AMD CPU speculation... and expert conjecture

[blackkstar]

from those slides, another sentence that caught my eye was "thin layer of abstraction" but how thin? amd claims it is extendable to other uarches and forward compatible. doesn't that mean it will eventually become bloated? may be i'm being too skeptical.

Extendable to other uarches doesn't mean adding layers on top. MANTLE consists of two layers: one API plus the driver. If you substitute the MANTLE driver for GCN by another for Intel or Nvidia the MANTLE API will work on top of non-AMD hardware.

Woah, someone else who understands what an API is. My mind is blown. I am going outside for a walk, I simply can't deal with seeing someone else understand the differences between API and implementation of an API. My head is spinning.

BUT I THOUGHT MANTLE ONLY BEING IMPLEMENTED ON GCN CARDS MEANT THAT IT WAS GCN ONLY FOREVER!!!!!

 

[juanrga]

Other members from Poland have labeled that site as untrustworthy for results.

I know it has been accused of fabricating the benchmarks :lol:

 

[Cazalan]

Well, you could argue that it was...

However, you could also argue that it wasn't...since GF has lost significant money since it was spun off, where would AMD be right now? Hemorrhaging cash right now...that's where. From a business perspective it made sense in some ways, and not in others. I think all we are doing is arm chair quarterbacking at this point.

AMD really had no choice but to spin GF. They would have gone bankrupt.

 

[juanrga]

What if I already have in my hands the official desktop roadmap for 2014?

If that was the case, we would have already seen the slide for it 1000x because you would be trying to convince us that there is no dCPU coming, and that would be your "holy grail" of evidence. However, I am more willing to bet you have the official 2014 Desktop APU roadmap that everyone else has...

Another bet that you lose, because I have THE 2014 desktop roadmap and it appears one big CPU mentioned in it...

 

[gamerk316]

And the world has been accused of being flat by Nobel Prize winning Physicists. That doesn't make it true. Doesn't make it false either.

*shrug*

There is a big problem here that chips can no longer scale in the ways they previously have, and that we have to do something else to make a difference.

The path you are suggesting of sticking to single core rendering and not looking for alternatives is suggesting that we create a world where there's no longer a reason to upgrade your CPUs because Intel can't make anything faster and AMD is still catching up in single thread.

But as I'm trying to point out, this is the exact same argument made back in the late 70's in favor of distributed computing (really, multi-CPU mainframes). OS's were developed that allowed cooperatively scheduled threading to give the developer fine control of application performance, and significant amounts of time and money were used to developed hard coded assembly to take advantage of those features.

DYI, it didn't work, because it was found after a handful of physical CPU's, performance gains fell off a cliff. And this is more of an issue now since, in a pre-emptively scheduling OS, you have even less control over threading, so you'd expect less scaling then on a cooperatively scheduled OS.

As I've said, there are things that can scale reasonably well. Rendering, obviously, which has been done for about 15 or so years now. Physics, which we see being offloaded from the CPU. You could do AI too. But then you have to manage those threads, keeping the right ones running and keeping the state sane (remember: You don't control what threads run when), so you need some type of locking scheme (locks, mutexs, semaphores, etc) OR perform optimistic processing with a VERY high worst-case outcome.

the issue I have with AMD isn't that they are going to more cores, its that they went to more cores while reducing per-core performance. The issue that is doubling the cores is pointless if its competitors cores end up being 50% more powerful [remember, non-perfect scaling + overhead].

The situation with the BD arch has not changed: It lags behind current mid-tier i5 chips in the BEST case. But I still see plenty of people (wrongly) claiming that a 6350 beat an i5-3570k in gaming (it doesn't), or the old BD argument of "It will get better over time" (it hasn't).

And I was one of two or three people here who called this, back in 2009, based SORELY of my knowledge of how the OS/Software works, not even bothering to look at the details of the BD arch. Remember, I said BD would be a benchmark monster, but it games, it would be low-tier i5 level performance? And I nearly got laughed out of the forums.

