×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

AMD A10 Kaveri APU Details Emerge, Combining Steamroller and Graphics Core Next

Soulskill posted about 5 months ago | from the onward-and-upward dept.

AMD 105

MojoKid writes "There's a great deal riding on the launch of AMD's next-generation Kaveri APU. The new chip will be the first processor from AMD to incorporate significant architectural changes to the Bulldozer core AMD launched two years ago and the first chip to use a graphics core derived from AMD's GCN (Graphics Core Next) architecture. A strong Kaveri launch could give AMD back some momentum in the enthusiast business. Details are emerging that point to a Kaveri APU that's coming in hot — possibly a little hotter than some of us anticipated. Kaveri's Steamroller CPU core separates some of the core functions that Bulldozer unified and should substantially improve the chip's front-end execution. Unlike Piledriver, which could only decode four instructions per module per cycle (and topped out at eight instructions for a quad-core APU), Steamroller can decode four instructions per core or 16 instructions per quad-core module. The A10-7850K will offer a 512-core GPU while the A10-7700K will be a 384-core part. Again, GPU clock speeds have come down, from 844MHz on the A10-6800K to 720MHz on the new A10-7850K but should be offset by the gains from moving to AMD's GCN architecture."

cancel ×
This is a preview of your comment

No Comment Title Entered

Anonymous Coward 1 minute ago

No Comment Entered

105 comments

Why all the polish namings? (-1, Flamebait)

Anonymous Coward | about 5 months ago | (#45591801)

Is there something about polish that excites AMD?

Re:Why all the polish namings? (-1)

Anonymous Coward | about 5 months ago | (#45591871)

They love to gag on Polish sausages.

Once burnt, twice shy (-1, Troll)

Taco Cowboy (5327) | about 5 months ago | (#45591911)

Dunno about you, but I ain't gonna be excited by AMD's offerings anymore, after what they dished to us on their Bulldozer roll out

For more than a year before Bulldozer came into being they told us that the Bulldozer gonna be revolutionary - they hyped the Bulldozer so much that many forums were filled with people just couldn't wait to get their hands on it

But when the rubber hits the tarmac everything gone flat - that Bulldozer was a dog

No man, I just ain't gonna believe AMD anymore

Re:Once burnt, twice shy (3, Insightful)

Heretic2 (117767) | about 5 months ago | (#45592303)

Dunno about you, but I ain't gonna be excited by AMD's offerings anymore, after what they dished to us on their Bulldozer roll out

For more than a year before Bulldozer came into being they told us that the Bulldozer gonna be revolutionary - they hyped the Bulldozer so much that many forums were filled with people just couldn't wait to get their hands on it

Did you think the same thing about Intel after the Pentium4 too?

Re:Once burnt, twice shy (1)

Kjella (173770) | about 4 months ago | (#45593639)

Did you think the same thing about Intel after the Pentium4 too?

This is starting to get ancient history but as I remember it Intel was pushing the PIII hard right up until the launch of PIV, they were never in the "please hold out a little longer, please don't buy an AMD our PIV is going to be twice as fast and give free blowjobs" mode. Of course they did keep pushing it after everyone knew it was a dud, after all that's what they had to sell much like AMD now. It's pre-launch when all you get are "leaks" that are really plants, PR statements and astroturf/fanboy hype but no real benchmarks to compare and the hype goes over the top that it backfires, Bulldozer was hailed as AMD's savior long before it hit the stores. When you build up that kind of hype and don't deliver the pendulum swings the other way, it's not just poor it's outright horrible compared to what you expected.

Re:Once burnt, twice shy (0)

Anonymous Coward | about 4 months ago | (#45596341)

Yes, that's why I had AMD CPUs at the time, starting with T-Bird until they royally screwer up going to socket AM2 and virtually no CPU improvement meanwhile Intel had moved onto core and was thoroughly thrashing them at lower clock speeds.

ATM we're in the EXACT OPPOSITE situation that we were in the early - mid 00s with AMD this time pushing clocks in a feeble attempt to make up for underperforming CPU arch.

