AMD CPU speculation... and expert conjecture

[juanrga]

You found another technologically outdated game that ignores extra cores: FX 8-core, 6 core, and 4-core perform very similarly.

And not to forget this is a Nvidia sponsored game.

Looks like they just re-compiled the engine to support AVX now, haha.

Take a look at the FX 4100 and the Phenom II 980 and the big jump the FX4320 is over both of them.

Cheers!

The difference between 4320 and 4100 is almost explained by the clock boost and the IPC gain BD->PD. No?

 

[8350rocks]

Spoiler

1. Your confusion about the word CISC was funny, but I was really referring to all the further nonsense that you posted against RISC/ARM.

2. The chip runs background processes to the game such as social stuff, recording, checking for online updates... it doesn't run the OS.

3. You said that that you "saw" PS4 benchmarks @2.6 Ghz, that you waited the "actual final specs will likely fall closer to the 2.4 mark, with possibly a turbo core feature to allow a higher clock under some instances that use fewer cores." Then you strongly misinterpreted the PS4 patents doc and said to everyone here that the CPU run at 2.75 GHz. Even hapidupi had to correct your nonsense. Hapidupi! LOL!

4. You claimed that bulk was impossible, that the people who said bulk was no working for AMD anymore, you insinuated that he didn't know the tech and pretended that the delay was caused by the migration to FD-SOI. When people complained. You did search and post a talk by Glofo and tried to convince us that FD-SOI was cheaper than bulk and AMD was going all SOI. "It is evident" you claimed...

5. Therefore you still insist on saying every novice that a SR FX 8-core CPU is coming for AM3+ and that AM3+ is a good platform for upgrade?

6. Easy. That is an ancient mobo with AM4 in the model code. Someone at the database did a mistake and indexed it as AM4 socket mobo. The rest is only in your imagination. It is not a new mobo with a new socket for a forthcoming 5GHz SR 8-core FX CPU...

I don't think you understand the points I was making about RISC/CISC, however, you don't have the architecture knowledge to understand it anyway. So, I am going to write this off as you simply don't understand. In gamer terms "Learn 2 Research".

My understanding is enough to detect your nonsense.

You did not read a word I said:

2. Sony has confirmed an additional chip on the PS4 to run background processes, and the design lead for the entire project stated the OS would be run primarily off the GPU leaving 8 cores available for developing games. Do you think Sony's project lead was lying? Why would he? That information will be verifiable easily...

Can you read it better now?
--------------------------------

This is the second time that I read your nonsense. The question is: do you read? I don't know what is more funny, that you write "GPU" or that you don't understand that the OS runs on the jaguar cores in the APU and that the secondary chip in the PS4 runs background tasks to the game, such as decoding, downloading, social stuff...

There were ES benchmarks run @ 2.6 GHz, Jaguar cores will actually clock quite a bit higher than that, you know that right? They were likely testing to see what the thermal limits and power consumption would be. I did say that I suspected it would end up closer to ~2.2-2.4 GHz, than the 1.6 GHz many were claiming. By the way, what is the clockspeed on the PS4 APU? Just curious...oh...that's right...it's 2.0 GHz. Who was right?

Hum, let us see you claimed the PS4 runs at 2.75GHz, but that was plain nonsense. Sony did claim 1.6Ghz; therefore, you are off by more than 1GHz or about 72% of error.

I never said bulk was impossible...I did say it was improbable, and that there would be massive clockspeed and thermal penalties to going bulk. I was not wrong on any of those counts. Your poor mastery of the English language is showing.

No. You said us it was SOI. Someone wrote:

I believe that the 28nm process used for SR and Kaveri will be bulk but I'm not sure.

And your answer was:

No, it will be a PD-SOI process...from GloFo.

One thing is that you are wrong, but another is that you pretend now to hide what you wrote during months.

I tell them a SR FX replacement is coming, I also tell them I have no idea what socket, or in that regard, much of any information about it at all.

No. You said us that Steamroller FX is AM3+ socket. Someone asked "8350 or wait for Steamroller?" and your answer was:

The good news is though, if you buy an AM3+ board and a new CPU, you won't need to buy a new board for steamroller, it will be AM3+.

I wonder how many newbies followed your advice, believing that you know what you are writing.

It could very easily be the case, *very* easily; however, Foxconn should not be advertising AM4 socket MB drivers when no such product clearly exists. I was a bit curious when I saw that...and pointed it out to you and a few others to confer. The consensus, that it was not what it looked like, was reached before you ever wrote back to me.

There is no AM4 sockect mobo on Foxconn. I already explained there is a mistake in their indexing of an ancient mobo, but please ignore facts and continue fantasizing. It is much more funny.

i will just leave it here :

http://amdfx.blogspot.com/2013/10/amd-kaveri-benchmarks-more-steamrolling.html

If legit, it confirms that SR is ~30% faster than BD. Precisely in my estimation of kaveri performance I assumed a 30% faster than BD (or ~20% faster than PD) to show that Kaveri CPU would be at the i5 level of performance.

The regression in FP could be related to SR using a simplified (streamlined) FPU. This is not a serious problem because SR comes in HSA APUs where the GPU will be used as a giant FPU.

They're probably tweaking it to prepare for 256 bit FMAC FPUs (AVX2 instructions) in excavator and running into some issues. That would be my guess...

At least now you make clear that you are guessing.... lol

256-bit FMAC units don't make any sense for me, but of course AMD can prove me wrong.

1.

•Thirdly, said Cerny, "The original AMD GCN architecture allowed for one source of graphics commands, and two sources of compute commands. For PS4, we’ve worked with AMD to increase the limit to 64 sources of compute commands -- the idea is if you have some asynchronous compute you want to perform, you put commands in one of these 64 queues, and then there are multiple levels of arbitration in the hardware to determine what runs, how it runs, and when it runs, alongside the graphics that's in the system."

"The reason so many sources of compute work are needed is that it isn’t just game systems that will be using compute -- middleware will have a need for compute as well. And the middleware requests for work on the GPU will need to be properly blended with game requests, and then finally properly prioritized relative to the graphics on a moment-by-moment basis."

http://www.gamasutra.com/view/feature/191007/inside_the_playstation_4_with_mark_.php?page=2

Maybe now you understand what GPU means...because the GPU is not an additional ARM core...

Unsurprisingly that is unrelated to what you wrote before about GPU and unrelated to your nonsense that the OS is run in a secondary chip and 8 jaguar cores are for games exclusively.

2.

RISC runs differently, and yes x86 CPUs have had underlying RISC architecture characteristics for a long time. Since the Pentium days really; however, as was pointed out by Palladin earlier, x86 allows MUCH larger instructions to be converted into bytecode to be run on the CPU itself.

The added complexity of x86 was my point. That is easily it's greatest strength while also being an inherent weakness.

ARM's strength and weakness both lie in it's simplicity. That's why it excels for low power devices and simple things like Micro Servers. It's also the primary reason it's not a terribly valid Desktop uarch option.

In order to make ARM a serious x86 competitor, you would have to add several layers of complexity. That complexity would drive up transistor counts and die complexity, requiring quad channel memory controllers, and many other things that draw more power. Once you've done that, you have an x86 competitor...that no longer consumes power like a mobile/low power solution. Because the added complexity draws more power, your consumption numbers spike upward dramatically.

x86 ISA has been dealing with this in it's architecture since x586 (K6-2 days). ARM has not had the benefit of time spent tweaking their architecture for such added complexities, and it takes a *LONG* time to get that stuff right. Which is part of what we see in the current AMD and Intel uarch's, Intel has a far more *REFINED* uarch, because it hasn't changed dramatically since P4 days. Where as AMD's uarch is only 2-3 years old at this point, and not nearly as well refined and tuned.

So, what you're talking about with ARM taking over DT, or even a large share of notebooks, etc., will not come about for quite some time.

The reasons for this are simple:

1.) Most of the consumer DT world runs on Windows, like it or not, M$ still has some clout. They don't want to redesign their OS entirely for ARM, and WART is a terrible execution.

2.) With no major OS player taking ARM seriously any time soon, hardware advances will come slowly because it's not in high demand. Only way ARM becomes a big player is if some large player in the PC world backs it and pushes hard. AMD making Micro Servers using ARM is not that push into the consumer sector you expect. It's a gimmick to say "see, we can do low power better than Intel", nothing more.

3.) Without a Major OS player backing ARM, the development of consumer software will be slow. Open source groups may do something, but how has that worked out for Linux so far? Outside of Android, it's still not terribly popular as an OS in the PC world considering roughly 3% of the world is likely running it on a DT PC. I think Linux should see more use than it does, but in the consumer space, M$ is still king.

4.) As ARM adds complexity, it will add power consumption, and the more you need to be able to ask the ISA to do, the more convoluted the hardware, middleware, software becomes to do those things. So, as the hardware adds complexity, the power draw increases. Once you get ARM running at a 50W+ TDP, x86 becomes a clear winner. Which is what would happen with a billion transistor ARM chip running at 4 GHz.

So, you may not like what I am saying, and you may disagree entirely. However, your declaration that ARM will rule desktop any time soon is a mere pipe dream...much like Acorn was back when it first started. That's why it's a non-profit organization that designs cores and licenses them, not an organization making chips and selling PCs.

That was my CISC vs. RISC rant...If you don't understand what I am talking about then that is your own fault for not knowing the difference between the 2.

That only covers a fraction of the nonsense that you have said about RISC and about ARM. Both that fraction and what you don't quote was corrected before.

3. PS4 runs @ ~2.0 GHz, which is 25% higher than the 1.6 GHz initially claimed. I also stated that there were ES's of the custom chip run @ 2.6 GHz, and there were.

