AMD CPU speculation... and expert conjecture

[juanrga]

Cazalan: Valve has just promised that the ~3000 games in Steam will be available for SteamOS for the beta of the SteamBox

http://store.steampowered.com/livingroom/SteamMachines/

Combine that with MANTLE and I think we can say that the main advantage of windows (games) is gone.

We would need always need a trusty copy of XP 32-bit, just for those older games like Baldur's Gate, and Total War: Rome.

The first game has a native port for linux

http://www.phoronix.com/scan.php?page=news_item&px=MTI1MDg

The windows version also work on Wine/playOnLinux

 

[esrever]

Mantle is not really a game changer unless AMD gets a much bigger market share. I would assume it would include APU optimizations. I don't think it will change much just like I don't think steambox will change much. DX11 will be supported everywhere, all games will need that render path. So in the end, what will we get? more games that runs worse if you don't have gcn because the devs spend all their time and money trying to deal with a low level API.

Low level API gives more choices but also decrease hardware compatibility and thats just no good unless you are an extremely large studio. Considering devs can't even both to support dx11. I don't think games will use it much.

 

[gamerk316]

Since when is PhysX open? what the hell are you on? PhysX is a Closed tech and they just made the documents FOR DISPLAY DRIVER on Linux as open source, they still have to confirm PhysX will be open too which i doubt and it wont be any time soon, PhysX can not even run in AMD GPUs, it may run on AMD CPUs but not on GPUs, so i am not sure what sort of med are you on.

PhysX happens to be totally free for commercial use; AMD is free to implement the API any time it wants, at no cost. The only thing you can not do for free is modify the API itself. Aside from that, PhysX is free for all to use.

And yes, PhysX can run on AMD GPU's; all they would have to do is re-implement via Directcompute [NVIDIA implemented via CUDA].

PhysX is EXACTLY as open as MANTEL is. Which is why I'm pointing out the irony that the same exact people who are bashing PhysX are embracing MANTEL, for THE SAME EXACT REASONS.

 

[-Fran-]

Since AMD has marketed Mantle as an ISA, it's much more powerful than just marketing it as an API. If you ask me, APIs are way more susceptible to be changed over time than a fully adopted ISA. Try to make the idea behind Mantle of what X86 is for the world today. You have a full set of instructions supported by the hardware, that an API can make use as it pleases (hence, I don't think the DX-OGL deal is that big on one hand) and dropping support for certain parts of the ISA is way harder than in an API (the exception being OGL).

The could do whatever they want re-organizing the HW inside the GPU as long as it supports the ISA they are showing/primising us now. Binary code already compiled for it, will run in whatever uArch they choose for the GPU down the road, just like you can run binary code from the Pentium era in todays CPUs. I said OGL is the exception, because you can run ancient OGL binaries on todays hardware and they *should* run. Direct X doesn't have that privilege because of design.

Anyway, we need more information on what AMD plans to *really* do with Mantle, but since it will be an open standard, I'm guessing nVidia and Intel will support it, but won't do any publicity for it. Just like Intel supports X86_64 now.

Cheers!

 

[8350rocks]

Since when is PhysX open? what the hell are you on? PhysX is a Closed tech and they just made the documents FOR DISPLAY DRIVER on Linux as open source, they still have to confirm PhysX will be open too which i doubt and it wont be any time soon, PhysX can not even run in AMD GPUs, it may run on AMD CPUs but not on GPUs, so i am not sure what sort of med are you on.

PhysX happens to be totally free for commercial use; AMD is free to implement the API any time it wants, at no cost. The only thing you can not do for free is modify the API itself. Aside from that, PhysX is free for all to use.

And yes, PhysX can run on AMD GPU's; all they would have to do is re-implement via Directcompute [NVIDIA implemented via CUDA].

PhysX is EXACTLY as open as MANTEL is. Which is why I'm pointing out the irony that the same exact people who are bashing PhysX are embracing MANTEL, for THE SAME EXACT REASONS.

No, I am not embracing MANTLE for the same reasons I am not keen on PhysX.

On the contrary, MANTLE allows low level access, with developer tools that will be very close to the hardware API for the consoles.

