AMD to reuse the FX brand name for Zambezi line-up of CPUs!

[DarthShader]

I could write similar "news" just based on what various people here in the news section of xtremesystems write... All your clicks are belong to Fuad!

[informal]

And now some Fud:
http://www.fudzilla.com/processors/i...ose-to-core-i7
I`m really "staggered" by how many sources these guys have; do they work for the CIA/Interpol, etc.?)
As FlawleZ also mentioned, I`m also expecting mediocre expectations, it`s better this way.

I already posted the link,read the thread man.

[generics_user]

Meh, I'd like to hope so. But then again, that's what everyone said about Phenom being "Phenomenal." I have hope 100% that AMD unleashes a monster with BD. However, I'll hold my epectations to a modest level to help prevent being let down or underwhelmed.

without the TLB bug and higher frequencys phenom would've been on par with kentsfield but the slow NB frequency and core speeds of 2-2.4ghz instead of the originally targeted 2.6-3ghz it was underwhelming, and back then we knew much more: 65nm brisbane sucked; cache speeds were slower than 90nm and it was delayed several times...

with bulldozer we only know that it's 1 quarter ahead of the last schedule from late 2009 instead of 2 quarters late like barcelona was and the new 32nm process is the biggest change ever since the introduction of SOI which can de a good or a bad thing

[Mats]

with bulldozer we only know that it's 1 quarter ahead of the last schedule from late 2009 instead of 2 quarters late like barcelona was and the new 32nm process is the biggest change ever since the introduction of SOI which can de a good or a bad thing

AMD said their 32 nm was only 1 quarter behind Intel, I guess that was just too optimistic.

[badboy18187]

I know, I`m being ironic(like everyone else) with regards to Fud, whenever they have some piece of "news".

[generics_user]

AMD said their 32 nm was only 1 quarter behind Intel, I guess that was just too optimistic.

this information contradicts with their roadmaps from 2008; 2009 and 2010, all of them put first 32nm chips in 2011

[Mats]

this information contradicts with their roadmaps from 2008; 2009 and 2010, all of them put first 32nm chips in 2011

Sorry, it was GF, not AMD.

[FlanK3r]

btw, liuttle speculation about performance 8-core Zambezi...Simulated with x6 1100T, core multi efectivity, higher core performance Zambezi chip about 15%+- etc etc...
So, Cinebench R10 at 3.3 GHz will be about 30 000points, at R11.5 about 9.3 points. Remember, its only theoretical estimate But I think, it will be not far from the truth

[Sn0wm@n]

great news ... so that would make bulldozer an ipc increase of 20+ % right???

[Johnny87au]

Fud has some supposedly leaked info from early Zambezi samples:



In the past AMD's engineering samples weren't usually representative of final product performance levels(remember first K8 benchmarks). I expect X6 Zambezi to come close to Gulftown and X8 to outperform it. Also we should take note that desktop performance depend a lot on usually poorly threaded applications so if BD comes close to i7 generally it means that single thread performance is up to a comparable level or close to it. FX brand is back for a reason .

Lets hope your right mate! been a while since AMD has been able to compete

[Gilgamesh]

Bulldozer 50% Faster than Core i7 and Phenom II

http://www.techpowerup.com/138328/Bu...Phenom-II.html

Here, take some salt. AMD reportedly gave out performance figures in a presentation to its partners, performance figures seen by DonanimHaber. It is reported that an 8-core processor based on the "Bulldozer" high-performance CPU architecture is pitched by its makers to have 50% higher performance than existing processors such as the Core i7 950 (4 cores, 8 threads), and Phenom II X6 1100T (6 cores). Very little is known about the processor, including at what clock speed the processor was running at, much less what other components were driving the test machine.

Taking this information into account, the said Bulldozer based processor should synthetically even outperform Core i7 980X six-core, Intel's fastest desktop processor in the market. Built from ground-up, the Bulldozer architecture focuses on greater inter-core communication and reconfigured ALU/FPU to achieve higher instructions per clock cycle (IPC) compared to the previous generation K10.5, on which its current Phenom II series processors are based. The processor is backed by new 9-series core logic, and a new AM3+ socket. AMD is expected to unveil this platform a little later this year.


original source: DonanimHaber


As my grandfather used to say: "OPTIMISM IS SALT OF LIFE" (translated from italian's local slang

[duploxxx]

Lets hope your right mate! been a while since AMD has been able to compete

is depending how you look at IT, they are more then adequate to compete on the server level

Bulldozer 50% Faster than Core i7 and Phenom II

http://www.techpowerup.com/138328/Bu...Phenom-II.html

Here, take some salt. AMD reportedly gave out performance figures in a presentation to its partners, performance figures seen by DonanimHaber. It is reported that an 8-core processor based on the "Bulldozer" high-performance CPU architecture is pitched by its makers to have 50% higher performance than existing processors such as the Core i7 950 (4 cores, 8 threads), and Phenom II X6 1100T (6 cores). Very little is known about the processor, including at what clock speed the processor was running at, much less what other components were driving the test machine.