(6) PS4 APU ES's have been benchmarked in the 2.4-2.6 GHz range already. I don't anticipate they will necessarily end up at 2.6 GHz, though I think 2.2-2.4 GHz with a turbo core for less threaded situations is entirely feasible.

http://www.tomshardware.com/forum/id-1721986/amd-cpu-performance-increase-nextgen-consoles-release.html

Sony said 1.6Ghz for the PS4. The 2.0Ghz is only a rumor. Moreover both are far from your previous pretension that it runs a 2.75Ghz. The funny part is that hapidupi was right and you wrong. LOL

4. Look at how old that thread is...seriously? We had less information then, than we do now...and we don't know much now. That was purely speculation based on expectations of current trends continuing from FX. You had some posts from 6 months ago saying things that we now know to be different from reality as well. I am not going to waste time digging them up...but they are there for sure.

LOL. A pair of posts ago you affirmed that you never said such thing. Now the excuse change to ups I said but that is old

5. Are you dense? Read what I wrote...it was determined that it was not, in fact, AM4 MB before you ever wrote me back. Blackkstar and I came to that conclusion before you ever replied to me.

Seeing as you pretended above to hide what you wrote, do you really pretend I to trust what you claim you were thinking one day? LOL

You clearly did not read what I wrote...how long are you going to continue this blatant ignorance?

Does anyone else want to explain to juanrga what I said?

What is your native language? It's clearly not English because you don't understand it very well. Where did I say 2.75 GHz in the post? You reference topics from May, and claim that it's relevant since the information we had at the time changed. You also said exactly what I did at that time, because that's what we knew then. Now, you would deny that you were prepared for AM3+ steamroller on FD-SOI????

 

[blackkstar]

You found another technologically outdated game that ignores extra cores: FX 8-core, 6 core, and 4-core perform very similarly.

And not to forget this is a Nvidia sponsored game.

Looks like they just re-compiled the engine to support AVX now, haha.

Take a look at the FX 4100 and the Phenom II 980 and the big jump the FX4320 is over both of them.

Cheers!

The difference between 4320 and 4100 is almost explained by the clock boost and the IPC gain BD->PD. No?

Recompiling is a fickle beast.

Best case I saw was a more than doubling of speed with Blender. Worst case I saw was hardly any gain in firefox (around 5%).

Recompiling CAN give you massive results and it can do absolutely nothing.

It is really too difficult to tell if that difference is due to BD architecture or new instructions being used.

Although, about that leak running a t1.8ghz. Let me help you guys with something I didn't notice before.

AMD Eng Sample: 1M186092H4468_23/18/14/05_1304h

See that M?

Take look here: http://en.wikipedia.org/wiki/List_of_AMD_Accelerated_Processing_Unit_microprocessors#Comal_-_.22Trinity.22_.282012.2C_32_nm.29_2

See A10 desktop APUs have their second letter as a D?

See mobile APUs have second letter as M?

This chip is a 1.8ghz laptop part. However I still have no explanation for 2.9ghz 7800k part.

 

[Cazalan]

This chip is a 1.8ghz laptop part. However I still have no explanation for 2.9ghz 7800k part.

If the GPU clock speeds are accurate it's likely to accommodate that and still fit at 95W.

 

[designasaurus]

Shows a point I've been making for about 4 years now: More cores != more performance. Also shows relative scaling between various chips, and the continuing trend of Intel outperforming AMD. FX-8350 trading blows...with an i3 3220. Heck, even games like BF4 have higher tier i3s being competitive with AMD's mid-range chips.

I'll say it again: If AMD doesn't get its IPC problem fixed, they are going to go away.

If that's your point then you need a different benchmark. The quad-core FX is markedly slower than the octo-core FX, despite running at the same clockspeed. More cores does matter for AMD.

Aside from that, it is a terrible benchmark setup to begin with. A bottlenecking test is only useful if it represents something that might be seen in the real world. Running a Titan at 1080p is not a realistic scenario, at least not one that should be encouraged by anyone except Nvidia's Marketing Dept.

Even the results aren't good. Average fps, but nothing else? At least include minimum fps so people can see under the hood a bit. It's really a bad test setup, which results in minimal information to be gained from the result. If you're doing a bottlenecking test, use a setup that might see use in the real world. For 1080p, test using a card that is known to run 1080p easily, i.e. a Radeon 7870 or a GTX 580. Otherwise it's almost meaningless.

 

[tracker45]

okay.

 

[palladin9479]

I've started to use minimum FPS on any modern game (the above game is not modern in the slightest). Modern games are using a dynamic threading concept, you still have your two primary threads but also have dozens of other threads that do work on demand. You can see it in Crysis 3, BF3 and it's really apparent in BF4. Looking at the sky or wondering around a village with vegetation doesn't use much beyond ~3 cores worth of power. Once environmental interactions, explosions and physics start going on you see the extra cores shoot up in utilization. What matters is the performance during a large firefight, not the performance while your sightseeing.

 

[8350rocks]

If that was a 7800k part, I would imagine it's one of 2 things:

1. That was something akin to a "beta" ES ramping up clockspeeds.

OR

2. That is the result of the wonderful decision to go bulk wafers, and they will likely be chewing on that for a while, meanwhile, the product will bomb with laptop CPU-esque clockspeeds. They will try to sell the daylights out of HSA if that is how the yields turn out...but it won't matter. They'd need a good 75% increase in the instruction efficiency category to compete or be slightly ahead at lower clocks.

 

[blackkstar]

This chip is a 1.8ghz laptop part. However I still have no explanation for 2.9ghz 7800k part.

If the GPU clock speeds are accurate it's likely to accommodate that and still fit at 95W.

7800k designations would most likely mean top apu @100 watts but that 2.9 clock rate is interesting. Has amd equaled intels ipc, and no longer needs higher clocks to compete ?
http://tinyurl.com/ns9b24n

Someone at OCN who reads Italian stated that the 2.9ghz is not final clockspeed as that was claimed somewhere in (edit) another article.

We, to simplify, we will use the name "A10-7800K."

Basically, at least one part of "A10-7800k runs at 2.9ghz" is false.

 

[blackkstar]

There is no official announcement on the name, calling it a 7800k apu would be obvious until it is official, According to the link 2.9 is the base, turbo core is 3.2. Maybe they are saving the high clocks for there steamroller cpu only.

The article basically said "we don't know what this is so lets call it A10 7800k"

Pretty good way to get a ton of page views for people who don't read the article (I did this first as well).

 

[juanrga]

Spoiler

1. Your confusion about the word CISC was funny, but I was really referring to all the further nonsense that you posted against RISC/ARM.

2. The chip runs background processes to the game such as social stuff, recording, checking for online updates... it doesn't run the OS.

3. You said that that you "saw" PS4 benchmarks @2.6 Ghz, that you waited the "actual final specs will likely fall closer to the 2.4 mark, with possibly a turbo core feature to allow a higher clock under some instances that use fewer cores." Then you strongly misinterpreted the PS4 patents doc and said to everyone here that the CPU run at 2.75 GHz. Even hapidupi had to correct your nonsense. Hapidupi! LOL!

4. You claimed that bulk was impossible, that the people who said bulk was no working for AMD anymore, you insinuated that he didn't know the tech and pretended that the delay was caused by the migration to FD-SOI. When people complained. You did search and post a talk by Glofo and tried to convince us that FD-SOI was cheaper than bulk and AMD was going all SOI. "It is evident" you claimed...

5. Therefore you still insist on saying every novice that a SR FX 8-core CPU is coming for AM3+ and that AM3+ is a good platform for upgrade?

6. Easy. That is an ancient mobo with AM4 in the model code. Someone at the database did a mistake and indexed it as AM4 socket mobo. The rest is only in your imagination. It is not a new mobo with a new socket for a forthcoming 5GHz SR 8-core FX CPU...

I don't think you understand the points I was making about RISC/CISC, however, you don't have the architecture knowledge to understand it anyway. So, I am going to write this off as you simply don't understand. In gamer terms "Learn 2 Research".

My understanding is enough to detect your nonsense.

You did not read a word I said:

2. Sony has confirmed an additional chip on the PS4 to run background processes, and the design lead for the entire project stated the OS would be run primarily off the GPU leaving 8 cores available for developing games. Do you think Sony's project lead was lying? Why would he? That information will be verifiable easily...

Can you read it better now?
--------------------------------

This is the second time that I read your nonsense. The question is: do you read? I don't know what is more funny, that you write "GPU" or that you don't understand that the OS runs on the jaguar cores in the APU and that the secondary chip in the PS4 runs background tasks to the game, such as decoding, downloading, social stuff...

There were ES benchmarks run @ 2.6 GHz, Jaguar cores will actually clock quite a bit higher than that, you know that right? They were likely testing to see what the thermal limits and power consumption would be. I did say that I suspected it would end up closer to ~2.2-2.4 GHz, than the 1.6 GHz many were claiming. By the way, what is the clockspeed on the PS4 APU? Just curious...oh...that's right...it's 2.0 GHz. Who was right?

Hum, let us see you claimed the PS4 runs at 2.75GHz, but that was plain nonsense. Sony did claim 1.6Ghz; therefore, you are off by more than 1GHz or about 72% of error.

I never said bulk was impossible...I did say it was improbable, and that there would be massive clockspeed and thermal penalties to going bulk. I was not wrong on any of those counts. Your poor mastery of the English language is showing.

No. You said us it was SOI. Someone wrote:

I believe that the 28nm process used for SR and Kaveri will be bulk but I'm not sure.