That said, I'm not really happy with hothardware's conclusion as AMD DID change the arch a bit, so they cannot possibly make conclusions yet like dropping clocks by 20% will negate the 10-20% arch perf increase. Apparently commenters of that article imply that there are other articles out there about kaveri, but I haven't looked for/read them yet, so I'll leave it at this. ...and one last thing...
AMD(more specifically ATI) cannot write drivers to save their lives, plus they're apparently in the business of making space heaters obsolete...

Re:Once burnt, twice shy (0)

Anonymous Coward | about 4 months ago | (#45597387)

It would be better for both companies to focus on combining their cpus with their top of the line graphics for an APU rather than top of the power-saving-bottom-of-the-barrel graphics. The people who will benefit the most from an APU won't have any idea what an APU is for another 10 years at least...They'll just buy the newest laptop/pre-built and use whatever it comes with.

I realize it would be a ridiculous amount of power consumption and heat generation, to the point of probably not being viable, but at the very least they could build it so that the APU could be paired with ANY discrete graphics card instead of only really weak ones...

Re:Once burnt, twice shy (5, Insightful)

Fjandr (66656) | about 5 months ago | (#45592325)

So did you stop believing in Intel after their bugged Pentiums rolled off the line? ARM only from now on, until they screw something up?

Just because a company has a product that flopped doesn't mean they won't ever produce anything good again. While it's fine to not be excited until it's actually hit shelves, writing them off for the end of time seems a bit premature.

Re:Once burnt, twice shy (1)

0123456 (636235) | about 4 months ago | (#45594975)

So did you stop believing in Intel after their bugged Pentiums rolled off the line?

The Pentium had a bug that was fixed. Steamroller was just a horribly flawed design that didn't come close to what it was supposed to be.

Re:Once burnt, twice shy (0)

Anonymous Coward | about 5 months ago | (#45592349)

Linux Benchmarks offered a better view of AMD Bulldozer cpu!

Re:Once burnt, twice shy (2)

Smauler (915644) | about 5 months ago | (#45592355)

AC wrote : They love to gag on Polish sausages.

You wrote : Dunno about you, but I ain't gonna be excited by AMD's offerings anymore, and some other bumpf.

How exactly were you replying to the AC?

I know policy is to stick your comment as high as possible, if possible..... but you replied to someone who said "They love to gag on Polish sausages". You must have know that you weren't actually replying to them.

Re:Why all the polish namings? (3, Interesting)

nikkipolya (718326) | about 5 months ago | (#45591887)

If "Kaveri" is what you are referring to, it also happens to be the name of a river in South India.

Re:Why all the polish namings? (2)

Tapani_Q (876850) | about 5 months ago | (#45592667)

Maybe, but Kaveri APU translates as "friend help" in Finnish...

Re:Why all the polish namings? (1)

gauthamg (2427650) | about 4 months ago | (#45593763)

Indus, the name of the notebook platform in the Kaveri series of APUs, is also a river that flows through India.

Re:Why all the polish namings? (4, Informative)

Luckyo (1726890) | about 5 months ago | (#45592177)

"Kaveri" in finnish means "pal" as in a friend.

Which is actually pretty fitting for the chip that has CPU and GPU on one die.

Re:Why all the polish namings? (2)

higuita (129722) | about 4 months ago | (#45593609)

For several years now, AMD is using islands names [wikipedia.org] for the internal GPU names (being the type/location of island used to group families) and river names [wikipedia.org] for the CPUs/APUs. Kaveri [wikipedia.org] is a river in India... that just by luck is also a word in Polish and Scandinavia.

Phenom || instead of Bulldozer (2)

harshal.tawade (3010845) | about 5 months ago | (#45591853)

I think AMD used Phenom || instead of bulldozer, as Phenom has already proven its significane over the bulldozer. Besides implementing CGN into pehnom || would againg start phenom ||'s production.

Re:Phenom || instead of Bulldozer (2, Insightful)

Billly Gates (198444) | about 5 months ago | (#45591893)

I wish I had mod points.

Proud Phenom II user here. Awesome chip and I still use it on the gaming platform ... from 2010?!

