads, i swear! :>

Yes, and that's why many people don't even think of AMD processors while building their CPU.

^^It shows the potential these BD chips have.....not everybody is gonna buy amd pc...its just the ppl like us who know there is a world apart from intel.
I would really like to know how these prices are goin to translate into Indian rupees...lately rupee is on the weaker scale so expect the prices to be on the upside...even more than sb 2600k for the top end BD.

So the whole bulldozer series has been released or some of them have been left ??

^^ I think we will see some some less powerful and cheap BD cpus later in the Q1/Q2 of next year but AMD still have to sell their good performing Phenom II cpus which will be either EOLed or get a price drop - so for customers it will be a win win situation ;-)

Oh well that is a relief for me because I was thinking that more powerful processors will be released in next quarter.

gameranand said:
So the whole bulldozer series has been released or some of them have been left ??

Actually, it hasn't been released yet. :mrgreen:

Eerste officiële benchmarks AMD FX processor | Hardware.Info Nederland

Proves nothing. Particularly at this point of time.

topgear said:
^^ All from Delta Peripherals - also they have ASUS Crosshair V Formula 990FX at 14.7k - want to grab one , eh

moi got one already

@Jaskanwar Singh
link is not working for me.

^^ working fine for me. try again.

guys check this out ;-)

many motherboard makers claim that their AMD AM3 mainboards are compatible with AM3+ processor by BIOS upgrade. However, this method may be not stable enough to provide a reliable computing, and may result in certain effects. The latest ASRock Real AM3+ socket motherboards were solidly built with AM3+ CPU power solution and all AM3+ related hardware components that provide users an advanced and efficient computing choice! Why users should choose Real AM3+ MB? We provide six reasons for answers!

*www.asrock.com/news/events/2011am3%2B/1.jpg

and check the source - there's some great differences shown clearly between AM3 and AM3+ ;-)

I thought bulldozer was releasing on 13 september. Did I missed something ??

^^ no - desktop BullDozer cpu release delayed again

AMD's Bulldozer CPU is on the verge of being released. Sever markets will see the CPU soon, while desktop customers will have to wait until Q4 (which is only a month away at this point). No one likes to ship a delayed part, but if you do your job right the part that follows should arrive in a timely fashion. The follow-on to Bulldozer is called Piledriver and it will make its debut with AMD's Trinity APU in 2012.

Read more ;-)

AnandTech - Look Out Bulldozer, Here Comes Trinity: AMD's 2012 Demo on Video at IDF

T

Good thing I didnt wait on BD and bought Ph4

This baby is getting delayed like anything.

Well I am still waiting for bulldozer and radeon 7000 seriesfor my purchase. I already have radeon 5770 so even if I do purchase other components then also I'll wait for 7000 series GPUs to release in Q1 2012,

I already have radeon 5770

That card will server you without any problem at least for next 6-7 months, which is Q2, 2012. And by that time we can even expect some amount of price drop in 7xxx, as nvidia will release their cards too.

^depends on the resolution and settings he games at.

He can also play game at lower resolution to increase fps a bit for the time being.

d6bmg said:
He can also play game at lower resolution to increase fps a bit for the time being.

yeah but full hd gaming is much more enjoyable.

I play games at 1080p after my purchase of monitor purchase Benq G2420HD in August. It was giving quite good performance even on full resolution with many games which I have to play. But nevertheless I have to upgrade and I'll buy new PC soon with all your suggestions.

AMD Bulldozer FX-81X0 Official Benchmarks vs Intel Core i7-980X, i5-2500

Contains same information of the link given by Jas earlier. Again, with no detailed hardware specification and running just a couple of benchmarks proved nothing IMO.

X

New benchmarks leaked/purposefully shown.
Show FX-8150 being almost twice as slow as i7 2600K in an age old benchmark.
This made me sad...

We need some proper trusted source for complete comparision between processor not some random link with just a few benchmarks. I hope to see comparisions soon with Bulldozer winning in that comparision.

^^ me too

I'm not giving any kind of importance to these early benches floating around - only after seeing some real benchmarks with the final released retail product from some trusted sources we will get the true picture ;-)

AMD's Bulldozer 8.4 GHz+ OC Achievement: Cooled to Near-Absolute Zero | techPowerUp

^^ That was just an exception. It counts nothing towards extended better performance.

nilgtx260 said:
AMD's Bulldozer 8.4 GHz+ OC Achievement: Cooled to Near-Absolute Zero | techPowerUp

Quite honestly for the end customer these records hardly matter at all. They need nice performance on stock speed and even if they do overclock then also intensity for that is not much so these make no difference. I need a nice CPU who performs really good not a record holder CPU.

^^ agreed - but nice cpus most of the time tends to be a record holder ;-)

topgear said:
^^ agreed - but nice cpus most of the time tends to be a record holder

Then I hope that bulldozer would be damn good when it gets released.

Not Celeron though.

I am going to make rig in mid oct will bulldozer be out then or i will go for sandy bridge?

All AMD FX Processors will be unlocked

^^I highly doubt Bulldozer to compete with SB i7... I guess thats the reason AMD is trying whatever possible...

Jus my opinion..

Intel will be releasing the i7 2700 around the same time. So price to performance ratio might not be that bad.

New BullDozer CPU Pricing ;-)

AMD’s FX Series will be very, very cheap: the six-core FX-6100 (i.e. three Bulldozer modules) clocked at 3.3GHz, with a Turbo Core boost to 3.9GHz, will retail for just $155. The eight-core (four-module) FX-8120, clocked at 3.1GHz and boosted to 4GHz, will retail for $185 — and the 3.6GHz/4.2GHz FX-8150 will retail for $230. Each Bulldozer module has 2MB of L2 cache, so the FX-6100 has 6MB of L2 — and its eight-core brethren have 8MB. All three chips have 8MB of L3 cache

Source

OMG ! If this is going to happen we will be able to get a 6 Core BullDozer CPU at only ~7.5k which is a lot less Cheaper than P2 based 6 core cpus and The 8 core FX-8120 will be a lot less cheaper than P2 based top of the line 6 core cpu - so how much price drop we will see on P2 based quad and hexa core after the release of BullDozer Cpu - A a quad core Cpu for everyone - anyone ;-)

Awesome. I expected prices to be low but not this much for sure.

topgear said:
New BullDozer CPU Pricing

Source

OMG ! If this is going to happen we will be able to get a 6 Core BullDozer CPU at only ~7.5k which is a lot less Cheaper than P2 based 6 core cpus and The 8 core FX-8120 will be a lot less cheaper than P2 based top of the line 6 core cpu - so how much price drop we will see on P2 based quad and hexa core after the release of BullDozer Cpu - A a quad core Cpu for everyone - anyone

You converted that $155 directly to Rs but thats not how prices in India will be determined!! I think FX-6100($155) will retail somewhere around 9-9.5k when launched over here!!

well, i7-2600k costs 319$ in us and around 15.5k in india. So i am assuming the 8 core fx cpu will cost around 11.5k.....

2600k's price has stabilized over time. Newer products would be priced a bit higher. Something like 1USD=60INR.

Well topgear is right. When i bought my i5 750, it was retailing around 199$. Here, it was 10.3k. So i think the fx 6100 will retail here within 8k for sure. 7-7.5k will be a steal.

Now that's really aggressive pricing. Amd surely knows how to price its cpu's.

So price-wise AMD has done an awesome job.. Waiting for the performance!!!

Hope Indian pricing will be right.

===========================================================

Just the piece of information we needed:

AMD FX parts coming October 12

I highly doubtful to this pic but still wanna share with you guys.
*techiser.com/wp-content/uploads/2011/03/AMD-Bulldozer-Benchmarks-Leaked.png

What type of CPU is "Scientific Linux 6"?

Some more news:

Bulldozer to be succeeded by Vishera core

Scientific Linux 6 is not a cpu - it's linux distro AFAIK ;-)

and thanks for the 12th Oct release date of BullDozer Desktop cpus.

Exactly my question - what's it's doing in a bunch of CPUs?

On 12th its also releasing in India?

^^ I don't think so - but it will arrive here quickly after the release ;-)

Skud said:
What type of CPU is "Scientific Linux 6"?

Some more news:

Bulldozer to be succeeded by Vishera core

Vishera is the successor of zambezi and it and it will be based on piledriver architecture (which is a slightly improved bulldozer architecture. Vishera has replaced the previous Komodo which was almost the same cpu but with on-die pci-express controller and fitting into the FM2 socket.

New Comparision slides released today on Donanim haber...amd bulldozer fx-8150 performance slides
have a look:
AMD Bulldozer FX resmi test sonuÃ§larÄ±

The authenticity of the performance cannot be verified but the performance is awesome!!!
waiting for professional reviewer for review.

G

they comparing intel 4 core vs amd 8 core cpus

^^ dude they are comparing 8-core vs intel 4 core with hyperthreading,
4 core and 4 core with hyperthreading is not same...!

Pretty interesting.

For sale AMD FX-8150 Price 8 Core Bulldozer Processor - Processors - AMD (Pune, ClubIT.in)

Price - Rs Call

Yes 1 call and its yours

^^ I don't think it's legitimate or this could be just a Engineering Sample ( this thing was posted on Aug, 11 2011 ) - better wait for couple of weeks to get a nice deal on a proper version ;-)

Fake.

I actually think Bulldozer will be bad.

ico said:
I actually think Bulldozer will be bad.

panauti

ico said:
I actually think Bulldozer will be bad.

Ha Finally, someone here thinks exactly as my instincts.. :))

if amd have such a high confidence in them,then i think BD won't be bad.

Amd will be bad cuz its not bad but it's very late i guess.

The thing is it wont be best but it wont be bad either....u all can expect the performance to be near 2600k or little more.....in multithreading applications.but for end user it would be good for multimedia,solid gaming performance,and all the office apps would run just great.

don't think it will get near SB-E processors but will give i7 2600k a run for its money

I concur with snyper & sunny10. I don't think BD was ever supposed to beat i5/i7. Its meant to give us near about performance to i5/i7 but at a lesser price. I think thats what AMD was aiming all the while - to lure more consumers.

^^^ i feel the same too!!! in fact they have alredy declared the successor to the bulldozer series before its release, which i think will be aimed against the ivy bridge cpus!!!!

By the way is there any software or game in the market that fully utilizes 8 cores

Hey guys what I find AMD WC kit with High ebd FX Bulldozer

AMD's Water Cooling Kit for FX-Bulldozer Processors Exposed

Lets just wait a few more days for official release.

SO for FX processors WC will be bundled as stock

sunny10 said:
SO for FX processors WC will be bundled as stock

That's not a good idea, I'd keep a few towels handy just in case, high end WCs from corsair sometimes leak, no doubt these will too, and AMD warranty in India is handled by rashi right?

tkin said:
AMD warranty in India is handled by rashi right?

No...

R

tkin said:
That's not a good idea, I'd keep a few towels handy just in case, high end WCs from corsair sometimes leak, no doubt these will too, and AMD warranty in India is handled by rashi right?

Not sure, but it aint bad....

I gave my 2 year and 11.5 month old processor for replacement and they said they WILL give me a new one in a couple of days, hope they actually do...

Well personally I don't like the idea of water cooling. What if leakage causes damage to other components ?? Will they cover that too ??

ico said:
No...

That's a relief, cause on the back of the money receipt(from MD Computers), Rashi is listed as the Service provider for AMD, here too: Corporate Profile

If they are not then who is?

gameranand said:
Well personally I don't like the idea of water cooling. What if leakage causes damage to other components ?? Will they cover that too ??

Corsair covers that in USA(total), but you can guess what will happen to Indian customers... I would strongly suggest to stay away from the WC kits. Even corsair said that we have to ship any damaged part to USA to get is replaced, that will cost more than the product itself.

not a good move by AMD. bundling a WC will kick the price up by 4k or more & will easily overshoot 2600k's price. what about those who already have a HP aircooler? i guess there shouldn't be any problem about the compatibility.

why not release some FX with WC as a premium bundle (& price is premium) and the rest with simple air coolers. lets wait. AMD may surprise us.

I think if the the cpus are really that high performing then AMD should not bundle any kind of coolers with the FX cpus - this will keep the cpu prices much lower ( and edge over SB K sku cpus which stock cooler ain't god ) and customers will get a wide choice of cpu coolers and if FX is targeted at the enthusiast users then they don't give a damn about stock cpu coolers as they will get some after market high end cpu cooler for sure ;-)

R

but guys, for the general public, many don't go for an after market cooler, this would be a nice 'buy' point for them....someone who is not that well informed, might be fascinated by the 'Liquid Cooling' Bundled...so as long as they are not too cheap quality, I think its not such a bad thing if you think from AMD's point..

Sam said:
why not release some FX with WC as a premium bundle (& price is premium) and the rest with simple air coolers. lets wait. AMD may surprise us.

and then we will cry 'Get the H100 instead' and so on..?

rajan1311 said:
and then we will cry 'Get the H100 instead' and so on..?

Crying is better than frying up other components ain't it??

R

having said that, if ur H50/80/100/whatever leaks, you will cry again? So stick to air huh?

Yup just stick to air cooling. Thats best because of very less or no risk at all.

R

agreed

Hold on guys.... This kit will be sold separately and may not bundled with the proccy.......

Let's just wait for 12th Of October....... Hope this diwali is going to be great

Oh thats a relief.

I was also not fascinated by the liquid cooling part because of the danger of leak.
But it is good that WC will not be stock

What you says guys what will be the biggest hit Ra.One or Bulldozer...........

I am just crossing my finger for Bulldozer.......

AMD is bundling Air Coolers with FX cpus ;-)

New FX-8120 Bulldozer Pics & Benches hopefully in the next couple of hours! - Overclock.net - Overclocking.net

topgear said:
AMD is bundling Air Coolers with FX cpus
New FX-8120 Bulldozer Pics & Benches hopefully in the next couple of hours! - Overclock.net - Overclocking.net

Man you made my day. Thanks. Benchmarks are also there although I didn't understood much of that. Still waiting for comparative benchmarks with SB.

Bulldozer coming out today. I'm sort of unenthusiastic by now. Expecting things to be fixed in Piledriver.

Well I hope that its just awesome. Just waiting for comparisions.

oZeros » Review: AMD Bulldozer FX-8150

AMD Bulldozer â€“ procesory FX-8150 a 8120 v testu (1/2)

Reviews from obscure parts of the world are out. Waiting for the real ones now.

T

I am not gonna read anything till I see a Production CPU tested at Anandtech or Tomshardware.

Fifteen minutes more for those.

@ 9:30 am

Bulldozer fail.

HARDOCP -

HardOCP's review was up and now down. 404 error.

*i.imgur.com/CeFl2.jpg

ico said:
Fifteen minutes more for those.

@ 9:30 am

Bulldozer fail.

HARDOCP -

Its giving error 404 page not found.

AMD FX-8150 8-Core CPU Review: Bulldozer Is Here - HotHardware

[H] review is working now.

disappointing!!

I've got no idea why AMD released this. IPC has decreased compared to Thuban wtf? They should have just added two more cores and released a 32nm X8 Thuban. It'd have performed better. Or they could have canceled this altogether and moved onto Piledriver as it appears ready.

Or may be, there is some bug and they are thinking it will be rectified with another stepping. My guess is, they only released it for revenue. What's with higher power consumption than Thuban anyways?

Barcelona #2 or nVidia GeForce 'FX' 5000.

this -
AMD FX-8150 Processor Review - Bulldozer Arrives - AMD Brings Bulldozer To The Yard - Legit Reviews

seems interesting. behind 990x still.
8150 and 2600k seem exchanging positions.

power consumption is a big disappointment. not expected from amd.

TOMS HARDWARE -
AMD FX-8150 Review: From Bulldozer To Zambezi To FX : AMD Sets The Stage For FXâ€™s Performance

GlobalFoundries need to sort out their 32nm process too.

tbf, this is AMD's Pentium 4. Only thing is, it won't sell. Even Pentium 4's IPC had decreased compared to Pentium 3.

single threaded performance decreased than phenom x6 :-(

G

seems like i7 2600k still is a winner..!!

Feeling sorry for those who specially invested in an AM3+ board. well...bright side? Phenom II 1090T doesn't really look THAT bad.

Duke Nukem Forever of the processor world.

seems b/w 2500k and 2600k in toms.
still intel reigns champion.

what will happen when SB E will come. bulldozer blown out of water?

Goddamn so all the wait for nothing ?? Anyways when SB-E is going to release ??

Ya, Bulldozer is not able to live againt the expectation, i.e. beating the 2600K. But I don't think it is a faliure at all. Just finished the legitreview and Toms Hardware review of the FX processor and find out that it is placed somewhere between 2600K and 2500K..in fact it is more closer to 2600K in terms of performance. Now after launch we can expect a price drop from AMD's side, making it a viable solution in highly multi-threaded environment and for multimedia applications.
And don't compare it with Sandybridge-E series processor, Zambezi was never meant to compete against Sandybridge-E. I think AMD has already provided their roadmap for 2012 and Trinity might be the true competitor for Sandybridge-E.

IMO...its not epic fail....actually it was
1.too late.
2.too overhyped.
3.people misunderstood it as the "masterchief" from HALO but it turned out to be maxpayne...does the job but generally lagging here and there...!

PPL loyal to amd,would surely buy one having 95% functionally of 2600k for lil lesser price.

G

so who all buying AMD bulldozer..!!

why actually it failed when its architecture was better than 2600k or this why it is said that theory is always theory it will never suits the real word practical.btw is there any bug in the processor because of which it is not performing as promised or the programs are no able to use its features?

---price will play a vital role---

IF AMD wants this one to sold just like phenoms, then it must be priced sweet

BTW the funny thing
BD 8150 =8 cores and
i7 2600k = 4 cores

A

Bulldozer 8150 doesn't have 8 "cores" but 4 modules.

Bulldozer module doesn’t incorporate two complete cores. Instead, it shares certain parts of what we’d expect to find as dedicated resources in a typical execution core, including instruction fetch and decode stages, floating-point units, and the L2 cache.

^^ as said earlier it has 2 integer cores per module that translates to 1.75 of a normal dual core processor
2.programs are actually not able to use its features, windows 7 is not able to utilise its true potential.
3.If the prices are corrct in India then im in for bulldozer.

^^but in toms review they have also given the performance in win 8 and there is no much difference.the single threaded performance may improve but the over all performance still remains epic fail.i am totally disappointed,95% of the reviewers there don't recommend or suggest i5 over this and don't even think about comparing this with 2600k.
I am completely disappointed.my question is where AMD failed even when it is having a very good architecture?why amd? why?

it looks like the only place where AMD defeated intel buy a hell lot of margin is............power consumption.may be even for 10 years in future the intel won't be able to defeat this.

^^Win 8 is in the development stage now not complete...many optimization are to be done,
amd ppl have not failed to deliver,its just that the performance is not as good as 2600k in single threaded application...in multithreading optimized application it will perform good if not best.
BTW a total revamp of the architechture and getting performance close to i7-series is not a easy task especially when u are the only contender in the field against Intel for mainstream market.
Which AMD product has thrashed intel products in the last 2~3 years,not in the price /performance ratio but in pure performance...none still ppl bought the product coz it has lower price upto the mark performance....
And in gaming leave it,frame rates above 30 are pure not noticible for human eye,and ppl fighting over mere 2~8 frames is sheer bragging nothing else...still most games are Gpu depended not cpu (i hope GTA 5 comes to pc first and then ported to consoles.) with few exceptions.

A

the bottomline is bulldozer has dissapointed many. the performance they are going to deliver now has been delivered by intel almost a year ago and price wise too sandy bridge shines :neutral:

sukesh1090 said:
^^but in toms review they have also given the performance in win 8 and there is no much difference.the single threaded performance may improve but the over all performance still remains epic fail.i am totally disappointed,95% of the reviewers there don't recommend or suggest i5 over this and don't even think about comparing this with 2600k.
I am completely disappointed.my question is where AMD failed even when it is having a very good architecture?why amd? why?

it looks like the only place where AMD defeated intel buy a hell lot of margin is............power consumption.may be even for 10 years in future the intel won't be able to defeat this.

Sukesh, stop crying buddy, in most of the review sites like Toms hardware, Legitreviews, guru3d, FX 8150 is placed between i5 2500K and i7 2600K. So a slight price cut will make it a hot deal. In heavily multi-threaded applications FX 8150 has shown its potential in lots of the test benchmarks, performing neck to neck with 2600K and sometimes beating it.

It is the single threaded performance where it failed completely. According to me, AMD should treat each of the modules as a SMT ebnabled single unit like two logical cores of a HT enabled core rather than make them treated as two physical cores by OS. As a result when a single threaded application is assigned to any of the cores of a module, the 2nd core is not getting used although theoritically it is possible to execute instructions of the assigned thread in both the cores as they share same frontend (Fetch-decode unit).

Lets hope upcoming programs and OS will be optimized to utilize the new architecture benefits.

sukesh1090 said:
^^but in toms review they have also given the performance in win 8 and there is no much difference.the single threaded performance may improve but the over all performance still remains epic fail.i am totally disappointed,95% of the reviewers there don't recommend or suggest i5 over this and don't even think about comparing this with 2600k.
I am completely disappointed.my question is where AMD failed even when it is having a very good architecture?why amd? why?

it looks like the only place where AMD defeated intel buy a hell lot of margin is............power consumption.may be even for 10 years in future the intel won't be able to defeat this.

ROFL

Anyway, don't worry, think of this as GTX480 of AMD, GTX580(aka PD I guess) might make it work, the first product of any generation sucks(except intel cpus starting from C2D).

PS: 2B transistors? What are they trying to beat nvidia gpus with their cpus?

Piyush said:
---price will play a vital role---

& (misleading) Ads too.

tkin said:
PS: 2B transistors? What are they trying to beat nvidia gpus with their cpus?

ok, add this to the ad section as well.

8core. 2B transistor. 3.6Ghz. auto overclock to 4.*Ghz. priced at 16k. but fails to beat i7 2600/k

I will just leave this here:

*t3.gstatic.com/images?q=tbn:ANd9GcR7nHFP6DeRIZg6QxlEXq9K4OonYVR-rexjy3ONGt1zGrEgcEoKAMf7g1jAJw

BTW, I just read this in another forum:

Seems like AMD is intent on burying something, hopefully it's not their CPU division.

Bulldoze, pile, roll, excavate, bury. Did I just give you a look into the future?

Anyone has read reviews of 4110 & 6110?
Any will the prices of phenom processors drop?This will be a much better decision when compared to launching Bulldozer?

G

Seening AMD FX performance it seems that i7 2600k price will not go down for a while .

yup no drop on 2600k prices. 2500k may go lower.

Cilus said:
In heavily multi-threaded applications FX 8150 has shown its potential in lots of the test benchmarks

this along with this -

tkin said:
Anyway, don't worry, think of this as GTX480 of AMD, GTX580 might make it work

yep, i think it has potential.

Jaskanwar Singh said:
yup no drop on 2600k prices. 2500k may go lower.

I highly doubt that, the only price cut that needs to happen is for Bulldozer, top end BD prices are not competitive at all considering 2500k price is really nice.

Jaskanwar Singh said:
yup no drop on 2600k prices. 2500k may go lower.

this along with this -

yep, i think it has potential.