Taking this information into account, the said Bulldozer based processor should synthetically even outperform Core i7 980X six-core, Intel's fastest desktop processor in the market. Built from ground-up, the Bulldozer architecture focuses on greater inter-core communication and reconfigured ALU/FPU to achieve higher instructions per clock cycle (IPC) compared to the previous generation K10.5, on which its current Phenom II series processors are based. The processor is backed by new 9-series core logic, and a new AM3+ socket. AMD is expected to unveil this platform a little later this year.


original source: DonanimHaber


As my grandfather used to say: "OPTIMISM IS SALT OF LIFE" (translated from italian's local slang

well that is not really unexpected, i7 950 is running with 4+4ht cores, while BD CMP is full 8 core for sure on the synthetical benchmarks they did, and they have also the turbo methodology (which is actually better then compared platform) i don't think they will hit the 980 performance though in all synthetical benchmarks. It would be a failure for BD and AMD if they are not able to get to that level of performance.

[FlanK3r]

whau, very good news!

[jeremyshaw]

is depending how you look at IT, they are more then adequate to compete on the server level

mostly in a certain range and niche in the server level.... then again, in my experience, almost every server is filling some niche role, lol.

[SubZero.it]

Seems there is a reason for releasing again FX branding
http://www.donanimhaber.com/islemci/...daha-hizli.htm
http://www.techpowerup.com/138328/Bu...Phenom-II.html

[flyck]

The statement is to much like the one JF gave us a year ago.

33% more cores for 50% more performance. Seems like a reinterpretation of that information.

[-Boris-]

Nothing new really. And the don't compare it to the high end i7s. Saying 50% over i7 is just wrong.

[flyck]

Nothing new really. And the don't compare it to the high end i7s. Saying 50% over i7 is just wrong.

three different categories (media, rendering and game) in comparing the overall assessment of the Bulldozer processor 8-core Core i7 950 is 50% faster stressed. Carefully examined the performance table in the 8-core processor, AMD's Bulldozer makes a difference, especially game and rendering tests.

well if the average is 50% and the biggest differences are gaming and rendering those 2 should be above 50% or at least one should be. If gaming would be remote to 50% of i7 @ 3.33Ghz then .... maybe we can talk about a white dead (to much salt).

[informal]

The statement is to much like the one JF gave us a year ago.

33% more cores for 50% more performance. Seems like a reinterpretation of that information.

It's has been discussed before that Zembezi's improvement on desktop will be somewhat different than Interlagos improvement in server workloads. But still,we have 33% more cores,higher IPC,higher clock,higher Turbo. This should lead to much better performance.

Nothing new really. And the don't compare it to the high end i7s. Saying 50% over i7 is just wrong.

50% over 950 i7,in mixed benchmarking with lots of poorly threaded workloads in client space would put Zambezi easily ahead 980x Gulftown.
Check this :
http://www.hardware.fr/articles/815-...dy-bridge.html
50% over 1100T/950 i7 is above 3.33Ghz Gulftown by 20/11%. That's top of the line performance in client space.

Google translate of the last paragraph from donanimhaber:

As mentioned above, but not yet test results are detailed in Hardware News AMD's official documentation of performance we were able to reach. In this document, AMD Bulldozer 8-core processor (model name and clock speed performance segment, but that information has not been specified), 6-core Phenom and Core i7 950 and compares II X6 1100T. The estimated results in the document, processors, three different categories (media, rendering and game) in comparing the overall assessment of the Bulldozer processor 8-core Core i7 950 is 50% faster stressed. Carefully examined the performance table in the 8-core processor, AMD's Bulldozer makes a difference, especially game and rendering tests.