And your answer was:

No, it will be a PD-SOI process...from GloFo.

One thing is that you are wrong, but another is that you pretend now to hide what you wrote during months.

I tell them a SR FX replacement is coming, I also tell them I have no idea what socket, or in that regard, much of any information about it at all.

No. You said us that Steamroller FX is AM3+ socket. Someone asked "8350 or wait for Steamroller?" and your answer was:

The good news is though, if you buy an AM3+ board and a new CPU, you won't need to buy a new board for steamroller, it will be AM3+.

I wonder how many newbies followed your advice, believing that you know what you are writing.

It could very easily be the case, *very* easily; however, Foxconn should not be advertising AM4 socket MB drivers when no such product clearly exists. I was a bit curious when I saw that...and pointed it out to you and a few others to confer. The consensus, that it was not what it looked like, was reached before you ever wrote back to me.

There is no AM4 sockect mobo on Foxconn. I already explained there is a mistake in their indexing of an ancient mobo, but please ignore facts and continue fantasizing. It is much more funny.

i will just leave it here :

http://amdfx.blogspot.com/2013/10/amd-kaveri-benchmarks-more-steamrolling.html

If legit, it confirms that SR is ~30% faster than BD. Precisely in my estimation of kaveri performance I assumed a 30% faster than BD (or ~20% faster than PD) to show that Kaveri CPU would be at the i5 level of performance.

The regression in FP could be related to SR using a simplified (streamlined) FPU. This is not a serious problem because SR comes in HSA APUs where the GPU will be used as a giant FPU.

They're probably tweaking it to prepare for 256 bit FMAC FPUs (AVX2 instructions) in excavator and running into some issues. That would be my guess...

At least now you make clear that you are guessing.... lol

256-bit FMAC units don't make any sense for me, but of course AMD can prove me wrong.

1.

•Thirdly, said Cerny, "The original AMD GCN architecture allowed for one source of graphics commands, and two sources of compute commands. For PS4, we’ve worked with AMD to increase the limit to 64 sources of compute commands -- the idea is if you have some asynchronous compute you want to perform, you put commands in one of these 64 queues, and then there are multiple levels of arbitration in the hardware to determine what runs, how it runs, and when it runs, alongside the graphics that's in the system."

"The reason so many sources of compute work are needed is that it isn’t just game systems that will be using compute -- middleware will have a need for compute as well. And the middleware requests for work on the GPU will need to be properly blended with game requests, and then finally properly prioritized relative to the graphics on a moment-by-moment basis."

http://www.gamasutra.com/view/feature/191007/inside_the_playstation_4_with_mark_.php?page=2

Maybe now you understand what GPU means...because the GPU is not an additional ARM core...

Unsurprisingly that is unrelated to what you wrote before about GPU and unrelated to your nonsense that the OS is run in a secondary chip and 8 jaguar cores are for games exclusively.

2.

RISC runs differently, and yes x86 CPUs have had underlying RISC architecture characteristics for a long time. Since the Pentium days really; however, as was pointed out by Palladin earlier, x86 allows MUCH larger instructions to be converted into bytecode to be run on the CPU itself.

The added complexity of x86 was my point. That is easily it's greatest strength while also being an inherent weakness.

ARM's strength and weakness both lie in it's simplicity. That's why it excels for low power devices and simple things like Micro Servers. It's also the primary reason it's not a terribly valid Desktop uarch option.

In order to make ARM a serious x86 competitor, you would have to add several layers of complexity. That complexity would drive up transistor counts and die complexity, requiring quad channel memory controllers, and many other things that draw more power. Once you've done that, you have an x86 competitor...that no longer consumes power like a mobile/low power solution. Because the added complexity draws more power, your consumption numbers spike upward dramatically.

x86 ISA has been dealing with this in it's architecture since x586 (K6-2 days). ARM has not had the benefit of time spent tweaking their architecture for such added complexities, and it takes a *LONG* time to get that stuff right. Which is part of what we see in the current AMD and Intel uarch's, Intel has a far more *REFINED* uarch, because it hasn't changed dramatically since P4 days. Where as AMD's uarch is only 2-3 years old at this point, and not nearly as well refined and tuned.

So, what you're talking about with ARM taking over DT, or even a large share of notebooks, etc., will not come about for quite some time.

The reasons for this are simple:

1.) Most of the consumer DT world runs on Windows, like it or not, M$ still has some clout. They don't want to redesign their OS entirely for ARM, and WART is a terrible execution.

2.) With no major OS player taking ARM seriously any time soon, hardware advances will come slowly because it's not in high demand. Only way ARM becomes a big player is if some large player in the PC world backs it and pushes hard. AMD making Micro Servers using ARM is not that push into the consumer sector you expect. It's a gimmick to say "see, we can do low power better than Intel", nothing more.

3.) Without a Major OS player backing ARM, the development of consumer software will be slow. Open source groups may do something, but how has that worked out for Linux so far? Outside of Android, it's still not terribly popular as an OS in the PC world considering roughly 3% of the world is likely running it on a DT PC. I think Linux should see more use than it does, but in the consumer space, M$ is still king.

4.) As ARM adds complexity, it will add power consumption, and the more you need to be able to ask the ISA to do, the more convoluted the hardware, middleware, software becomes to do those things. So, as the hardware adds complexity, the power draw increases. Once you get ARM running at a 50W+ TDP, x86 becomes a clear winner. Which is what would happen with a billion transistor ARM chip running at 4 GHz.

So, you may not like what I am saying, and you may disagree entirely. However, your declaration that ARM will rule desktop any time soon is a mere pipe dream...much like Acorn was back when it first started. That's why it's a non-profit organization that designs cores and licenses them, not an organization making chips and selling PCs.

That was my CISC vs. RISC rant...If you don't understand what I am talking about then that is your own fault for not knowing the difference between the 2.

That only covers a fraction of the nonsense that you have said about RISC and about ARM. Both that fraction and what you don't quote was corrected before.

3. PS4 runs @ ~2.0 GHz, which is 25% higher than the 1.6 GHz initially claimed. I also stated that there were ES's of the custom chip run @ 2.6 GHz, and there were.

(6) PS4 APU ES's have been benchmarked in the 2.4-2.6 GHz range already. I don't anticipate they will necessarily end up at 2.6 GHz, though I think 2.2-2.4 GHz with a turbo core for less threaded situations is entirely feasible.

http://www.tomshardware.com/forum/id-1721986/amd-cpu-performance-increase-nextgen-consoles-release.html

Sony said 1.6Ghz for the PS4. The 2.0Ghz is only a rumor. Moreover both are far from your previous pretension that it runs a 2.75Ghz. The funny part is that hapidupi was right and you wrong. LOL

4. Look at how old that thread is...seriously? We had less information then, than we do now...and we don't know much now. That was purely speculation based on expectations of current trends continuing from FX. You had some posts from 6 months ago saying things that we now know to be different from reality as well. I am not going to waste time digging them up...but they are there for sure.

LOL. A pair of posts ago you affirmed that you never said such thing. Now the excuse change to ups I said but that is old

5. Are you dense? Read what I wrote...it was determined that it was not, in fact, AM4 MB before you ever wrote me back. Blackkstar and I came to that conclusion before you ever replied to me.

Seeing as you pretended above to hide what you wrote, do you really pretend I to trust what you claim you were thinking one day? LOL

You clearly did not read what I wrote...how long are you going to continue this blatant ignorance?

Does anyone else want to explain to juanrga what I said?

What is your native language? It's clearly not English because you don't understand it very well. Where did I say 2.75 GHz in the post? You reference topics from May, and claim that it's relevant since the information we had at the time changed. You also said exactly what I did at that time, because that's what we knew then. Now, you would deny that you were prepared for AM3+ steamroller on FD-SOI????

You can try that tactic, you can pretend that you never said so or when caught with a quote, you can pretend that you said it in "May", but not latter. However. it is not a wise thing to do, because I can link to your posts.

Look at this one, you said that the PS4 is clocked at 2.75Ghz, someone corrects you and explain you that 2.75 is the freq. of the memory and that the CPU is clocked at 1.6GHz. Your typical ignorant answer was

http://www.tomshardware.co.uk/forum/352312-28-steamroller-speculation-expert-conjecture/page-138#11425669

Now pay attention to the next message after yours, where the same person corrects you again and explain you again that 2.75 is the memory freq. Your reply to him was again "NO".

You were plain wrong for days. I had to confirm here

http://www.tomshardware.co.uk/forum/352312-28-steamroller-speculation-expert-conjecture/page-141#11457221

that 2.75Ghz is the WCK of the memory, and that the freq. of the CPU is 1.6GHz. My post was followed by a series of funny replies.

Did you learn anything? Nope. Because days latter you wrote:

It has already been all but confirmed that the APUs will be running closer to ~2.0-2.2 GHz for the XBone and PS4. If you think that number won't increase over time, you're far more naïve than I thought. Just because the memory is clocked at one frequency has nothing to do with CPU clockspeed.

Microsoft has confirmed that Xbox1 is clocked at 1.75GHz. But you continue posting misleading info.

About SOI. So late as September I wrote that Kaveri/SR is bulk:

http://www.tomshardware.co.uk/forum/352312-28-steamroller-speculation-expert-conjecture/page-142#11461096

This generate a series of answers from several experts (including you) trying to convince me that Kaveri was being made on SOI process. Some quotes:

My thoughts run to doing it on SOI, as JK was a big proponent of the K7/K8 going to SOI originally.

Other sources would even say their 22nm FinFET on bulk was actually lackluster compared to the projections...though that would mean I am right about bulk vs. SOI and you'd be wrong about the delay from AMD for Kaveri. Thus, I don't anticipate you'll acknowledge that.