I think it does, only issue is that even with the monstrous power consumption and temps GTX480/470 actually BEAT the competition at intended price points.

tkin said:
I think it does, only issue is that even with the monstrous power consumption and temps GTX480/470 actually BEAT the competition at intended price points.

well yes you are right but i just wanted to point out potential. :))

---------------------------------

nice one -

The good news is AMD has a very aggressive roadmap ahead of itself; here's hoping it will be able to execute against it. We all need AMD to succeed. We've seen what happens without a strong AMD as a competitor. We get processors that are artificially limited and severe restrictions on overclocking, particularly at the value end of the segment. We're denied choice simply because there's no other alternative. I don't believe Bulldozer is a strong enough alternative to force Intel back into an ultra competitive mode, but we absolutely need it to be that. I have faith that AMD can pull it off, but there's still a lot of progress that needs to be made. AMD can't simply rely on its GPU architecture superiority to sell APUs; it needs to ramp on the x86 side as well—more specifically, AMD needs better single threaded performance. Bulldozer didn't deliver that, and I'm worried that Piledriver alone won't be enough. But if AMD can stick to a yearly cadence and execute well with each iteration, there's hope. It's no longer a question of whether AMD will return to the days of the Athlon 64, it simply must. Otherwise you can kiss choice goodbye.

AnandTech - The Bulldozer Review: AMD FX-8150 Tested

bulldozer has a good multi thread performance but still there are some days for the applications to come which will use 8 cores completely.but the single thread performance is pathetic,may be it is a program mistake which is treating half of the module as single core,but the program developer can't simply develop a program solely for bd there should always be a effort from AMD to optimize bd as they can make the program to treat a module as a single core.lets see what happens there may be some revisions where we can see these bug like things are fixed.but the field where they completely lost is power consumption :sad:

guys 8150 is easily beating 2600k in multi threaded performance.isn't it guys?
actually AMD itself made the hype by comparing it with 980x or else BD was a huge success.if they sell 8150 at around 11k then i am sure that they will kick intel's ***.may be BD will win when we compare 2600k and 8150 after 1 year where program will be optimized to use multi cores and latest instructions. :razz:

sukesh1090 said:
bulldozer has a good multi thread performance but still there are some days for the applications to come which will use 8 cores completely.but the single thread performance is pathetic,may be it is a program mistake which is treating half of the module as single core,but the program developer can't simply develop a program solely for bd there should always be a effort from AMD to optimize bd as they can make the program to treat a module as a single core.lets see what happens there may be some revisions where we can see these bug like things are fixed.but the field where they completely lost is power consumption
guys 8150 is easily beating 2600k in multi threaded performance.isn't it guys?
actually AMD itself made the hype by comparing it with 980x or else BD was a huge success.if they sell 8150 at around 11k then i am sure that they will kick intel's ***.may be BD will win when we compare 2600k and 8150 after 1 year where program will be optimized to use multi cores and latest instructions.

Have you even remotely read any reviews of BD? I guess not, so here is the rundown, BD single core performance(IPC) is so horrible that even with 8 cores it can't match either their predecessors(Phenom II) or sandy bridge, even with higher freq, more cache, deeper pipelines, in single as well multithreaded benchmarks, 8 core phenoms would be faster than BDs, everything is wrong with that architecture, low IPC, memory latency is not good, cache latency and speed is disastrously horrible, power consumption is through the roof, 4.8GHz BD draws close to 600w, thats just plain nuts, so if you buy BD your electricity bill may well make you go bankrupt.

*img189.imageshack.us/img189/6627/ocpower.png

And here is what multithreaded for BD looks like:

*oi55.tinypic.com/6hs306.jpg
From hardware-canucks.

OMG WTF???? It's the biggest let down by AMD I have ever seen, I am so disappointed now after seeing Bulldozer's performance. It's not a epic fail but from price point of view.....YEAH IT IS. I mean how the hell AMD fix that kind of stupid high price of that processor which should compete against i7 960/970/2600/2600K but eventually ended up by delivering same performance of 2500K/Phenom II X6 1100T with more power consumption & less gaming performance. From a gamer point of view why should we have this processor which has high price & consumes more power than Intel & deliver average gaming performance? What the hell AMD actually done with its new architecture??? Now I am very doubtful whether AMD repeats same kind of failure with its Radeon HD 7000 series which also has new architecture with its 32mm gpu. In the next year Intel will drop another bomb with Ivy bridge & Sandy Bridge E is already knocking the door prepared with i7 Xtreme series. Now where do we put AMD Bulldozer ?

amd should do this but they are not so i am doing this.but still brother performance in multithread is good but is single thread it is failing because of it module thing which the present programs can't understand.about power consumption thats what i am telling from the beginning that its just an epic fail.intel can never ever beat this bd in that field.hope AMD will also won't beat it with its newer architecture.BD is just like modern instruction set pentium 4(bcoz logic behind the architecture are all same) who is competing with athlon.

Review that compares the FX 6100 and FX 4100.

~~Buddy it will be good if you provide the source or paste the link of actual image because i can't read it at all.i will need a very high magnifying glass to read it.thank you.~~
sorry now i got it but the thing is quad core BD is placed lower than the Athlon II quad cores.this is very very bad for AMD.are they moving forward in past or future.I am not understanding at all.though looking at the 8150 position we can say AMD is lagging behind just by a hair with Intel's best.but still if i am going to buy a processor i will go for i5 rather than 8150 because i don't want to make electricity companies crorepathies. :wink:

BD may have a bright future with future programs able to use it full features but still power is a very big concern in these days where there is a lack of electricity production in India. :mrgreen:

After reading tom's, i see that i5 2500k and i7 2600k are still the processors of choice for a new system build which includes the enthusiast and gaming platforms. Lets see what fx 6100 and 4100 bring to the table and see if they can manage to steal the limelight from i5 2400.

High power consumption is because of GlobalFoundries immature HKMG 32nm process and AMD's previous inexperience with the process. Much like the first iteration for Fermi. Just hoping this thing gets fixed because it needs to.

After reading all the reviews, I only can say one word - 'fail'.

gameranand said:
Goddamn so all the wait for nothing ?? Anyways when SB-E is going to release ??

this is what I'm thinking right now... why not they tested the cpu performance ( in dev stage ) with benchmarks ??

as many of you already told I'm considering it something like GTX480 for which we were able get the world fastest single gpu like GTX 580 - they will learn a lot from the this and the next cpu might be better than this,

in 2003 AMD Brought 64-Bit Computing to the Desktop and on the 10th Anniversary they might bring another wonder in desktop cpu world .

For me - I will wait for the next cpu release ( from both side ) ;-)

This was their performance series right ?? If it performed like this then what can we expect from future releases. I can't understand what happened to AMD are we on the road of Intel's monotony ?? Still I have hope for them. Come on AMD do something. Now waiting for 7000 series. I hope that wait would be fruitful.

M

Hopeless...
Any body, 6module/4module BD review link?

G

so Sandy bridge still rules ..!!

A lot of people in multiple forums (even the international ones) are banging their heads against the walls. Its sad and I feel genuinely bad for people who waited for atleast a year. AMD is clearly damaging its loyalty. Phenom deja vu, anybody?

I am already banging my head. This was their best chance to defeat Intel. They must do something radical here to remain in close competition.

topgear said:
why not they tested the cpu performance ( in dev stage ) with benchmarks ??

exactly.

nilgtx260 said:
Review that compares the FX 6100 and FX 4100.

Yep, this one was real bad. I expected a lot more from Bulldozer. Llano was more exciting than this (although it was not for enthusiasts). They should have launched this 6-8 months back and they could have introduced the next series early next year.
They must remember that the price differences compared to Intel are not as much as they were 2-3 years back. So AMD loyalists won't be hanging on for long

I am damn sure that they knew about the performance and power consumption problem of BD but still why they tried to compare it with i5 and 980X.they were just openly comparing their bd benchmark with the intel one.when their BD was not up to the mark then why did they tried to compare it with SB.i can't understand AMD.but still lets wait for 3-4 months and see if there any revisions get s released with these things fixed.

Guys, one good news for AMD. Just checking the Anandtech review and found out something useful.
Anandtech also tested X264 encoding using a moddified Binary compiled to support AVX and AMD XOP instruction set and found out that in 2nd pass (which is the original pass where video gets encoded originally) FX 8150 is beating out i7 2600K.
This is really interesting because this example shows how an optimized application for AMD Bolldozer architecture can be benefited and has some serious performance boost. Hoping to see some patch releases to optimize Bulldozer's performance.

Check out here. In Windows 8 preview there is a performance improvement ranging from 4% to 10% over Windows 7. The reason given by AMD is that Windows 7 Scheduler is not aware about Bulldozer's module based architecture and places threads wherever it finds a core is free, rather than judging the state of the module. For example suppose at time t Bulldozer has two free modules (that is 4 cores to OS) and there are two threads waiting for OS to schedule them in CPU. Now if OS is not aware of the modules, it may assign both the threads to the cores of a single module, resulting low resource utiliztion, confilts etc as we all know two cores of a module are not totally independent, they share Fetch-Decode, FP unit and L2 cache.
Now if OS is aware of the modules then two threads can be assigned to two different modules. Here each of the threads gets two cores to finish execution of the instructions present in each of them, resulting faster execution.

Similarly it will also help to improve the Turbo core performance. For example if two threads, say Th1 and Th2 where Th2 is dependent upon Th1, are present, they should be assigned to the two cores of a single module to improve resource sharing and to cut down all the other modules to reach at the peak turbo speed when a single module as all the other module are not in used and can be cut from power.

In Windows 7 it is not possible all the time due to OS' inability to recognize the modules.
But if the OS is aware of a module and the cores inside it, those problems can be addressed and scheduling can be done in much organized manner.

^^That is what i told in my previous thread....not in a explanatory way as you did ,but......the point is we dont have applications optimised for BD,that is the reason we have this low scores in benchmarks.
and the high power consumption is due the faulty TMSC manufacturings.
If applicaions are optimised for BD's architechture in future then we have a good processor in hand.

I know it, Max. In fact I am much disappointed than others because of Bulldozer's not so gr8 performance. But you believe it of not, AMD is the pioneer of lots of concept which are groundbreaking and more futuristic than Intel. In fact Intel Nehalem and Sandybridge have taken lots of those concept from AMD to imrove their performance. Examples are On-Die memory controller, Serial linking between CPU and Northbirgde instead of FSB, True multi-core architecture etc.
Here AMD has developed a completely new and out of the box design for SMT which is really great but it is actually little ahead of its time. As a result lack of proper OS and Application supports driving it back in terms of performance.

I am just hoping with latest Windows patches, application releases and with Windows 8, those problems will be addressed in some extent so that we can fetch a little more performance from it.

Cilus said:
I am just hoping with latest Windows patches, application releases and with Windows 8, those problems will be addressed in some extent so that we can fetch a little more performance from it.

But by that time, the Sandy Bridge-E might be out... If this happens & this is true, AMD will drown...

Before the release i was so tempting to buy this processor so that my aging c2d can retire...but benckmarks have somewhat pulled me back...still if i find this in a reasonable price i will surely try one...coz ivy-bridge is not coming sooner and who wants to buy sb-e which will cost a bomb in India.
Ivy bridge is coming in march-april till then BD will be back in new avataar "piledriver" to compete...and hope till then current BD will be more mature......
IMO its still not a fail as phenom-1 was in early days.
End user will get to know no difference between sb and bd when general computing.
As far as games go if sb gives 90 frames and bd gives 80 frames in a particular benchmark..who cares,can u spot the difference while gaming????

i will definately praise AMD for doing something new.... they build this out of scratch and once the application trts using tyhe multi thereded processor thi proccy will be the Hero...

we need AMD to keep the Intel within our reach...

Re: PC Buying Guide 2011- Q4

amd fx 8150 is released and it's not even close to core i5 2500k regarding performance and power consumption

MegaMind said:
But by that time, the Sandy Bridge-E might be out... If this happens & this is true, AMD will drown...

Megamind, you're not getting the point. To compete against Sandybridge-E processors, AMD has already declared their roadmap for the new gen of processors, based on the Bulldozer architecture. So if OS and software applications can address the issues of optimized use of the architecture, all the upcoming CPUs from AMD will be benefited, not just the current series of Bulldozer FX processors.

@cilus ^^Are you planning to buy this proccy when the prices settle?
Im sure to buy one if and only if prices are not exactly pitched as same as current sandybridge line-up..!

Cilus said:
Megamind, you're not getting the point. To compete against Sandybridge-E processors, AMD has already declared their roadmap for the new gen of processors, based on the Bulldozer architecture. So if OS and software applications can address the issues of optimized use of the architecture, all the upcoming CPUs from AMD will be benefited, not just the current series of Bulldozer FX processors.

You are talking about the piledriver right? If so the link i gave says,

AMD Piledriver 10% faster than Bulldozer

And yes, if its SB-E vs piledriver, AMD might win...
But if its Ivy bridge vs piledriver, AMD might disappoint again...

Keep in mind that Intel is ahead of AMD for the last 4~5 years...SO if Intel launches a proccy then to counter it correctly Amd needs 1 generation advances..
Then too Sandybridge-E is not the direct competitor to Piledriver....Ivybridge is the head on competition......
AMD IS NOT COMPETING PILEDRIVER WITH SANDYBRIDGE-E...COZ ITS NEW ARCHITECHTURE (LGA2011) MORE OF A ENTHUSIAST END SYSTEM. period.........

rajatGod512 said:
amd fx 8150 is released and it's not even close to core i5 2500k regarding performance and power consumption

Performance wise in most cases and in multi-threaded applications FX 8150 is better than 2500K and stands between i5 2500K and i7 2600K. But power consumption wise it is no match for Sandybridge.

Thanks for clarifying MAx_snyper. No I'm not planning to buy one right now as I'm having 1090T overclocked @ 3.6 GHz. Gaming performance wise I don't think I need an immegiate upgrade.

MEgamind, I am not talking about any particular processor based on the module based design. All I am saying that if OS amd software are optimized to take benefit of the Module based design then all the module based CPus are gonna get some performance boost.
For example in Windows 8 preview direver, FX 8150 is performing 4% to 10% better than when used in Windows 7 and we can surely expect more performance increase with the final release of Windows 8 with the same processor.

So there is hope for AMD ?? Man I want to go for AMD but the performance is keeping me at bay.

Re: PC Buying Guide 2011- Q4

Cilus said:
Performance wise in most cases and in multi-threaded applications FX 8150 is better than 2500K and stands between i5 2500K and i7 2600K. But power consumption wise it is no match for Sandybridge.

well anandtech benchmark shows that i5 2500k and amd fx 8150 are mostly head to head in many performance benchmark (fx wins some , i5 wins some).
But Gaming wise sandy bridge blows it out of the water .

Also i think it is priced at 280 USD and i5 is at 220 (atleast on newegg and some other websites )

So i think i5 2500k is the way to go for now .

AnandTech - Bench - CPU

As programs are not optimised to use and undestand the new features and futristic design of BD this is the reason why there is drastic decrease in single
Thread performance but in multi thread BD is already a winner.also amd has shown what actually turbo boost is,where there is a huge difference in intel sb turbo boost and amd BD turbo boost.and in oc also BD is a huge success.if the programs get optimised and understand bd then BD will go head to head with SB and some times even perform better.thats what i told in my earlier post that if we compare sb and bd after a year from today then bd will win over sb by a good margin.but the only problem remains is power lets see what global foundry and amd will do about it in future.

For me it looks like bd is a bit early to release now because its architecture design is a bit away in future,though amd is ready for this change but others are not.they still need some to develop os and programs for BD's design.
@anand,
Brother i will suggest u to wait for some more time to see if there is any revisions for bd and new optimised programs.as you have already waited for a long time for this,why don't just wait a bit more.

^^ but how long ?? 2-3 months ??

^^ Nicely explained Sukesh. I think you deserve a Rep for all your contribution. So Rep+.
gameranand, I am with Sukesh' suggestion to wait a little for some revisions of the Bulldozer to be released and applications and OS to become little optimized for Bulldozer.
I don't think we need to wait until windows 8 release as optimization can be provided to Windows 7 with some patch update (just like Multi-core CPU support patch for Windows XP) and optimization packs for the commonly used software too.

@Cilus, i got it..

T

Guess going for Phenom X4 was a good decision as its satisfying my needs and BullDozer has no Bulls in it.

@cilus,
thank yo very much brother.
@tech_wiz,
thats what we are discussing here from yesterday that this is too early to comment anything about the performance of BD.just read the review of anandtech and toms and you can see that BD is winning in the multithread performance but lagging in single thread.so wait for some time to justify your decision of buying 955.after optimization i am sure that there will be huge increase in single thread and a bit increase in multithread performance.after that you may cry along with me that you could have waited for a bit long.

As much as I could understand after the revision, the performance would increase and the revision could take 2-3 months.Would it be worth buying this processor at the present scenario as I have waited almost an year for this processor to be launched

nope it is not at all advised to buy this processor right now as its power consumption is at its peak.if you can manage with your electricity bill then you can think about buying.but still i suggest you to wait a bit long buddy.

T

sukesh1090 said:
@cilus,
thank yo very much brother.
@tech_wiz,
thats what we are discussing here from yesterday that this is too early to comment anything about the performance of BD.just read the review of anandtech and toms and you can see that BD is winning in the multithread performance but lagging in single thread.so wait for some time to justify your decision of buying 955.after optimization i am sure that there will be huge increase in single thread and a bit increase in multithread performance.after that you may cry along with me that you could have waited for a bit long.

No we wont mate. As long as its satisfies our needs who needs an upgrade.

and its weird to see Win 7 not optimized for a Proceesor...I thought this data is shared with the OS people in advance so that they can release that stuff in Regular Updates before product gets launched.

But as a AMD Fan I seriously hope that AMD gets a good boost like 15-20% minimum with that glitch resolved.

^^buddy how can Microsoft know about BD when they were releasing win 7.i guess even AMD wouldn't have known completely about BD at that time.the optimization we can see only from now onwards after its release.i hope that after optimization and all BD will at least see a 30-35% increase in its single thread performance and that much is must for it to fight against the SB.and a 10% increase in multithread is more than enough.right now i don't think even it needs any boost in its multithread performance.
think you want to make an ornament or something for which you need silver.and you go to shop and find that you are getting silver and gold at the same rate.which one you will buy????gold isn't it?though silver is more than enough for you but still why would you leave opportunity to get something better at the same price. :wink:

So the revised version can be expected to be released with HD 7xxx series GPU as they will be released in Q1 2012 right ??

i can't say anything about the date.but still guess that it may take 3-4 months.i can understand your condition brother,you have already waited for a long time.you want to go with amd processor but its performance is holding you back.

Exactly you just stole words from my mouth. If I am purchasing a PC for 100+K then I don't want to regret later that damn I should have waited for a few months.

gameranand said:
Exactly you just stole words from my mouth. If I am purchasing a PC for 100+K then I don't want to regret later that damn I should have waited for a few months.

dont act like a child bro

Its your money
you know when to spend and how to spend
going for 2600k will be a great idea for you coz you have waited pretty long enough
and you can wait for HD 7xxx series if you wanna get something from Red camp
coz your 5770 will still do a decent job until 7xxx arrives
got my point?

Honestly I have waited just a couple of months maybe less.

But man I hate waiting. Also I am not on my PC and I have some old games to finish.

^^then buy 2600k.but the thing is just what you said, you spend a lot of money to build a comp and then you should not regret that you could have bought a better one.if you have 5770 then i guess you can manage it with it for a while.isn't it?then wait for 3 months.if there is no improvement in BD then go with 2600k.
@piyush,
brother you are right that in current conditions 2600k is best solution but i am seeing some future tech hidden in BD.the architecture design of the BD looks as it is the future of the processor world.

@gameranand, if u're up for a gaming build forget bulldozer...
I doubt BD can get past 2600K or even 2500K(in gaming) with future tweaks/patches...

The Bulldozer Review: AMD FX-8150 Tested - Gaming Performance

gameranand said:
Honestly I have waited just a couple of months maybe less. But man I hate waiting. Also I am not on my PC and I have some old games to finish.

Buddy my suggestion is to jump in for sandybridge for your rig. Believe me, current bulldozer will never be able to beat sb even with optimizations. If you check tomshardware review, they have tested sb and bulldozer in windows 8 pre-build and found that both were gaining some performance grounds.

Its not like fx8150 will decimate i7 2600k. I don't even think it can beat it. Now intel will launch another i7 2700k next month at same price point as 2600k. So it will get tougher and tougher. Next year, pile driver will go head on with not one but two tough contenders i.e sandybridge-E and ivybridge. So things are a bit sketchy for bulldozer currently.

Even tomshardware said to give bulldozer a wide berth and their choice of cpu's were i5 2500k and i7 2600k for an overall performance.

Talk about multithreaded apps, i7 2600k is also performing equally good as fx 8150 and even beats it in maximum scenarios. So i suggest to skip bulldozer and go for a sandybridge based rig.

topgear said:
this is what I'm thinking right now... why not they tested the cpu performance ( in dev stage ) with benchmarks ??

as many of you already told I'm considering it something like GTX480 for which we were able get the world fastest single gpu like GTX 580 - they will learn a lot from the this and the next cpu might be better than this,

in 2003 AMD Brought 64-Bit Computing to the Desktop and on the 10th Anniversary they might bring another wonder in desktop cpu world .

For me - I will wait for the next cpu release ( from both side )

I agree, one thing though, on performance side GTX480/470 beat the 5870 and 5850 black and blue across ALL benchmarks, at competitive prices too, the only issue was with power consumption and temps(never was an issue though, GTX480 is one of the most stable cards out there) but for BD, amd's pricing sucks and still it can't perform anywhere near sandy bridge.

Cilus said:
Guys, one good news for AMD. Just checking the Anandtech review and found out something useful.
Anandtech also tested X264 encoding using a moddified Binary compiled to support AVX and AMD XOP instruction set and found out that in 2nd pass (which is the original pass where video gets encoded originally) FX 8150 is beating out i7 2600K.
This is really interesting because this example shows how an optimized application for AMD Bolldozer architecture can be benefited and has some serious performance boost. Hoping to see some patch releases to optimize Bulldozer's performance.

Check out here. In Windows 8 preview there is a performance improvement ranging from 4% to 10% over Windows 7. The reason given by AMD is that Windows 7 Scheduler is not aware about Bulldozer's module based architecture and places threads wherever it finds a core is free, rather than judging the state of the module. For example suppose at time t Bulldozer has two free modules (that is 4 cores to OS) and there are two threads waiting for OS to schedule them in CPU. Now if OS is not aware of the modules, it may assign both the threads to the cores of a single module, resulting low resource utiliztion, confilts etc as we all know two cores of a module are not totally independent, they share Fetch-Decode, FP unit and L2 cache.
Now if OS is aware of the modules then two threads can be assigned to two different modules. Here each of the threads gets two cores to finish execution of the instructions present in each of them, resulting faster execution.

Similarly it will also help to improve the Turbo core performance. For example if two threads, say Th1 and Th2 where Th2 is dependent upon Th1, are present, they should be assigned to the two cores of a single module to improve resource sharing and to cut down all the other modules to reach at the peak turbo speed when a single module as all the other module are not in used and can be cut from power.

In Windows 7 it is not possible all the time due to OS' inability to recognize the modules.
But if the OS is aware of a module and the cores inside it, those problems can be addressed and scheduling can be done in much organized manner.

I think this is intriguing, but one thing, BD IPC is abysmally low, cache read/write speeds are down the drain, memory speeds are not so good either, overall single core performance is bad, all of these problems are holding BD back, if they sort the cache thrashing problem with a new scheduler in win 8 that will increase performance but how much I doubt, in the meantime intel will just drop ivy bridge(by the time win 8 comes ivy will make it to the market and will be matured, late 2012), piledriver might be good but too little too late.