Now, if they turn this into a full blown ISA, and the tools gain support among enough developers...then it could, eventually, supplant DX as the graphic tool of choice. Dramatically improving PC gaming capabilities along the way (note: TrueAudio could lead into a complete DX type suite for Linux which would be a GODSEND!).

PhysX requires certain implementations into your compute hardware, such to the point that you basically have to support CUDA these days to support PhysX on a GPU.

That boils down to AMD saying..."we do GPU compute better our way, no thanks..." Consequently, I agree with AMD there. If NVidia allowed AMD to modify PhysX in such a way that they could implement it without having to basically embrace CUDA...then it would have likely taken off much better than it has.

It also doesn't bother me that, if any of your fears are founded, AMD is taking a page from the likes of Intel and NVidia and basically telling them to buzz off...since AMD has been the only one, for quite some time, that embraces open source and open standards.

EDIT: Imagine an open source DX suite that is compatible across all platforms for all game developers...how level is the PC gaming/console playing field at that point??? If they go that far, this is monumental for gaming. It's theoretically feasible too...AMD isn't so proprietary oriented as many other companies out there are *cough*M$/NVidia/Intel*cough*...and if this is as comprehensive as I would like to think, and as dynamic as it could be...it may well be, not just a game changer; however, it may well be the game changer.

 

[juanrga]

So in other words: Mantel is no different then PhysX for NVIDIA, right?

And yet, one is embraced while the other is shunned. For the same exact reasons...

In any case, I can basically guarantee Mantel is almost never going to get used. Three main reasons why:

1: Because Mantel is AMD only, you still need a DX/OGL render path. No dev is going to waste time and money having multiple different rendering paths. For a title with XP support, for instance, you'd likely have THREE render paths: DX9, DX11, and Mantel.

2: With Mantle, you run into SERIOUS problems as the hardware changes. Sure, you may gain 50% performance on a generation of cards, then two generations down the road, the hardware design changes, and guess what? Your carefully optimized to the metal code suddenly runs like crap because the assumptions you made in regards to the hardware no longer hold true. Hence why to the metal coding is ONLY used for embedded systems that have locked hardware AND need the performance. Both of these conditions do not apply for PC's.

3: Developers like me HATED having to have separate device drivers for every single piece of hardware; that's why Glide, and later OGL and DX became so widely adopted. Going back to needed optimized coding for each family of GPU is not going to catch on with any developers.

I don't know anything about "mantel", but the basic about MANTLE

PhysX is proprietary, not open.

1. MANTLE is open; open to all hardware. Several devs are already using MANTLE. Battlefield 4 is the first game that comes with MANTLE support. Andersson himself promises "more performance and a better gaming experience" from the MANTLE version of BF4 on PC.

MANTLE is cross-platform. This means that will reduce costs of developing games for Windows/linux/consoles.

2. You don't program for the hardware directly but for the MANTLE API, the MANTLE _driver_ is what manages hardware differences. If the Hardware changes the driver changes. MANTLE is a CMT (Close To the Metal) approach, so _close_ as possible but no more.

3. MANTLE simplifies cross-platform programming. You can do your game for console or for Windows or for linux and then port it easily to the other two.

 

[juanrga]

The LIMITATION of ARM is it's inability to do EVERYTHING that x86 can on the high end as efficiently.

I have tried to explain you this is untrue.

 

[griptwister]

I'll just leave this here...

http://www.maximumpc.com/amd_r9_290x_will_be_much_faster_titan_battlefield_4

For goodness sake Juan! No one agrees with you on this topic. If it actually happens in the near future that ARM replaces x86, you can have the right to say, "I told you so." But there is no need to debate everyone on the subject By the time ARM = x86 current gen performance, x86 will probably already have doubled in performance. I do believe we will see faster ARM processors, And I do believe we'll only see them in Tablets, Phones and low end PCs (and servers). So the future for the most part is ARM. But you're wrong if you believe Big Cores are going to be replaced with ARM.