My primary point being is that you aren't going to see continual scaling as you add more cores, so that approach, much like increasing IPC and clock, is going to come to an end. There's only so much you can do with the way CPU's are currently designed. Maybe quantum computing will change things, but I really think X86 is nearing its limit as a processor arch.

 

[8350rocks]

The most recent experiments show that gains become marginal past about 25-30 cores/processors. Beyond that you're just adding more for the sake of adding them...

 

[8350rocks]

What if I already have in my hands the official desktop roadmap for 2014?

If that was the case, we would have already seen the slide for it 1000x because you would be trying to convince us that there is no dCPU coming, and that would be your "holy grail" of evidence. However, I am more willing to bet you have the official 2014 Desktop APU roadmap that everyone else has...

Another bet that you lose, because I have THE 2014 desktop roadmap and it appears one big CPU mentioned in it...

Well, I have it as well, I was given a link:

http://phx.corporate-ir.net/phoenix.zhtml?c=74093&p=irol-newsArticle&ID=1876132&highlight=

Scroll to the bottom and click on product roadmaps, open the .pdf and you will see the one that has "PILEDRIVER 2nd GENERATION FX SERIES" which is listed as the "PERFORMANCE PROCESSOR" category.

Ironically, Kaveri is not listed as a performance processor...I wonder why...maybe because, as my source intimated, AMD understands Kaveri is not for HEDT, as you seem to want to assert it is.

 

[blackkstar]

And the world has been accused of being flat by Nobel Prize winning Physicists. That doesn't make it true. Doesn't make it false either.

*shrug*

There is a big problem here that chips can no longer scale in the ways they previously have, and that we have to do something else to make a difference.

The path you are suggesting of sticking to single core rendering and not looking for alternatives is suggesting that we create a world where there's no longer a reason to upgrade your CPUs because Intel can't make anything faster and AMD is still catching up in single thread.

But as I'm trying to point out, this is the exact same argument made back in the late 70's in favor of distributed computing (really, multi-CPU mainframes). OS's were developed that allowed cooperatively scheduled threading to give the developer fine control of application performance, and significant amounts of time and money were used to developed hard coded assembly to take advantage of those features.

DYI, it didn't work, because it was found after a handful of physical CPU's, performance gains fell off a cliff. And this is more of an issue now since, in a pre-emptively scheduling OS, you have even less control over threading, so you'd expect less scaling then on a cooperatively scheduled OS.

As I've said, there are things that can scale reasonably well. Rendering, obviously, which has been done for about 15 or so years now. Physics, which we see being offloaded from the CPU. You could do AI too. But then you have to manage those threads, keeping the right ones running and keeping the state sane (remember: You don't control what threads run when), so you need some type of locking scheme (locks, mutexs, semaphores, etc) OR perform optimistic processing with a VERY high worst-case outcome.

the issue I have with AMD isn't that they are going to more cores, its that they went to more cores while reducing per-core performance. The issue that is doubling the cores is pointless if its competitors cores end up being 50% more powerful [remember, non-perfect scaling + overhead].

The situation with the BD arch has not changed: It lags behind current mid-tier i5 chips in the BEST case. But I still see plenty of people (wrongly) claiming that a 6350 beat an i5-3570k in gaming (it doesn't), or the old BD argument of "It will get better over time" (it hasn't).

And I was one of two or three people here who called this, back in 2009, based SORELY of my knowledge of how the OS/Software works, not even bothering to look at the details of the BD arch. Remember, I said BD would be a benchmark monster, but it games, it would be low-tier i5 level performance? And I nearly got laughed out of the forums.

My primary point being is that you aren't going to see continual scaling as you add more cores, so that approach, much like increasing IPC and clock, is going to come to an end. There's only so much you can do with the way CPU's are currently designed. Maybe quantum computing will change things, but I really think X86 is nearing its limit as a processor arch.

Did you watch the Mantle keynote? Mantle and HSA is not about using "MOAR COARS", it's about creating a set of tools to make using the right components for the right task easier.

Rendering is distributed across many cores because it can be, and GPGPU tasks like calculating global illumination will be passed off to another GPU while a main one renders the scene.