There are also other issues as well, for starters, even if GloFo screwed up, BD is a massive 2B transistors chip, and we all know what happen to big chips(Fermi), larger the chip, more power it will draw, even if GloFo fix the process power consumption will never match that of intels.

Check the hardwareheaven.net review of BD.There BD is beating i7 2600k in all the three games tested.They have used a different motherboard other than the ASUS' Crosshair V Formula used in almost all other reviews
AMD FX-8150 Black Edition 8-Core Processor vs Core i7-2600K Review - Deus Ex Human Revolution

I'll get my good old PC in mid november. Then I have some old games which runs damn good on that so I'll complete them which would take some months I guess. If by that time there would be no BD revisions then I'll go for the best available SB processor in my budget which would be 2700K if that is to be released next month. Whats your take on this ??

Just setting the record straight.

Too many firsts for AMD and GlobalFoundaries here. Complete new architecture, HKMG, Gate First and a huge ~320 sq. mm die for the CPU. Recipe for disaster if you ask me. Second, Bulldozer was a server oriented design...already too late and they didn't bother fixing it for client properly. Heck, they would have been better off by releasing a hypothetical X8 on 32 nm. Die size would have been approxiamtely as big as Llano (~220 sq. mm) and with 8 cores and ~10% IPC improvement it would have skimmed past i7-2600k in multithreaded benchmarks at least.

Now, if you think GTX 480 beat HD 5870 black and blue, then well..you are deluding yourself. It was 10% faster with 1.6x the die size (530 sq. mm) and 1.6x the transistor count (~3 billion). Too many firsts for nVidia there too. Completely new architecture, new 40 nm manufacturing process with no previous experience and a huge monolithic die.

Both are/were equal disasters. And turn arounds happen too. HD 4850/70 and GTX 500 series. Just hope Bulldozer is fixable. Neither AMD nor nVidia are Intel - in terms of size, revenue and R&D. Also, in the ability of selling crappy products when you're being outperformed by your competitors.

atm what I'm more interested in seeing is, how does Bulldozer (Interlagos and Valencia) performs against Magny Cours and Xeons. Just to know whether this thing sucks for servers too or not.

and sharing just for the sake of it, have I found one positive review? AMD FX-8150 Black Edition 8-Core Processor vs Core i7-2600K Review - Introduction

Every other review has used Crosshair V Formula whereas this review has used ASRock 990FX Extreme4.

yeah thanks for link ico and sunny.
here its close to 2600k and beating it in games. so its simple, gaming performance will vary across different games..

AMD FX-8150 Black Edition 8-Core Processor vs Core i7-2600K Review - F1 2011
Benchmark Results: F1 2011 : AMD FX-8150 Review: From Bulldozer To Zambezi To FX
so using a radeon card and a different mobo helped it get past?

I think BIOS upgrades with newer microcode will help in increasing the performance. Something is actually 'bugged.' It appears that the ASRock motherboard had a BIOS with an updated microcode. You see, every review apart from this has used Asus Crosshair V Formula.

ico said:
Just setting the record straight.

Too many firsts for AMD and GlobalFoundaries here. Complete new architecture, HKMG, Gate First and a huge ~320 sq. mm die for the CPU. Recipe for disaster if you ask me. Second, Bulldozer was a server oriented design...already too late and they didn't bother fixing it for client properly. Heck, they would have been better off by releasing a hypothetical X8 on 32 nm. Die size would have been approxiamtely as big as Llano (~220 sq. mm) and with 8 cores and ~10% IPC improvement it would have skimmed past i7-2600k in multithreaded benchmarks at least.

Now, if you think GTX 480 beat HD 5870 black and blue, then well..you are deluding yourself. It was 10% faster with 1.6x the die size (530 sq. mm) and 1.6x the transistor count (~3 billion). Too many firsts for nVidia there too. Completely new architecture, new 40 nm manufacturing process with no previous experience and a huge monolithic die.

Both are/were equal disasters. And turn arounds happen too. HD 4850/70 and GTX 500 series. Just hope Bulldozer is fixable. Neither AMD nor nVidia are Intel - in terms of size, revenue and R&D. Also, in the ability of selling crappy products when you're being outperformed by your competitors.

atm what I'm more interested in seeing is, how does Bulldozer (Interlagos and Valencia) performs against Magny Cours and Xeons. Just to know whether this thing sucks for servers too or not.

and sharing just for the sake of it, have I found one positive review? AMD FX-8150 Black Edition 8-Core Processor vs Core i7-2600K Review - Introduction

Every other review has used Crosshair V Formula whereas this review has used ASRock 990FX Extreme4.

And apparently the ONLY website to do so, if it was really the mobo holding it back then AMD would have already opened their mouth, they seem suspiciously quite about it, the site cranked up the game settings/res so much that the CPU is no longer relevant, see their forum, looks like a lot of forum members agree with me: AMD FX-8150 Black Edition Processor Launch Review @ HH

ico said:
Just setting the record straight.

Too many firsts for AMD and GlobalFoundaries here. Complete new architecture, HKMG, Gate First and a huge ~320 sq. mm die for the CPU. Recipe for disaster if you ask me. Second, Bulldozer was a server oriented design...already too late and they didn't bother fixing it for client properly. Heck, they would have been better off by releasing a hypothetical X8 on 32 nm. Die size would have been approxiamtely as big as Llano (~220 sq. mm) and with 8 cores and ~10% IPC improvement it would have skimmed past i7-2600k in multithreaded benchmarks at least.

Now, if you think GTX 480 beat HD 5870 black and blue, then well..you are deluding yourself. It was 10% faster with 1.6x the die size (530 sq. mm) and 1.6x the transistor count (~3 billion). Too many firsts for nVidia there too. Completely new architecture, new 40 nm manufacturing process with no previous experience and a huge monolithic die.

Both are/were equal disasters. And turn arounds happen too. HD 4850/70 and GTX 500 series. Just hope Bulldozer is fixable. Neither AMD nor nVidia are Intel - in terms of size, revenue and R&D. Also, in the ability of selling crappy products when you're being outperformed by your competitors.

atm what I'm more interested in seeing is, how does Bulldozer (Interlagos and Valencia) performs against Magny Cours and Xeons. Just to know whether this thing sucks for servers too or not.

and sharing just for the sake of it, have I found one positive review? AMD FX-8150 Black Edition 8-Core Processor vs Core i7-2600K Review - Introduction

Every other review has used Crosshair V Formula whereas this review has used ASRock 990FX Extreme4.

It varied between 10%-30%: AnandTech - Bench - GPU11

For the server side BD consumes too much power, servers are all about power efficiency, and otherwise I want to see a review in which BD server cores come close to intel in terms of power consumption.

tkin said:
And apparently the ONLY website to do so, if it was really the mobo holding it back then AMD would have already opened their mouth, they seem suspiciously quite about it, the site cranked up the game settings/res so much that the CPU is no longer relevant, see their forum, looks like a lot of forum members agree with me: AMD FX-8150 Black Edition Processor Launch Review @ HH

Also look at the link Jas posted regarding F1 2011 FPS in Tom's hardware review and HH. Both at 1080p. Shared it just for the sake of it. Something odd. Nothing less and Nothing more.

tkin said:
It varied between 10%-30%: AnandTech - Bench - GPU11

That's how you derail a thread.

Next someone posts a Tomshardware review link. Next Guru3D and everyone keeps on fighting over platform biased games.

Keyboard warriors.

But for the sake of it, I'll quote Anandtech's review itself.

The GTX 480 is between 10 and 15% faster than the Radeon 5870 depending on the resolution, giving it a comfortable lead over AMD’s best single-GPU card.

tkin said:
For the server side BD consumes too much power, servers are all about power efficiency, and otherwise I want to see a review in which BD server cores come close to intel in terms of power consumption.

For your kind information, power consumption is one of the last things enterprises worry about. All they care about is maximum throughput/performance from a limited rackspace and floorspace. If performance outdoes the running cost, data center people are happy. They aren't even going to overclock to get more performance. It is very very different from the client scenario and BD is going to be power efficient compared to AMD's previous gen as far as servers are concerned.

Cheaper OEM cost by $40 or so and 0.08 kWh less energy consumption is not a factor here.

IMO.....It would have been better if they would have done die shrink on the ph-II series and launched them now...Instead of Bulldozer. Directly shifting to Piledriver series ,by that time they would have perfected the problems with manufacturing....!
Almost read al the reviews out there only 5%~6% of reviewers are positive...Thats bad for AMD.
If Ivy-bridge is launched in march-2011 with their 8-core variant then its very bad for Piledriver series....

gameranand said:
Honestly I have waited just a couple of months maybe less. But man I hate waiting. Also I am not on my PC and I have some old games to finish.

well if your games are running fine now, then there is no need to upgrade
otherwise you know the path

guys take a look at these links,
Why I bought a Bulldozer inside - CPUs - CPU-Components

Our Take on AMD FX | Game Blog

ico said:
For your kind information, power consumption is one of the last things enterprises worry about. All they care about is maximum throughput/performance from a limited rackspace and floorspace. If performance outdoes the running cost, data center people are happy. They aren't even going to overclock to get more performance. It is very very different from the client scenario and BD is going to be power efficient compared to AMD's previous gen as far as servers are concerned.

Cheaper OEM cost by $40 or so and 0.08 kWh less energy consumption is not a factor here.

Actually yes, enterprises really don't worry about power consumption that much but if its off the roof, then there are some concerns. I would say bd is one power hungry cpu and using it in server clusters will definitely adversely effect power bills.

But it depends how its confronted. If a firm doesn't care and in maximum case scenario it is, then there's little to worry in that front.

But all i care and of course enterprises is performance. Processes, subroutines are queued up and there's a lot to process always. If server bulldozer matches xeon in this, i see no harm for firms eyeing bulldozer as the choice of server cpu. Pricing is also a factor.

But i see a slim chance on amd taking over intel in the server space as well.

I'm hypothetically assuming that a hypothetical Rs. 2000 cheaper AMD offering with more cores compared to a comparable Intel part is utilizing 40w more constantly the whole year. (which won't be true ALL the time, again a hypothetical scenario)

0.04 * 24 * 365 = 350.4 units. Now I'm taking a cluster of 100. 35040 units more than than Intel. Commercial electricity is almost Rs. 1.50 per unit. 35040 * 1.5 = Rs. 52560 spent more with AMD than Intel.

But then the AMD offerings were Rs. 2000 cheaper. Multiply by 100. Rs. 2 lakh saved.

Do your math now.

Electricity isn't a huge deciding factor for data centers.

And datacenters will also not mind buying 100 Intel offerings than AMD offerings too despite the fact they'll have to pay more.

The most important factor for them is...throughput they can get from the limited amount of space available to them. Whether it's Intel or AMD, they don't care.

Heck, runtime cost whether you choose AMD or Intel for 4 years turns out to be same.

If you go with AMD, you pay 2 lakhs less for the server but ~50k more for electricity per year. If you go Intel, you pay 2 lakhs more for the server but ~50k less for electricity per year.

This again vindicates my point of maximum performance from a limited floorspace. That's all what matters for datacenters. With reliability ofc.

Moroever, they deal in crores, not lakhs. This discussion is silly as much as tkin's post was.

Looking at various BD reviews. Now at least I have no grudges that my motherboard doesn't support AM3+ proccy

J

retarded discussion.

Latest supercomputer to run on InterLagos cores. | SemiAccurate

ico said:
I'm hypothetically assuming that a hypothetical Rs. 2000 cheaper AMD offering with more cores compared to a comparable Intel part is utilizing 40w more constantly the whole year. (which won't be true ALL the time, again a hypothetical scenario)

0.04 * 24 * 365 = 350.4 units. Now I'm taking a cluster of 100. 35040 units more than than Intel. Commercial electricity is almost Rs. 1.50 per unit. 35040 * 1.5 = Rs. 52560 spent more with AMD than Intel.

But then the AMD offerings were Rs. 2000 cheaper. Multiply by 100. Rs. 2 lakh saved.

Do your math now.

Electricity isn't a huge deciding factor for data centers.

And datacenters will also not mind buying 100 Intel offerings than AMD offerings too despite the fact they'll have to pay more.

The most important factor for them is...throughput they can get from the limited amount of space available to them. Whether it's Intel or AMD, they don't care.

Heck, runtime cost whether you choose AMD or Intel for 4 years turns out to be same.

If you go with AMD, you pay 2 lakhs less for the server but ~50k more for electricity per year. If you go Intel, you pay 2 lakhs more for the server but ~50k less for electricity per year.

This again vindicates my point of maximum performance from a limited floorspace. That's all what matters for datacenters.

Actually i want to say something on the bold part. You calculated the units correctly but the price slab is incorrect i guess. Not sure but it isn't a constant 1.50. Afaik there are various slab structures according to number of units consumed. Correct me if i am wrong. :smile:

Yes, your points thereafter are true. Like you said, datacenters hardly care about power consumption. Its all about the performance index in a limited floorspace. So it has to be the performance amd should eye if its targeting server space.

About the 2lakh vs 50k, i guess they are even stevens. Lets say you spend 2k less per server going with amd and pay 50k more per year. But servers aren't meant to last a year but more. Assuming a minimum of 4 year lifecycle , its 50k x 4 i.e 2lakhs. So it equates out the amount saved when buying a cluster of 100. For intel, it works the same...pay more first and then save later.

vickybat said:
Actually i want to say something on the bold part. You calculated the units correctly but the price slab is incorrect i guess. Not sure but it isn't a constant 1.50. Afaik there are various slab structures according to number of units consumed. Correct me if i am wrong.

yup. It's just a hypothetical scenario.

saz said:
Looking at various BD reviews. Now at least I have no grudges that my motherboard doesn't support AM3+ proccy

Finally one positive. :lol:

Friends is the FX-4100 worth for gaming because it is performing near the FX-8150 in gaming.
AMD FX 8150 - 8120 - 6100 and 4100 performance review

^^if you correctly take a look then you can see that phenom II X4 is ahead of both.thats why i am telling to wait for some time to buy or pass your comment on BD.

T

Sukesh instead of buying BD lets buy a CM212+ and kick our phenoms to 4.2 GHz

(j/k)

but only doubt remain is why amd is not commenting on anything.it is completely silent.and tech wiz,buddy i am not going to buy bd even if they sell it for 3k.i bought my processor hardly one month ago and this is more than enough for me.

sukesh what will be the most probable price of FX-4100.It should cost less than p2 X4 980BE

it should be around 5k.may be even less than 5k.

R

Cilus said:
Thanks for clarifying MAx_snyper. No I'm not planning to buy one right now as I'm having 1090T overclocked @ 3.6 GHz. Gaming performance wise I don't think I need an immegiate upgrade.

Having said that, even a BD will be sufficient for gaming na....so if the price is right, it still just might be competitive....hope switching to new fabs might fix their power issues or at least, cheaper price..

sukesh1090 said:
it should be around 5k.may be even less than 5k.

At that price would not the processor be a steal

yes but only if its power consumption issues gets fixed.i hope it will be fixed in next revisions and performance is not a worry.so if you want to but BD wait for some time.
@rajan,
he is already having 6 core phenom II.and in market there is no game which will use 6 core completely right now.so he is not willing to upgrade and it is not needed also.

R

sukesh1090 said:
yes but only if its power consumption issues gets fixed.i hope it will be fixed in next revisions and performance is not a worry.so if you want to but BD wait for some time.
@rajan,
he is already having 6 core phenom II.and in market there is no game which will use 6 core completely right now.so he is not willing to upgrade and it is not needed also.

that is what I meant... its not the performance that soooo bad, just power consumption is Phenom I type

...

will be buying BD next week for sure though...

Guys, any AM3+ board is fine for BD right?

yes any am3+ is good but try to get 9XX FX chipset mobo.

HARDOCP - CPUs and DX11 Gameplay - AMD Bulldozer / FX-8150 Gameplay Performance Review

MSI 990FXA-GD80 and radeon 6970 used.

Jaskanwar Singh said:
HARDOCP - CPUs and DX11 Gameplay - AMD Bulldozer / FX-8150 Gameplay Performance Review

MSI 990FXA-GD80 and radeon 6970 used.

The settings at which they are testing, the games already become severely GPU bound(except maybe games like Civ 5 which uses DX11 multithreading), so they perform either same or 2500k pulls a bit ahead.

and thats the settings we play tkin. they should matter to us.

Jaskanwar Singh said:
and thats the settings we play tkin. they should matter to us.

In that case people can buy a cheaper Quad core Phenom II and save 10k over the FX8150 which will allow them to play games just fine without any loss in performance. Hell, even old intel quad cores(C2Q series) hold fine at those GPU restrained settings.

tkin said:
In that case people can buy a cheaper Quad core Phenom II and save 10k over the FX8150 which will allow them to play games just fine without any loss in performance. Hell, even old intel quad cores(C2Q series) hold fine at those GPU restrained settings.

well if its vfm then why not ;-)

they will concentrate on gpu then.

games are meant for enjoying at higher resolution. dont they?

jas, thanks for the links.except civ 5 in all the games 8150 is winning over intel ones.so what else do we need in performance ???the multi thread performance is good,game performance is good the only head ache is power consumption thats all,if thats fixed this processor is going to rock.so guys BD is not a fail.

@tkin,
if thats the case then brother we also don't need i5 and i7,a 5k phenom IIX4 is more than enough.why should people spend 10k for i5 and 15k for 17.its totally waste.if a person buy a 15k processor then i am damn sure that he will buy a 15-20k graphics card or atleast a 11-12k card.in that case also we don't see any performance difference with our eyes.and a 5k phenom II can easily handle those cards without being a bottle neck,then why do we need these above 10 k processor???

sukesh1090 said:
jas, thanks for the links.except civ 5 in all the games 8150 is winning over intel ones.so what else do we need in performance ???the multi thread performance is good,game performance is good the only head ache is power consumption thats all,if thats fixed this processor is going to rock.so guys BD is not a fail.

@tkin,
if thats the case then brother we also don't need i5 and i7,a 5k phenom IIX4 is more than enough.why should people spend 10k for i5 and 15k for 17.its totally waste.

Sure, buying 2600k just for gaming is plain stupid, 2400 is good enough for that, or Phenom II anyday.

10k+ processors are good for Video encoding, running multiple VMs etc.

PS: I found a comic, Operation Scorpius

^^in VMs and encoding and all 8150 is ahead of intel.so its better to go with 8150 than 2600k if its power consumption issues gets fixed.isn't it?

sukesh1090 said:
^^in VMs and encoding and all 8150 is ahead of intel.so its better to go with 8150 than 2600k if its power consumption issues gets fixed.isn't it?

That's a big if, but if it does, then yes, definitely.

Update: even with vms and encoding 8150 is faster than 2500k, not 2600k, but the price difference makes 8150 a better choice.

^^lets hope it does or else we have to wait for piledriver.but if it does then the good time for AMD will begin.btw thanks for the comics.while preparing that comic may be AMD didn't know that FX group is going to need a hell lot of food to survive. :wink:

yes, but brother the programs need a bit tweaking and optimization for working effectively in BD and for that we have to wait and after that even if it gets a mere 5-6% boost in performance it will go ahead.

sukesh1090 said:
^^in VMs and encoding and all 8150 is ahead of intel.so its better to go with 8150 than 2600k if its power consumption issues gets fixed.isn't it?

8150 cannot get past 2600k even in multithreaded apps. That's because its single threaded performance is very low actually lower than the thubans.

Overall, its not recommended to go for bulldozer now considering its performance and not power consumption. Memory read/write speeds are also abysmal.

memory read and write speed of AMD was always lower when compared to Intel because they never ever tried to improve their memory controller.but the multi thread performance is very good but the single thread is not good may be because of its newer design.

sukesh1090 said:
memory read and write speed of AMD was always lower when compared to Intel because they never ever tried to improve their memory controller.but the multi thread performance is very good but the single thread is not good may be because of its newer design.

Multithreading is good but not good enough. Remember that mutlithreading performance will always depend on single core performance. They are directly proportional.

Anyways an interesting article:

Did We Expect Too Much of AMD Bulldozer?

^^thanks for the link brother.the one comment whic caught me was that the decision of AMD buying ATI.now AMD has to compete both with nvidia and Intel.which is getting harder for them i guess.but still we need this company running or else we will see 2600k selling for 50k and 560 selling for 45k.

^^ You're welcome mate. :smile:

Yes there should be competition or else end users like us will be affected.

rajan1311 said:
will be buying BD next week for sure though...
Guys, any AM3+ board is fine for BD right?

If its for gaming, I don't think its a good choice...

Guys anyone checked HardwareCanucks?? They give pretty awesome reviews..

^^ thanks for the link ;-)

rajan1311 said:
that is what I meant... its not the performance that soooo bad, just power consumption is Phenom I type ...

will be buying BD next week for sure though...
Guys, any AM3+ board is fine for BD right?

not any Am3+ mobo is good for BD cpus - some Am3+ mobos has 95w cpu TDP limitation like asus M5A78L-M LX @ 2.8k - if you want a 95w+ tdp am3+ cpu then look for Gigabyte GA-880GM-USB3 ( 3.1 rev ) @ 4.8k - there's more pricier mobo based on 9 series chipset which has native suuport for am3+ ie BullDozer cpu but they cost even more as well.

sukesh1090 said:
yes but only if its power consumption issues gets fixed.i hope it will be fixed in next revisions and performance is not a worry.so if you want to but BD wait for some time.

Most probably AMD will fix the power consumption with next revision and performance might improve as well but for some huge leap in performance we have to wait for their next cpu release ;-)

And when is their next CPU release ??

i think it is in somewhere around q2 in 2012 but not sure as AMD have only mentioned 2012.that processor is piledriver.but lets wait for the next revision.may if that power consumption gets fixed then surely AMD will increase the frequency to what they were first intended to.i guess power consumption was the reason because of which they didn't increased the frequency to 30% more than the phenom.

Oh boy 2nd quarter. I hope revision come with hd7000 series as I'll buy pc when 7xxx get release.

Buying BD now is a stupid thing to do... Be happy with whatever you have now ... Wait for couple of months or for Ivy Bridge.... AMD may come with revision or AMD FX v 2.0 with optimised performance in single thread apps and lower poer consumption......

BD power usage is not good considering that it is a 32 nm proccy.. People at AMD are not mad they know where they stand against Intel...

I would like to see AMD succeed if they loose we loose.. I don't want to buy a 3 Ghz Intel proccy or a nvidia mid range card at Rs 25000 because if AMD does not come with any good Intel or Nvidia will be asking too much....

@gameranand,
the piledriver is intended to be released in early 2012.so hope it will be released in Q1.

^^piledriver release will be on the early q2 of 2012.
I think it would be better if they price BD close to 2500k here in India,price close to 2600k would not make the cut. afterall its India where Intel is known even to those people who dont have basic knowledge of pc hardware.
Found out in the reviews that for gaming,fx-4110/6110 is not at all bad choice...lets see how its priced in India.

please give links for 4110/6110 reviews other than the guru 3d review

^^buddy are you kidding.you only have given the link for the guru 3d review of 4XXX and 6XXX in post 846.now why you are asking for the link?

max_snyper has written reviews which means that he has read reviews other than the guru 3d review

^^i was collectively counting on reviews for all bulldozers...!
only one till now (guru3d).

max_snyper said:
Found out in the reviews that for gaming,fx-4110/6110 is not at all bad choice...lets see how its priced in India.