 

[simon12]

I like the mantle idea and hope Nvidia use it too, anything that is pure gaming focused unlike M$ (which don't want PC competing with Xbox) that can be used regardless of OS and hopefully GPU manufacturer will be good for gaming on all platforms. I seriously hope it doesn't take Nvidia out of the market for not using it as that would mean all GPU costing a bomb, the same as if AMD couldn't compete on price/performance with Intel.
I hope Steam OS does well but I expect more of a slow take up and for it to be small for a year or 2 before it gets close to a 30% share of steam users. I think its unlikely (but very possible) but it would be strange if in 2 years the best gaming PC is an AMD APU with HSA and an Nvidia card using mantle running steam OS and nothing Intel or M$ can do comes close even with an AMD or Nvidia card (and next gen consoles are obsolete).

 

[BeastLeeX]

Cazalan: Valve has just promised that the ~3000 games in Steam will be available for SteamOS for the beta of the SteamBox

http://store.steampowered.com/livingroom/SteamMachines/

Combine that with MANTLE and I think we can say that the main advantage of windows (games) is gone.

We would need always need a trusty copy of XP 32-bit, just for those older games like Baldur's Gate, and Total War: Rome.

The first game has a native port for linux

http://www.phoronix.com/scan.php?page=news_item&px=MTI1MDg

The windows version also work on Wine/playOnLinux

I figured the Enhanced Ed. might be released, but still, not every old game will run on SteamOS/Linux at the start. Im sure Wine has its limits too, although ive never used Wine or Linux, so im kinda making assumptions. But if the SteamOS does what it is claiming, it is definitely going on my machine.

 

[etayorius]

I like the mantle idea and hope Nvidia use it too, anything that is pure gaming focused unlike M$ (which don't want PC competing with Xbox) that can be used regardless of OS and hopefully GPU manufacturer will be good for gaming on all platforms. I seriously hope it doesn't take Nvidia out of the market for not using it as that would mean all GPU costing a bomb, the same as if AMD couldn't compete on price/performance with Intel.
I hope Steam OS does well but I expect more of a slow take up and for it to be small for a year or 2 before it gets close to a 30% share of steam users. I think its unlikely (but very possible) but it would be strange if in 2 years the best gaming PC is an AMD APU with HSA and an Nvidia card using mantle running steam OS and nothing Intel or M$ can do comes close even with an AMD or Nvidia card (and next gen consoles are obsolete).

There is a myriad of reason why to love and embrace MANTLE, first of all because it will be OPEN, anyone can contribute to it and modify it...

Damn this generation on PC will be EPIC, HSA, HUMA, SteamOS and MANTLE! goodbye crappy and horrible underperforming ports.

If all this come true, can you all imagine the increases of performance and the new tech that will develop on PC Games in the next 5 years? EPIC.

I don`t expect SteamOS to be Main Gaming OS in the next 2-3 years, i can see up to 10-15% of Steam users moving to SteamOS in the first year of release, but it will be the main Gaming OS in maximum 5 years, every one is abandoning Microsoft like a sinking ship including nVidia, AMD, Intel and a heck ton of Developers, this will happen... the days of Windows as the main Gaming OS are numbered.

About ARM vs x86, i will show you the following link:

http://www.bit-tech.net/news/hardware/2013/03/29/tegra-5-faster-xbox-360-ps3/

Those ARM CPUs are fast and efficient as hell, but i don`t see them taking the crown from x86 anytime soon... perhaps if they ignore power efficiency and concentrate in high performance? who knows! now, can we all put the ARM vs x86 away and move on to Steamroller and AMD?

 

[GOM3RPLY3R]

http://www.xbitlabs.com/news/graphics/display/2013090230253_Nvidia_Is_Preparing_the_Most_Amazing_Thing_Ever_Made_Mark_Rein.html#discussion_last

I have been waiting for nvidia shadowplay for a long time. Now with a gtx 670 and 650m this will be great. I wonder if amd release something like this as shadowplay uses built in h264 encoder built into the kepler gpu.

Valve already did, it's a feature of SteamOS and it doesn't require proprietary hardware. It also is free as in beer and free as in freedom. Once again Nvidia is going to end up bringing a proprietary, locked down platform to compete against something free and open.

Look how well that worked out for PhysX.

Bullet: Free and open, almost never used
PhysX: Free and closed, moderately used
Havok: Licensed and closed, heavily used

So...what point were you trying to make again?