Had you paid attention to APU13, you would have seen Oxide's presentation where they showed a ton of on screen objects and then ran a benchmark where FX 8350 at stock, FX 8350 at 2ghz, and i7 4770k were all performing the same and the 290x was a performance bottleneck.

I don't know what else you want. At APU13 AMD announced Mantle will make it possible to shift:

1. Rendering across multiple GPUs and CPU cores
2. Physics to GPU
3. AI to GPU
4. Global Illumination across GPUs

If you'd like to tell me that part of the game that's going to need strong single thread performance when you use Mantle, please enlighten me about it, because I have no idea what it is right now.

 

[tracker45]

So far Steamroller is a disappointment, the pointless 3 day conference where they unveiled one APU, they didn't even display a game with Mantle.

Maybe Steamroller is just one product and AMD are making cutbacks.

 

[8350rocks]

What if I already have in my hands the official desktop roadmap for 2014?

If that was the case, we would have already seen the slide for it 1000x because you would be trying to convince us that there is no dCPU coming, and that would be your "holy grail" of evidence. However, I am more willing to bet you have the official 2014 Desktop APU roadmap that everyone else has...

Another bet that you lose, because I have THE 2014 desktop roadmap and it appears one big CPU mentioned in it...

Well, I have it as well, I was given a link:

http://phx.corporate-ir.net/phoenix.zhtml?c=74093&p=irol-newsArticle&ID=1876132&highlight=

Scroll to the bottom and click on product roadmaps, open the .pdf and you will see the one that has "PILEDRIVER 2nd GENERATION FX SERIES" which is listed as the "PERFORMANCE PROCESSOR" category.

Ironically, Kaveri is not listed as a performance processor...I wonder why...maybe because, as my source intimated, AMD understands Kaveri is not for HEDT, as you seem to want to assert it is.

It does say kaveri = mainstream performance all in one and elludes to warsaw being on 32nm for desktop

It says Mainstream / performance all-in-one.

Frankly...there is nothing "performance" about AIOs. My wife works on one at home...it's a 1.5 or 1.8 GHz dual core with a 500 GB HDD and 4 GB RAM. AIOs are bargain bin "walmart" computers for $500 retail, and you're honestly overpaying at that price point...

Kaveri is not a performance CPU/APU/GPU. AMD knows this, and so does the rest of the world...except juan it seems.

 

[noob2222]

Spoiler

Disagreeing is fine, but he writing "to save their ass", "a crappy cpu", "and an idle IGP", "weak ass cores"... clearly denotes hate.

Specially when he is plain wrong. As shown in my article about Kaveri a 3.7GHz SR CPU perform like a SB/IB i5 with ordinary CPU workloads, loosing in the FP intensive ones but outperforming in the integer workloads. There I assumed 20% IPC over PD, but some late leaks suggest that the final improvement is >30%. Therefore add to the scores I published if the leak is true.

you want to claim I am wrong yet you only offer your opinion. APU cores are weak, always have been.

the lowly fx-4100 is 46% faster than the A10 5700 and clocked slower. The fx-4320 is 58% faster and the fx-8350 and the I5 3470 is 73% faster. good luck catching that i5.

This is the same architecture. Id call that a weak ass core any day.

again, 4320 = 40% faster, 8350 = 56% faster, I5 3470 = 73% faster.

4320 - 52% , 8320 - 83%,I5 3470 - 89%

4320 - 33%, 8320 - 50%, i5 3470 - 62%

... there is plenty more where these came from

now tell me using these RL results how removing the L3 cache in favor of making the cpu weaker and adding an IGP is such a great thing to ever happen to the computing industry?

How is kaveri going to catch the I5? 8350? ... heck even the 4320 ...

Id say the a10 5700 is a pretty good spot to start with Kaveri figures since they both clock at 3.7 ghz. As you put it "in ordinary cpu workloads" shown above, its starting at negative 40% already just to get to the 4320.