I like the 6 core and only 10% slower than an icore 7! ... 1st generation icore 7 from 2010. :-(

IT is obsolete and I see no purpose to upgrade my system with it with another one. It is like making a multicore 486 at 3ghz. It would not hold a candle to anything made in the last 15 years.

AMD needs to do an Intel. Dump Netburst 2.0. Intel failed with the pentium IV but after 3 years the core2duo put them on the roadmap again. Intel kept trying to tweak and add instructions and overclo0ck the bloated Pentium IV until they gave up. AMD give up on steamroller ok? An integrated GPU was a nice idea that could have been the next 290X for a fraction of the cost, but like Itanium it never followed through. Make this a low end crap low power APU for tablets and a new architecture and another video card for everything else. No s hared FPUs either as that failed as well.

Re:Phenom || instead of Bulldozer (-1)

Smauler (915644) | about 5 months ago | (#45592421)

Proud Phenom II user here. Awesome chip and I still use it on the gaming platform ... from 2010?!

I'm sorry... no you don't.

I run a core 2 duo on a motherboard 8 years old, with a gtx460 (it was originally with an 8800GT, which I pensioned off) and I will guarantee you my PC outperforms most PCs sold today, gaming-wise. Do not believe the hype. Look at the numbers.

I used to run an athlon with a ti4200 for the same reason, and with the same result.

Re:Phenom || instead of Bulldozer (3, Insightful)

Lonewolf666 (259450) | about 4 months ago | (#45593267)

I run a core 2 duo on a motherboard 8 years old, with a gtx460 (it was originally with an 8800GT, which I pensioned off) and I will guarantee you my PC outperforms most PCs sold today, gaming-wise.

The Core2Duo was a good chip for its time, but current Intels outperform it by a wide margin. I'm pretty sure that even current AMDs beat it, despite their Bulldozer mis-design. Likewise, the GTX460 will be beaten by modern cards.

If you are talking about Intel PCs that use only integrated graphics, your claim might be true. But gamers usually understand that they need a discrete GPU ;-)

i dont believe you (1)

cheekyboy (598084) | about 4 months ago | (#45593365)

I had a core2 E5300, and I replaced it with a new Q6600 from ebay dirt cheap, yes more cores, a bit hotter, but more cores is more flops.

I'll be looking for an even faster Q9550, as its close to i7s, but way cheaper.

Yes, we can buy full PCs for $300+ that give you latest i7s running way faster.

But reusing old Qxxx's on older mbs is close enough when it costs less than 3 pizzas.

Re:i dont believe you (1)

Billly Gates (198444) | about 4 months ago | (#45596993)

But like the phenom II it is obsolete compared to todays CPU.

Actually the Phenom II is a step up and an AthlonFX64 would be the AMD equivalent of your setup. Fine for light work but I would not want to purchase one today if needing a new computer unless I am broke and then I would buy it at Salvation Army used and just rewipe it.

Only games, compiling, and HD video editing require anything newer than a 2006 era machine which is why XP just wont die already! First it was multitasking you need a $3000 machine and upgrade every 2 years, then spreadsheets, then database work, then just games, and now just the 3 scenarios above.

In another 5 - 10 years Windows 7 will be even more of an XP and no one and I mean on ONE will ever need to upgrade again. Even a 7 year old system has amazing powers at hundreds of millions of operations a second and would be a geeks wet dream 2 decades ago as a mini supercomputer.

What's the GPU for? (3, Interesting)

rsilvergun (571051) | about 5 months ago | (#45591855)

Laptops? While I'd love to see a nice, low cost CPU/GPU combo that can hang with my (rather meager) Athlon X2 6000+ and GT 240, I'm still running pretty low end gear. If this is targeted at enthusiasts they're just going to replace it with a card...

Re:What's the GPU for? (0, Interesting)

Anonymous Coward | about 5 months ago | (#45591933)

For everyone that doesn't play games. Every Intel CPU for years has included a GPU which is perfectly good for HD Video, web, even CAD. The higher end versions actually work quite well on modelling and games that are a few years old.

Every new release means less and less need for a discrete GPU at all (look up Iris Pro). AMD have to try to keep up with Intel or they will be sunk. Nvidia will loose either way.