[kl0012]

50% over 950 i7,in mixed benchmarking with lots of poorly threaded workloads in client space would put Zambezi easily ahead 980x Gulftown.
Check this :
http://www.hardware.fr/articles/815-...dy-bridge.html
50% over 1100T/950 i7 is above 3.33Ghz Gulftown by 20/11%. That's top of the line performance in client space.

Google translate of the last paragraph from donanimhaber:

Did they say in "mixed benchmark"? I would not be surprised if perf. numbers were related to high-threaded integer benchmark. Also, i'm not sure if Bulldozer will be faster then 1100T in pure floating point code (thuban is capable to execute 6x2 fp instruction per cycle, bulldozer - 8x1 (or 4x2) without AVX).

[informal]

Did they say in "mixed benchmark"? I would not be surprised if perf. numbers were related to high-threaded integer benchmark. Also, i'm not sure if Bulldozer will be faster then 1100T in pure floating point code (without AVX thuban is capable to execute 6x2 fp instruction per cycle bulldozer - 8x1 (or 4x2).

In my world,when someone says media ,game and rendering it's indeed mixed benchmarking. Media can be threaded well but it depends a lot on used applications(many don't support more than 2/4 threads). Media (encoding) is mostly integer workloads too.Games are usually poorly threaded(also mostly integer in nature),supporting up to 4 threads and many times as low as 1-3. Rendering is mostly well threaded,FP oriented. The donanimhaber link said the games and rendering results are making the biggest difference ,which is intriguing(hinting at much better perf. with both fewer threads and many threads in int and fp workloads-games and rendering). That's mixed benchmarking right there.

As for Thuban Vs BD in FP workloads,JF-AMD once said that there shouldn't be a case where BD(Interlagos) won't clearly outperform older design(MC),especially in traditional(non-recompiled) FP workloads. This is actually worst case comparison since server workloads are well threaded and make most use of available fp execution potential. Zambezi/Thuban retains the same ratio of fp execution potential as Interlagos/MC while it's playing in different space(client) which is not dominated that much by workloads that can make most of the design in terms of threading potential.In conclusion: it only can be better in Zambezi case vs Interlagos case and Interlagos is said to clearly outperform MC.

[Sn0wm@n]

this all sound good

now we need more am3+ mobo leaks

[w0mbat]

pls have in mind that a 4m bd isnt a full 8-core cpu.

[zalbard]

Bulldozer 50% Faster than Core i7 and Phenom II

http://www.techpowerup.com/138328/Bu...Phenom-II.html

Here, take some salt. AMD reportedly gave out performance figures in a presentation to its partners, performance figures seen by DonanimHaber. It is reported that an 8-core processor based on the "Bulldozer" high-performance CPU architecture is pitched by its makers to have 50% higher performance than existing processors such as the Core i7 950 (4 cores, 8 threads), and Phenom II X6 1100T (6 cores).D

So twice more cores and just 50% faster? This better be incorrect.

[Hornet331]

pls have in mind that a 4m bd isnt a full 8-core cpu.

Actually JF said it is:

by: HalfAHertz
--------------------------------------------------------------------------------
No it is an octa core - every core in the module has a dedicated SP but they share a "fat" FP which can either do 1 FP calc for each or an advanced 256-bit calc (which we probably won't se for a while because nobody will have ready code...)
--------------------------------------------------------------------------------

Actually every core has its own dedicated FMAC for floating point. If you want to do 256-bit floating point with AVX you can merge the 2 FMACs. Intel handles 256-bit AVX by merging their 128-bit FPU with the SSE functions (and you have to recompile all of your code to make SSE into AVX-128.


by: DriedFrogPills
--------------------------------------------------------------------------------
I think it's more likely to be scenario 2 as I remember an article on anandtech midway through last year, that stated each core is one half of a bulldozer module. What we really need is for JF-AMD to clarify the module versus core thing
--------------------------------------------------------------------------------

Modules are an architectural facet of the design, we will not market modules. The cores are cores. They are not "half cores" as some suggest. If you look at what defines a core, it is the integer execution pipeline. When the system boots up it will see all of the cores as integer cores, the OS will see them and the application will see them. All arguments have fallen flat on their face.

One BD "module" = dualcore. The only special thing is that it only has "one" FP unit that can handel 2 128bit functions at the same time or one 256bit. Which means if only 128bit FB code is handeld its basically like every other dualcore.

In the end it doesn't matter if amd places its octacore against intels hexacore, if its cheaper and can outperform it, who cares?