Kaveri is not going to be the answer your hoping it will be. It will not catch the i5 3470 very often (if ever,) it may here and there, but that will take some luck "in ordinary cpu workloads"

Tell me just exactly how I am "just plain wrong"?

I already said this to you. Also you continue using essentially the same logic than in your previous attack to AMD ARM line.

Here you pick very old benchmarks (not optimized for AMD architecture, one of them is a Nvidia sponsored game) and an old 5700 Trinity APU and you claim this is how Kaveri will perform.

You miss the estimation of Kaveri CPU performance in the BSN* article, you miss the leaked benchmarks comparing Kaveri to Bulldozer and Piledriver FX, and you miss the BF4 benchmark given by AMD during October talk, where a Richland APU got the 98% of the performance of a FX-6350 and the 96% of the performance of the FX-8350 (the three using a R9 280X and playing @ 1080p ultra). I think you continue missing the subsequent discussion on multiplayer BF4. And you miss that AMD is in the consoles now, with a CPU based in jaguar cores.

Can you compare the performance of the PS4 CPU to Kaveri CPU? I can.

Maybe you don't still understand this, but game developers will be offloading the consoles CPUs and running the heavy computations on the consoles GPUs. That is why both consoles have GPGPU abilities and HSA support.

You also miss that MANTLE aims to liberate some CPU bottlenecks that exist in current gaming technology. This is from Oxide talk at APU13:

Mantle Unleashed: How Mantle changes the fundamentals of what is possible on a PC. Over the last 5 years, GPUs have become so fast that it has become increasingly difficult for the CPU to utilize them. Developers expend considerable effort reducing CPU overhead and often are forced to make compromises to fully utilize the GPU. This talk will discuss real-world results on how Mantle enables game engines to fully and efficiently utilize all the cores on the CPU, and how it’s efficient architecture can eliminate the problems of being CPU bound once and for all.

get over yourself. Very old benchmarks? I specifically looked for games released in 2013 ... ermago ... thats soo friggin old.

a10 5700 = piledriver without l3 cache
4320 = piledriver fx
8350 = piledriver fx

whats soo old about the a10 5700? all that richland brought was higher clock speeds over trinity, kaveri brought lower clock speeds. you can't compare the 4.2 ghz richland to the 3.7 ghz kaveri and say its going to be 30% faster on top of being slower clock. 3.7 ghz piledriver vs 3.7 ghz kaveri is a fair comparison.

If anything id describe AMD's APU as a gpu with an integrated cpu while Intel is making cpus with an integrated gpu.

The reason your stuck on this "BF4 ERMAGO BENCHMARK" is because it doesn't stress the cpu AT ALL. Its a gpu bound benchmark. Thats why it was chosen, its a tactic called marketing.

As for the BSN article, its was pulled from your website.

Agree on that "very old" was an exaggeration from my part, but it was needed to compensate your exaggerated attack on Kaveri APU (I mean that one where you wrote "ass", "crappy", and "ass").

In the same paragraph I also wrote what I mean by "old", (="not optimized for AMD architecture"). Sorry but no, I was not referring to if was released in early 2013 or in late 2009.

I am not discussing marketing, you are. I am discussing technical and economic details behind marketing and execution plans by a company. I am explaining you that the whole master plan (which I have given you some elements) is towards offloading the CPU more and more. As you don't get it, offloading the CPU means you push more work on the GPU. Therefore a GPU bound benchmark is more characteristic of how next gen games will behave than old Intel+Nvidia games.

I note how you avoided my question about the jaguar-based CPU in the consoles...

Juan we do agree that richland and piledriver is basicly the same, expect for powermanagement and the like, right? what does the richland APU have that the fx doesn't? And specifically what is it that makes the APU be the only one recieving performance increases:

The six factors, Except for the piledriver -> steamroller/HSA (Won't help in singlethreaded), doesn't everything else apply to fx and older apu too..?

The APU lacks L3 cache. I don't know if there are other differences which AMD has not disclosed. What I know is what follows.

The BF4 benchmark given at the October talk to OEMs shows a Richland APU performing as well as FX-6350 and FX-8350. The APU gives a 98% and 96% of the performance of each FX respectively.