Bullet is used as much or more than PhysX.

Though, I will grant you Havok is used more than both of them...how that happens is mind boggling honestly. Though I guess it's brand recognition that some developers look for...Havok offers less than both of the others...

I've played many games (a lot of them). I'm going to tell you that I have never heard of Bullet before. Does this clear things up? ^_^

 

[8350rocks]

http://www.xbitlabs.com/news/graphics/display/2013090230253_Nvidia_Is_Preparing_the_Most_Amazing_Thing_Ever_Made_Mark_Rein.html#discussion_last

I have been waiting for nvidia shadowplay for a long time. Now with a gtx 670 and 650m this will be great. I wonder if amd release something like this as shadowplay uses built in h264 encoder built into the kepler gpu.

Valve already did, it's a feature of SteamOS and it doesn't require proprietary hardware. It also is free as in beer and free as in freedom. Once again Nvidia is going to end up bringing a proprietary, locked down platform to compete against something free and open.

Look how well that worked out for PhysX.

Bullet: Free and open, almost never used
PhysX: Free and closed, moderately used
Havok: Licensed and closed, heavily used

So...what point were you trying to make again?

Bullet is used as much or more than PhysX.

Though, I will grant you Havok is used more than both of them...how that happens is mind boggling honestly. Though I guess it's brand recognition that some developers look for...Havok offers less than both of the others...

I've played many games (a lot of them). I'm going to tell you that I have never heard of Bullet before. Does this clear things up? ^_^

Ever played Grand Theft Auto? I bet you have...

In that case, you've heard of Bullet, you just didn't know you had.

 

[jdwii]

I like the mantle idea and hope Nvidia use it too, anything that is pure gaming focused unlike M$ (which don't want PC competing with Xbox) that can be used regardless of OS and hopefully GPU manufacturer will be good for gaming on all platforms. I seriously hope it doesn't take Nvidia out of the market for not using it as that would mean all GPU costing a bomb, the same as if AMD couldn't compete on price/performance with Intel.
I hope Steam OS does well but I expect more of a slow take up and for it to be small for a year or 2 before it gets close to a 30% share of steam users. I think its unlikely (but very possible) but it would be strange if in 2 years the best gaming PC is an AMD APU with HSA and an Nvidia card using mantle running steam OS and nothing Intel or M$ can do comes close even with an AMD or Nvidia card (and next gen consoles are obsolete).

If nvidia does go out for not being able to compete then it does its not like i care about paying extra for their name but then again Amd will turn to crap if nvidia does go away.

 

[griptwister]

http://www.xbitlabs.com/news/graphics/display/2013090230253_Nvidia_Is_Preparing_the_Most_Amazing_Thing_Ever_Made_Mark_Rein.html#discussion_last

I have been waiting for nvidia shadowplay for a long time. Now with a gtx 670 and 650m this will be great. I wonder if amd release something like this as shadowplay uses built in h264 encoder built into the kepler gpu.

Valve already did, it's a feature of SteamOS and it doesn't require proprietary hardware. It also is free as in beer and free as in freedom. Once again Nvidia is going to end up bringing a proprietary, locked down platform to compete against something free and open.

Look how well that worked out for PhysX.

Bullet: Free and open, almost never used
PhysX: Free and closed, moderately used
Havok: Licensed and closed, heavily used

So...what point were you trying to make again?

Bullet is used as much or more than PhysX.

Though, I will grant you Havok is used more than both of them...how that happens is mind boggling honestly. Though I guess it's brand recognition that some developers look for...Havok offers less than both of the others...

I've played many games (a lot of them). I'm going to tell you that I have never heard of Bullet before. Does this clear things up? ^_^

Ever played Grand Theft Auto? I bet you have...

In that case, you've heard of Bullet, you just didn't know you had.

Apparently they aren't using the engine efficiently...

http://memebase.cheezburger.com/videogames/share/7822955264

 

[juanrga]

For goodness sake Juan! No one agrees with you on this topic. If it actually happens in the near future that ARM replaces x86, you can have the right to say, "I told you so." But there is no need to debate everyone on the subject By the time ARM = x86 current gen performance, x86 will probably already have doubled in performance. I do believe we will see faster ARM processors, And I do believe we'll only see them in Tablets, Phones and low end PCs (and servers). So the future for the most part is ARM. But you're wrong if you believe Big Cores are going to be replaced with ARM.