Until i asked you "If you have one source that says that Kaveri is being manufactured on SOI process, please share it with us." Your answers:

You can't follow the link to the SOI conference anymore, however, shortly after AMD announced going bulk over a year ago, they then fired a bunch of people (those that spoke of bulk included) and then they were talking to GF a month later about FD-SOI @ 28nm at the global SOI conference...you do the math.

You insisted with your it is SOI, SOI is ready, AMD is talking about SOI... My answer:

http://www.tomshardware.co.uk/forum/352312-28-steamroller-speculation-expert-conjecture/page-142#11467899

and during page 143 you continued claiming your confidence in that was SOI, because SOI was ready, trololo

You can now pretend that you never said that Steamroller is AM3+, that you never said that Kaveri/SR is SOI, that you never said that PS4 clock is 2.75Ghz, that you never said that Xbone ~2.0--2.2GHz, that you never said that PhysX is not in PS4, that you never said...

You can pretend that you said those in "May", but not latter. The problem is that your posts show otherwise.

 

[juanrga]

Spoiler

You found another technologically outdated game that ignores extra cores: FX 8-core, 6 core, and 4-core perform very similarly.

And not to forget this is a Nvidia sponsored game.

Looks like they just re-compiled the engine to support AVX now, haha.

Take a look at the FX 4100 and the Phenom II 980 and the big jump the FX4320 is over both of them.

Cheers!

The difference between 4320 and 4100 is almost explained by the clock boost and the IPC gain BD->PD. No?

Recompiling is a fickle beast.

Best case I saw was a more than doubling of speed with Blender. Worst case I saw was hardly any gain in firefox (around 5%).

Recompiling CAN give you massive results and it can do absolutely nothing.

It is really too difficult to tell if that difference is due to BD architecture or new instructions being used.

Although, about that leak running a t1.8ghz. Let me help you guys with something I didn't notice before.

AMD Eng Sample: 1M186092H4468_23/18/14/05_1304h

See that M?

Take look here: http://en.wikipedia.org/wiki/List_of_AMD_Accelerated_Processing_Unit_microprocessors#Comal_-_.22Trinity.22_.282012.2C_32_nm.29_2

See A10 desktop APUs have their second letter as a D?

See mobile APUs have second letter as M?

This chip is a 1.8ghz laptop part. However I still have no explanation for 2.9ghz 7800k part.

Yes, my complain was about the supposed desktop APU with 2.9GHz for CPU and 1.1--1.2GHz for the GPU. Those frequencies make no sense at all. They even disagree with 1050 GFLOP given by AMD labs.

My red flags raised when the same source that gave those freq. added that frequencies are not decided still

 

[gamerk316]

I'll just post this:

http://www.techspot.com/review/733-batman-arkham-origins-benchmarks/page5.html

Spoiler

So if you run a Titan at 1080p, probably any 2+ core cpu from the last 6 years will run Batman at ~60fps average at those settings. Great? Or is the point that any Piledriver cpu with 2M+ will max out a 120Hz monitor? My point is that it'd be nice if you could elaborate how this relates to Steamroller (or any of the many off-topic topics in this thread) rather than just posting a weird benchmark.

Shows a point I've been making for about 4 years now: More cores != more performance. Also shows relative scaling between various chips, and the continuing trend of Intel outperforming AMD. FX-8350 trading blows...with an i3 3220. Heck, even games like BF4 have higher tier i3s being competitive with AMD's mid-range chips.

I'll say it again: If AMD doesn't get its IPC problem fixed, they are going to go away.

The problem children you point at mostly are games running on long in the tooth engines that are nearing the end of their life cycles, but hung on because there are lots of less powerful PCs in the world still.

Plus, it's quite a bit cheaper to develop on UDK3 versus UDK4.

Arkham series started on UDK3, and stayed with it to reuse the source code as much as possible, and maintain continuity. They've basically done as much as they can on UDK3 at this point. I expect that UDK3 will not produce any more AAA titles as UDK4 is becoming more proliferated now, and it runs on multiple cores well.

UDK3 was great when we were talking about Athlon 2 6400+ processors...it's outdated now though. That's why modern GPUs can run it at 120+ FPS with a modern processor...which is entirely overkill considering better than 80% of the monitors out there won't even support better than 60 FPS @ 1080p.

You're pointing at archaic software and saying, "see IPC is most important". Reality is, software still lags behind hardware, and the world turns another revolution. Efficiency of instruction processing is moderately important, but handling multiple threads at once will become more important as the paradigm shifts with this generation of consoles.

Out of curiosity, how is the engine "outdated"? Its still capable of outputting top tier visuals, handling every major Physics engine out there, and unlike everyone elses engines, does it at greater then 60 FPS.

Granted, its aged, but Unreal 3 is still quite the viable game engine to work with.

 

[juanrga]

Not the first time it has happened. Everyone is looking. This could be a 65watt part or even a dual core to explain the clock speed. Did the bulk process cost that much in clock speed to get satisfactory yields ?

According to the source that is the top 100W quad-core APU. I don't trust them, because they freq don't match with the performance measured by AMD labs and because they claim that the freq. that they report are not still decided.

Glofo already has ~3.6 GHz on bulk and according to some sources, them have been tweaking SR on bulk for almost one year for improving yields and freq.

Note: if AMD is able to obtain the same performance with 1GHz less, that is welcomed, of course. But it is difficult to believe that could obtain 50% IPC in a single gen. Time will say.

 

[gamerk316]

If that's your point then you need a different benchmark. The quad-core FX is markedly slower than the octo-core FX, despite running at the same clockspeed. More cores does matter for AMD.

Emphasis mine. More cores matter more for AMD because, with only four cores, they are getting totally overloaded due to their poor IPC. As a result, if even ONE core gets loaded, performance tanks. Hence why AMD's performance tends to scale linearly as you OC. Intel quads, by contrast, don't have that problem (for the most part) at base clocks, hence why OCing tends to offer less performance increase (no bottleneck to remove).

Hence why games like BF4, where AMD gains significant performance as more cores are added, yet Intel performance is still sorted largely by IPC + Clock performance, and also why Intel tends to maintain its gaming lead.

See:
http://www.bf4blog.com/battlefield-4-retail-gpu-cpu-benchmarks/
http://pclab.pl/art55318-3.html

FX-8350 ~ i5 2500k in BF4, despite how well threaded it is. That's how superior IPC is better for overall performance in a nutshell. For Intel, more cores essentially just lowers overall core loading, since its high tier i5's aren't bottlenecked.

This was my exact argument against BD from the very beginning, and three years in, AMD still can't beat SB i7's. Even in games using over a dozen threads, like BF4, AMD still looses, or at best, matches Intel, head to head.

 

[juanrga]

More cores matter more for AMD because, with only four cores, they are getting totally overloaded due to their poor IPC. As a result, if even ONE core gets loaded, performance tanks. Hence why AMD's performance tends to scale linearly as you OC. Intel quads, by contrast, don't have that problem (for the most part) at base clocks, hence why OCing tends to offer less performance increase (no bottleneck to remove).

Hence why games like BF4, where AMD gains significant performance as more cores are added, yet Intel performance is still sorted largely by IPC + Clock performance, and also why Intel tends to maintain its gaming lead.

See:
http://www.bf4blog.com/battlefield-4-retail-gpu-cpu-benchmarks/
http://pclab.pl/art55318-3.html

FX-8350 ~ i5 2500k in BF4, despite how well threaded it is. That's how superior IPC is better for overall performance in a nutshell. For Intel, more cores essentially just lowers overall core loading, since its high tier i5's aren't bottlenecked.

This was my exact argument against BD from the very beginning, and three years in, AMD still can't beat SB i7's. Even in games using over a dozen threads, like BF4, AMD still looses, or at best, matches Intel, head to head.

Your prediction, before BF4 beta was released was that 8350 would perform as an i3. You are now changing to an i5, but benchmarks show how the 8350 performs like an i7

FX-8350 ~ i7 2600k in BF4.

 

[palladin9479]

If that's your point then you need a different benchmark. The quad-core FX is markedly slower than the octo-core FX, despite running at the same clockspeed. More cores does matter for AMD.

Emphasis mine. More cores matter more for AMD because, with only four cores, they are getting totally overloaded due to their poor IPC. As a result, if even ONE core gets loaded, performance tanks. Hence why AMD's performance tends to scale linearly as you OC. Intel quads, by contrast, don't have that problem (for the most part) at base clocks, hence why OCing tends to offer less performance increase (no bottleneck to remove).

Hence why games like BF4, where AMD gains significant performance as more cores are added, yet Intel performance is still sorted largely by IPC + Clock performance, and also why Intel tends to maintain its gaming lead.

See:
http://www.bf4blog.com/battlefield-4-retail-gpu-cpu-benchmarks/
http://pclab.pl/art55318-3.html

FX-8350 ~ i5 2500k in BF4, despite how well threaded it is. That's how superior IPC is better for overall performance in a nutshell. For Intel, more cores essentially just lowers overall core loading, since its high tier i5's aren't bottlenecked.

This was my exact argument against BD from the very beginning, and three years in, AMD still can't beat SB i7's. Even in games using over a dozen threads, like BF4, AMD still looses, or at best, matches Intel, head to head.

Umm did you actually look at the benchmarks you posted? The FX8350 beats the i5 and is within the i7 range, especially if you remember minimum FPS is far more important the average.