The 'old' argument that FX is 30--50% faster because has L3 cache doesn't apply here.

The argument that Suez map is single player and not well-multithreaded doesn't mean anything, because a FX-4350 will not be 30--50% faster than the FX-6350 and FX-8350.

meaningless ... really ...

ya, ... multiplayer really favors the APU core in the 750k doesn't it.

Just to clarify,
750k = piledriver without l3 cache and no IGP.
4350 = piledriver fx
6300 = piledriver fx
8350 = piledriver fx

lets compare the 4.5 ghz piledriver 750k to the 4.7 ghz fx. That only accounts for a 4.5% difference in clock speed, if perfect scaling (wich its not) then subtract 4.5% from the results.

4350 = 18% faster than the l3 cacheless APU core
6300 = 47% faster than the l3 cacheless APU core
8350 = 76% faster than the l3 cacheless APU core

How many times do you have to be proven wrong? Single player benchmark is meaningless because it doesn't stress the cpu AT ALL. Its strictly a gpu benchmark until you drop below 3.0 ghz.

http://static.techspot.com/articles-info/734/bench/CPU_01.png

More of the same. Here you pick again the same benchmark that I commented before in a reply to you, when you linked it by the first time. And then you repeat the same without reading what was said to you. So typical.

And you always change the story. You stated that kaveri will =i5 in ordinary cpus workloads. When proven wrong now it's only in apu specialized software.

You may be happy with weaker cores coupled with a software solution, it will not go over well when the reviews come out.

And unsurprisingly you come with the same misunderstanding again, one that I corrected before and before...

In my BSN* article, which evidently you didn't read, I show how kaveri performs as an i5 using ordinary cpu workloads. I am not using "apu specialized software" as you pretend.

Finally, I am happy with the idea of software using my hardware. All my hardware (or most of it) and not only one half or one third of it. There is another person here with similar ideas to me. He compiled a program for his hardware and now it runs 2x faster or said in another way the former unoptimized program was using only a 50% of the performance of his hardware.

You seem to prefer the other way. If the software only uses a 50% of the hardware you update to a 2x more powerful hardware for that the same software can now ignore the 50% of more.

I love the idea of utilizing software. Not at the expense of only releasing low end hardware and relying solely on the software to make up the lack of good hardware. We need both. APU are not high end. Period.

APU are a little of both, and a master of none. Without the specialized software as I have shown kaveri needs 80% or more boost to catch the low end i5. It needs 40% to catch the 4320. This is in ordinary gaming cpu workloads.

Your the one not looking at the data I have provided and coming up with lame excuses instead of trying to convince me with hard evidence. Your website and marketing slides that are designed to only show the best possible scenario do not count as evidence. Those will be only true in a few select cases and are not representative of "ordinary workloads".

Kaveri is not "low end hardware".

And as explained before the benchmarks given are using "ordinary workloads". They are not "specialized software" for APUs neither the "best case".

You don't understand what was made/measured in the BSN* article. I have corrected your misunderstandings again and again and again. Still you insist on that those benchmarks are "specialized software" for APUS, when are not.

Pure AMD hate...

the only reason you keep talking about the BSN article is this:

This article was originally published by Juan Ramón González Álvarez at http://juanrga.com/en/AMD-kaveri-benchmark.html

I have already stated my theory of why your claims are flawed. You refuse to respond to that, only saying "you never listen to me". This is not a BSN article, its your article published on their website.

How can kaveri catch the i5 when its 80% slower in the workloads I have shown without resorting to HSA?

How can kaveri catch the 4320 in the same workloads starting at 40% behind without resorting to HSA?

How is a APU thats slower than the previous gen CPU "not low end"?

As I stated, APU is a mix of both cpu and gpu, and a master of none. APU will not be HEDT. APU is great for laptop, AIO and small form factor pcs/htpcs.