Can you please justify the above by sharing those links mate? Afaik, they don't qualify as good gaming cpu's. They are also beaten by previous generation athlon 2 and phenom 2 x4's.

Guru3d has tested only farcry 2 and crysis 2 and both these cpu's are right at the bottom of the pack. So can you clarify by sharing some other reviews?

^areee dude IMO when u play at the higher resolution there is low stress on cpu than gpu,as we all know if next gen games are still gpu depended then any cpu would do as long as it has more than 2 physical cores.

and as we are discussing on southern islands..this might be your interest.
Report: First AMD 28nm GPU Due in December

^^wow nice info mate. hd 7 series will really be something. Can't wait to see how the new GCN architecture based Tahiti-XT & PRO perform.

I am no more thinking about 4100 as its cpu performance is even lesser than p2 x4.Its equal to p2 x3 and athlon2 x3.
No more BD in my mind.Would either get a SB or p2 x6

^^^i no more thinking of the amd platform itself.....i was thinking my next build to be from amd camp....their upgradability was of keen interest but due to not so good performance(i said not so good instead of "poor" coz they are average-ish) im more thinking of a intel platform around november end..may be a 2500k build.As they are offering ivy bridge next gen on the same package (1155).

Guys see this- AMD Spreads Propaganda, Ex-Employee Speaks Out

yes I am also got fixed between whether to take SB to upgrade to IB or take Phenom to upgrade to Piledriver

M

max_snyper said:
^^piledriver release will be on the early q2 of 2012.
I think it would be better if they price BD close to 2500k here in India,price close to 2600k would not make the cut. afterall its India where Intel is known even to those people who dont have basic knowledge of pc hardware.
Found out in the reviews that for gaming,fx-4110/6110 is not at all bad choice...lets see how its priced in India.

Yes,max people are too much intel centric most of the people even think AMD has heating problem now it is the real problem with them.

Minion said:
Yes,max people are too much intel centric most of the people even think AMD has heating problem.

I totally agree with you. I have seen ppl commenting on AMD from days of athlon 2xxx, that AMD heats a lot. Although AMD had the problem but not now i guess coz i'm also using athlon x2. You will be surprised to know that, that in todays IT era,in my home town (Gaya), no PC shop keeps AMD procy

When i bought my first pc, i got 845 chipset being told as new, although 945 had arrived then. (I was totally a n00b that time

)

sunny10 said:
yes I am also got fixed between whether to take SB to upgrade to IB or take Phenom to upgrade to Piledriver

IMO, AMD will try to defeat the current Gen. intel(Sandybridge) with their Piledriver CPUs & by that time Intel would have long gone with their Ivy bridge CPUs...

M

dashing.sujay,Intel has much more resource than AMD even their income is more. To do research it requires money if nobody is going to support you then how Somebody will compete in this fierce market. So its really hard time for them I feel if they overcome shortcoming of BD and releases next version of BD much early then they are back into game again.

Again people need to understand phenom x4 series provide great value for money BD is completely new architecture that is the reason why it miserably fails While Microsoft works very closely with Intel to utilize full power of their CPUs

In earlier Days AMD was a research company AMD develop hyper threading for intel which push intel a long way even today i don't believe how they are losing to a company for whom they develop technologies.

if anybody missed this -
AMD FX-8150 Black Edition CPU Water Cooler Review - Temperature Testing Results - Legit Reviews

so guys will AMD get bankrupted?? :shock:

just a doubt wandering in head.

^^^ subh subh bolo bhai!!!!1

)

@sukesh...dude its a multi-million company they havent invested in BD consumer products entirely...they still have ample of money and they have already signed up for the oem contracts....so dont worry!!!!
Their GPU division is doing too well so they are unlikely to go bankrupt.

^^hahahaa.i was just kidding.but if they go on releasing BD like processors then sure they will face that condition.i never want that because i love AMD.

As I said earlier.. If AMD loose we loose...neither Intel nor nvidia should get monopoly.... If AMD go bankrupt we will have to face Intel and nvidia both and have to use whatever they provide...

If AMD was not there we would not have got this multi core processors... They came with 3, 6 core proccy and now 8...

What if they come with a masterpiece in next copule of months...

Even Intel fan should thank AMD for forcing Intel to go 64bit, multi core, etc.

^^ I agree with you ;-)

We all need AMD to succeed. We've seen what happens without a strong AMD as a competitor. We get processors that are artificially limited and severe restrictions on overclocking, particularly at the value end of the segment. We're denied choice simply because there's no other alternative. I don't believe Bulldozer is a strong enough alternative to force Intel back into an ultra competitive mode, but we absolutely need it to be that. I have faith that AMD can pull it off, but there's still a lot of progress that needs to be made. AMD can't simply rely on its GPU architecture superiority to sell APUs; it needs to ramp on the x86 side as well—more specifically, AMD needs better single threaded performance. Bulldozer didn't deliver that, and I'm worried that Piledriver alone won't be enough. But if AMD can stick to a yearly cadence and execute well with each iteration, there's hope. It's no longer a question of whether AMD will return to the days of the Athlon 64, it simply must. Otherwise you can kiss choice goodbye.

Source

this why AMD needs to come up with a strong cpu and this why we are seeing ( still ) a lot of choices when someone needs to buy a cpu ;-)

+1
I agree with you here. AMD's performance is really important as if they don't perform then we are going towards intel's monopoly which is too bad for us.

looks like every one is thinking a lot about AMD.in world there are some people who trust AMD.thats why some people without even waiting for the review just bought the BD.but now because of BD's performance they lost trust in AMD.so hope AMD gains back it by releasing some revisions.

We should accept the fact that AMD BD is a new thing.... I would say it is ahead of its time... The benchmarks would have been in favr of BD if msot of the software, games are design to use multi thread correctly...

If discuss about the power consumption then I have read in some forum that sandy bridge - E will be vary muich power hungry.....

We should not blame AMD as this is totally a new propcessor and they would have predicted that some problem will arise... Hebce the next Piledriver will come with be good see which will address all the problem currently seen in BD

And at last do not consider BD as totally fail.....

Sandy-E uses quad channel rams, and has 6 cores/12 threads, of course it will be power hungry, we are talking about Performance per watt, and I believe Sandy-E will blow all other processors out of the water in that category.

^^^And you forgot to mention one thing they will be insanely costly!!
Especially in India!!

max_snyper said:
^^^And you forgot to mention one thing they will be insanely costly!!
Especially in India!!

Well yeah, they are replacements for the legendary X58 after all, and if BD didn't fail like that we would have gotten some Sandy E at cheaper price too, but what can we do, 2600k still remains the fastest processor, these processors have PCIE 3.0, quad channel rams, the QPI interconnect, more cache, fully unlocked(6 core ones), they will probably decimate even AMD piledriver when it launches, no wonder Intel is bumping the price, there is no competition at that level :cry:

Well if Intel's monopoly continues Ivy-Bridge will be overpriced for sure

I will again say that don't curse AMD for BD... Its a new thing and every new thing looks odds at first time....

I am happy that AMD has guts to do new things

What the use of a Intel processor if it sells for Rs 50000 and I can't afford it.... Not every one is Ambani or Tata....

I kind of agree with sumesara. Intel is just too costly to be considered.

baccilus said:
I kind of agree with sumesara. Intel is just too costly to be considered.

Really? A 11k 2500k is not affordable? I agree intel high ends are costly, but the entire Sandy Bridge line up is nothing but pure performance vs price, a 2600k sometimes matches a 50k 980x in benches, now you want the best of the best, you have to pay more, think of 980x as Rolls Royce of processors. But 2500/2400 are great vfm.

Intel extreme processors are always costly, its just for those who can pay, if AMD had their they would charge the same for extreme processors like that(I forgot but I think there were some amd processors in the past that were really costly, when it beat intel black and blue).

Intel mobos are a bit costly at the low end(sub 10k), but since both platforms use DDR3, ram prices are same as well.

PS: Ivy bridge are sandy replacements, they would either have the same performance vs price ratio or higher, Intel never went backwards with their performance vs price ratio.

baccilus said:
I kind of agree with sumesara. Intel is just too costly to be considered.

Thanks baccilus at least someone thinks like me....

.

Well, Bulldozer highest end processor FX8150 is still something which can compete against i5 2500K and may be in some cases with i7 2600K. Now if the pricing is right, FX 8150 retails at say 10K range in India, it is a good buy.

tkin said:
Intel extreme processors are always costly, its just for those who can pay, if AMD had their they would charge the same for extreme processors like that(I forgot but I think there were some amd processors in the past that were really costly, when it beat intel black and blue).

Yes, I remember well, that in days of athlon 3xxx/4xxx series, when AMD launched athlon 5200+, I called AMD india helpline to confirm its pricing. It was 50k in 2006! :shock:

I just slammed the reciever after hearing the price! :))

Extreme series from any company is always too costly.

PS- If intel are more VFM in mid-range, AMD's are more VFM in low end range!

dashing.sujay said:
Yes, I remember well, that in days of athlon 3xxx/4xxx series, when AMD launched athlon 5200+, I called AMD india helpline to confirm its pricing. It was 50k in 2006! I just slammed the reciever after hearing the price! Extreme series from any company is always too costly.

PS- If intel are more VFM in mid-range, AMD's are more VFM in low end range!

50k in 2006? Hell, well actually I think they were going after Intel extreme's throat, every intel processor which is at the top of desktop stack had the X suffix and cost 999$.

^^ Yup, 50k. I remember very well, the lady other side said, "50 thousand sir, are you willing to buy" :banghead:

I replied- "I'm out of station but will buy in 2-3 months

" lol

But AMD's top offering would never cross Intel's, I think so. May be understanding this, AMD is now no more trying to kick Intel's eXtreme series; rather they focussed on VFM, which is working, at least in low segment though. May be we can expect a lot from piledriver, if not better than Ivy, at least better than current SB's.

Cilus said:
Well, Bulldozer highest end processor FX8150 is still something which can compete against i5 2500K and may be in some cases with i7 2600K. Now if the pricing is right, FX 8150 retails at say 10K range in India, it is a good buy.

But even if its 10K it isn't good enough for a gaming rig.. :neutral:

The only reason we needed Bulldozer to be good is because no one can make a balanced Sandy Bridge rig with i5-2500k in 50k. That's a fact.

Basically i5-2500k + an ATX Z68 motherboard takes up ~half the budget straightaway. H67 doesn't make sense. P67 too. Add 2k more to a P67 motherboard, you get Z68.

Jaskanwar Singh said:
if anybody missed this -
AMD FX-8150 Black Edition CPU Water Cooler Review - Temperature Testing Results - Legit Reviews

Nice find - thanks for the link ;-)

a little quote from the first page ;-)

To launch the company's first water cooler they teamed up with no other than Asetek. The folks at Asetek were one of the first companies to offer closed loop water coolers and are also the original manufacturer behind popular water cooling kits like the Corsair H50 and H70 and the Antec Kuhler 620 and 920. The AMD kit resembles the Antec Kuhler 920 the closest. From what we have been told, it's basically the same as the Antec Kuhler 920 but with cosmetic tweaks and Chill Control software tweaks. The unit features a single 120mm double thick radiator, with twin 120mm fans. The pump/cold plate housing is a low profile design and is connected to the radiator with flexible non-corrugated tubing. The flexible tubing helps relieve stress on connections as the tubing doesn’t try and straighten itself. It also helps in the install because it bends easier and you are not fighting the stiffness of the tubing to get parts where you want them. The top of the pump housing is the AMD FX logo. The FX part of the logo is back lit with RGB LED that the color can be changed by the user in the Chill Control interface.

Read on more ..
AMD FX-8150 Black Edition CPU Water Cooler Review - AMD FX Water Cooler - Legit Reviews

M

Sandy E has about 10-15% performance upgrade from the present sandys. It will be better but not phenomenally better!!!

Bd is not running upto speed because the front end is getting bomblasted... the reason this is happening is in the architecture.. the BD acts not like a true 8-core but more like a four core with an additional FPU pipeline.. when windows treats it like an 8-core, its causing the front end to be insufficient..

Windows 8 in that matter is better at managing these cores apparently.. The IIPC of BD is actually better than the phenom II's.. it is evident when 1 core is disabled in each module.. it causes the IIPC to increase upto 20 percent above its original benchmarks!!

mrcool63 said:
Sandy E has about 10-15% performance upgrade from the present sandys. It will be better but not phenomenally better!!!

Bd is not running upto speed because the front end is getting bomblasted... the reason this is happening is in the architecture.. the BD acts not like a true 8-core but more like a four core with an additional FPU pipeline.. when windows treats it like an 8-core, its causing the front end to be insufficient..

Windows 8 in that matter is better at managing these cores apparently.. The IIPC of BD is actually better than the phenom II's.. it is evident when 1 core is disabled in each module.. it causes the IIPC to increase upto 20 percent above its original benchmarks!!

Really? Two more cores and you get 10-15% performance upgrade instead of say (2/4)*100=50%?
My educated guess is that given the quad channel ram, and QPI, it will no doubt be at least 30-50% faster than 2600k any day(talking about the 6 cores ones, not the 4 core one, which will be, as you said, 10-15% faster than 2600k).

About the new scheduler, the same can be said for 2600k, windows 7 also treats it as 8 core, but since its hyper-threaded, we have just 4 cores, if windows 8 comes with a new scheduler that benefits BD it will no doubt benefit 2600k as well, and will also benefit Sandy-E because all of them are hyper-threaded.

If you read here: *www.fudzilla.com/processors/item/24473-core-i7-3960-is-up-to-36-percent-better-than-i7-990x
Its 15% better than 990x, which on the other hand is about 15% faster than 2600k give or take. On multithreaded benchmarks 990x is a lot faster than 2600k.

tkin said:
Really? Two more cores and you get 10-15% performance upgrade instead of say (2/4)*100=50%?
My educated guess is that given the quad channel ram, and QPI, it will no doubt be at least 30-50% faster than 2600k any day(talking about the 6 cores ones, not the 4 core one, which will be, as you said, 10-15% faster than 2600k).

About the new scheduler, the same can be said for 2600k, windows 7 also treats it as 8 core, but since its hyper-threaded, we have just 4 cores, if windows 8 comes with a new scheduler that benefits BD it will no doubt benefit 2600k as well, and will also benefit Sandy-E because all of them are hyper-threaded.

If you read here: *www.fudzilla.com/processors/item/24473-core-i7-3960-is-up-to-36-percent-better-than-i7-990x
Its 15% better than 990x, which on the other hand is about 15% faster than 2600k give or take. On multithreaded benchmarks 990x is a lot faster than 2600k.

Tkin, even Windows XP can differencitate between logical cores and physical cores of a Hyper-threaded processors. So don't expect performance improvement due to optimization in Windows 8 on this area. But Windows 8 also has other optimizations too which will increase the performance of Sandybridge processors too along with Bulldozer.

M

^^ my point almost mirrors yours.. windows 7 has a tough time working out the BD architecture which win 8 will probably be optimized to do.. Hyper threading has already been recognized by windows in the 7 edition however BD's architecture being new is not recognized by windows 7.. that is why by windows 8 will have a comparable performance of both 2600k and BD..

also sandy-e will be terribly overpriced.. you will have to pay through your nose just to get one.. also sb-e will involve a new socket... and.. intel have a bad record with new socket releases(since 1156, then 1155)!!! the lowest one will almost match the 2600k apparently and is a locked variety unlike 2600k.

^^IMO IF we are talking about the VFM of the intel and amd processors...heres my 2 penny on it.
I bought my second build in 2005 with pentium 4 ht 630 series...last i upgraded it to 2gb ram and a ati hd4670 512mb card in 2008.
it ran each and every game on 1680*1050 med-high settings till date (i mean up till deus-ex,hell ya even crysis 2.)(15~45 fps)
It played without even breaking a sweat.....talk about VFM..a outdated machine playing new-gen game thats Intel.
I trust Intel now a little more now,if they are planning for Ivy-bridge then its gonna be better than SB.
But a good attempt by AMD for BD..they better get their things right for piledriver if they want to be VFM king.

M

dude with a 9600gt even my athlon 3200+(5 year old rig!!) played every game including battlefield 2 on high settings at 1280x1024.. 15fps is not good... really..

no games use more than one core and only recently they have began using two cores.. AMD has been price vs performance king for very long.. intel used to be good performance but horribly overpriced .. now with sandy they have come down a little.. but the ultimate vfm king was always AMD everytime..!! Just see the phenom II or the athlon range before it..

AMD has always been a pioneer for invention of newer tech.. 64bit coding was first embeded by amd.. dual core first by amd.. now BD architecture first by AMD..

I am not a fanboy but i dont like it when people guage anything just by its cover.. It is a new chip.. give it time to mature..

^^ hey mrcool63 did you not read my previous opinion....it was for all company policies in early 2000's and now...a chip was to last for atleast 3~4 years for offcially casted as outdated now-a-days every 1~2 years there is new iteration for systems.
And i know 15fps mean..i have been in the gaming scene since the doom days so i pretty much know everything about gaming.
Im too not a fanboy of intel or amd...
Just that AMD has landed in VFM market 2~3 years back till that time Intel was the only chip known commonly in India.AMD was too costly and not avaliable everywhere...it has just landed into the scene of vfm after ph-ii 955 was sold like hot cakes in India.

mrcool63 said:
^^ my point almost mirrors yours.. windows 7 has a tough time working out the BD architecture which win 8 will probably be optimized to do.. Hyper threading has already been recognized by windows in the 7 edition however BD's architecture being new is not recognized by windows 7.. that is why by windows 8 will have a comparable performance of both 2600k and BD..

also sandy-e will be terribly overpriced.. you will have to pay through your nose just to get one.. also sb-e will involve a new socket... and.. intel have a bad record with new socket releases(since 1156, then 1155)!!! the lowest one will almost match the 2600k apparently and is a locked variety unlike 2600k.

Why are people going ga ga over Sandy-E, its clearly made for super rich enthusiasts, damn quad channel 32GB(4x8GB) ram kit from corsair costs a freaking 999$, so you can see the entire line up is made for wealthy buyers, on the other hand we will have Ivy, with an improved GPU and also 10-30% increased performance, less heat, power consumption, and hence more OC potential at a very consumer friendly price(to avoid clash with Sandy-E, ivy will probably max out below 350$, like 2700k now).

The improved scheduler will affect both 2600k and BD, and I am guessing, to edge out the competition 2600k will take 2500k's place and 2700k will be the new 2600k, so both of intel's top sandy will be hyper-threaded, effectively nullifying any performance improvement BD will have on win 8.

Some thoughts after going through the reviews and all:-

1) BD is either too late or too ahead of its time, depending on the way you look at it.

2) With so much talks going on single-core performance, I wonder why Intel/AMD not releasing a 4Ghz single core CPU, or at best a 4Ghz dual core with strong per core performance and strong overclocking potential. It looks like that should be enough for our normal PC usage for the time being. I mean, how many of the general PC users and even gamers are interested in running multiple VM simultaneously or in heavily threaded apps?

3) Pricing of the products is pretty much spot on. The 8120 looks like the CPU to go for, if you are actually thinking of buying a BD.

4) The biggest flop of the lot is the FX-4100. It is worse than Athlon II X4 at quite a few benches making the older Phenom II or even Llano A8 CPUs a better choice.

5) In continuation with the previous point, it looks like BD needs 4 modules/8 cores to remain competitive and can't go lower than 3 modules/6 core. So Piledriver with 6 modules/12 cores can actually deliver the promised/expected performance level of BD. If AMD can fix the single-core performance by that time, it might actually compete well with Ivy Bridge too. I do agree, at this moment all these are rather wishful thinking.

6) The Phenom II suddenly looks better than before. Reviewers are a funny lot.

7) The biggest problem seems to be investing in the AM3+ platform at this moment. With the final generation of AM3+ CPUs expected to come out in 2012 itself, users won't be getting a much longer upgrade path.

8) For gamers on a budget, nothing much has changed. Going the BD route would probably allow a better GPU compared to SNB which in turn means better gaming performance except in CPU-intensive games, which are, thankfully, getting fewer by days.

tkin said:
Why are people going ga ga over Sandy-E, its clearly made for super rich enthusiasts, damn quad channel 32GB(4x8GB) ram kit from corsair costs a freaking 999$, so you can see the entire line up is made for wealthy buyers, on the other hand we will have Ivy, with an improved GPU and also 10-30% increased performance, less heat, power consumption, and hence more OC potential at a very consumer friendly price(to avoid clash with Sandy-E, ivy will probably max out below 350$, like 2700k now).

The improved scheduler will affect both 2600k and BD, and I am guessing, to edge out the competition 2600k will take 2500k's place and 2700k will be the new 2600k, so both of intel's top sandy will be hyper-threaded, effectively nullifying any performance improvement BD will have on win 8.

+1 for that. Windows 8 can't change the scenario overnight. Particularly, no one knows what will actually happen after 1 year. And by that time, we would be talking about newer CPUs for sure.

^^I have come to the conclusion that...its a fact that BD does not beat 2600k black and blue..and provides the functionality of 2500k so if priced around 10k in India its a win situation,but one problem it retails around $279 on newegg at the moment so may be when launched in India its gonna be priced around 16k.

i agree with u SKUD...that bring a dual core 4ghz processor with HT thats gonna rock at a mid segment level.

Theres not going to be drastic increase in performance on BD with "win 8" unless and untill applications are developed for BD chips.

IMO opinion seriously its not a bad idea if u want to invest in BD right now if u really want to as piledriver is up ahead on am3+ platform.......but investing in a z68 platform is not a bad idea either.
As down the line ivybridge is also coming for the z68 platform.

Price is already falling

Prices AMD FX-8150 Black Edition already falling

And more problems:-

Rumor: AMD Working with TSMC for Bulldozer Manufacturing

That roughly calculates to 14.5k INR with or w/o taxes in India coz europe and Indian prices are somewhat similar due to vat.....Thats too bad if they are pitching against what intel has now in the market....Not gonna make the cut here.....I still remember how p2-ii 955 created a storm in India when it was launched....BD just cant live up to that.

Initial prices will be a bit high anyway.

max_snyper said:
That roughly calculates to 14.5k INR with or w/o taxes in India coz europe and Indian prices are somewhat similar due to vat.....Thats too bad if they are pitching against what intel has now in the market....Not gonna make the cut here.....I still remember how p2-ii 955 created a storm in India when it was launched....BD just cant live up to that.

I guess around 15k+

^^ So thats the case then why would a customer buy 15k+ proccy if hes getting same performance for 11k (2500k) or 15K (2600k).It sits right between both cpus thats what amd tried for.
only the + point for amd config is lower ram prices,lower mobo prices....some amount of money to buy ....may be gaming mouse or something else.

T

AMD FX-8150 in six position on cpubenchmark

source

max_snyper said:
^^ So thats the case then why would a customer buy 15k+ proccy if hes getting same performance for 11k (2500k) or 15K (2600k).It sits right between both cpus thats what amd tried for.
only the + point for amd config is lower ram prices,lower mobo prices....some amount of money to buy ....may be gaming mouse or something else.

Ram prices are same, both DDR3, mobo prices are similar if you compare the features.