Re:What's the GPU for? (1, Flamebait)

Billly Gates (198444) | about 5 months ago | (#45591959)

Catch up with Intel?

AMD is creaming Intel in this area. Intel's graphics SUCK. They are as fast as 2006 era graphics and makes game developers pull their hair out and scream more than web developers with IE 6 as they need many work arounds with such poor performance.

The new 5000 series is only 5 years obsolete from what I hear. But Intel likes it this way as they want people to think it is 1995 all over again and buy beefy over priced cpus for better fps instead of upgrading a video card.

AMD has made some mistakes sadly. One is to leave pentium IV/netburst 2.0 behind and invest a new architecture. Make this nice APU for tablets and cellphones with an arm/radaeon that can do 1080p and angry birds 3d in glory.

Re:What's the GPU for? (0)

Anonymous Coward | about 5 months ago | (#45592019)

Iris Pro is on par with the 650m for gaming and the 650m isn't even 2 years old. In compute it creams it. Where did you get this 5 years obsolete bullshit?

Re:What's the GPU for? (4, Informative)

Rockoon (1252108) | about 5 months ago | (#45592285)

Iris Pro is on par with the 650m for gaming and the 650m isn't even 2 years old.

The Iris pro is on a $500 part only made possible by bolting expensive eDRAM onto a processor that otherwise would cost $300.

The mind boggles at how people think that this is boasting material.

Re:What's the GPU for? (4, Informative)

Anonymous Coward | about 5 months ago | (#45592071)

> AMD is creaming Intel in this area. Intel's graphics SUCK. They are as fast as 2006 era graphics

Nope.

http://www.notebookcheck.net/Intel-Iris-Pro-Graphics-5200.90965.0.html

"Thanks to the fast eDRAM memory, the average performance of the Iris Pro is only about 15 percent behind the dedicated mid-range cards GeForce GT 650M and GT 750M. This makes the Iris Pro even faster than AMDs Radeon HD 8650G and the fastest integrated GPU of 2013. Therefore, many current games can be played fluently in medium or high detail settings and a resolution of 1366 x 768 pixels. In some older or less demanding titels like Diablo III or Fifa 2013, even higher resolutions or quality settings may be possible."

Re:What's the GPU for? (1)

Dr Max (1696200) | about 5 months ago | (#45592191)

Are you saying the gt 650mobile and gt750mobile are the same performance? That seems like a big rip off from NVIDA. Also who can you play a modern game at 1366 X 768? you wont get much detail in fps.

Re:What's the GPU for? (0)

Anonymous Coward | about 5 months ago | (#45592631)

Yes, there isn't much in it. The 6->7 just means that the 7 is newer (though often they just take existing products and bump up the number). The 50 is the performance level.

Re:What's the GPU for? (0)

Anonymous Coward | about 5 months ago | (#45592547)

notebookchecks benches for some reason don't stand the same way as other benches and actual game benches.

Re:What's the GPU for? (1)

viperidaenz (2515578) | about 5 months ago | (#45592075)

They're up to mid range 2009 level
The Iris 5200 is about the same performance as a discrete GT 240, like what gp said they have.

Re:What's the GPU for? (0)

Anonymous Coward | about 5 months ago | (#45592593)

GT 240 was called GT9600 then. It was already rather low range at that time. The midrange would have been the GT260, very different architecturally.

Re:What's the GPU for? (0)

Anonymous Coward | about 5 months ago | (#45592171)

From my point of view this processor is a game changer! For the first time programmers will be able to offload software to the gpu, and back to the CPU without the need to copy data to the GPU's memory!

The software optimizations I hope to see soon are:
1. Hash table lookups in languages like Python and Ruby coded to to search using the GPU. Consid
2. Database engines coded to use the GPU Indexing is the first thing that comes to mind. There is already precedent with SQLITE: http://www.cs.virginia.edu/~skadron/Papers/bakkum_sqlite_gpgpu10.pdf (go to page 7 for the performance information)

Re:What's the GPU for? (0)

Anonymous Coward | about 5 months ago | (#45592365)

You benchmark!