 

[GOM3RPLY3R]

Sorry about jumping in here, but I just saw this flowchart and thought it would be really good to give people understanding, as well as a fair debate about our new console friends. ^_^ Enjoi

 

[noob2222]

^^ @tourist nested spilers don't work, let me edit that real quck, or go back 2 pages for the orignal posting.

spoiler nesting removed.

Xb one .. 8 core MS custom cpu? wha ..

 

[kansasboy001]

At long last we finally have to answer that we have been waiting for. There will not be an BD FX successor for 2014. We will have to keep pushing our 8350s to higher clocks. I personally will be shooting for 5.0GHz base, 5.2GHz turbo, with cool and quiet and other power saving features enabled.

[/url] [/img]

 

[etayorius]

Nothing new, we already knew this since that Chilenian Site claimed to have talked to AMD.

 

[blackkstar]

So far Steamroller is a disappointment, the pointless 3 day conference where they unveiled one APU, they didn't even display a game with Mantle.

Maybe Steamroller is just one product and AMD are making cutbacks.

^^ @tourist nested spilers don't work, let me edit that real quck, or go back 2 pages for the orignal posting.

spoiler nesting removed.

Xb one .. 8 core MS custom cpu? wha ..

The company that is most pissed off about Mantle is MS.

MS now has to buy APUs from AMD when AMD has created a direct competitor to DirectX. The kicker is that AMD's APU is capable of Mantle and would run better than DirectX would run on the DirectXBone.

My guess is that MS is going to want to separate themselves from AMD. Either that or whoever made this infographic is an MS fanboy who wants to make the APU in the MS system look superior. The XBone has no hardware advantage other than Kinect.

Things are going to be interesting if there's another Xbox.

Nvidia completely pissed Microsoft off with the original xbox and now AMD is pissing off MS by releasing a competing product to one of MS's flagship technologies.

XBox Two powered by Intel.

And yes, kansasboy I am disappointed too, but the FX is still at least a good chip. I would have really loved to drop my render times by 30% just by dropping in a new CPU for $200 but this FX has already saved me a ton of time from my i7 920 and made me a lot more than I've spent on the chip.

EDIT: Wow, mixing up AMD and MS so much =[

 

[anxiousinfusion]

What if I already have in my hands the official desktop roadmap for 2014?

If that was the case, we would have already seen the slide for it 1000x because you would be trying to convince us that there is no dCPU coming, and that would be your "holy grail" of evidence. However, I am more willing to bet you have the official 2014 Desktop APU roadmap that everyone else has...

Another bet that you lose, because I have THE 2014 desktop roadmap and it appears one big CPU mentioned in it...

Well, I have it as well, I was given a link:

http://phx.corporate-ir.net/phoenix.zhtml?c=74093&p=irol-newsArticle&ID=1876132&highlight=

Scroll to the bottom and click on product roadmaps, open the .pdf and you will see the one that has "PILEDRIVER 2nd GENERATION FX SERIES" which is listed as the "PERFORMANCE PROCESSOR" category.

Ironically, Kaveri is not listed as a performance processor...I wonder why...maybe because, as my source intimated, AMD understands Kaveri is not for HEDT, as you seem to want to assert it is.

It does say kaveri = mainstream performance all in one and elludes to warsaw being on 32nm for desktop

It says Mainstream / performance all-in-one.

Frankly...there is nothing "performance" about AIOs. My wife works on one at home...it's a 1.5 or 1.8 GHz dual core with a 500 GB HDD and 4 GB RAM. AIOs are bargain bin "walmart" computers for $500 retail, and you're honestly overpaying at that price point...

Kaveri is not a performance CPU/APU/GPU. AMD knows this, and so does the rest of the world...except juan it seems.

I believe juan has an understanding that Kaveri is a mid range product. Neither high end or low end.

 

[Cazalan]

My primary point being is that you aren't going to see continual scaling as you add more cores, so that approach, much like increasing IPC and clock, is going to come to an end. There's only so much you can do with the way CPU's are currently designed. Maybe quantum computing will change things, but I really think X86 is nearing its limit as a processor arch.