Actually 990FX based mobos are bit costlier. And where are the 990X and 970 chipsets? Still no sign of them.

max_snyper said:
^^ hey mrcool63 did you not read my previous opinion....it was for all company policies in early 2000's and now...a chip was to last for atleast 3~4 years for offcially casted as outdated now-a-days every 1~2 years there is new iteration for systems.
And i know 15fps mean..i have been in the gaming scene since the doom days so i pretty much know everything about gaming.
Im too not a fanboy of intel or amd...
Just that AMD has landed in VFM market 2~3 years back till that time Intel was the only chip known commonly in India.AMD was too costly and not avaliable everywhere...it has just landed into the scene of vfm after ph-ii 955 was sold like hot cakes in India.

Max_Snyper, your information is not entirely true. AMD is available for a long time here, not just 2/3 years earlier, and even pre-Athlon 64 bit era Athlon XP processors was little better in gaming that their competitor early gen P4 processors due to the 3D Now instruction set. But they were not known to mass market in India.
My 1st desktop @ 2003 was an Athlon XP 2600+ with Nforce2 mobo + 32 MB Gforce2 IGP used to play Far Cry while my firend's 3 GHz P4 processors simply couldn't start the game.
Then around 2005 I had purchased my Athlon 64 3000+, priced @ 5.4K whereas P4 EE CPUs was available @ 6 to 6.5K and nowhere near to Athlon 64 in terms of performance.
And taling about outdated chip performing well, that is true for both AMD and Intel, not only for Intel. It cannot be a trust increasing factor for any brand. If you have an Athlon X2 6000+, launched at 2006 with a 8800GT, you can play all the games in medium setting @ 1366X768 resolution.

^^ oh boy you are truly loyal to AMD.

Hey guys check this

AMD Bulldozer no fix needed | Apple AMD Bulldozer patch, the Crash, Web-bots, Greece Default, Free Stock Footage

Is it true.......

AMDZone.com • View topic - List of Useful Bulldozer Apps

pretty interesting

sumesara said:
Hey guys check this

AMD Bulldozer no fix needed*|*Apple AMD Bulldozer patch, the Crash, Web-bots, Greece Default, Free Stock Footage

Is it true.......

^^ What's that, some sort of conspiracy site? Poor grammar, senseless rubbish, profanity, a poll on left that looks like some 13 year old child's rambling, anyway thanks for the laugh, this site should go in the 'Dumbest Thing about Computer Thread'

User comment on that site:

No registry fix.

No UMS problems.

No Bios fix.

You lied, and you persist in deleting both our posts and your own in an attempt to change the past to hide your own flaws.

Based on this, and the rest of the site – GET MEDICAL HELP.

Deleting this won’t help you, it won’t make you right, it won’t change history. By not admitting your flaws, you are far worse than any of the atrocities you accuse others of.

Signing off – No Faith.

I can't stop laughing.

+That guy talks about big foot.

Jaskanwar Singh said:
AMDZone.com • View topic - List of Useful Bulldozer Apps

pretty interesting

These people are going though a phase, its called "DENIAL," just don't get bothered.

@cilus...i was referring to the VFM market that amd captured 2~3 years ago...
I know initial p4 478 pins cpu were complete dud in performance as compared to amd series...overheating problems here and there.
But my question to you is was amd avaliable in mass quantity as intel was back then?
And how many players in lamington road market(mumbai) had stacked up each and every amd proccy iteration at that time.they started stackingup in 2004 i think when athlon64. came
at that time around in 2002 searched for cheapest pc for my 1st build couldnt find other than Intel p4 1.6~1.7 ghz.
Im not a fanboy of any of these companies,but scenario changes when any pc component enter pc Indian market.

PS: I saw this feedback of FX8150 in New egg, couldn't stop laughing, thought its worth a share.

Pros: low power for 8 cores
IT has 8 CORES!!
Working with the amd and using the fx990s and my 6870
rules i got the unlock haha(watch the video on neweggs youtube channel for the new procs)
do not own one my friend got his yesterday from amd

Cons: does not support stock over drr3 1866 (they should realy inprove that)
realy was hopping for lager L1,2,3 caches'
or hyper threading(mabye a hyper threaded black edition
srry but it seem ever time Amd get the spec. edition there black)

Other Thoughts: Go look at the Intel 6 cores' they are 130watt and the new Amds' are 125watt for 8 cores yes its only 5watts but wait its 5watts and 2 cores also the new 6 core amds are only 95 watts thats 45watt differencs. amd is great on power and speed but there is more to it. I don't want to start a huge debate(on new egg) over Intell and Amd fans but they are both good and I use both from time to time
I use Amd for my games and Intell for my anything else.

max_snyper said:
@cilus...i was referring to the VFM market that amd captured 2~3 years ago...
I know initial p4 478 pins cpu were complete dud in performance as compared to amd series...overheating problems here and there.
But my question to you is was amd avaliable in mass quantity as intel was back then?
And how many players in lamington road market(mumbai) had stacked up each and every amd proccy iteration at that time.they started stackingup in 2004 i think when athlon64. came
at that time around in 2002 searched for cheapest pc for my 1st build couldnt find other than Intel p4 1.6~1.7 ghz.
Im not a fanboy of any of these companies,but scenario changes when any pc component enter pc Indian market.

It clearly was.

But people still bought Intel for higher Gigahertz and companies only used Intel because of their underhand dealings.

Proven fact.

~~^^i don't think it is true.just take a look at the comments in that page and you will come to know.~~
sory this is in reply for that post by sumesara.

we can clearly divide the last decade into 2 parts.....pre 2005 and post 2005
Due to mainly scarcity of components in pre 2005 and post 2005 for everything u have "options".
i remember searching for geforce 2 mx-440 (64mb ram) throughout lamington agp card...
those were the days searching for components was real job....LoL

tkin said:
These people are going though a phase, its called "DENIAL," just don't get bothered.

Couldn't get the point about denial, its mostly a compilation from various sites. BD has done fairly well in heavily threaded apps like 7-zip, POV-ray etc. across various sites. It has not decimate the top SNB at every benchmark, but at its price point it doesn't need to. Suddenly people are trying to say X6 was already very good in threaded apps and BD hasn't improve much over it. But then I remember, people (read reviewers) had similar feelings when Barts & Cayman came out.

Don't get me wrong, I am also hugely disappointed with BD's performance in general, particularly for it's inconsistencies, but it's not a complete failure. You may look it from a different angle, why we are still talking about single-core performance when both AMD and Intel has stopped producing single-core CPUs much before.

BD is a forward looking architecture, and looking back a couple of mistakes is becoming apparent:-

1) The server chip should have been released before the desktop chip. But then they are already behind the schedule.

2) Instead of 8-core, AMD better marketed this as a 4 core/8 thread CPU in lines of Intel's hyperthreading. Things would have looked far far better at that time.

^^ Its not about single core performance but single threaded performance. Its about how a single thread is processed by a single execution core normally combination of integer and floating point units with a scheduler.

This also determines multithreaded performance because individual threads containing dependent or independent instructions will be processed by the core execution units concurrently or simultaneously.

If one fast single core can process a thread in 4 secs, then 4 similar cores will do it in 1 sec.

On contrary, a slower core or execution unit processes a thread in 15 secs, 4 cores will take 3.75 secs. Its just a general analogy.

So single threaded performance determines multithreaded performance and this is one of the reasons why intel is ahead this generation. If amd would have concentrated on this aspect, then today we would have been seeing 8150 beating a 2600k handsdown across all benchmarks.

The reason most probably lies in amd's execution units themselves. Maybe they are not good enough i.e the integer and floatiing point units present inside a bulldozer module though architecturally looks good but not good enough in performing integer or float operations. Similar operations in sandybridge core that takes lets say 4 secs for an operation, might take 10 secs in a bulldozer core.

DISAPPOINTED, I had high hopes!
Nevertheless its should be a good starting point for pile driver

I was following this topic closely, been very very busy and now disappointed :\

M

sumesara said:
I will again say that don't curse AMD for BD... Its a new thing and every new thing looks odds at first time....

I am happy that AMD has guts to do new things

What the use of a Intel processor if it sells for Rs 50000 and I can't afford it.... Not every one is Ambani or Tata....

Right,for that reason I don't even consider Intel,when buying new PC Agree processor is a important part of PC but if i can't feel the difference what is the use of pouring money there instead go for better graphics card and lots of memory.It will provide you same performance even better.

^^ But we should all agree at some point.......investing money in the intel platform for now,is better choice if not the best...though it may be little costly than AMD.
You can choose AMD BD platform if you really want to (fanboy or whatever),,if you want to go for piledriver series in future.

max_snyper said:
^^ But we should all agree at some point.......investing money in the intel platform for now,is better choice if not the best...though it may be little costly than AMD.
You can choose AMD BD platform if you really want to (fanboy or whatever),,if you want to go for piledriver series in future.

I agree on that. Choosing Intel seems a no brainer right now, unless you like to gamble. Lets see at which price point it debuts in India.

You know that I'm very much loyal to AMD because they are loyal to end users too. When Athlon 64 bit was released, they even launched a SOCEKT A version of it to be fited in Athlon XP motherboards. However, I'm not a fanboy and in my opinion, right now anybody investing 40K or above should consider Intel Sandybridge quad cores (read i5 2400) because Bulldozer (read FX 8150) is ahead of Sandybridge in only some specific applications and almost none of them comes under day to day application list.
AMD's new architecture looks promising but they mmay gain some performance advantage with the coming multi-threaded apps and with Windows 8 but they need some hardware revisions too to improve the thermal levels, power consumptions and per core performance, at least marginally.

And price too.

Guys seriously, i had high hopes on fx 4100 and 6100. But their performance is the most disappointing in the entire bulldozer lineup. I mean these $114 and $165 respective cpu's had a high chance of cutting into the mainstream market if they would have had a little bit of firepower in them.

In gaming too they are in the last place. Some of my friends are buying their systems after a long wait for bulldozer. Now they are asking questions why i told them to wait for bulldozer in the first place and why i'm denying them now.

lol, I told two of my friends to buy i3-2100.

Wise choice.

IM just waiting to get the news regarding the hd7xxx series cards from the amd camp...their cpus have dissapointed me....i thought to be 2600k killer but later prior to the release some price cuts & their product placements generated quite a suspecion around the world about their performance.....If they would have built a cpu for current applications with high single threaded performance it would have been better....!

BD has left us in an embarrassing position. :facepalm:

max_snyper said:
IM just waiting to get the news regarding the hd7xxx series cards from the amd camp...their cpus have dissapointed me....i thought to be 2600k killer but later prior to the release some price cuts & their product placements generated quite a suspecion around the world about their performance.....If they would have built a cpu for current applications with high single threaded performance it would have been better....!

HD7xxx will be good, no doubt about that, nVidia is no way near intel, beating them won't be a problem, never was, I am expecting around 30% performance improvement for successor models and 20-30% performance improvement for the same price bracket.

R

tkin said:
HD7xxx will be good, no doubt about that, nVidia is no way near intel, beating them won't be a problem, never was, I am expecting around 30% performance improvement for successor models and 20-30% performance improvement for the same price bracket.

In which terms? Money-making?

rajnusker said:
In which terms? Money-making?

I'm saying, say 7870 will be 20-30% faster than 6870(just a guess from previews and speculations).

R

tkin said:
I'm saying, say 7870 will be 20-30% faster than 6870(just a guess from previews and speculations).

Actually, I was pointing your comment where you said nVIDIA is no way near Intel.

Almost everything.

rajnusker said:
In which terms? Money-making?

Revenue. Profit. R&D. Size. Production capability.

nVidia doesn't even have its own fab. Same for AMD.

Beating Nvidia is more easy than beating Intel in their own game.
Nvidia is not wrong company..just the company which does things a lil bit wrong way!
BTW 28nm shrink is a half node right for AMD.

rajnusker said:
Actually, I was pointing your comment where you said nVIDIA is no way near Intel.

In every imaginable way.

M

ok guys single threaded apps are bad on BD because of two things
1. The cores are thinner... Sandy's are much thicker..
2. The 8core is actually behaving more like a 4 core + one additional FPU per core.. now when a program assumes that to be an 8 core it distributes the calculations among them making it saturate the front end... so in the next BD they plan to increse L2 and L3..

If you want to test the BD in a single threaded app.. disable the 4 additional fpu cores and then test.. you will see the IIPC is about 10-20 percent more.. because the front end has better handling capabilities..

This is another argument in favour of BD

SB E will be horribly overpriced.. the models in the price bracket of the 2600k is a locked proccy and not unlocked as in 2600k. also its socket will be 2011 and not 1155.. LGA 2011 boards as of release will be minimum 15k and above.. Ivy bridge will be 1155 but it is expected to release around may next year.. so a pretty long wait for you if you want a ivy..

So unless you are prepared to shell out minimum 30k+ for just mobo and proccy then waiting is a useless prospect..

Now do you understand why BD is competitive... 2600k will be the best till next year ivy for mid range..

mrcool63 said:
ok guys single threaded apps are bad on BD because of two things
1. The cores are thinner... Sandy's are much thicker..
2. The 8core is actually behaving more like a 4 core + one additional FPU per core.. now when a program assumes that to be an 8 core it distributes the calculations among them making it saturate the front end... so in the next BD they plan to increse L2 and L3..

If you want to test the BD in a single threaded app.. disable the 4 additional fpu cores and then test.. you will see the IIPC is about 10-20 percent more.. because the front end has better handling capabilities..

This is another argument in favour of BD

SB E will be horribly overpriced.. the models in the price bracket of the 2600k is a locked proccy and not unlocked as in 2600k. also its socket will be 2011 and not 1155.. LGA 2011 boards as of release will be minimum 15k and above.. Ivy bridge will be 1155 but it is expected to release around may next year.. so a pretty long wait for you if you want a ivy..

So unless you are prepared to shell out minimum 30k+ for just mobo and proccy then waiting is a useless prospect..

Now do you understand why BD is competitive... 2600k will be the best till next year ivy for mid range..

Would you elaborate what you mean by a thick core and a thin core? I didn't get the head or tail of it. And what has the fpu unit got to do with single threaded performance?

Bulldozer's fpu is a completely different execution unit that only handles float operations or instructions from a thread. Even sandybridge's core has one. If the scheduler finds float instructions,then its assigned to the fpu.
As simple as that.

Now disabling all fpu units will result in even slower performance cause it will just ignore all floating point operations. The statement you made seems ridiculous unless you throw some more light into it.

Now coming to sandybridge-E, they are different from mainstream sandybridge when it comes to overclocking. Although the non extreme parts have locked multiplier but doesn't feature a locked bclk. That means base clock can be incremented to overclock the cpu. In 1155 sandybridge, the bclk is locked. So you know, even the sub $300 sandybridge-E parts will make sense for enthusiasts on a budget.

And i still don't understand how you call BD competitive. Care to explain that ?

@mrcool63
why dont you understand SB-E is for enthusiast who have deeeeep pockets to buy that stuff.....
This is what you wnat===Whose comparing who
1.AMD BD <> Intel previous gen i-series as well as new gen i-series(well some of them).
2.AMD Piledriver <> Intel Ivybridge.

SB-E is more of a server grade system with quad channel,new qpi and what not...
Its not for common people....as the i-series 2xxx and amd ph-ii & BD.
get it now!!!!

M

dude i referred to sb-e more for a timeline... and to tell some people who said wait for sb-e and ivy to upgrade..

as u said sb-e is enthusiasts proccy.. so will be premium priced.. the next proccy in the 2600k range will be ivy... follow me...

now ivy will be released by may here.. so till next year 2600k is king.. BD's performance is comparable to sandy.. so the next BD will be almost equal to 2600k releasing by jan or feb. so till ivy releases amd will have a proccy to compete with ivy..

where this is all leading to is that BD is quite a good bet

@vicky-- dude the architecture for BD is tricky to understand.. here is something that will make my argument a little clear

from semiaccurate..

That brings us to the oddest part of the architecture, the FP unit. It is shared between the two Int units, and is seen as a coprocessor, not an integrated pipeline like almost every other modern CPU. This means that any FP instruction will be fired off to the shared FP scheduler, there is only one, and when the instruction is completed, the FP unit signals the ‘core’ that it is done.
Remember those added resources that were mentioned earlier? Currently, the ‘Stars’ cores have a 128-bit FP unit. With Bulldozer, there is one FP unit that can crunch two 128-bit numbers per clock. The shared scheduler means there is a single central arbiter that can make sure things are ‘fair’ to both cores, but if one core doesn’t use an FP instruction that clock, the other core can use twice the resources it is usually allowed to.

So even though the FP scheduler is shared there are two 128bit FMAC cores as opposed to one for every core in the conventional core topology.. When you disable one core in a module the other core will have two 128 bit FMAC's instead of one as is the convention.. Hence my statement ' One core plus an additional fpu'

Now do you understand??

Dude, let BD release in India first. Depending on its price, we may or may not recommend it.

mrcool63 said:
ok guys single threaded apps are bad on BD because of two things
1. The cores are thinner... Sandy's are much thicker..
2. The 8core is actually behaving more like a 4 core + one additional FPU per core.. now when a program assumes that to be an 8 core it distributes the calculations among them making it saturate the front end... so in the next BD they plan to increse L2 and L3..

If you want to test the BD in a single threaded app.. disable the 4 additional fpu cores and then test.. you will see the IIPC is about 10-20 percent more.. because the front end has better handling capabilities..

This is another argument in favour of BD

SB E will be horribly overpriced.. the models in the price bracket of the 2600k is a locked proccy and not unlocked as in 2600k. also its socket will be 2011 and not 1155.. LGA 2011 boards as of release will be minimum 15k and above.. Ivy bridge will be 1155 but it is expected to release around may next year.. so a pretty long wait for you if you want a ivy..

So unless you are prepared to shell out minimum 30k+ for just mobo and proccy then waiting is a useless prospect..

Now do you understand why BD is competitive... 2600k will be the best till next year ivy for mid range..

I have explained the OS problem while handling BD modules. It is not because saturated Frontend but because of the inability of OS to not understanding the module based design and two cores inside it. OS sees it at 8 separate cores. Here is the link of my previous post: *www.thinkdigit.com/forum/cpu-motherboards/135848-amd-bulldozer-news-discussion-27.html#post1508789

mrcool63 said:
dude i referred to sb-e more for a timeline... and to tell some people who said wait for sb-e and ivy to upgrade..

as u said sb-e is enthusiasts proccy.. so will be premium priced.. the next proccy in the 2600k range will be ivy... follow me...

No , the next cpu in the 2600k line up is going to be 2700k and its going to launch next month. Not all sandybridge -E cpu's are premium priced. The entry level ones will also beat 2600k. For eg. i7 3820 is going to cost $294 and seems affordable imo.

mrcool63 said:
now ivy will be released by may here.. so till next year 2600k is king.. BD's performance is comparable to sandy.. so the next BD will be almost equal to 2600k releasing by jan or feb. so till ivy releases amd will have a proccy to compete with ivy..

where this is all leading to is that BD is quite a good bet

Its leading nowhere. You cannot predict a processor's performance out of thin air speculations.BD's performance is not comparable to sandy and its mainstream cpu's are a complete failure. Next bulldozer not only has to compete with 2600 and 2700k but also 3820. Things really look bad in amd's perspective now. Pile driver has to be a complete evolution in order to turn things away.

mrcool63 said:
@vicky-- dude the architecture for BD is tricky to understand.. here is something that will make my argument a little clear

from semiaccurate..

So even though the FP scheduler is shared there are two 128bit FMAC cores as opposed to one for every core in the conventional core topology.. When you disable one core in a module the other core will have two 128 bit FMAC's instead of one as is the convention.. Hence my statement ' One core plus an additional fpu'

Now do you understand??

First and foremost, you cannot compare different architectures and predict performance. In case of bulldozer, it has two 128bit FMAC execution units. I won't call it a core but a part of it. If you see sandybridge's floating point execution unit per core, it will look something like the following:

*i53.tinypic.com/2cwrbjn.jpg

Now you see sandybridge's execution cluster. Floating point multiplication, addition and boolean are performed by different execution units in a single cluster. Now this part of a core wheres athe other part has an integer unit. Each sandybridge core has a single frontend whereas each bulldozer module has a single front end.

Besides amd sees avx in a different perspective than intel. Bulldozer has two 128 bit sse (fmac unit) which will be combined for 256 bit avx operations. But in sandybridge, it allows two 256bit avx operations in a single clock cycle thus has twice FP throughput.

So there are other flaws in bulldozer than simply the architecture. Although the modular architecture is good , it wasn't implemented by amd properly and thus has flaws.

M

No , the next cpu in the 2600k line up is going to be 2700k and its going to launch next month. Not all sandybridge -E cpu's are premium priced. The entry level ones will also beat 2600k. For eg. i7 3820 is going to cost $294 and seems affordable imo.

Once again read my earlier post.. i7 3820 along with a lga2011 mobo will be beyond normal people.. i7 will be with a locked multiplier.. not as easy to overclock as the sandy but can be done no doubt.. the kicker will be the x79 chipset boards for the 2011.. they are now hefttily expensive going above 15k for the normal ones.. also pcie3 support is still doubtful...if you still doubt the x79 prices check it in google...

Its leading nowhere. You cannot predict a processor's performance out of thin air speculations.BD's performance is not comparable to sandy and its mainstream cpu's are a complete failure. Next bulldozer not only has to compete with 2600 and 2700k but also 3820. Things really look bad in amd's perspective now. Expect pile driver to a complete evolution in order to turn things away.

2700 is a 2600k with a higher clock.. everybody knows that it was proposed to be released to counter BD!!! 3820 is what i am talking about above.. You are saying that a person who feels BD at 12k is expensive will invest in a 3820 at 17k with a x79 mobo at 16k or more and call it value for money?? how are you predicting 3820's performance?

First and foremost, you cannot compare different architectures. In case of bulldozer, it has two 128bit FMAC execution units. I won't call it a core but a part of it. If you see sandybridge's floating point execution unit per core, it will look something like the following:

yeah dude spot on there... those are all the reasons why BD is bad in single threaded apps

My say was that instead of overloading and potentially bottlenecking the front end and the FPU by using two cores with 8 integer pipelines, running one core with 4 integer pipelines with the existing FPU will decrease the bottleneck and give upto 20 percent more performance gains.

Now do you follow my drift

mrcool63 said:
Once again read my earlier post.. i7 3820 along with a lga2011 mobo will be beyond normal people.. i7 will be with a locked multiplier.. not as easy to overclock as the sandy but can be done no doubt.. the kicker will be the x79 chipset boards for the 2011.. they are now hefttily expensive going above 15k for the normal ones.. also pcie3 support is still doubtful...if you still doubt the x79 prices check it in google...

Never denied x79 to be cheap and why should it be? Bulldozer is not a competition for x79 parts. Sandy-E is in a league of its own.

mrcool63 said:
700 is a 2600k with a higher clock.. everybody knows that it was proposed to be released to counter BD!!! 3820 is what i am talking about above.. You are saying that a person who feels BD at 12k is expensive will invest in a 3820 at 17k with a x79 mobo at 16k or more and call it value for money?? how are you predicting 3820's performance?

Hmmm you can say that it was released to counter BD but now its not even required after seeing bulldozer's performance. 2700k will demolish 8150 because you've no idea how sandybridge chips respond to even slightest clock increments. See the [performance difference between i5 2500 and 2400 and you'll know.

A person whose dead-set to get x79 parts lets say i7 3820+x79 mobo won't even look at 1155 based 2xxx cpu's. Forget bulldozer. Its not even in contention.