BF4 is following the same tactic that BF3 and C3 did with using ~2 primary threads and then loading additional work onto the extra threads as needed. Walking around a village looking at scenery is a rather useless metric when the real experience will be during combat which is where the additional cores are loaded. Its the dynamic environmental interaction that's using the extra cores, something that is fairly parallel friendly to do. I'm waiting to see intense multi-player action (after release), I expect we'll see the same repeat of the BF3 scenario.

 

[8350rocks]

Spoiler

1. Your confusion about the word CISC was funny, but I was really referring to all the further nonsense that you posted against RISC/ARM.

2. The chip runs background processes to the game such as social stuff, recording, checking for online updates... it doesn't run the OS.

3. You said that that you "saw" PS4 benchmarks @2.6 Ghz, that you waited the "actual final specs will likely fall closer to the 2.4 mark, with possibly a turbo core feature to allow a higher clock under some instances that use fewer cores." Then you strongly misinterpreted the PS4 patents doc and said to everyone here that the CPU run at 2.75 GHz. Even hapidupi had to correct your nonsense. Hapidupi! LOL!

4. You claimed that bulk was impossible, that the people who said bulk was no working for AMD anymore, you insinuated that he didn't know the tech and pretended that the delay was caused by the migration to FD-SOI. When people complained. You did search and post a talk by Glofo and tried to convince us that FD-SOI was cheaper than bulk and AMD was going all SOI. "It is evident" you claimed...

5. Therefore you still insist on saying every novice that a SR FX 8-core CPU is coming for AM3+ and that AM3+ is a good platform for upgrade?

6. Easy. That is an ancient mobo with AM4 in the model code. Someone at the database did a mistake and indexed it as AM4 socket mobo. The rest is only in your imagination. It is not a new mobo with a new socket for a forthcoming 5GHz SR 8-core FX CPU...

I don't think you understand the points I was making about RISC/CISC, however, you don't have the architecture knowledge to understand it anyway. So, I am going to write this off as you simply don't understand. In gamer terms "Learn 2 Research".

My understanding is enough to detect your nonsense.

You did not read a word I said:

2. Sony has confirmed an additional chip on the PS4 to run background processes, and the design lead for the entire project stated the OS would be run primarily off the GPU leaving 8 cores available for developing games. Do you think Sony's project lead was lying? Why would he? That information will be verifiable easily...

Can you read it better now?
--------------------------------

This is the second time that I read your nonsense. The question is: do you read? I don't know what is more funny, that you write "GPU" or that you don't understand that the OS runs on the jaguar cores in the APU and that the secondary chip in the PS4 runs background tasks to the game, such as decoding, downloading, social stuff...

There were ES benchmarks run @ 2.6 GHz, Jaguar cores will actually clock quite a bit higher than that, you know that right? They were likely testing to see what the thermal limits and power consumption would be. I did say that I suspected it would end up closer to ~2.2-2.4 GHz, than the 1.6 GHz many were claiming. By the way, what is the clockspeed on the PS4 APU? Just curious...oh...that's right...it's 2.0 GHz. Who was right?

Hum, let us see you claimed the PS4 runs at 2.75GHz, but that was plain nonsense. Sony did claim 1.6Ghz; therefore, you are off by more than 1GHz or about 72% of error.

I never said bulk was impossible...I did say it was improbable, and that there would be massive clockspeed and thermal penalties to going bulk. I was not wrong on any of those counts. Your poor mastery of the English language is showing.

No. You said us it was SOI. Someone wrote:

I believe that the 28nm process used for SR and Kaveri will be bulk but I'm not sure.

And your answer was:

No, it will be a PD-SOI process...from GloFo.

One thing is that you are wrong, but another is that you pretend now to hide what you wrote during months.

I tell them a SR FX replacement is coming, I also tell them I have no idea what socket, or in that regard, much of any information about it at all.

No. You said us that Steamroller FX is AM3+ socket. Someone asked "8350 or wait for Steamroller?" and your answer was:

The good news is though, if you buy an AM3+ board and a new CPU, you won't need to buy a new board for steamroller, it will be AM3+.

I wonder how many newbies followed your advice, believing that you know what you are writing.

It could very easily be the case, *very* easily; however, Foxconn should not be advertising AM4 socket MB drivers when no such product clearly exists. I was a bit curious when I saw that...and pointed it out to you and a few others to confer. The consensus, that it was not what it looked like, was reached before you ever wrote back to me.

There is no AM4 sockect mobo on Foxconn. I already explained there is a mistake in their indexing of an ancient mobo, but please ignore facts and continue fantasizing. It is much more funny.

i will just leave it here :

http://amdfx.blogspot.com/2013/10/amd-kaveri-benchmarks-more-steamrolling.html

If legit, it confirms that SR is ~30% faster than BD. Precisely in my estimation of kaveri performance I assumed a 30% faster than BD (or ~20% faster than PD) to show that Kaveri CPU would be at the i5 level of performance.

The regression in FP could be related to SR using a simplified (streamlined) FPU. This is not a serious problem because SR comes in HSA APUs where the GPU will be used as a giant FPU.

They're probably tweaking it to prepare for 256 bit FMAC FPUs (AVX2 instructions) in excavator and running into some issues. That would be my guess...

At least now you make clear that you are guessing.... lol

256-bit FMAC units don't make any sense for me, but of course AMD can prove me wrong.

1.

•Thirdly, said Cerny, "The original AMD GCN architecture allowed for one source of graphics commands, and two sources of compute commands. For PS4, we’ve worked with AMD to increase the limit to 64 sources of compute commands -- the idea is if you have some asynchronous compute you want to perform, you put commands in one of these 64 queues, and then there are multiple levels of arbitration in the hardware to determine what runs, how it runs, and when it runs, alongside the graphics that's in the system."

"The reason so many sources of compute work are needed is that it isn’t just game systems that will be using compute -- middleware will have a need for compute as well. And the middleware requests for work on the GPU will need to be properly blended with game requests, and then finally properly prioritized relative to the graphics on a moment-by-moment basis."

http://www.gamasutra.com/view/feature/191007/inside_the_playstation_4_with_mark_.php?page=2

Maybe now you understand what GPU means...because the GPU is not an additional ARM core...

Unsurprisingly that is unrelated to what you wrote before about GPU and unrelated to your nonsense that the OS is run in a secondary chip and 8 jaguar cores are for games exclusively.

2.

RISC runs differently, and yes x86 CPUs have had underlying RISC architecture characteristics for a long time. Since the Pentium days really; however, as was pointed out by Palladin earlier, x86 allows MUCH larger instructions to be converted into bytecode to be run on the CPU itself.

The added complexity of x86 was my point. That is easily it's greatest strength while also being an inherent weakness.

ARM's strength and weakness both lie in it's simplicity. That's why it excels for low power devices and simple things like Micro Servers. It's also the primary reason it's not a terribly valid Desktop uarch option.

In order to make ARM a serious x86 competitor, you would have to add several layers of complexity. That complexity would drive up transistor counts and die complexity, requiring quad channel memory controllers, and many other things that draw more power. Once you've done that, you have an x86 competitor...that no longer consumes power like a mobile/low power solution. Because the added complexity draws more power, your consumption numbers spike upward dramatically.

x86 ISA has been dealing with this in it's architecture since x586 (K6-2 days). ARM has not had the benefit of time spent tweaking their architecture for such added complexities, and it takes a *LONG* time to get that stuff right. Which is part of what we see in the current AMD and Intel uarch's, Intel has a far more *REFINED* uarch, because it hasn't changed dramatically since P4 days. Where as AMD's uarch is only 2-3 years old at this point, and not nearly as well refined and tuned.

So, what you're talking about with ARM taking over DT, or even a large share of notebooks, etc., will not come about for quite some time.

The reasons for this are simple:

1.) Most of the consumer DT world runs on Windows, like it or not, M$ still has some clout. They don't want to redesign their OS entirely for ARM, and WART is a terrible execution.

2.) With no major OS player taking ARM seriously any time soon, hardware advances will come slowly because it's not in high demand. Only way ARM becomes a big player is if some large player in the PC world backs it and pushes hard. AMD making Micro Servers using ARM is not that push into the consumer sector you expect. It's a gimmick to say "see, we can do low power better than Intel", nothing more.

3.) Without a Major OS player backing ARM, the development of consumer software will be slow. Open source groups may do something, but how has that worked out for Linux so far? Outside of Android, it's still not terribly popular as an OS in the PC world considering roughly 3% of the world is likely running it on a DT PC. I think Linux should see more use than it does, but in the consumer space, M$ is still king.

4.) As ARM adds complexity, it will add power consumption, and the more you need to be able to ask the ISA to do, the more convoluted the hardware, middleware, software becomes to do those things. So, as the hardware adds complexity, the power draw increases. Once you get ARM running at a 50W+ TDP, x86 becomes a clear winner. Which is what would happen with a billion transistor ARM chip running at 4 GHz.

So, you may not like what I am saying, and you may disagree entirely. However, your declaration that ARM will rule desktop any time soon is a mere pipe dream...much like Acorn was back when it first started. That's why it's a non-profit organization that designs cores and licenses them, not an organization making chips and selling PCs.

That was my CISC vs. RISC rant...If you don't understand what I am talking about then that is your own fault for not knowing the difference between the 2.

That only covers a fraction of the nonsense that you have said about RISC and about ARM. Both that fraction and what you don't quote was corrected before.

3. PS4 runs @ ~2.0 GHz, which is 25% higher than the 1.6 GHz initially claimed. I also stated that there were ES's of the custom chip run @ 2.6 GHz, and there were.