I am not here for agreeing with everyone! I am here to state my opinion and for learning something new.

It seems you are one of those few who don't still understand that ARM is already in the same performance envelope than x86. Of course I am not mentioning the ARM chip in your phone, but the ARM chips that will be used in servers, supercomputers, desktops...

Phone (ARM A8): 4 GFLOP
Phone (ARM A9): 24 GFLOP
Desktop FX-8350 (Piledriver): 256 GFLOP
Server Opteron (Interlagos): 384 GFLOP
Server Seattle (ARM A57): 256 GFLOP

And floating point is not the strong point of the ARM architecture. In practice this is not a real problem because heavy floating point computations are made in GPGPUs/accelerators.

The above figures can give you an idea of the raw performance of the new AMD Seattle CPU. And it consumes less than a 50% of the energy of a FX-8350.

About ARM vs x86, i will show you the following link:

http://www.bit-tech.net/news/hardware/2013/03/29/tegra-5-faster-xbox-360-ps3/

Those ARM CPUs are fast and efficient as hell, but i don`t see them taking the crown from x86 anytime soon... perhaps if they ignore power efficiency and concentrate in high performance? who knows! now, can we all put the ARM vs x86 away and move on to Steamroller and AMD?

The goal of Tegra 5 is not to replace x86. Nvidia plans to replace x86 using the Denver project

http://blogs.nvidia.com/blog/2011/01/05/project-denver-processor-to-usher-in-new-era-of-computing/

Denver CPU will appear in Tegra 6

Now everything has been explained once again we could return to Steamroller. I have a question about Steamroller but I will ask below to separate from ARM topic.

 

[juanrga]

As you know I am preparing an article about Kaveri performance. I am receiving assistance from some experts, one of them called my attention about MANTLE. Since Kaveri has a GCN based GPU, it may support games using the new API. It seems totally reasonable to me, specially considering consoles are APUs and that Kaveri will be announced after new Radeons.

Your opinion?

 

[8350rocks]

As you know I am preparing an article about Kaveri performance. I am receiving assistance from some experts, one of them called my attention about MANTLE. Since Kaveri has a GCN based GPU, it may support games using the new API. It seems totally reasonable to me, specially considering consoles are APUs and that Kaveri will be announced after new Radeons.

Your opinion?

I am sure it will work with MANTLE, I don't know how effective it would be given the DDR3 memory. However, it should, in theory, make a large impact relatively.

The Achilles heel of the APUs happens to be that they are bandwidth starved.

I would expect the top of the line APU to have graphics quality slightly below something like the R7-250X based on the best extrapolation we can do with current data.

 

[8350rocks]

For goodness sake Juan! No one agrees with you on this topic. If it actually happens in the near future that ARM replaces x86, you can have the right to say, "I told you so." But there is no need to debate everyone on the subject By the time ARM = x86 current gen performance, x86 will probably already have doubled in performance. I do believe we will see faster ARM processors, And I do believe we'll only see them in Tablets, Phones and low end PCs (and servers). So the future for the most part is ARM. But you're wrong if you believe Big Cores are going to be replaced with ARM.

I am not here for agreeing with everyone! I am here to state my opinion and for learning something new.

It seems you are one of those few who don't still understand that ARM is already in the same performance envelope than x86. Of course I am not mentioning the ARM chip in your phone, but the ARM chips that will be used in servers, supercomputers, desktops...

Phone (ARM A8): 4 GFLOP
Phone (ARM A9): 24 GFLOP
Desktop FX-8350 (Piledriver): 256 GFLOP
Server Opteron (Interlagos): 384 GFLOP
Server Seattle (ARM A57): 256 GFLOP

And floating point is not the strong point of the ARM architecture. In practice this is not a real problem because heavy floating point computations are made in GPGPUs/accelerators.

The above figures can give you an idea of the raw performance of the new AMD Seattle CPU. And it consumes less than a 50% of the energy of a FX-8350.