People will rather invest in 1155 than current bulldozer at every pricepoint. Heck previous gen amd x4 and x6 cpu's makes greater sense.

mrcool63 said:
yeah dude spot on there... those are all the reasons why BD is bad in single threaded apps My say was that instead of overloading and potentially bottlenecking the front end and the FPU by using two cores with 8 integer pipelines, running one core with 4 integer pipelines with the existing FPU will decrease the bottleneck and give upto 20 percent more performance gains.

Now do you follow my drift

Nope, if you remove the additional integer core from a module, then performance will further drop down. It will no longer be called a a module anymore.

The problem is in the scheduling logic in current operating systems which cannot distinguish modules from cores. Cilus was trying to convey the same.
Windows 8 will try to address this as said by its lead designer "ARUN KISHAN".

Dependent instructions from separate threads will be assigned to single bulldozer module by the shared frontend to fully utilize the architecture and windows7 is unable to do that now.

^^so vicky how much performance increase we will see in win 8 with BD?

Vicky is right here. The OS limitation is also stopping Bulldozer to use its Turbo Core feature to maximize the performance in lightly threaded environment.
For example consider a Thread T1 which is quite big and need 5 CPU time slice or 5 iterations (switching back to main memory after each time slice and then again assigning it to CPU. Known as Context Switching and handled by OS)to be completed. Now Say Bulldozer have two mdoules M1 and M2 and 4 cores C1, C2 belongs to M1 and C3, C4 belongs to M2.

Now for enabling Turbo-core, in each of iteration, T1 needs to be assigned to a single module, say in M1, to disable the module M2 completely and increase the clock speed of M1 to fasten the execution.

Since, Windows 7 is simply not aware of Bulldozer module and it sees a Dual module chip as 4 independent cores, namely C1, C2, C3 and C4, it may assign the thread T1 to any of those cores. Now for the 1st two iterations, by luck, T1 is assigned to C1 and C2, belongs to same module, resulting enabling Turbo core for these two iterations. But in the 3rd, 4th and 5th iterations, say Win 7 Assigned them to either C3 or C4, resulting Turbo-Core to be disabled as both the modules are now working on a single thread but not concurrently.

^^but still there is no sign of power consumption fixes from AMD.we may get a performance boost in win8.this os problem could be the reason why BD is showing inconsistent performance.once it goes above all the processor but in some test it catches dirt.

sukesh1090 said:
^^so vicky how much performance increase we will see in win 8 with BD?

I would say a 10-20% increment in light to heavily threaded apps. But sandybridge and all its successors are also going to benefit from windows 8.

For this reason, i would say people to give bulldozer a try. Besides, you also have the newer instruction sets at your disposal.
A normal user won't see any performance deficit in real life scenario. I don't think fx 4100 and 6100 are power hungry. They are 95 watt cpu's right?

Cilus said:
Vicky is right here. The OS limitation is also stopping Bulldozer to use its Turbo Core feature to maximize the performance in lightly threaded environment.
For example consider a Thread T1 which is quite big and need 5 CPU time slice or 5 iterations (switching back to main memory after each time slice and then again assigning it to CPU. Known as Context Switching and handled by OS)to be completed. Now Say Bulldozer have two mdoules M1 and M2 and 4 cores C1, C2 belongs to M1 and C3, C4 belongs to M2.

Now for enabling Turbo-core, in each of iteration, T1 needs to be assigned to a single module, say in M1, to disable the module M2 completely and increase the clock speed of M1 to fasten the execution.

Since, Windows 7 is simply not aware of Bulldozer module and it sees a Dual module chip as 4 independent cores, namely C1, C2, C3 and C4, it may assign the thread T1 to any of those cores. Now for the 1st two iterations, by luck, T1 is assigned to C1 and C2, belongs to same module, resulting enabling Turbo core for these two iterations. But in the 3rd, 4th and 5th iterations, say Win 7 Assigned them to either C3 or C4, resulting Turbo-Core to be disabled as both the modules are now working on a single thread but not concurrently.

Yup this explanation is perfect buddy.Context switching is the right term and like you said, turbocore is having limitations because the modules are getting worked on unnecessarily and cannot be disabled to bump clock speed. One of the reasons of bulldozer's current dismal performance.

But i see hope in windows 8.

Problem is that Piledriver, which is expected to release in Q1 2012, is supposedly the last upgrade that AM3+ will receive as AMD is apparently moving towards a newer socket. If that is true then even Piledriver would be without the support of Win 8 for a good 7-8 months. So committing to a platform, which will get CPU upgrades for less than a year and no optimum OS support for a similar period, doesn't seem wise at this moment. By the time Win 8 will come out, we will most probably be talking about some other processors.

Hopefully, BD will do and sell well in server market.

^^Yup you are right mate. Amd's next socket is FM2 and will unify cpu and apu to a common platform. I guess pile-driver will feature komodo cores (5 modules) and will get the FM2 treatment along with trinity.

Windows 8 is not that far off. But intel will constantly make life harder for amd by launching more and more cpu's. Believe it or not, they are even eyeing trinity with their ivybridge gpu. They say its a big leap from sandybridge's gpu. Must say that igp performance will never be the same again and the future truly is fusion. :smile:

Might be a big leap by Intel's standard.

M

Intel said so with the sandy's HD 3000 IGP.. but still amd trouced it.. for embedded gpu's intel still has a lot of work to do to catch up... Amd is much much better in that process..

Sandy benefiting from windows 8 will be comparatively less than BD.. BD will show much more improvement over sandy as they are saying BD will be optimized for win8 especially with the instruction sets... however will it be able to beat 2600k then is still a 40-60 chance.. my guess will be no.. it may improve drastically but beating 2600k in its present state may be hard..

Skud said:
Might be a big leap by Intel's standard.

True but once intel sets standards ,it gives competition a tough time. What they said so far has been true unlike amd.

mrcool63 said:
Intel said so with the sandy's HD 3000 IGP.. but still amd trouced it.. for embedded gpu's intel still has a lot of work to do to catch up... Amd is much much better in that process..

Sandy benefiting from windows 8 will be comparatively less than BD.. BD will show much more improvement over sandy as they are saying BD will be optimized for win8 especially with the instruction sets... however will it be able to beat 2600k then is still a 40-60 chance.. my guess will be no.. it may improve drastically but beating 2600k in its present state may be hard..

Yup it has a lot of hard work to do. But you never know.... a company as powerful as intel can easily acquire firms like nvidia. If in future this ever happens, then tables might turn. Amd's gpu section is its strongest weapon now.

To beat it in its own game, a strong merger or acquisition like the above is necessary and there's always a probability.

I think intel will make something like the cell cpu after the failure of its larrabee project.

Vicky, believe it or not, in integrated GPU business, Intel simply sucks and nothing have been working for them till now. In fact couple of years earlier they tried to challenge Nvidia (in times of launching the 8000 series GPU) with their Larabee project, developing a 16 core design where each of the cores can execute both CPU and GPU tasks and can increase IGP performance in a dedicated GPU level. But that project failed badly and Ibtel had to dump the larabee concept because the architecture was too much to even for Intel to develope and was not feasible in terms of price also.
In IGP segment AMD has shown far fast growth than Intel and they are way ahead in terms of performance, architecture and price point. In fact their architecture is true fusion, Intel's architecture is not. The Intel HD 2000/3000 IGP is just a Graphics core, not at all any fused design, completely separated from the CPU cores but just put inside a single die. They also work in the same way a mobo based IGP works, reserving some portion of the Ram for GPU calculation.
on the other hand AMD Fusion is a heterogeneous core design, multiple cores are present inside a Die, some of them are CPU cores and some are GPU cores and they use common memory access logic. In fact you're the one who provided me the link where it is shown that AMD may replace the FPU of its processor with a GPU core as GPU is far more powerful than CPU while executing floating point instructions. In fact this architecture has several advantages as here you both kind of cores (CPU and GPU cores) can help each other by sharing the resources and executing the parts where one is better than other. As a result while performing GPU based computing, CPU cores can help GPU to decode and execute complex and scalar instructions and GPU cores can help CPU by executing the parallel and vector instructions.

BTW, here is another review of FX series with couple of more games tested:
*www.techspot.com/review/452-amd-bulldozer-fx-cpus/

^^piledriver will be BD with gpu.isn't it?then in pile driver we can surely say that the performance will very good when compared to BD as gpu cores will help the cpu in its work.

Found this mobo review, might be helpful. Give some more insight to BD's strength and weaknesses:-

MSI 990FXA-GD80 AM3+ Motherboard

Still waiting for a review of high end gaming. May be 2 systems of same price from Intel and AMD camp, instead of same hardware config. This might get interesting.

sukesh1090 said:
^^piledriver will be BD with gpu.isn't it?then in pile driver we can surely say that the performance will very good when compared to BD as gpu cores will help the cpu in its work.

No mate pile driver is a pure cpu. Trinity is an apu and will have bulldozer cores.

What cilus said might become a possibility in future but definitely not in piledriver.

Here comes the IVY-BRIDGE......spring 2012....not so far away!!!!
Link: Intel to Sell Ivy Bridge Late in Q4 2011

Already noticed that, good news.

Skud said:
Found this mobo review, might be helpful. Give some more insight to BD's strength and weaknesses:-

MSI 990FXA-GD80 AM3+ Motherboard

Still waiting for a review of high end gaming. May be 2 systems of same price from Intel and AMD camp, instead of same hardware config. This might get interesting.

thats a nice performance by 8150 in their.in about 75% of the test it is above 2500k or match with 2500k when over clocked.so 8150 is a very good buy if it's price is around 10-10.5k.if they can still increase its performance by revisions then they can sell it around 12-12.5k.

Problem is they can't increase the price revision, can they?

sorry brother,i din't get you.

What SKUD is trying to convery that the Price of a specific processor revision normally has same price as the non revison or old versions. So if a initial version of FX8150 is available @ 10.5K the next revision should be available at the same price, not in higher price point. Consider the case of Phenom II X4 955 125W and C3 revison version with 95W TDP as example. Both are available at same price point.

Thanks Cilus for taking the trouble on behalf of me. Exactly what I was trying to convey. They may sell a 8160/8170 at higher price point but not the 8150 after debuting it at a particular price point.

That 955 reminds me, 8120 is in a similar position.

Also found this OC test:-

AMD's FX-8150 further overclocked - The Tech Report

Hoping against hope:-

Oddly enough, the benchmarks we selected months ago for our overclocking performance tests seem to be pretty well suited to the Bulldozer architecture. Thus, turning up the clock frequency allows the FX-8150 to put up some really nice numbers, tying or beating a Core i7-2600K overclocked to 4.5GHz in several cases. There are some pain points here, such as the difference in single-threaded Cinebench performance between the FX-8150 at 4.7GHz and the Core i5-2500K at stock (scores of 1.16 vs. 1.48, respectively). Still, had Bulldozer landed at frequencies north of 4.5GHz within conventional power envelopes, the competitive landscape might look rather different. Indeed, if GlobalFoundries can manage to refine its 32-nm fabrication process to allow such speeds in the coming months, who knows?

oh.thanks.then lets wait and see what AMD will do.btw is BD available in the market?does AMD supplying BD ?
^^now looks like power consumption is the only problem.btw thanks for the links.

If anyone still can't enough, here's rumor of B3 stepping:-

AnandTech - AMD Working on Bulldozer B3 Stepping

^^ nice find ... ;-)

No timeframe for the update is known but if the past has any meaning, it won't be anytime soon. For example C3 stepping came about 9 months after the original release of Phenom II X4 with C2 stepping.

we need BullDozer cpus with B3 Stepping more earlier this time ;-)

Actually if my memory serves me right, AMD was reportedly working for B3 stepping as they had no plan to release B1/B2 due to clock speed issues. Looks like they are stuck somewhere. We can only hope this to be Radeon 2900XT equivalent. AMD has a history of striking back when down. Hope they will continue to add to it.

T

Yeah I also recall reading that AMD will Come Up with a B3 at start.

ps: BD is no more in List of Upgrade List till I get something more convincing. Heck if it could OC to 5 GHz on Air I would have bough it

.
Stepping changes if history repeats will help push OC limits higher by a couple hundred MHz.

^^buddy overclocking BD is still not a problem,people are able to overclock 4.4-4.5GHz with stock cooler. if you get a good air cooler then you will be able to go upto 4.8-4.9GHz,may be even up to 5.0GHz.
btw very good news.lets hope B3 stepping rocks.

sukesh1090 said:
^^buddy overclocking BD is still not a problem,people are able to overclock 4.4-4.5GHz with stock cooler. if you get a good air cooler then you will be able to go upto 4.8-4.9GHz,may be even up to 5.0GHz.
btw very good news.lets hope B3 stepping rocks.

Problem is not the overclocking capability, but the scaling and power usage - both of which are not favorable at this moment.

^^yea thats what i was telling him.oc is not a problem in BD its power consumption.as you increase you clock speed of processor the electricity meter also starts to run at 5GHz. :wink:

T

After that 8.4 GHz OC Pics floating around I was hoping for a 5 GHz + on Air.

Electricity is not a concern for me

but Temp is.

May be the 95W 8120 part would be better.

^^yup that would be better.but still if electricity is not the concern then he can go with 8150 only.

Tech_Wiz said:
After that 8.4 GHz OC Pics floating around I was hoping for a 5 GHz + on Air.

Electricity is not a concern for me but Temp is.

So only the clock speeds matter for u & not the performance?

The ironical fact is that it is AMD who first pointed out that clock speed can not be a direct parameter to measure performance while launching the Athlon 64 bit processors. They are the 1st one to point out that it is the Throughput, i.e. amount of work done or number of instructions completed in unit time is directly proportional to the performance.

They have actually shown the world that Athlon 64 3000+, running at 1.8 GHz speed, outperforming the 3.2 GHz Pentium 4 Prescott processors.

And now...rather improving performance by other means like lower cache latency, single core performance, advanced pipelining, they are creating gimmik about clock speed.....What the Hell!

T

MegaMind said:
So only the clock speeds matter for u & not the performance?

Output matters but I personally like High Ghz Numbers on CPU

(And I Dont Like Intel

)

@dashing.sujay: yeah Man. Really upset about BD

remember first gen Phenom was a flop even when the cheapest one was picked as Editors choice by Digit mag. 2nd gen Phenom offered good VFM & performance.

Hope we will have a AMD Piledriver Discussion Thread as early as possible.

This thread has been derailed. Deleted some ~15 posts.

Will open it later.

[Phoronix] AMD FX-8150 Bulldozer On Ubuntu Linux Review

Time to start discussing real things.

^^it is just the same results as we saw in windows.but here the case was 50:50 between 2500k and 8150 and Linux it is 80:20.but still good to see 8150 giving a very good performance in multi threaded and that too consistently.

*techreport.com/r.x/2011_10_24_Ready_set_go/comic-20111024-big.png

:rofl:

^^Epic lol :rofl:

Nice one Skud

Thanks.

^^good one SKUD
it would have been also funny ...if the bulldozer gone in reverse direction...!

I am almost heartbroken to say the truth. I don't want to upgrade to another Intel platform, but looks like I am destined for another one.

^^Do you even need to upgrade?

(for me your config is fine, except procy, but still ok)

Proccy is the bottleneck. Also planning to go CFX. Can't go with this proccy. And changing the CPU means changing the mobo and RAM too.

Why don't you wait for Ivy ?

Lets wait and see. I have time in my hand.

fine, what about this

That's what I am doing. But already pretty scared to go for an Intel platform which will be more than a year old by the time I upgrade. Damn, I have enough time in my hand to stop thinking.

PS- Why scared about going for Intel? Upgrade after reviews of Ivy.

You never no how quickly upgrades are gonna dry up.

Some details on Trinity:-

AnandTech - Details on Trinity - AMD's Next Gen APU

2133 Mhz RAM & 7xxx gfx ! :hyper:

Thnx for the link.

OHHH noooo first AMD-BD got lots and lots of negative reviews.......and then R.A.ONE got lots and lots of negative reviews on the net..........I think World is really coming to and end in 2012!!!!!!!!!!!

And btw HAPPY DIWALI to all.....supporters and demoters of AMD BD!!!!!!

max_snyper said:
OHHH noooo first AMD-BD got lots and lots of negative reviews.......and then R.A.ONE got lots and lots of negative reviews on the net..........I think World is really coming to and end in 2012!!!!!!!!!!!

And btw HAPPY DIWALI to all.....supporters and demoters of AMD BD!!!!!!

I knew it wold be a bad movie. At least after watching MNIK and seeing how SRK made everyone think they like the movie by marketing alone. But I had high hopes from BD. And here I am waiting for the courier guy to bring my 2500K.

^^all the over hyped things went to dustbin recently like BD,Battle field 3,Rage.....the list still goes on.
so don't give much publicity to the product and you will be good to go,if you give publicity and people think it will be epic,and when the product will be released even though it is good it will fail because because people expected it to be epic.

Loosing it all

Multi-Core Scaling Performance Of AMD's Bulldozer

^^thanks for the link buddy.for me it is the same thing which we came across a month before.same performance, good in some test and very bad in some.no moves from AMD,for me it looks like BD is already dead and may be they are working on piledriver.that is correct also because there is not much time left for q1 2012 when pile is scheduled for launch,so if they spend time on working and fixing BD,piledriver will get late.so better ditch BD and fix things in pile as both of them are of same architecture and move on.

But here it lost all :!:

I agree with you on AMD's future targets/approach.

sukesh1090 said:
^^all the over hyped things went to dustbin recently like BD,Battle field 3,Rage.....the list still goes on.
so don't give much publicity to the product and you will be good to go,if you give publicity and people think it will be epic,and when the product will be released even though it is good it will fail because because people expected it to be epic.

has Battlefield 3 became a disappointment :!:

Re: PC Buying Guide 2011- Q4

Bulldozer is also very good.

Re: PC Buying Guide 2011- Q4

How? :shock:

Some good news for AMD finally:-

AnandTech - AMD Q3 2011 Results: $97mil Profit On Strong Llano Sales

Unsurprisingly the breadwinner for the quarter was Llano, which launched just before the start of the quarter. Overall AMD’s mobile business revenue increased 35% over Q2, and at this point AMD is selling Llano as fast as they can produce it. This is why the continuing status of GloFlo’s 32nm process is so important to AMD, as at this point AMD’s mobile growth is limited only by supply constraints. And where are all of those Llanos going? While AMD doesn’t break down shipments of individual CPU families by region, AMD has cited China and India as major growth markets for the quarter, where they saw double digit growth in both markets.

Re: PC Buying Guide 2011- Q4

My i7 920 kicks AMD FX8150. Click Here to know more.

i7 2600k kills AMD FX8150 in the same table comparision. I hope FX8170 is also in the same league.

May be with multitasking it may shine with next generation BD, but not with current FX series. IMO its a big time flop show.

Re: PC Buying Guide 2011- Q4

eh... except in games, the 8150 is pretty much ahead in most benches while being close in others.

@sunny10,
yes its single player campaign is useless.its mp is good but still people are not happy with the gameplay and all.campaign is too small etc....
@skud,
nice find.looks like still things are going right for amd.btw why the gpu profit is so less?
amd should have better profit in the gpu market.isn't it?because their gfx cards are selling a lot and they have less competition from nvidia in present conditions.but still less profit??

here some thing about BD,
Laying the Tracks | Business Blog

Truth in Numbers | Game Blog

AMD Bulldozer might be the right fit for small business - Feature - Techworld.com

AMDâ€™s FX chip and the autobahns of Windows 8 | TG Daily

HARDOCP - Playable Settings - The Bottom Line - AMD Bulldozer / FX-8150 Gameplay Performance Review

Re: PC Buying Guide 2011- Q4

Any review with a Crosshair V Formula mobo can be disregarded.

That mobo needs to be updated with a decent BIOS for BD, because the current one doesnt know how to use the cores.
Cant give you any links to vouch for it because I heard it from an aussie friend who works at a computer store.

Also, microsoft needs to update windows for Bulldozer, since it is two cores in one unit unlike previous architectures where 1 unit was one core.

We also need more applications that can take advantage of 8 cores.

Re: PC Buying Guide 2011- Q4

For me, there are two major problems for BD:- scaling and power consumption. While the former may be tackled in future, how they are going to bring the load power consumption down? Performance is otherwise OK as far as its pricing goes.

Hope AMD will bounce back just like they did from the ashes of Radeon 2900XT. There are similarities galore - delay in release, temp, power, the way they define core/SP differently - lets hope the future would be similar too.

Probably the most interesting read on Bulldozer so far:-

A quick look at Bulldozer thread scheduling - The Tech Report

In every case but one, distributing the threads one per module, and thus avoiding sharing, produces roughly 10-20% higher performance than packing the threads together on two modules. (And that one case, the FDom function in picCOLOR, shows little difference between the three affinity options.) At least for this handful of workloads, the benefits of avoiding resource sharing between two cores on a module are pretty tangible. Even though the packed config enables a higher Turbo Core frequency of 4.2GHz, the shared config is faster.

Our test apps, obviously, are not your typical desktop applications, and they may not be a perfect indicator of what to expect elsewhere. However, since many games and other apps are lightly threaded, with three or four threads handling the bulk of the work, we wouldn't be surprised if one-per-module thread affinities were generally a win on Bulldozer-based processors.

Naturally, some folks who have been disappointed with Bulldozer performance to date may find solace in this outcome. With proper scheduling, as may come in Windows 8, future AMD processors derived from this architecture may be able to perform more competitively. Unfortunately, Windows 8 probably won't ship during the model run of the current FX processors.

Re: PC Buying Guide 2011- Q4

Well I blame windows. This new arch is a total breakaway from previous CPU archs.

Skud said:
Some good news for AMD finally:-

AnandTech - AMD Q3 2011 Results: $97mil Profit On Strong Llano Sales

thanks for the links.they area set of good news for amd and us.

^Its very old.

Re: PC Buying Guide 2011- Q4

Extreme Gamer said:
Well I blame windows. This new arch is a total breakaway from previous CPU archs.

Well, you can't put total blame on Windows. AMD should have thought of every situation before they actually 'release' their BD. They failed to do it properly, and as a result, BD failed.
At least that's how I think of the current situation.

Re: PC Buying Guide 2011- Q4

Or may be Microsoft fails to provide BD support in Win7 despite it taking such a long time to release. XP had got a patch once dual core CPUs came out, don't think it will be very tough to provide BD support in Win7. And it looks like AMD's claim of 10-15% performance increase is somewhat true.

Still I would have loved to see BD giving good performance rather than speculation of good performance.

dashing.sujay said:
^Its very old.

^^Nope.. A week old

R

Re: PC Buying Guide 2011- Q4

Skud said:
Or may be Microsoft fails to provide BD support in Win7 despite it taking such a long time to release. XP had got a patch once dual core CPUs came out, don't think it will be very tough to provide BD support in Win7. And it looks like AMD's claim of 10-15% performance increase is somewhat true.

Still I would have loved to see BD giving good performance rather than speculation of good performance.

Windows 8 should solve those issues. Or Windows 7 SP2?

MegaMind said:
^^Nope.. A week old

I meant that only

. Since I'm subscribed to it (i guess you are too), i got it the released day, but after going through it, I didn't found worthy to post it. (correct me if i'm wrong)

Something to cheer about?