(6) PS4 APU ES's have been benchmarked in the 2.4-2.6 GHz range already. I don't anticipate they will necessarily end up at 2.6 GHz, though I think 2.2-2.4 GHz with a turbo core for less threaded situations is entirely feasible.

http://www.tomshardware.com/forum/id-1721986/amd-cpu-performance-increase-nextgen-consoles-release.html

Sony said 1.6Ghz for the PS4. The 2.0Ghz is only a rumor. Moreover both are far from your previous pretension that it runs a 2.75Ghz. The funny part is that hapidupi was right and you wrong. LOL

4. Look at how old that thread is...seriously? We had less information then, than we do now...and we don't know much now. That was purely speculation based on expectations of current trends continuing from FX. You had some posts from 6 months ago saying things that we now know to be different from reality as well. I am not going to waste time digging them up...but they are there for sure.

LOL. A pair of posts ago you affirmed that you never said such thing. Now the excuse change to ups I said but that is old

5. Are you dense? Read what I wrote...it was determined that it was not, in fact, AM4 MB before you ever wrote me back. Blackkstar and I came to that conclusion before you ever replied to me.

Seeing as you pretended above to hide what you wrote, do you really pretend I to trust what you claim you were thinking one day? LOL

You clearly did not read what I wrote...how long are you going to continue this blatant ignorance?

Does anyone else want to explain to juanrga what I said?

What is your native language? It's clearly not English because you don't understand it very well. Where did I say 2.75 GHz in the post? You reference topics from May, and claim that it's relevant since the information we had at the time changed. You also said exactly what I did at that time, because that's what we knew then. Now, you would deny that you were prepared for AM3+ steamroller on FD-SOI????

You can try that tactic, you can pretend that you never said so or when caught with a quote, you can pretend that you said it in "May", but not latter. However. it is not a wise thing to do, because I can link to your posts.

Look at this one, you said that the PS4 is clocked at 2.75Ghz, someone corrects you and explain you that 2.75 is the freq. of the memory and that the CPU is clocked at 1.6GHz. Your typical ignorant answer was

http://www.tomshardware.co.uk/forum/352312-28-steamroller-speculation-expert-conjecture/page-138#11425669

Now pay attention to the next message after yours, where the same person corrects you again and explain you again that 2.75 is the memory freq. Your reply to him was again "NO".

You were plain wrong for days. I had to confirm here

http://www.tomshardware.co.uk/forum/352312-28-steamroller-speculation-expert-conjecture/page-141#11457221

that 2.75Ghz is the WCK of the memory, and that the freq. of the CPU is 1.6GHz. My post was followed by a series of funny replies.

Did you learn anything? Nope. Because days latter you wrote:

It has already been all but confirmed that the APUs will be running closer to ~2.0-2.2 GHz for the XBone and PS4. If you think that number won't increase over time, you're far more naïve than I thought. Just because the memory is clocked at one frequency has nothing to do with CPU clockspeed.

Microsoft has confirmed that Xbox1 is clocked at 1.75GHz. But you continue posting misleading info.

About SOI. So late as September I wrote that Kaveri/SR is bulk:

http://www.tomshardware.co.uk/forum/352312-28-steamroller-speculation-expert-conjecture/page-142#11461096

This generate a series of answers from several experts (including you) trying to convince me that Kaveri was being made on SOI process. Some quotes:

My thoughts run to doing it on SOI, as JK was a big proponent of the K7/K8 going to SOI originally.

Other sources would even say their 22nm FinFET on bulk was actually lackluster compared to the projections...though that would mean I am right about bulk vs. SOI and you'd be wrong about the delay from AMD for Kaveri. Thus, I don't anticipate you'll acknowledge that.

Until i asked you "If you have one source that says that Kaveri is being manufactured on SOI process, please share it with us." Your answers:

You can't follow the link to the SOI conference anymore, however, shortly after AMD announced going bulk over a year ago, they then fired a bunch of people (those that spoke of bulk included) and then they were talking to GF a month later about FD-SOI @ 28nm at the global SOI conference...you do the math.

You insisted with your it is SOI, SOI is ready, AMD is talking about SOI... My answer:

http://www.tomshardware.co.uk/forum/352312-28-steamroller-speculation-expert-conjecture/page-142#11467899

and during page 143 you continued claiming your confidence in that was SOI, because SOI was ready, trololo

You can now pretend that you never said that Steamroller is AM3+, that you never said that Kaveri/SR is SOI, that you never said that PS4 clock is 2.75Ghz, that you never said that Xbone ~2.0--2.2GHz, that you never said that PhysX is not in PS4, that you never said...

You can pretend that you said those in "May", but not latter. The problem is that your posts show otherwise.

I said, and I quote:

Per the patent applications, the maximum clockspeed listed for PS4 is 2.75 GHz

That statement is entirely accurate. I didn't say specifically that it would be clocked at those speeds...in fact, I said that I expected it would come in quite a bit closer to ~2.2-2.4 GHz multiple times in this thread and others.

I did say Steamroller would be AM3+, at the time AMD had announced one more generation of processors for AM3+ and the Centurion line had not been announced...what was the logical conclusion to make?

I did say Kaveri would likely be SOI...I never denied that. In fact, I am not entirely convinced to this point that it will still be on bulk as you claim.

http://www.advancedsubstratenews.com/2013/07/globalfoundries-on-cost-vs-performance-for-fd-soi-bulk-and-finfet/

There it shows GF is ready to produce 28nm SHP (FD-SOI), and that the costs are less than bulk process. This is because the design phase doesn't require all the masking layers that bulk does. AMD has said many things, and then done something different before...we will wait to see what the product actually is to confirm bulk or SOI. However, if it's bulk, I expect Kaveri will not be the knight in shining armor they need for APUs. Performance will end up similar to Richland because of the lower clocks and higher heat generation thresholds.

http://www.globalfoundries.com/dac2013/seminardetails.aspx

http://www.electronicsnews.com.au/news/globalfoundries-to-take-on-stmicroelectronics%E2%80%99-fd

http://www.globalfoundries.com/technology/tech_elements.aspx

http://www.globalfoundries.com/technology/advanced_tech.aspx

There is no reason to suggest that GF is not ramping FD-SOI. Especially after they announced at the consortium this year that production would ramp up Q4 2013. I think this is credible because they have been trying to ramp it up since end of 2012.

Charlie @ S|A dissected the PS4 APU, and said it would run right at ~2.0 GHz. He dissected the XBone APU and said it would run at ~1.8 GHz. So, I was right, it was closer to 2.2-2.4 than 1.6 GHz.

I fail to see what you're talking about where I was wrong...where do you have proof that AMD has said anything about bulk since 2012? You don't...considering the plethora of things that have changed since Q1 2012...I would say it's fair to think that bulk may entirely be wrong, just as much as it may entirely be right. We will see...

 

[8350rocks]

If that's your point then you need a different benchmark. The quad-core FX is markedly slower than the octo-core FX, despite running at the same clockspeed. More cores does matter for AMD.

Emphasis mine. More cores matter more for AMD because, with only four cores, they are getting totally overloaded due to their poor IPC. As a result, if even ONE core gets loaded, performance tanks. Hence why AMD's performance tends to scale linearly as you OC. Intel quads, by contrast, don't have that problem (for the most part) at base clocks, hence why OCing tends to offer less performance increase (no bottleneck to remove).

Hence why games like BF4, where AMD gains significant performance as more cores are added, yet Intel performance is still sorted largely by IPC + Clock performance, and also why Intel tends to maintain its gaming lead.

See:
http://www.bf4blog.com/battlefield-4-retail-gpu-cpu-benchmarks/
http://pclab.pl/art55318-3.html

FX-8350 ~ i5 2500k in BF4, despite how well threaded it is. That's how superior IPC is better for overall performance in a nutshell. For Intel, more cores essentially just lowers overall core loading, since its high tier i5's aren't bottlenecked.

This was my exact argument against BD from the very beginning, and three years in, AMD still can't beat SB i7's. Even in games using over a dozen threads, like BF4, AMD still looses, or at best, matches Intel, head to head.

Umm did you actually look at the benchmarks you posted? The FX8350 beats the i5 and is within the i7 range, especially if you remember minimum FPS is far more important the average.

BF4 is following the same tactic that BF3 and C3 did with using ~2 primary threads and then loading additional work onto the extra threads as needed. Walking around a village looking at scenery is a rather useless metric when the real experience will be during combat which is where the additional cores are loaded. Its the dynamic environmental interaction that's using the extra cores, something that is fairly parallel friendly to do. I'm waiting to see intense multi-player action (after release), I expect we'll see the same repeat of the BF3 scenario.

+1

 

[gamerk316]

Funny how GameGPU always tends to disagree with other benchmarkers though:

http://pclab.pl/art55318-3.html

MP benchmarks, with the FX-8350 essentially equal to the i5-2500k, both at stock.

http://www.tomshardware.com/reviews/battlefield-4-graphics-card-performance,3634-10.html

Toms shows the same result, with the FX-8350 just behind the i5-2500k (higher minimum, lower average).

Waiting on other sites to do benchmarking, but I've noticed a trend for a while now that GameGPU tends to bias toward AMD. I noted this going back to the BF3 benchmarks a year or so ago, as well as in a few other titles (Crysis 3, etc).

EDIT

There could be a SP/MP bias going on, where SP benefits AMD more then MP. That would be an interesting discussion if true, since you'd reason MP would end up more threaded in most cases. Might be something worth looking into.