Re:What's the GPU for? (1)

Bengie (1121981) | about 4 months ago | (#45603061)

Current Intel IGPs are about 10% slower than AMDs current. Intel is claiming some sizable performance boost in next gen IGPs, but the new AMD A10 is also getting that. We shall see.

Re:What's the GPU for? (1)

0123456 (636235) | about 4 months ago | (#45594995)

For everyone that doesn't play games.

If you don't play games, why do you care about 3D performance?

Sure, you might do CAD or similar 3D work, but then you can afford a real GPU.

Re:What's the GPU for? (1)

bigdanmoody (599431) | about 4 months ago | (#45597791)

You will likely not be able to do CAD work on an Intel GPU. Intel's OpenGL support is awful, and most professional CAD and CAM software relies pretty heavily on OpenGL.

Re:What's the GPU for? (0)

Anonymous Coward | about 4 months ago | (#45602939)

This is rubbish I do CAD work on an intel GPU all the time.

Re:What's the GPU for? (2)

plasticsquirrel (637166) | about 5 months ago | (#45591973)

Laptops? While I'd love to see a nice, low cost CPU/GPU combo that can hang with my (rather meager) Athlon X2 6000+ and GT 240, I'm still running pretty low end gear. If this is targeted at enthusiasts they're just going to replace it with a card...

Basically it's a CPU + GPU bundle that only takes up the size of the CPU. It's not meant for the hardcore gamers, just pragmatists who are looking for value and simplicity. Like every company, AMD has a product lineup -- different products are marketed in different ways (although AMD is not always as clear about the matter as it could be). For the price, these chips are usually pretty good values.

Re:What's the GPU for? (1)

Bengie (1121981) | about 4 months ago | (#45603099)

Actually, their intent is for the IGP to be used like a co-processor. The IGP has about 2 magnitudes lower latency than discreet GPUs, that makes a difference.

Re:What's the GPU for? (1)

Rockoon (1252108) | about 5 months ago | (#45592133)

You ask in the title "What's the GPU for?"

You are all over the place. You wonder what the GPU is for, then state that you actually will love this very product because its a low cost CPU/GPU combo, but then specifically name your "rather meager" rig that is even slower than the last generation of APU's in both CPU and GPU performance (ie, your rig is the thing that cannot hang), and finish the whole thing off hypothesizing that AMD might in fact be targeting "enthusiasts."

Are you some sort of discordian shill?

Re:What's the GPU for? (1)

gman003 (1693318) | about 5 months ago | (#45592383)

I believe if you have a discrete GPU based on the same architecture (GCN in this case), you can use both simultaneously for a small speed boost, or switch between them depending on load (so your 250W video card doesn't need to spin its fans up just to render the desktop).

There's also some consideration for using the integrated GPU for lower-latency GPGPU stuff while using the discrete GPU for rendering. I don't think that's actually used in anything yet, but I'm not actually using an APU in any of my machines yet.

Laptops (1)

DarthVain (724186) | about 4 months ago | (#45594925)

Exactly. That's why the big deal with Intel's Haswell was basically "consumes a lot less power", the rest was incremental and a few added instructions for the future. AMD seems to have the same tech analysts as Netcraft crying "The Desktop is dying, the desktop is dying!"

If you play to own anything that is a desktop, then anything like this from AMD or Intel, that can be replaced with something that is TWICE is fast using the cheapest 50$ dedicated video card, makes the advances absolutely meaningless.

In fact, the only thing this effects is that you might be able to get away from buying a 2000$ gaming laptop and buying a 500$ laptop that can marginally play most games. Congratulations for moving the mediocrity yard stick a bit further...

Re:Laptops (1)

Bengie (1121981) | about 4 months ago | (#45603141)

There are some upcoming new techs that make use of IGPs, in that the IGP is potentially 10x faster than a discreet GPU because of latency issues.

Beat that icore3!! (0)

Anonymous Coward | about 5 months ago | (#45591869)

Come on AMD you can do it and then we can party like is 2009!

I do not know how they stay in business.