Every year people predict the end of Moore's law and yet it still goes on. There are so many facets to the compute equation that can be tweaked. New meta-materials, new algorithms, cheaper computers. Every year more people are exposed to computers and whether it's X86/ARM/PowerPC/MIPS, the ISA is just one means to an end.

 

[sora]

Honestly although AMD is attempting to catch up to Intel I'm pretty sure Intel will always be ahead of the game.

 

[juanrga]

What if I already have in my hands the official desktop roadmap for 2014?

If that was the case, we would have already seen the slide for it 1000x because you would be trying to convince us that there is no dCPU coming, and that would be your "holy grail" of evidence. However, I am more willing to bet you have the official 2014 Desktop APU roadmap that everyone else has...

Another bet that you lose, because I have THE 2014 desktop roadmap and it appears one big CPU mentioned in it...

Well, I have it as well, I was given a link:

http://phx.corporate-ir.net/phoenix.zhtml?c=74093&p=irol-newsArticle&ID=1876132&highlight=

Scroll to the bottom and click on product roadmaps, open the .pdf and you will see the one that has "PILEDRIVER 2nd GENERATION FX SERIES" which is listed as the "PERFORMANCE PROCESSOR" category.

Ironically, Kaveri is not listed as a performance processor...I wonder why...maybe because, as my source intimated, AMD understands Kaveri is not for HEDT, as you seem to want to assert it is.

Yes I know. I have the roadmap, do you remember? And it shows AMD will continue selling old FXs.

Do you see it now? All your speculations about SR FX, Phenom return, AM4, FX replacement... vanished in the air.

The word "performance" also appears in the Kaveri row. And don't be confused but Kaveri is much more powerful than a FX-8350

FX-8350: 256 GFLOP
Kaveri: 118+738 = 856 GFLOP

It will be funny to do the first HSA benchmarks and show how Kaveri destroy a FX-8350 in a number of workloads.

 

[kansasboy001]

well the ONLY way kaveri will destroy an 8350 is with the iGPU. if you disable the iGPU the 8350 kills kaveri.

 

[juanrga]

Had you paid attention to APU13, you would have seen Oxide's presentation where they showed a ton of on screen objects and then ran a benchmark where FX 8350 at stock, FX 8350 at 2ghz, and i7 4770k were all performing the same and the 290x was a performance bottleneck.

Right!!! They mentioned how a 8350 @ 2GHz was able to compete with both i7-4770k and 8350 at stock freq.

We also know that

8350 @ 2 GHz ~ 4 SR cores @ 3.7GHz

which means that the CPU in Kaveri will perform like a FX-8350. As I said before the slide #13 given by AMD at October talk, showing an APU in close competition with FX-8350, was the prototype of benchmark that AMD was transmitting to OEMs.

This is the relevant slide of Oxide presentation at APU13

http://www.hardware.fr/medias/photos_news/00/43/IMG0043517_1.jpg?

The relevant bullet: "Blazing fast CPU not necessary, a mid-range CPU will be sufficiently fast to drive the best GPU"

Which confirms my previous claim that Kaveri APU will be able to run a R9 290X.

I also find it fascinating how Oxide showed a concrete example where MANTLE improved performance by 3x (200%) and still gamerk pretends that the DX overhead is at best of 10% :ROFL:

 

[Cazalan]

The FX-8350 to Kaveri comparisons are getting tired. They're different products, made on different processes, with significant TDP differences, for different market segments.

 

[juanrga]

well the ONLY way kaveri will destroy an 8350 is with the iGPU. if you disable the iGPU the 8350 kills kaveri.

Kaveri has up to 12 compute units. If you disable 8 of them then the chances are that the remaining 4 lose to the eight-cores of the 8350, except in workloads that are single, dual, triple, or quad threaded.

Previously I showed a leaked integer benchmark with four Kaveri cores outperforming four Piledriver FX cores. I attach it again:

 

[anxiousinfusion]

http://www.xbitlabs.com/picture/?src=/images/news/2013-11/amd_roadmap_desktop_2014.png

Anyone who is clinging to the legacy dCPU model is in for a surprise.