 

[de5_Roy]

Waiting on other sites to do benchmarking, but I've noticed a trend for a while now that GameGPU tends to bias toward AMD. I noted this going back to the BF3 benchmarks a year or so ago, as well as in a few other titles (Crysis 3, etc).

may be some details are left out in the gamegpu review texts. pclab usually explains more and better than gamegpu if you take the trouble to translate the text. between the two, i believe pclab more. it always pays to look into benchmarks.
unless ofc, one parrots the shiny charts and pictures only.

 

[8350rocks]

Funny how GameGPU always tends to disagree with other benchmarkers though:

http://pclab.pl/art55318-3.html

MP benchmarks, with the FX-8350 essentially equal to the i5-2500k, both at stock.

http://www.tomshardware.com/reviews/battlefield-4-graphics-card-performance,3634-10.html

Toms shows the same result, with the FX-8350 just behind the i5-2500k (higher minimum, lower average).

Waiting on other sites to do benchmarking, but I've noticed a trend for a while now that GameGPU tends to bias toward AMD. I noted this going back to the BF3 benchmarks a year or so ago, as well as in a few other titles (Crysis 3, etc).

EDIT

There could be a SP/MP bias going on, where SP benefits AMD more then MP. That would be an interesting discussion if true, since you'd reason MP would end up more threaded in most cases. Might be something worth looking into.

By your logic, according to TH's benches, the 2500k > 3960x.

I think that entire argument seems a bit flawed...especially considering minimum FPS.

Conveniently, you like to ignore minimum FPS though...

 

[juanrga]

Funny how GameGPU always tends to disagree with other benchmarkers though:

http://pclab.pl/art55318-3.html

MP benchmarks, with the FX-8350 essentially equal to the i5-2500k, both at stock.

http://www.tomshardware.com/reviews/battlefield-4-graphics-card-performance,3634-10.html

Toms shows the same result, with the FX-8350 just behind the i5-2500k (higher minimum, lower average).

Waiting on other sites to do benchmarking, but I've noticed a trend for a while now that GameGPU tends to bias toward AMD. I noted this going back to the BF3 benchmarks a year or so ago, as well as in a few other titles (Crysis 3, etc).

EDIT

There could be a SP/MP bias going on, where SP benefits AMD more then MP. That would be an interesting discussion if true, since you'd reason MP would end up more threaded in most cases. Might be something worth looking into.

Or you could take the other way and say that you often quote benchmarks biased against AMD.

 

[palladin9479]

There could be a SP/MP bias going on, where SP benefits AMD more then MP. That would be an interesting discussion if true, since you'd reason MP would end up more threaded in most cases. Might be something worth looking into.

I believe they're MP code isn't finished yet and thus the "beta" moniker. Also exactly what part of the game are they benchmarking? I say this because doing controlled runs where your just looking at scenery or in very limited fights won't get you anymore then three or four cores worth of load. That's why the discrepancy in the minimum vs average FPS.

I could setup a benchmark where all I did was stare at a tree for 10 minutes and you'd get the i3 ranking close to the i5. Now I don't think people are doing that but I do believe the exact environment needs to be described. This is the problem with benchmarking "live" games, any situation that would be repeatable wouldn't have much actual load in it.

 

[juanrga]

Spoiler

1. Your confusion about the word CISC was funny, but I was really referring to all the further nonsense that you posted against RISC/ARM.

2. The chip runs background processes to the game such as social stuff, recording, checking for online updates... it doesn't run the OS.

3. You said that that you "saw" PS4 benchmarks @2.6 Ghz, that you waited the "actual final specs will likely fall closer to the 2.4 mark, with possibly a turbo core feature to allow a higher clock under some instances that use fewer cores." Then you strongly misinterpreted the PS4 patents doc and said to everyone here that the CPU run at 2.75 GHz. Even hapidupi had to correct your nonsense. Hapidupi! LOL!

4. You claimed that bulk was impossible, that the people who said bulk was no working for AMD anymore, you insinuated that he didn't know the tech and pretended that the delay was caused by the migration to FD-SOI. When people complained. You did search and post a talk by Glofo and tried to convince us that FD-SOI was cheaper than bulk and AMD was going all SOI. "It is evident" you claimed...

5. Therefore you still insist on saying every novice that a SR FX 8-core CPU is coming for AM3+ and that AM3+ is a good platform for upgrade?

6. Easy. That is an ancient mobo with AM4 in the model code. Someone at the database did a mistake and indexed it as AM4 socket mobo. The rest is only in your imagination. It is not a new mobo with a new socket for a forthcoming 5GHz SR 8-core FX CPU...

I don't think you understand the points I was making about RISC/CISC, however, you don't have the architecture knowledge to understand it anyway. So, I am going to write this off as you simply don't understand. In gamer terms "Learn 2 Research".

My understanding is enough to detect your nonsense.

You did not read a word I said:

2. Sony has confirmed an additional chip on the PS4 to run background processes, and the design lead for the entire project stated the OS would be run primarily off the GPU leaving 8 cores available for developing games. Do you think Sony's project lead was lying? Why would he? That information will be verifiable easily...

Can you read it better now?
--------------------------------

This is the second time that I read your nonsense. The question is: do you read? I don't know what is more funny, that you write "GPU" or that you don't understand that the OS runs on the jaguar cores in the APU and that the secondary chip in the PS4 runs background tasks to the game, such as decoding, downloading, social stuff...

There were ES benchmarks run @ 2.6 GHz, Jaguar cores will actually clock quite a bit higher than that, you know that right? They were likely testing to see what the thermal limits and power consumption would be. I did say that I suspected it would end up closer to ~2.2-2.4 GHz, than the 1.6 GHz many were claiming. By the way, what is the clockspeed on the PS4 APU? Just curious...oh...that's right...it's 2.0 GHz. Who was right?

Hum, let us see you claimed the PS4 runs at 2.75GHz, but that was plain nonsense. Sony did claim 1.6Ghz; therefore, you are off by more than 1GHz or about 72% of error.

I never said bulk was impossible...I did say it was improbable, and that there would be massive clockspeed and thermal penalties to going bulk. I was not wrong on any of those counts. Your poor mastery of the English language is showing.

No. You said us it was SOI. Someone wrote:

I believe that the 28nm process used for SR and Kaveri will be bulk but I'm not sure.

And your answer was:

No, it will be a PD-SOI process...from GloFo.

One thing is that you are wrong, but another is that you pretend now to hide what you wrote during months.

I tell them a SR FX replacement is coming, I also tell them I have no idea what socket, or in that regard, much of any information about it at all.

No. You said us that Steamroller FX is AM3+ socket. Someone asked "8350 or wait for Steamroller?" and your answer was:

The good news is though, if you buy an AM3+ board and a new CPU, you won't need to buy a new board for steamroller, it will be AM3+.

I wonder how many newbies followed your advice, believing that you know what you are writing.

It could very easily be the case, *very* easily; however, Foxconn should not be advertising AM4 socket MB drivers when no such product clearly exists. I was a bit curious when I saw that...and pointed it out to you and a few others to confer. The consensus, that it was not what it looked like, was reached before you ever wrote back to me.

There is no AM4 sockect mobo on Foxconn. I already explained there is a mistake in their indexing of an ancient mobo, but please ignore facts and continue fantasizing. It is much more funny.

i will just leave it here :

http://amdfx.blogspot.com/2013/10/amd-kaveri-benchmarks-more-steamrolling.html

If legit, it confirms that SR is ~30% faster than BD. Precisely in my estimation of kaveri performance I assumed a 30% faster than BD (or ~20% faster than PD) to show that Kaveri CPU would be at the i5 level of performance.

The regression in FP could be related to SR using a simplified (streamlined) FPU. This is not a serious problem because SR comes in HSA APUs where the GPU will be used as a giant FPU.

They're probably tweaking it to prepare for 256 bit FMAC FPUs (AVX2 instructions) in excavator and running into some issues. That would be my guess...

At least now you make clear that you are guessing.... lol

256-bit FMAC units don't make any sense for me, but of course AMD can prove me wrong.

1.

•Thirdly, said Cerny, "The original AMD GCN architecture allowed for one source of graphics commands, and two sources of compute commands. For PS4, we’ve worked with AMD to increase the limit to 64 sources of compute commands -- the idea is if you have some asynchronous compute you want to perform, you put commands in one of these 64 queues, and then there are multiple levels of arbitration in the hardware to determine what runs, how it runs, and when it runs, alongside the graphics that's in the system."

"The reason so many sources of compute work are needed is that it isn’t just game systems that will be using compute -- middleware will have a need for compute as well. And the middleware requests for work on the GPU will need to be properly blended with game requests, and then finally properly prioritized relative to the graphics on a moment-by-moment basis."

http://www.gamasutra.com/view/feature/191007/inside_the_playstation_4_with_mark_.php?page=2

Maybe now you understand what GPU means...because the GPU is not an additional ARM core...

Unsurprisingly that is unrelated to what you wrote before about GPU and unrelated to your nonsense that the OS is run in a secondary chip and 8 jaguar cores are for games exclusively.

2.

RISC runs differently, and yes x86 CPUs have had underlying RISC architecture characteristics for a long time. Since the Pentium days really; however, as was pointed out by Palladin earlier, x86 allows MUCH larger instructions to be converted into bytecode to be run on the CPU itself.

The added complexity of x86 was my point. That is easily it's greatest strength while also being an inherent weakness.

ARM's strength and weakness both lie in it's simplicity. That's why it excels for low power devices and simple things like Micro Servers. It's also the primary reason it's not a terribly valid Desktop uarch option.