Maximum PC | AMD Says Trinity Coming 'Very Early Next Year'

AMD OC Record Broken, Still Powered by AMD FX-8150 | techPowerUp
AMD FX sets new overclocking record :lol:

Vcore: 2V!!!!!!!! :shock:

sunny10 said:
AMD OC Record Broken, Still Powered by AMD FX-8150 | techPowerUp
AMD FX sets new overclocking record

Practically if anyone tries this trick I can assure that he will fry up his CPU. :twisted:

sunny10 said:
AMD OC Record Broken, Still Powered by AMD FX-8150 | techPowerUp
AMD FX sets new overclocking record

thanks for the link and Crosshair V Formula is one hell of a OCers mobo for sure ;-)

BTW, how much power it will consume at 8461.51 Mhz ( 2 cores ) with 2v vcore ??

HARDOCP - Introduction - AMD FX-8150 Multi-GPU Gameplay Performance Review

AnandTech - Bulldozer Does It Again: Overclocked to 8.58GHz

A review on BD's water cooler:-

AMD Bulldozer Water Cooler Review - Introduction & Specifications

^^^great news guys !!!! BULLDOZER now in india
TechShop.in
*www.smcinternational.in/index.php?option=com_virtuemart&page=shop.browse&category_id=28&Itemid=75

^^Its already available at smcinternational.

^^^yeah i knw!!! i gave the link above!!!! i think prices will be much lower in local retail shops.... i guess!!1

You added the link later mate

And prices at local shops are mostly on the lower side only.

now the main question is that is it worth buying with ivy bridge around the corner??? price of fx 8150 seems to be on the higher side, but with AMD i know it will fall!!! but intel cpus price dont tend to fall that easily!!

This is a debatable question, though Intel is on brighter side.

Read this whole thread for your anwser!

Re: Hardware price list/spec sheet

@Cilus: I didnt mean HT per se. I meant that it wont arrange the threads properly.

Re: Hardware price list/spec sheet

Extreme Gamer said:
@Cilus: I didnt mean HT per se. I meant that it wont arrange the threads properly.

If you didn't mean then why did you write that Bulldozer cores are treated as HT cores? You should have said what you are saying now.
If a processor is not HT enabled they cannot be treated as HT core and sabdly Bulldozer is not at all any Ht enabled Processor.

If you want your name in the guinness book then buy a bulldozer. :grin:

AMD Bulldozer Speed Record Broken Again at 8.58GHz

Re: Hardware price list/spec sheet

because in windows 7 the result is similar. If you have a Ci7 HT enabled, it will not put two threads per core, but use HT as the last resort for active threads. Same case here- it will send the threads through different modules instead of keeping the threads of one app together.

Windows 7 doesnt recognize 1 module as two fully operational cores.

The story changes in windows 8.

Re: Hardware price list/spec sheet

Extreme Gamer said:
because in windows 7 the result is similar. If you have a Ci7 HT enabled, it will not put two threads per core, but use HT as the last resort for active threads. Same case here- it will send the threads through different modules instead of keeping the threads of one app together.

Windows 7 doesnt recognize 1 module as two fully operational cores.

The story changes in windows 8.

Can you explain the bold part? The way i see it, windows 7 sees it as full 8 operational cores. That's where the flaw lies.

Re: Hardware price list/spec sheet

Extreme Gamer said:
Windows 7 sees 8 logical cores, not physical cores.
Since it does not have the info on how to handle a BD module, it tries to operate it like a hyperthreaded core, by placing only 1 thread per module and if the situation of more threads arises, instead of putting two threads per module it will put one and then as all the modules have 1 thread each, it will assign another thread to one module.
So if one app needs more than one thread, and all the modules already have 1 thread each, the threads will be spread across different modules, which results in poor resource management.

The bold part is completely haphazard. Why the heck will an app need more threads? Do you know what a thread is and what do they contain??

Re: Hardware price list/spec sheet

Extreme Gamer said:
Windows 7 sees 8 logical cores, not physical cores.
Since it does not have the info on how to handle a BD module, it tries to operate it like a hyperthreaded core, by placing only 1 thread per module and if the situation of more threads arises, instead of putting two threads per module it will put one and then as all the modules have 1 thread each, it will assign another thread to one module.
So if one app needs more than one thread, and all the modules already have 1 thread each, the threads will be spread across different modules, which results in poor resource management.

What the Hell.... Windows 7 sees all the Bulldozer cores as separate Physical cores, not 8 logical cores and AMD is marketing Bulldozer as 8 core processor, not 8 logical cores. Windows 7 is not even aware that there is something like module in Bulldozer CPU.
Buddy use a little common sense, AMD cannot market Bulldozer as 8 core processor if it is treated as 8 logical cores. You need to have 8 physical cores to sale a product highlighted as 8 core CPU.

What Vickybat is saying is perfectly right, the problem lies of assigning available threads to any of the 8 cores available, irrespective of which module they belongs to. Buddy, read a little before posting wrong information.
Microsoft is also confirmed that issue and it is completely opposite what you've said(Win 7 cannot recognise 1 module as two separate functional unit). In fact Win 7 sees two separate cphysical ores instead of a module.
Now the thing is Bulldozer's two cores inside a module are not exactly independent as they share the FPU and Fetch/Decode hardwar (known as Frontend of the CPU) and only integer units are independent. So placing two interrelated threads inside a module will increase better resource sharing and high degree of ILP which Win 7 simply can't do as it is not aware of Module and places those two interrelated threads to any two of the available 8 cores. It also restricts Turbo boost to fire in its full potential as if a thread needs multiple CPU times to be executed completely, Win 7 assigns it to any cores rather than the cores inside the module. So multiple modules are getting used for only 1 thread, resulting all the modules being used ineffectively and restricting cutting power from the other Modules and turbo boosting only one module to the highest level for faster processing.

If a module can be treated as two logical cores belongs to one Physical Module, then the assignment will be far better. So what you are stating as problem, Windows 8 is gonna have the same logic to resolve the issue.

A quote from Anandtech:

AMD also shared with us that Windows 7 isn't really all that optimized for Bulldozer. Given AMD's unique multi-core module architecture, the OS scheduler needs to know when to place threads on a single module (with shared caches) vs. on separate modules with dedicated caches

Read HERE and HERE

Re: Hardware price list/spec sheet

^^ even if the updates are provided to win 7 for recognizing 8 separate physical cores as a 4-module based architecture that could also do the trick...for thread handling....!
as a quad core cpu...!
i still think if processes are handled by the win 7,as if on the quad core cpu..performance could increase.

Re: Hardware price list/spec sheet

@Vickybat: A thread is a sequence if instructions in a program/sub-system that may/may not run in parallel to another thread.

Ever heard of multithreading?

Let me clarify:

You have three applications running. Each is running in a separate module. Now you launch a program that can multi-thread (i.e. run more than 1 thread in parallel), and can use two cores.
Obviously, its two threads will be spread across two modules, because Windows 7 wont recognize 2 physical cores in the processor, and treat one module like a hyperthreaded core.

However, if windows 7 knew how to handle a BD module (which it should in the coming months because microsoft will patch Windows 7), both threads of the application/program would've been kept in the same module and more efficient use of memory would take place.

@Cilus:

Windows 7 sees all the Bulldozer cores as separate Physical cores

then according to you Windows 7 also sees a core i7 having 8/12 physical cores.

Windows 7 is not even aware that there is something like module in Bulldozer CPU.

Exactly, it does not have the information to handle a BD module.

Thread assignment in windows 7 for BD takes place in the same manner as it would in a Core i7, causing inefficient cache utilization in a module.

Re: Hardware price list/spec sheet

Extreme Gamer said:
@Vickybat: A thread is a sequence if instructions in a program/sub-system that may/may not run in parallel to another thread.

Ever heard of multithreading?

Oh no i'm hearing these terms first time from you. :lol:

Sorry but that bold comment really made me laugh.

I suggest you to read the basics first before coming here and posting irrelevant info. Do you know the difference between SMT and Super threading? Its a very common misconception and i definitely guess you too are a victim.

Every program is termed as process. Since executing a single large process takes a hell lot of cpu time, its divided into multiple threads having different instances or states.

Threads contain instructions which are stateless. But instructions can be dependent and in the real world, this has to happen. Cilus's explanation is perfectly correct ( i really owe him for clearing a lot of my misconceptions).

Let me explain a bit:

You see bulldozer has a total of 8 physical integer execution units but four floating point units. Usually, the integer units are regarded the main portion of a cpu core because a cpu stresses more on integer calculations than fixed point operations.

As cilus pointed, Each bulldozer module has a shared front-end consisting of branch prediction , fetch ,decode and despatcher units ( roughly). These are responsible for assigning threads and in turn instructions to the execution units whether integer or float. Lets stress on integer operations from now on and ignore float operations.

Suppose there are two threads T1 and T2.

T1 thread as 4 instructions which are A,B,C & D.

T2 thread as 3 instructions which are E, F & G.

Lets say these threads belong to the same process and thus have dependent instructions in them.

Say, A& G are dependent.

Now consider a 4 module bulldozer cpu having MOD1 , MOD2, MOD3 ,MOD4.

Now OS along with the cpu's own prediction logic assigns thread T1 to MOD1 and T2 to MOD 3.

Lets say, the 1st integer core starts executing the instructions one by one from A TO D. When it comes to D , it cant be executed because its dependent on instruction G of T2 which has been assigned to MOD 3 and not yet been processed. It has to wait until MOD3 finishes executing E,F& G and then send information G TO MOD1 so that instruction D can be processed.

But if the OS is aware of modular architecture its prediction logic will allow T1 & T2 to be assigned to MOD1. T1 will be handled by the integer core 1 and T2 by integer core 2 of MOD1. Thus all dependent instructions can exchange info in the singe module and thus result in faster execution. Here instruction level parallelism is employed along with TLP as they are dependent on each other.

Turbo boost will also work because all other modules are off and a single module i.e MOD1 can achieve highest boost frequency whereas in the first case it wouldn't achieve that much boost because MOD3 was active and two modules will be cut instead of three in the optimal case.

Windows 8 will address this.

Extreme Gamer said:
@Cilus:

then according to you Windows 7 also sees a core i7 having 8/12 physical cores.

This part is absolutely absurd. I have no idea why in the blue hell you're saying this.

topgear said:
You're welcome

Bought a Corsair GS600 @ 4.1k From MD Computers on first day of this month

Congrats man. :smile:

Re: Hardware price list/spec sheet

The multithreading question was a joke and i'm glad you laughed

I sure as hell hope that you knew it was a joke.

Superthreading is pretty similar to what hapens when a hyperthreaded core is assigned two threads, unrelated or otherwise.
Both threads wont undergo simultaneous execution. Exactly opposite in Simultaneous multithreading.

I know BD has only 4 FP units and 8 integer and logic units, but what I was trying to say is that the end result of thread assignment is similar to hyperthreading.

Computers have been my ******* since 1999 lol. Studying hard to get into a good college for pure CS with video game development.

Re: Hardware price list/spec sheet

then according to you Windows 7 also sees a core i7 having 8/12 physical cores.

There is book called Advanced Computer Architecture by Hennessy patterson. I suggest you start reading it.

in a HT processor, a single core can handle instructions from two different threads simultaneously. Ever heard of a term Pipe-lining? If yes then let me tell you it the single core uses Pipelining to execute multiple instructions in parallel by overlapping their execution time. They don't have separate execution unit to execute multiple instructions simultaneously. Any HT enabled processors like i7 2600 or i7 920 uses the same methodology.

In Bulldozer module it does have two separate Integer Execution unit and they can process instructions in parallel irrespective what the other one is doing. So it is treated as two separate cores as two separate execution units are available. Here the advantage is two separate execution cores are having single Fetch/Dispatch unit and they can start processing even instructions from a single thread in parallel, a feature not possible in HT enabled processor due to the presence of a single execution unit. So if Windows 8 identify a module as an unit and assign a single thread to it properly, its integer instructions can be shared by the two Integer cores and Floating point instructions can be put in pipeline for the FPU to enhance ILP.

Currently all the OS, starting from Windows XP or 98 can identify a HT enabled CPu and differentiate between logical cores and physical cores. So it can manage the thread assignment accordingly. So a 4 core HT enabled is treated as 8 logocal cores and 4 physical cores. In Bulldozer, there is nothing called HT enabled unit and module can be considered roughly equivalent to it. But again I am saying it: Windows 7 does not know the existence of Module, it sees it as 8 separate physical cores and assign works in random way to the cores. Just check the links I've posted in my previous post.

Now even after explaining everything I have an intuition that you're gonna again post some baseless comment without even having a look what I've posted or the links I've shared. So I suggest you share your opinion with Arun Kishan.
P.S. Read the spoiler before asking him.

Arun Kishan is the person who who owns process management and threading subsystem in Windows and actually has pointed out these issues with Windows 7 Thread management with Bulldozer.

Re: Hardware price list/spec sheet

@ extremegamer

I suggest what cilus said and start reading a bit on these to gain some valuable knowledge. Posting irrelevant and misleading info is termed as spamming and nothing more.
Its bad for all people getting involved with the material and in the reference of this forum, materials are nothing but posts.

You need to go deep into understanding and not just learn some terms and their definitions. Also go through the links which other forum members provide before starting baseless arguments. Its bad for the entire community (tdf universe).

Re: Hardware price list/spec sheet

OT but now on topic: Best updated book for computer hardware: Computer Architecture, Fifth Edition: A Quantitative Approach Link

Anyone who is interested can buy that.

Re: Hardware price list/spec sheet

vickybat said:
@ extremegamer

I suggest what cilus said and start reading a bit on these to gain some valuable knowledge. Posting irrelevant and misleading info is termed as spamming and nothing more.
Its bad for all people getting involved with the material and in the reference of this forum, materials are nothing but posts.

You need to go deep into understanding and not just learn some terms and their definitions. Also go through the links which other forum members provide before starting baseless arguments. Its bad for the entire community (tdf universe).

I totally abhor definitions, and always try to understand the fundamental concepts. Without knowing about my daily life, I do not think that you should assume that I learn terms/ definitions.

Obviously bulldozer arch is not HT and the steps involved in thread assignment vary. But unlike the Core i series arch where the L3 cache is shared by all cores, in BD each module has its own Cache. Windows 7 will not see a module yet, but it does see that two cores have shared cache. So, while assigning threads to idle cores, it spreads the threads across different modules [obviously] unwittingly, where the END RESULT, I repeat, END RESULT of thread assignment is the same as an HT core i series processor i.e. threads are assigned to alternate cores and not adjacent ones.

This is what I have been trying to say all along.

When I said that windows recognizes 8 logical cores, I meant that it was Windows's fault and not AMD's. However, I take that part back because after further reading up on the arch of BD, I found my mistake there.

Re: Hardware price list/spec sheet

But unlike the Core i series arch where the L3 cache is shared by all cores, in BD each module has its own Cache.

Bulldozer does habe shared L3 cache of 8 MB which is shared by all the modules or 8 cores, just like the L3 cache of Sandybridge. I think you're trying to point out the 2 MB L2 cache of a module which is shared by both the cores (integer) of that module.

But thread assignment is not done by checking the cache type in use, not even in the HT processors...there is no such thing that if multiple core shares a single Cache, they will be treated as HT cores. Cache management logic is present inside the CPU die and it cannot be directly controlled by OS. Every current gen processor has dedicated cache as well as Shared cache and they are internally handled by hardware logic prsent inside the CPU, not by OS. Cache management inside CPU is a Blackbox view to the OS.

Buddy, why don't you check the links we've provided? Check what Microsoft has said about the thread handling of Windows 7 in Bulldozer module. Here all the cores are treated as 8 separate cores, not any interrelated cores and the thread assignment is random.

If you wanna stick to your understanding then provide us some links where experts have analysed and found your's explanation.

Re: Hardware price list/spec sheet

Extreme Gamer said:
I totally abhor definitions, and always try to understand the fundamental concepts. Without knowing about my daily life, I do not think that you should assume that I learn terms/ definitions.

It isn't me saying so but your posts seem to speak for themselves.

Extreme Gamer said:
Obviously bulldozer arch is not HT and the steps involved in thread assignment vary. But unlike the Core i series arch where the L3 cache is shared by all cores, in BD each module has its own Cache. Windows 7 will not see a module yet, but it does see that two cores have shared cache. So, while assigning threads to idle cores, it spreads the threads across different modules [obviously] unwittingly, where the END RESULT, I repeat, END RESULT of thread assignment is the same as an HT core i series processor i.e. threads are assigned to alternate cores and not adjacent ones.

This is what I have been trying to say all along.

If possible, take a long break and analyze your own comment. Try and relate each and every sentence that you wrote. Are they falling in place? Not so to me.

From your own comment-" But unlike the Core i series arch where the L3 cache is shared by all cores, in BD each module has its own Cache."
what the heck does this line mean?

We all know that both sandybridge and bulldozer have dedicated L1 ( data and instruction cache), L2 cache per core ( module for bulldozer) and a large shared L3 cache.

So how the heck its related to hyperthreading or multithreading at all??

Like cilus said cache management is not decided by os but by internal hardware logic which is not known. You have completely misunderstood the very basic concepts and that's why you post gibberish every now and then.

The most important job for cache is to significantly reduce cpu read & write times by accessing cache memory internal to it rather than main memory to reduce latency as cpu cycles will be lost doing so. Thread assignment to execution units has got nothing to do with any type of cache at all. Cache memory is simply mapped to main memory either directly or in a single or bidirectional associative manner. The most used memory indexes are written over to cache index so that cpu can quickly fetch data , process and write back.

Read properly and come back again to post in a relevant manner.

Re: Hardware price list/spec sheet

The L3 cache is shared 2MB/module...

*upload.wikimedia.org/wikipedia/commons/e/ec/AMD_Bulldozer_block_diagram_%288_core_CPU%29.PNG

From your own comment-" But unlike the Core i series arch where the L3 cache is shared by all cores, in BD each module has its own Cache."
what the heck does this line mean?

I was referring to L3 cache only...

But thread assignment is not done by checking the cache type in use, not even in the HT processors...there is no such thing that if multiple core shares a single Cache, they will be treated as HT cores. Cache management logic is present inside the CPU die and it cannot be directly controlled by OS. Every current gen processor has dedicated cache as well as Shared cache and they are internally handled by hardware logic prsent inside the CPU, not by OS. Cache management inside CPU is a Blackbox view to the OS.

Cilus ok, then maybe I understood it wrong. But I did not say windows manages cache.

My whole concept will be clear if you answer this:

can windows see the cache (not saying it can manage it, never did...)?

So how the heck its related to hyperthreading or multithreading at all??

They are NOT treated as HT cores!! The END RESULT of THREAD ASSIGNMENT is the SAME!!

Re: Hardware price list/spec sheet

^^ Windows will show it as 8mb shared and not 2mb per module. They are shared by an internal interconnect and lie outside of the module. You can see it clearly given in the block diagram.

Your concepts will be clear if you read an article cilus provided on threading and reading the bulldozer article carefully ( i provided one in the bulldozer thread). Read them properly and have your doubts cleared.

AMD 1090FX and 1070 Chipsets Disclosed, No PCI Express 3.0 | techPowerUp

Re: Hardware price list/spec sheet

^^@vickybat...@extremegamer....
first of all caches are not handled by the OS but by the logic design of the cpu itself...!
PERIOD.
secondly if u are interested in processor design so much then buy a book "microprocessors and interfacing" by Douglas Hall....!
all your doubts & theories will be corrected.

And please discuss this somewhere else this is "Hardware price list/spec sheet"
not processor design section!!!!!!!!
what admins are doing i wonder......

Re: Hardware price list/spec sheet

Last off topic post: max, i never said windows handles cache.

Re: Hardware price list/spec sheet

@ max_snyper

I think you are right buddy. Got a bit carried away but couldn't resist incorrect posts and misleading info.

I will pm some moderators to move these posts to the bulldozer discussion thread.
Thanks for pointing out mate. :smile:

Btw in post # 4844, i clearly stated what you said just now about caches not handled by os. Cilus also said the same thing.

Re: Hardware price list/spec sheet

Max_Snyper, You're right. Even I was little carried away as you know CPU architecture is my field of interest. This is my last post regarding it. Tomorrow, I'll be moving all the related posts to Bulldozer Discussion thread. BTW, please have a look at my explanation and share your opinion if you wish.

Extreme Gamer; Yes, OS can see the CPU cache, but inside the Cahce how data is placed, in what sequence or if cache is full what line items are needed to be deleted and write back to memory is handled by CPU hardware logic, not by OS. Cache, present inside CPU die is entirely managed by CPU hardware logic which implements different hardware logic for efficiency like LRU algorithm for cache cleaning, Cache coherency problem resoving hardware etc. To OS, Cache operation is a Blackbox view.
I hope you know what blackbox view is, it means in a module you send the requested inputs and you will get the output without interfering or knowing the actual mechanism how the output is produced. In my previous post I've mentioned it, I never mention that OS is not aware of Cache.

And one thing...Thread assignment is never done on the base of Cache handling algorithm.

For example the L2 cache of a core in a HT enabled Nehalem CPU like i7 920/960, is although shared by two hyperthreaded logical cores, it is partitioned statically to keep any one thread from monopolizing all the resources. It is same like Bulldozer where the L3 cache is staically partitioned, 2 MB/per module.

But in Sandybridge, two logical cores of a physical core can access any position of the shared L2 cache as the division is dynamic, decided by the hardware Logic at run time. It is same as the 2 MB L2 cache per module in Bulldozer, shared dynamically by both the cores.

So you see, the shared cache mechanism is completely different in Nehemiah and Sandy-bridge HT processors, but does it poss any challenge for the OS to assign two tightly coupled threads into the two logical cores of a physical one? The answer is no. Because the entire thing is handled by the Cache management logic of the CPU.

Actually one Bulldozer module lies within a True Dual Core module and a SMT enabled mdoule. It does have some independent unit, mainly the Integer execution unit and some shared unit, like the Front-end (Fetch/Decode, OOO) and the FPU.
What you are saying, treating them as one module rather than two separate cores, will come with Windows 8.
Consider the example and please make sure you read it:-
Suppose we have two Thread T and T1 which are tightly coupled. So they share a lot of common resources and interdependent instructions. Now consider a Dual Module Bulldozer, having module M1 with C1 and C2, M2 with C3 and C4.

To windows 7, there is no existence of M1 and M2, it only sees C1, C2 C3 and C4 as 4 independent cores and assign T to C1 and T1 to C4.
Now whenever C1 faces an instruction from T which is dependent upon some instruction(s) of T2, it has to stall it, push it to the waiting queue C4 completes the instructions in T1 and write it back to L3 cache, if it is available. Then C1 has to read that value from L3 cache and process with the dependent instruction.
So it will waste lots of valuable CPU cycles because:

1. L3 cache is far slower than faster L2 cache which is nearer to CPU.

2. C4 does not have any knowledge that execution of the specific instruction from the instruction queue of T1 cache in the 1st place will fasten the execution of T thread in C1, even if it can do it.

3. C1 and C4, as they belongs to the different modules, have different Frontend (Fetch/Decode/Out of Order Execution). As they don't have any knowledge of the state of the other core, their out of Order logic cannot reschedule the instructions accordingly to fasten the execution of both the threads.

4. Although T and T1 are interrelated, they are placed in two different module s. But since they are interrelated, the single threaded performance of each of the module is poor due to loss of valuable CPU cycles. But the worst thing is:-As the threads are using all the CPU resources or both the module, Turbo boost will be disabled to kick up the single threaded performance.

Now Suppose Windows 8 can identify a Bulldozer Module and it treats C1 and C2 as part of M1 and C3 and C4 as part of M2. So C1 and C2 will be treated as not as independent cores, but something between a SMT core and Dual core.