About ARM vs x86, i will show you the following link:

http://www.bit-tech.net/news/hardware/2013/03/29/tegra-5-faster-xbox-360-ps3/

Those ARM CPUs are fast and efficient as hell, but i don`t see them taking the crown from x86 anytime soon... perhaps if they ignore power efficiency and concentrate in high performance? who knows! now, can we all put the ARM vs x86 away and move on to Steamroller and AMD?

The goal of Tegra 5 is not to replace x86. Nvidia plans to replace x86 using the Denver project

http://blogs.nvidia.com/blog/2011/01/05/project-denver-processor-to-usher-in-new-era-of-computing/

Denver CPU will appear in Tegra 6

Now everything has been explained once again we could return to Steamroller. I have a question about Steamroller but I will ask below to separate from ARM topic.

1.) NVidia is an extremely minor player in the ARM sweepstakes. Qualcomm or Samsung have the *best* chance of anyone to *try* something of that sort at this point.

2.) There is no consumer software for ARM that functions at a desktop level. There will not be anytime soon either.

EDIT: There is *FAR* more software out there for PowerPC at this point in the consumer space than there is for ARM. Given IBM's affinity to make cutting edge designs in POWER architecture...why isn't someone making a POWER8 desktop PC since there are already software environments for it? Especially considering POWER8 is *FAR* superior to ARM.

Because it won't supplant the x86 environment, and never will...the same as ARM. Remember when everyone thought Mac would conquer the PC world? Are you too young to remember that? If so, let me elaborate...this played out in the early/mid 90's but it was Apple's Mac on PowerPC instead of ARM then...same end result as we will see this time.

Like it or not, you're playing against Intel...even if ARM was somehow better at desktop (won't happen), Intel won't roll over for the same reasons they screwed AMD so many times over the years.

Good luck with that...additionally, ARM won't fight back because all they do is license cores. They won't go through all the grief that AMD and NVidia did years ago, they don't have deep enough pockets to take it to court and hold out long enough to matter.

ARM in DT is dead before it's born...even if a "miracle chip" design comes out...Intel will kill it before it gets going. Everyone knows they would have killed AMD off several times over were it not for lawsuits and courts intervening early on. At this point the only reason they're less ridiculous about it is to keep anti-trust lawsuits from coming about and fracturing up the company.

 

[Cazalan]

I am not here for agreeing with everyone! I am here to state my opinion and for learning something new.

It seems you are one of those few who don't still understand that ARM is already in the same performance envelope than x86.

Phone (ARM A8): 4 GFLOP
Phone (ARM A9): 24 GFLOP
Desktop FX-8350 (Piledriver): 256 GFLOP
Server Opteron (Interlagos): 384 GFLOP
Server Seattle (ARM A57): 256 GFLOP

Opinions are fine but you're touting numbers for a Seattle part that are a year away from release, as if it's here today.

You can't say "already in the performance envelope" when the parts are not for sale. And we all know how good AMD is at timely releases. Specs change, products slip.

I still can't TODAY buy a motherboard with a Kabini on it and they were "released" how long ago? 5 months?

 

[sarinaide]

It's my understanding that Mantle is an open standard (open source is software) and that Nvidia could easily program their drivers to communicate in it. No whether they chose to do so or not is a different story.

So in other words: Mantel is no different then PhysX for NVIDIA, right?

And yet, one is embraced while the other is shunned. For the same exact reasons...

In any case, I can basically guarantee Mantel is almost never going to get used. Three main reasons why:

1: Because Mantel is AMD only, you still need a DX/OGL render path. No dev is going to waste time and money having multiple different rendering paths. For a title with XP support, for instance, you'd likely have THREE render paths: DX9, DX11, and Mantel.

2: With Mantle, you run into SERIOUS problems as the hardware changes. Sure, you may gain 50% performance on a generation of cards, then two generations down the road, the hardware design changes, and guess what? Your carefully optimized to the metal code suddenly runs like crap because the assumptions you made in regards to the hardware no longer hold true. Hence why to the metal coding is ONLY used for embedded systems that have locked hardware AND need the performance. Both of these conditions do not apply for PC's.