In order to make ARM a serious x86 competitor, you would have to add several layers of complexity. That complexity would drive up transistor counts and die complexity, requiring quad channel memory controllers, and many other things that draw more power. Once you've done that, you have an x86 competitor...that no longer consumes power like a mobile/low power solution. Because the added complexity draws more power, your consumption numbers spike upward dramatically.

x86 ISA has been dealing with this in it's architecture since x586 (K6-2 days). ARM has not had the benefit of time spent tweaking their architecture for such added complexities, and it takes a *LONG* time to get that stuff right. Which is part of what we see in the current AMD and Intel uarch's, Intel has a far more *REFINED* uarch, because it hasn't changed dramatically since P4 days. Where as AMD's uarch is only 2-3 years old at this point, and not nearly as well refined and tuned.

So, what you're talking about with ARM taking over DT, or even a large share of notebooks, etc., will not come about for quite some time.

The reasons for this are simple:

1.) Most of the consumer DT world runs on Windows, like it or not, M$ still has some clout. They don't want to redesign their OS entirely for ARM, and WART is a terrible execution.

2.) With no major OS player taking ARM seriously any time soon, hardware advances will come slowly because it's not in high demand. Only way ARM becomes a big player is if some large player in the PC world backs it and pushes hard. AMD making Micro Servers using ARM is not that push into the consumer sector you expect. It's a gimmick to say "see, we can do low power better than Intel", nothing more.

3.) Without a Major OS player backing ARM, the development of consumer software will be slow. Open source groups may do something, but how has that worked out for Linux so far? Outside of Android, it's still not terribly popular as an OS in the PC world considering roughly 3% of the world is likely running it on a DT PC. I think Linux should see more use than it does, but in the consumer space, M$ is still king.

4.) As ARM adds complexity, it will add power consumption, and the more you need to be able to ask the ISA to do, the more convoluted the hardware, middleware, software becomes to do those things. So, as the hardware adds complexity, the power draw increases. Once you get ARM running at a 50W+ TDP, x86 becomes a clear winner. Which is what would happen with a billion transistor ARM chip running at 4 GHz.

So, you may not like what I am saying, and you may disagree entirely. However, your declaration that ARM will rule desktop any time soon is a mere pipe dream...much like Acorn was back when it first started. That's why it's a non-profit organization that designs cores and licenses them, not an organization making chips and selling PCs.

That was my CISC vs. RISC rant...If you don't understand what I am talking about then that is your own fault for not knowing the difference between the 2.

That only covers a fraction of the nonsense that you have said about RISC and about ARM. Both that fraction and what you don't quote was corrected before.

3. PS4 runs @ ~2.0 GHz, which is 25% higher than the 1.6 GHz initially claimed. I also stated that there were ES's of the custom chip run @ 2.6 GHz, and there were.

(6) PS4 APU ES's have been benchmarked in the 2.4-2.6 GHz range already. I don't anticipate they will necessarily end up at 2.6 GHz, though I think 2.2-2.4 GHz with a turbo core for less threaded situations is entirely feasible.

http://www.tomshardware.com/forum/id-1721986/amd-cpu-performance-increase-nextgen-consoles-release.html

Sony said 1.6Ghz for the PS4. The 2.0Ghz is only a rumor. Moreover both are far from your previous pretension that it runs a 2.75Ghz. The funny part is that hapidupi was right and you wrong. LOL

4. Look at how old that thread is...seriously? We had less information then, than we do now...and we don't know much now. That was purely speculation based on expectations of current trends continuing from FX. You had some posts from 6 months ago saying things that we now know to be different from reality as well. I am not going to waste time digging them up...but they are there for sure.

LOL. A pair of posts ago you affirmed that you never said such thing. Now the excuse change to ups I said but that is old

5. Are you dense? Read what I wrote...it was determined that it was not, in fact, AM4 MB before you ever wrote me back. Blackkstar and I came to that conclusion before you ever replied to me.

Seeing as you pretended above to hide what you wrote, do you really pretend I to trust what you claim you were thinking one day? LOL

You clearly did not read what I wrote...how long are you going to continue this blatant ignorance?

Does anyone else want to explain to juanrga what I said?

What is your native language? It's clearly not English because you don't understand it very well. Where did I say 2.75 GHz in the post? You reference topics from May, and claim that it's relevant since the information we had at the time changed. You also said exactly what I did at that time, because that's what we knew then. Now, you would deny that you were prepared for AM3+ steamroller on FD-SOI????

You can try that tactic, you can pretend that you never said so or when caught with a quote, you can pretend that you said it in "May", but not latter. However. it is not a wise thing to do, because I can link to your posts.

Look at this one, you said that the PS4 is clocked at 2.75Ghz, someone corrects you and explain you that 2.75 is the freq. of the memory and that the CPU is clocked at 1.6GHz. Your typical ignorant answer was

http://www.tomshardware.co.uk/forum/352312-28-steamroller-speculation-expert-conjecture/page-138#11425669

Now pay attention to the next message after yours, where the same person corrects you again and explain you again that 2.75 is the memory freq. Your reply to him was again "NO".

You were plain wrong for days. I had to confirm here

http://www.tomshardware.co.uk/forum/352312-28-steamroller-speculation-expert-conjecture/page-141#11457221

that 2.75Ghz is the WCK of the memory, and that the freq. of the CPU is 1.6GHz. My post was followed by a series of funny replies.

Did you learn anything? Nope. Because days latter you wrote:

It has already been all but confirmed that the APUs will be running closer to ~2.0-2.2 GHz for the XBone and PS4. If you think that number won't increase over time, you're far more naïve than I thought. Just because the memory is clocked at one frequency has nothing to do with CPU clockspeed.

Microsoft has confirmed that Xbox1 is clocked at 1.75GHz. But you continue posting misleading info.

About SOI. So late as September I wrote that Kaveri/SR is bulk:

http://www.tomshardware.co.uk/forum/352312-28-steamroller-speculation-expert-conjecture/page-142#11461096

This generate a series of answers from several experts (including you) trying to convince me that Kaveri was being made on SOI process. Some quotes:

My thoughts run to doing it on SOI, as JK was a big proponent of the K7/K8 going to SOI originally.

Other sources would even say their 22nm FinFET on bulk was actually lackluster compared to the projections...though that would mean I am right about bulk vs. SOI and you'd be wrong about the delay from AMD for Kaveri. Thus, I don't anticipate you'll acknowledge that.

Until i asked you "If you have one source that says that Kaveri is being manufactured on SOI process, please share it with us." Your answers:

You can't follow the link to the SOI conference anymore, however, shortly after AMD announced going bulk over a year ago, they then fired a bunch of people (those that spoke of bulk included) and then they were talking to GF a month later about FD-SOI @ 28nm at the global SOI conference...you do the math.

You insisted with your it is SOI, SOI is ready, AMD is talking about SOI... My answer:

http://www.tomshardware.co.uk/forum/352312-28-steamroller-speculation-expert-conjecture/page-142#11467899

and during page 143 you continued claiming your confidence in that was SOI, because SOI was ready, trololo

You can now pretend that you never said that Steamroller is AM3+, that you never said that Kaveri/SR is SOI, that you never said that PS4 clock is 2.75Ghz, that you never said that Xbone ~2.0--2.2GHz, that you never said that PhysX is not in PS4, that you never said...

You can pretend that you said those in "May", but not latter. The problem is that your posts show otherwise.

I said, and I quote:

Per the patent applications, the maximum clockspeed listed for PS4 is 2.75 GHz

That statement is entirely accurate. I didn't say specifically that it would be clocked at those speeds...in fact, I said that I expected it would come in quite a bit closer to ~2.2-2.4 GHz multiple times in this thread and others.

The complain is not about that statement, but about others quoted above where you pretended that the CPU was clocked at 2.75GHz. You can continue negating it...

I did say Steamroller would be AM3+, at the time AMD had announced one more generation of processors for AM3+ and the Centurion line had not been announced...what was the logical conclusion to make?

Funny how you changed your words, from your initial I never said AM3+ to your I said AM3+. Any bet that if I had not liked to a post with your exact words you would be still negating what you said?

I did say Kaveri would likely be SOI...I never denied that. In fact, I am not entirely convinced to this point that it will still be on bulk as you claim.

Spoiler

http://www.advancedsubstratenews.com/2013/07/globalfoundries-on-cost-vs-performance-for-fd-soi-bulk-and-finfet/

There it shows GF is ready to produce 28nm SHP (FD-SOI), and that the costs are less than bulk process. This is because the design phase doesn't require all the masking layers that bulk does. AMD has said many things, and then done something different before...we will wait to see what the product actually is to confirm bulk or SOI. However, if it's bulk, I expect Kaveri will not be the knight in shining armor they need for APUs. Performance will end up similar to Richland because of the lower clocks and higher heat generation thresholds.

http://www.globalfoundries.com/dac2013/seminardetails.aspx

http://www.electronicsnews.com.au/news/globalfoundries-to-take-on-stmicroelectronics%E2%80%99-fd

http://www.globalfoundries.com/technology/tech_elements.aspx

http://www.globalfoundries.com/technology/advanced_tech.aspx

There is no reason to suggest that GF is not ramping FD-SOI. Especially after they announced at the consortium this year that production would ramp up Q4 2013. I think this is credible because they have been trying to ramp it up since end of 2012.

Charlie @ S|A dissected the PS4 APU, and said it would run right at ~2.0 GHz. He dissected the XBone APU and said it would run at ~1.8 GHz. So, I was right, it was closer to 2.2-2.4 than 1.6 GHz.

I fail to see what you're talking about where I was wrong...where do you have proof that AMD has said anything about bulk since 2012? You don't...considering the plethora of things that have changed since Q1 2012...I would say it's fair to think that bulk may entirely be wrong, just as much as it may entirely be right. We will see...

Effectively, you said it.