Now OS has full access to each of the threads and by judging their nature, shared resources, operation memory locations or CONTEXT of each of threads, it can easily understand the interrelation between T and T1. So it will assign both of them to module M1 or to C1 and C2. Now look at the improvements:-

1. Common Fetch and Decode: Since both the Threads share resources , i.e. same memory locations, same operands, they need to be fetched only once. As you are minimizing slower memory access, an expensive process for CPU cycles, performance will be improved due to recovery of the wasted CPU cycles.

2. Out of Order Rescheduling of Both the Threads' instruction: As you know it reorders the instructions to increase the number of executions simultaneously. Now it has two thread full of instructions and a lot of them are dependent, out of order execution unit can reschedule them more effectively to increase the parallel execution. In HT enabled cores, OOO does the same thing but here as two discrete Integer execution units are available, the process will be far superior.
In Computer science it is observed that normally OOO logic can fetch 2 parallel instructions from a single Thread in one cycle and normally one core can run 4 instructions in parallel using Pipe-lining.

So here at least for integer, we have maximum of four instructions from T and T1 and two cores. So you can understand the speed of execution.

3. Data Sharing using L2 cache: As C1 and C2 shares dynamically partitioned same L2 cache, data sharing among them using it will be far faster.

4. Turbo Boost: As you can see, here module M2 is not in use, Turbo boost can make it sleep and charge up the Frequency of the M1 to increase processing speed.

Hope you understand now.

No signs of new socket.

^^brother now we don't need new socket.let them work on PD give what we are expecting.there are hell lot of things which needs to be fixed.and the one thing they need work on in the chipset department is their memory controller.which sucks like nothing.

AMD Bulldozer 8150 Optimised Applications vs Intel 2600K (Intel Loses) - Intel Videos : Firstpost Topic

i will upgrade my PC this december.
i have phenom II x4 955 in mind.
what will be the price of FX 6100 ??

is there any chance of getting any bulldozer proccy in 7-8k budget??

Well the FX6100 is priced at 10k
Check smcinternational.com
Is the FX 4100 worth buying
AMD FX-4100 Quad Core 3.6GHz Bulldozer Processor Review - The AMD FX-4100 CPU - Legit Reviews
At stock cooler it reaches a stable OC of 4.6Ghz and has a 27% improvement on scores in Cinebench 11.5
And in many tests it defeats the i3 2120 but gets defeated in almost all by the a8 3850
So is it worth buying for 6k

For me, if you really want a BD, whether you are upgrading or buying a new system, get any one of the octa core, both FX 6100 & FX 4100 are not good IMO.

But skud is the FX 4100 good at 6.5k?
It still beats i3 2120 in many tests

And gets beaten by a A8 3850 and takes a beating from Phenom II. And even after OCing, its Cinebench score is still 16% low than Phenom II X4 980 running at stock (almost 1 GHz slower). Now take your pick.

But Phenom II X4 980 is also very costly and so does A8 3850. There prices are almost 8K.

But you are getting much better performance with Phenom II and arguably the best IGP with A8. And in SMC, the A8 is priced just 850 bucks more than FX4100. That's money well spent IMO.

And regarding Phenom II, I think even the lower clocked and lower priced versions will be competitive with FX4100, if not beating it.

Of course, one negative point of A8 is that not many upgrades are forthcoming, whereas BD and Phenom II still has Piledriver to come.

@happy17292,
if you are upgrading the processor for the sake of gaming and if you are not upgrading your gfx card then please wait for PD or ivy.your pentium can easily handle that gfx card without any problem.even if you add phenom II or BD your graphics card will bottleneck the processor.

Are Llano notebooks available in India?

Try Acer.

Guys, posted some tidbits here on Trinity, have a look:-

*www.thinkdigit.com/forum/cpu-motherboards/148272-amd-trinity-apu-discussion.html

@piyush Only this is available and I like the performance of this lappy.Quite good for gaming.
Asus X Series X53TA-SX096D Laptop: Flipkart.com: Compare, Review Asus Notebook
@skud Want to know p2 955BE score in cinebench 11.5
But in the 3 games tested in two both i3 and a8 get defeated but in 1 game FX defeats the a8 in lower resolution.I think that FX should be priced lower than smc's price in local market.

Point is there's not enough performance for the money that I am spending. Nor as much features as the APU. And living in the shadow of future performance benefits of Windows 8 simply doesn't cut.

And it doesn't look like a good upgrade option of existing socket AM3+ users.

Newegg.com - AMD FX-4100 Zambezi 3.6GHz (3.8GHz Turbo) Socket AM3+ 95W Quad-Core Desktop Processor FD4100WMGUSBX
dude read the reviews.They seem quite good.
For the best part a man tells that he has unlocked all 8 cores

Are you eying for one?

That unlocking part is not a sureshot thing buddy, even if its true. I think its not wise to recommend something based on their hidden capabilities.

no dude not eyeing one but need to make an upgrade for his mobo+cpu for 12k.
he wants to change his i3 540+dh55tc

sunny10 said:
@piyush Only this is available and I like the performance of this lappy.Quite good for gaming.
Asus X Series X53TA-SX096D Laptop: Flipkart.com: Compare, Review Asus Notebook

the only downside is the clock speed ...only 1.4 ghz
though it has pretty good gfx support
thanks for the link though

Piyush said:
the only downside is the clock speed ...only 1.4 ghz
though it has pretty good gfx support
thanks for the link though

the proccy gets quite easily OC to 2-2.4 Ghz but still does not heat too much.If you are eyeing one you can get it for 28k locally

sunny10 said:
the proccy gets quite easily OC to 2-2.4 Ghz but still does not heat too much.If you are eyeing one you can get it for 28k locally

by manual OCing?

an article about bulldozer.
Can AMD survive Bulldozer's disappointing debut?

Very interesting read. Hope AMD can make a turnaround, with PD itself.

^^AMD may have already started fixing things for BD.

Opterons out now:-

AMD 16-core Opteron Processors Now Available < AMD, Processor, Servers, Office and Enterprise < PC World India News < PC World.in

Come on AMD do something. I am waiting for you.

I don't think its an 8 core... CMT's like Intel's SMT > only difference.. instead of bottle necking the resources of a core... you have 2 separate integer execution units.. thats about ALLLL(except for the cache difference)!!!!!!

It can decode a max of 16 instructions vs 12 of PII and i7 2600k can also do 16 instructions at once - Nothing 8core like here...

ALU/AGU Count = 4/4 per module (2x 2/2 per core) in BD Core. 3/3 per core in Phenom II Line. 3/2 in Sandybridge.

FPU = 2x128bit/1x256 in BD. 2x128bit in PII. While SB is capable of 2x256bit AVX instructions.

FX-8150 seems like an improvement to PII X4 at the very maximum when the hardware it carries in it falls short in most cases and equals in a few to that in an i7 quad core...

Some more Opteron news:-

TYAN Unveails 19 platforms supporting AMD OPTERON? 6200 AND4200 at SC11

M

Guys as of now three supercomputers are being designed using bulldozer opteron processors..

awesome... new one is by university of michigan or princeton or some one which folds a lot

would you guys recommend i go for fx8120 with a m5a97 pro? any increase compared to a 925/955

Price cut on AMD CPUs including FX6100, which is now on par with PII X4 970. At today's exchange rate its showing Rs 7855/-. Will Indian distis/retailers do something?

Source: AMD tweaks APU prices; releases Athlon II 651 CPU

R.I.P for bulldozer b2

Guys, here is the review of Bulldozer based Opteron Processor:
AnandTech - Bulldozer for Servers: Testing AMD's "Interlagos" Opteron 6200 Series

Here, Bulldozer is really performing well compared to the price point. It is performing very close to Xeon 5650 and 5670 which are resonably pricer, especially 5670, almost twice as costly as Opteron 6276. Check it out.

^^xeon 5670 is based on older nehalem architecture right?

Much better than the Desktop parts. Nothing ground breaking, but superb value nonetheless.

Its a good news that atleast in server processor world the bulldozer gave what it was expected to be.
@skud,
hey look at the last comment from the anadtech,opteron is now showing good performance and there is still some more juice in that processor but needs to be utilized in proper way which anandtech have promised to show.so we will wait and watch.

A 4CPU AMD will easily crush a 2CPU Intel.

sukesh1090 said:
Its a good news that atleast in server processor world the bulldozer gave what it was expected to be.
@skud,
hey look at the last comment from the anadtech,opteron is now showing good performance and there is still some more juice in that processor but needs to be utilized in proper way which anandtech have promised to show.so we will wait and watch.

My point was it is not going to make the top-end CPU of the competitor redundant like they did with Athlon64 (desktop). But good to see, there's quite a bit unearthed potential in BD. Hopefully, Piledriver is going to correct a lot of things.

hope things will change with PD.

Found this:
Blog - Bulldozer Memory Overclocking Preview

Extreme Gamer said:
A 4CPU AMD will easily crush a 2CPU Intel.

which cpu

may be eh is talking about opteron.

4CPU interagos vs 2CPU SB-E.

Wish fx 4100 better then 965 be

Extreme Gamer said:
4CPU interagos vs 2CPU SB-E.

why are you comparing those two? :?:

ranjitsd said:
Wish fx 4100 better then 965 be

nope it is not.right now it is even worse than athlon II X 4 :shock:

sukesh1090 said:
why are you comparing those two?

Instead of buying a dual CPU 8-core SB-EP setup worth $4k (of which the stillborn kids are SB-E), an IT department person will buy 4 Interlagos 16-core chips worth $2.5k.

16 cores vs. 64 cores where 64 cores are cheaper. See what I mean?

bulldozer will take time to mature guys.Dont expect a drastic change from it its just bulldozer after all.

revolt, wait for windows 8.

Or a Windows 7 patch

Wait for PD

win 8 is too late and don't expect any win 7 patch so only hope is PD or BD revision B3,if they went bad then thats it, no one is going to wait.AMD should bury themselves after bulldozer >pile driver >excavator..... burier and at last the Intel architecture will be condolence.

sukesh1090 said:
win 8 is too late and don't expect any win 7 patch so only hope is PD or BD revision B3,if they went bad then thats it, no one is going to wait.AMD should bury themselves after bulldozer >pile driver >excavator..... burier and at last the Intel architecture will be condolence.

Even after stating to reviewers that there will be one early next year?

sukesh1090 said:
win 8 is too late and don't expect any win 7 patch so only hope is PD or BD revision B3,if they went bad then thats it, no one is going to wait.AMD should bury themselves after bulldozer >pile driver >excavator..... burier and at last the Intel architecture will be condolence.

if PD Fails intel i3 will be 10k and PD 8 Core will be 5k

@extreme gamer,
what will come early next year?win 8?I don't think so because now only they have released developer preview.so next will be beta after a long time because from the developer preview only you can find that it is still incomplete.so after beta it will take some more 3-4 months for final.so can you expect it to get released early next year?
win 7 patch,i don't know much about it.if it is coming then it is a good news but still to get full out of you need hell lot of optimization for almost all softwares,which AMD can't expect in a market where people and developers are completely biased towards Intel.so AMD only should do some optimizations in their hardware and release it to the market.
@ranjitsd,
if PD fails then even don't expect that AMD will retail it.today you will hardly will be able to get your hands on a BD processor.

To late for them to improve BD. I have already upgraded and wont be buying a new CPU+Motherboard for another 3-4 years. Hope AMD is still around till then.

sukesh1090 said:
@extreme gamer,
what will come early next year?win 8?I don't think so because now only they have released developer preview.so next will be beta after a long time because from the developer preview only you can find that it is still incomplete.so after beta it will take some more 3-4 months for final.so can you expect it to get released early next year?
win 7 patch,i don't know much about it.if it is coming then it is a good news but still to get full out of you need hell lot of optimization for almost all softwares,which AMD can't expect in a market where people and developers are completely biased towards Intel.so AMD only should do some optimizations in their hardware and release it to the market.
@ranjitsd,
if PD fails then even don't expect that AMD will retail it.today you will hardly will be able to get your hands on a BD processor.

This is what they should have done with the desktop BD part: can it and instead utilize the resources to Trinity, Piledriver.

BD isnt a fail. It does what they made it for and it costs much less.

@Sukesh: The windows 7 patch WILL come out next year.

^^BD costs less because it didn't performed up to the mark and look at its power consumption.so BD is still a baby in that technology it needs to mature so it need some time and we hope AMD have that time in their hands.

Yeah Anandtech review makes things pretty clear... Although I have to say... that they conclude with this is not right... and we need to do a more detailed review again.

Nonetheless 8/16 bulldozer doesnt gain much(or at all) vs its 12 core older brother...

3 Questions @ AMD -

1. Why is Phenom II not coming in 32 nm?? It performs nearly as good in multi core vs BD and IPC is soooo much better, K10.6 has even up the ante with 6% higher IPC vs K10.5!!!!

2. Why is Trinity coming with PD cores?? Its IPC will only drop with PD cores and multi core performance of PD is not going to be good if you see K10.6 vs FX4100 benchmarks.. you can see where 4100 stands....!!!AMD FX-4100 Quad Core 3.6GHz Bulldozer Processor Review - The AMD FX-4100 CPU - Legit Reviews

3. When is 3870K is coming out??? (6% higher IPC than deneb & hoping that it will reach ~4.6Ghz on air... seems pretty decent.. for ~7k INR)

M

considering the 8150 now retails for 14k and 2600k at 18k... BD is now vfm.. almost touching 2600's performance in a few benchmarks and beating it in highly threaded ones.. good buy..

down point is still TDP.. so you need a good motherboard and psu in addition to a cooler..

mrcool63 said:
considering the 8150 now retails for 14k and 2600k at 18k...

2600k - 18K :shock:

Where in he*l u got that price??? I still get a quote of 16.5K(inc. VAT) for 2600K.

meh....different sites...different reviews
I would not bother looking at BD benchmarks knowing that current OSs are not able to work out with BD processors
2013 is the year I'm looking for

zis thread has been bulldozed.

Clarification from AMD. The Desktop 6-core Bulldozer transistor count was 1.2 billion, not 2 billion. PR debacle. And I'm happy that they sacked almost all of their PR.

AnandTech - AMD Revises Bulldozer Transistor Count: 1.2B, not 2B

This thread remains locked though.

One more thing:

AMD Bulldozer A Surprisingly Sell-Out Sales Success. Victims: Phenom II & Athlon II | techPowerUp
According to this P2 and A2 are discontinued and will be available till stocks last.

Credits to sunny10 for posting this.

Thread is cleaned up and back now.

AMD 'Bulldozer' gets an Update from Microsoft. | techPowerUp

Today Windows updater may have brought "Bulldozer" users a little surprise. A hotfix that increases the AMD flagship processors performance. As this "hotfix" is bleeding edge news any benchmarks have yet to be seen but this confirms Windows 7 was in fact hampering “Bulldozer” from performing at 100% in all prior benches. What percentage it was previously performing at has yet to be determined. Here is a small snippet from the Hotfix release notes.

This article introduces an update that optimizes the performance of AMD Bulldozer CPUs that are used by Windows 7-based or Windows Server 2008 R2-based computers. Currently, the performance of AMD Bulldozer CPUs is slower than expected. This behavior occurs because the threading logic in Windows 7 and in Windows Server 2008 R2 is not optimized to use the Simultaneous Multithreading (SMT) scheduling feature. This feature was introduced in the Bulldozer family of AMD CPUs.

again posted by sunny10.

Hopefully, the benchmarks will reflect something positive. Fingers crossed.

I'm wondering whether it will improve anything. Expect it to be a tid bit improvement here and there. Plus, further patches being released.

I think if the top 3 have enough improvement to separate them from 1100XT, that will do. But whether such magic is at all possible, is a big question.

Plus the patch is not available publicly atm. Looks like work in progress...

Some results: The 1st windows 7 scheduler patch results are IN. Have fun!

Improvement is only being seen in games.

That would be even better, from a gamer's perspective.

seems promising. waiting for reviews.

BD will remain in news for some more months as they still have B3 stepping and Windows 8 launch

Waiting for benchmarks.

Benchmarks are out :shrug:

Check ico's link.

Nah.They are just 2 games and cinebench and that too not tested in correct methodology.but still gives some idea.thanks ico.

I guess the FX6200 benchmarks would be interesting after this patch. Hopefully, they have done something to the power consumption to the very least.

That Hotfix has been pulled of by Microsoft because it resulted some drastic performance drop in some areas too. Currently Microsoft is investigating the reason and a fix for the FIX.

Oh i guess thats why a guy in that forum asking for the link to download that fix as he was not able to find it.looks like it is getting difficult for microsoft also to understand the BD.

I think AMD should come up with a fix for this ( like they made CPU driver and DCO for Xp ) - that would be much more better, stable and reliable ;-)

a nice analysis.

To back up our statements we decided to use a quad-core Bulldozer processor to replicate two possible ways of disabling CPU cores and compare the performance in both cases. In the first case we used a “real” FX-4100 with two modules and four cores, and in the second – an eight-core four-module Bulldozer where we manually disabled one core per module. To ensure that the comparison is fair, we set the clock frequency to 3.6 GHz for both processors. For your reference we also included the performance numbers of a fully-functional eight-core CPU with all cores active and running.

*www.xbitlabs.com/images/cpu/amd-fx-8120-6100-4100/table2.png

AMD FX-8120, AMD FX-6100 and AMD FX-4100 CPUs Review. Page 2 - X-bit labs
(not with patch)

oops intel pentium g680 is better then fx processor in gaming

AMD FX-8120, AMD FX-6100 and AMD FX-4100 CPUs Review. Page 6 - X-bit labs

^a patch is coming. worth waiting before giving some conclusion.

Jaskanwar Singh said:
^a patch is coming. worth waiting before giving some conclusion.

if we wait few more months we wont be able afford pentium processor
price r increasing and amd stopped production of phenom 2 :cry:

^^there is llano and trinity is coming and pd is also coming and the win 7 patch already showed some significant improvement in games.so need to wait and watch.

^^ So 2012 is going to be a great year for AMD ;-)

A8 3870K should o well for AMD -> Good IPC & 32nm so good OC...

I think you guys have concluded that this year is not good to AMD. Ya, it is true for geeks like us, but financially BD is a success n is selling like hot cake. The 1st 8 core processor in the world thing is attracting lots of customers towards BD and it is a financial success, suppressing the sell of 2500K. That's why Intel has released a new processor 2550K as a refresh to their line up.
Not all the time market is driven by the performance, it also driven by the advertisement and gimmick you can offer. Best thing is it is now favoring AMD.

Cilus said:
I think you guys have concluded that this year is not good to AMD. Ya, it is true for geeks like us, but financially BD is a success n is selling like hot cake. The 1st 8 core processor in the world thing is attracting lots of customers towards BD and it is a financial success, suppressing the sell of 2500K. That's why Intel has released a new processor 2550K as a refresh to their line up.
Not all the time market is driven by the performance, it also driven by the advertisement and gimmick you can offer. Best thing is it is now favoring AMD.

100% true

AMD is giving cashback on their BD CPUs:-

AMD launches cashback programme for FX processors | KitGuru

More cores, more cashback. Why don't they offer the same here? We are a poor country.

Are you the same guy who replied there also

Just checked. I have not commented there, I think they have some sort of linkback or link tracking type of thing. Definitely it is pointing to my post here.

Cilus said:
The 1st 8 core processor in the world thing is attracting lots of customers towards BD and it is a financial success, suppressing the sell of 2500K. That's why Intel has released a new processor 2550K as a refresh to their line up.

Then Intel should have decreased the price of 2500K which they didn't. :twisted:

^^In all this stuff one more thing is also true that Intel 2500k has been on sale from jan 2011 and Amd has just launched its bulldozer......!

It can be called financial success if it is able to sell atleast like the intel processors got sold back in Q1-Q2-Q3-Q4 of this year
It has not even completed a quarter(3 months quota) of this year
And i know Intel is too greedy with is processor pricing..no price cuts yet
see this happens when one company fails to produce competitive product against a giant.
True 1st 8 core processor but doesn't produce results as 8 core machine..!
If they can sort out this issue in PD then they are good to go!!!!
Any ways Amd does fail on the first time of its product linup and come out with a bang with its second lineup!!!!!

Sukesh has shared another link about the Overclocking efficiency of Bulldozer processors. Chek this out:-
AMD's Bulldozer Architecture: Overclocking Efficiency Explored : Overclocking And Undervolting AMD's FX Family

AMD needs to earn more money if we want to see more product to come in future. And also keeping Intel in our reach.

It looks like the much-awaited patch is live now:-

Early Results Achieved with AMD FX Processor Using WindowsÂ® 7 Scheduler Update | Game Blog

Waiting for some benchmarks. :neutral:

Here you go:-

Google Translate

Microsoft patches Bulldozer’s performance — we investigate | ExtremeTech

AMD FX-8150 Tested with Latest Windows Hotfixes, Still No Improvement | techPowerUp

Much ado about nothing.

Improvement is there. See the 4 thread benchmarks.

Wasn't expecting any improvement in full 8 threaded benchmarks and there isn't any.

ico said:
Improvement is there. See the 4 thread benchmarks.

Wasn't expecting any improvement in full 8 threaded benchmarks and there isn't any.

Was expecting a bit more. Still, any free improvement is welcome.

^^
don't expect much brother,it is very difficult to tweak an existing os.the os should be built from the base to get the improvement.so expect a bit from win 8 but not much.the only way to see improvement in BD is waiting for pile driver.

Win 8 and Piledriver. Will it be what AMD NEEDS?

Tomshardware has published a nice article about the Bulldozer performance after two Windows 7 Hotfix and UEFI upgrade. Check it out:-
AMD's FX-8150 After Two Windows 7 Hotfixes And UEFI Updates : Scheduling, Core Parking, And Throttling, Oh My!

^^ here's some more ;-)

AMD Bulldozer Performance-Patch: Updates von Microsoft im Test - Bulldozer Benchmarks mit KB2645594 und KB2646060 (2/3) - TweakPC
AMDFX

Some more:-

AnandTech - The AMD FX (Bulldozer) Scheduling Hotfixes Tested

C

Here's Tom's comparative review of the AMD FX-4100 and the Intel Core i3 2100 in a more realistic setting:

AMD FX-4100 Vs. Intel Core i3: Exploring Game Performance With Cheap GPUs

There is not much difference in gaming between the two barring a couple of titles. Also, the FX-4100 is not overclocked here, so things might be different in the real world.

Personally, I do not see the Bulldozer as being the failure it is deemed to be. Yes, it is underwhelming but it's not OMG-end-of-the-world-for-AMD bad.

If the FX-4100 would be 1k cheaper (current pricing: INR 6600; theitwares.com), it may be the good buy.

^^^IMHO
:wink:

CitizenVish said:
Here's Tom's comparative review of the AMD FX-4100 and the Intel Core i3 2100 in a more realistic setting:

AMD FX-4100 Vs. Intel Core i3: Exploring Game Performance With Cheap GPUs

There is not much difference in gaming between the two barring a couple of titles. Also, the FX-4100 is not overclocked here, so things might be different in the real world.

Personally, I do not see the Bulldozer as being the failure it is deemed to be. Yes, it is underwhelming but it's not OMG-end-of-the-world-for-AMD bad.

If the FX-4100 would be 1k cheaper (current pricing: INR 6600; theitwares.com), it may be the good buy.

^^^IMHO

BD is good, and honestly we need competition, but its out fault, we hyped BD too much, we thought it would be the next best thing.