3: Developers like me HATED having to have separate device drivers for every single piece of hardware; that's why Glide, and later OGL and DX became so widely adopted. Going back to needed optimized coding for each family of GPU is not going to catch on with any developers.

1) I go on the assumption that you speak for "most developers" since you say so in the absolute "no dev will". but will connect this later

2) So you are saying that it cannot be constantly evolved generation to generation?

3) The only analogy that comes to mind is Toyota and Bugatti, Toyota mass produce and have hundreds of thousands of defective cars sent back because they want numbers over quality, Bugatti build individually with care and precission to make the ultimate motor vehicle. This kind of goes with point one being you will not optimize code over an expanse of platforms because its time consuming, but this doesn't mean that there are others out there that will not do it. There are people out there that are less concerned about mass but the quality of the mass and actually do give a crap about the absolute best they can tailor towards and if Mantle helps they will use it.

 

[sarinaide]

Lots of talk on Mantle but I really doubt AMD will just let everyone use its IP without a type of proprietory standard, Intel and Nvidia have had such standards for some time now and AMD now has a proprietory standard that either you use and pay AMD money for or you dont' get optimal performance.

 

[de5_Roy]

Lots of talk on Mantle but I really doubt AMD will just let everyone use its IP without a type of proprietory standard, Intel and Nvidia have had such standards for some time now and AMD now has a proprietory standard that either you use and pay AMD money for or you dont' get optimal performance.

amd doesn't have that sort of weight. they always go the way of open standards because that's the only way to combat closed standards and monopolistic pracitces by intel and nvidia. if the power balance was different, amd woulda exchanged place with nvidia (which they will, within the next few years).

besides, if you (and the people who support amd) want amd to become like intel and nvidia, what's the point of supporting amd in the first place? ;-)

 

[sarinaide]

Lots of talk on Mantle but I really doubt AMD will just let everyone use its IP without a type of proprietory standard, Intel and Nvidia have had such standards for some time now and AMD now has a proprietory standard that either you use and pay AMD money for or you dont' get optimal performance.

amd doesn't have that sort of weight. they always go the way of open standards because that's the only way to combat closed standards and monopolistic pracitces by intel and nvidia. if the power balance was different, amd woulda exchanged place with nvidia (which they will, within the next few years).

besides, if you (and the people who support amd) want amd to become like intel and nvidia, what's the point of supporting amd in the first place? ;-)

Not everything will be closed standards but if you stumble on something that has massive proprietory benefits and in the end result in guarenteed cashflow, what any AMD, neutral or competitive fan will want is AMD's continued existence and competitiveness. Mantle may help.

 

[juanrga]

2.) There is no consumer software for ARM that functions at a desktop level. There will not be anytime soon either.

As I said before this is untrue.

Like it or not, you're playing against Intel...even if ARM was somehow better at desktop (won't happen), Intel won't roll over for the same reasons they screwed AMD so many times over the years.

As I said before, it is not David vs Goliath thing.

It is Intel vs [ AMD + Nvidia + Samsung + Apple + Qualcomm ... ]

I am not here for agreeing with everyone! I am here to state my opinion and for learning something new.

It seems you are one of those few who don't still understand that ARM is already in the same performance envelope than x86.

Phone (ARM A8): 4 GFLOP
Phone (ARM A9): 24 GFLOP
Desktop FX-8350 (Piledriver): 256 GFLOP
Server Opteron (Interlagos): 384 GFLOP
Server Seattle (ARM A57): 256 GFLOP

Opinions are fine but you're touting numbers for a Seattle part that are a year away from release, as if it's here today.

You can't say "already in the performance envelope" when the parts are not for sale. And we all know how good AMD is at timely releases. Specs change, products slip.

I still can't TODAY buy a motherboard with a Kabini on it and they were "released" how long ago? 5 months?

You can compare it to future still to be released Warsaw, Berlin, Kaveri... if you want, the result is the same: Seattle is "already in the performance envelope" than x86 chips, because ARM64 chips are already in the same performance envelop than x86.

Only to add that the above figure is assuming lower clock for Seattle. AMD said that the chip would run a 2GHz or more. I did the GFLOP computation for 2 GHz. The A57 Chip is prepared to run up to 3Ghz or so.