GCN goodies (0)

Anonymous Coward | about 5 months ago | (#45591913)

"first chip to use a graphics core derived from AMD's GCN (Graphics Core Next) architecture" is kinda inaccurate, given that their GPU's are "chips" and have been in production using GCN for quite a while now The ps4 and xbox one also used GCN, and were even APUs.

Will this new Kaveri have True Audio? I can assume it will support mantel. I wonder if they are going to offer a configuration that will work with GDDR5 or DDR4. There are some interesting things happening on the memory front these days!

Re: GCN goodies (1)

asliarun (636603) | about 5 months ago | (#45591991)

I think that Kaveri would become a very compelling choice for htpc and even gaming. You could easily build an entry level steam machine with this and because there is no discrete GPU, you could do a really small form factor with good airflow.

An audio server that uses true audio is another intriguing option.

There are even fanless cabinets that will take up to 95 watt CPUs like this one.

http://www.fanlesstech.com/2013/11/asktech-nt-zeno3.html [fanlesstech.com]

I also have a noob question. Can kaveri or even the existing a10 chips be used in crossfire mode? Meaning integrated graphics crossfired with a discrete GPU. Does it even make sense to do something like this? For example, it could be a good upgrade path.

Re: GCN goodies (1)

Dr Max (1696200) | about 5 months ago | (#45592197)

"I also have a noob question. Can kaveri or even the existing a10 chips be used in crossfire mode? Meaning integrated graphics crossfired with a discrete GPU. Does it even make sense to do something like this? For example, it could be a good upgrade path."

Yes and it should even automatically set it up for you.

Re: GCN goodies (1)

asliarun (636603) | about 5 months ago | (#45591999)

I think that Kaveri would become a very compelling choice for htpc and even gaming. You could easily build an entry level steam machine with this and because there is no discrete GPU, you could do a really small form factor with good airflow.

An audio server that uses true audio is another intriguing option.

There are even fanless cabinets that will take up to 95 watt CPUs like this one.

http://www.fanlesstech.com/2013/11/asktech-nt-zeno3.html [fanlesstech.com]

I also have a noob question. Can kaveri or even the existing a10 chips be used in crossfire mode? Meaning integrated graphics crossfired with a discrete GPU. Does it even make sense to do something like this? For example, it could be a good upgrade path.

Re: GCN goodies (0)

Anonymous Coward | about 5 months ago | (#45592059)

It's 2013 and slashdot hasn't implemented a duplicate post detector?
Ah well, reuters.com haven't either so at least you're in good company.

Re: GCN goodies (0)

Anonymous Coward | about 5 months ago | (#45592077)

Can kaveri or even the existing a10 chips be used in crossfire mode?

If it's like the other AMD APUs then yes you can, though your selection is limited to compatible ones.

Re: GCN goodies (1)

asliarun (636603) | about 5 months ago | (#45592095)

Apologies for the double post. The submit button didn't respond for several seconds so I clicked it again. In fact, I think I did it thrice.

OpenCL 2.0 support? (1)

nikkipolya (718326) | about 5 months ago | (#45591923)

Will this new architecture of AMD support OpenCL 2.0?

Re:OpenCL 2.0 support? (0)

Anonymous Coward | about 5 months ago | (#45592131)

I don't know about OpenCL but I'm personally going to watch those hotchips25 HSA tutorials when they supposedly come available at the middle of this month. This year's conference contain some further information about Richland and Kabini SOC as well.

Re:OpenCL 2.0 support? (1)

Bengie (1121981) | about 4 months ago | (#45603177)

These are fully programmable GPUs that support preemptive multitasking, protected mode memory-addressing, can even cause page faults to use virtual memory transparently with the OS. Now for the good part. Fully C and C++ compliant. If you can write OpenCL in C or C++, then you can write it on these GPUs.

the problem is... (1)

Anonymous Coward | about 5 months ago | (#45592055)

"enthusiasts" don't give a rat's tail about on-board graphics.. so strip that shit out and give us an unlocked processor for less coin. tyvm.

Re:the problem is... (1)

serviscope_minor (664417) | about 4 months ago | (#45593789)

so strip that shit out

It will be much harder to have the GPU cache coherent with the CPU if that "shit" is stripped out. It is this advance far more than anything else which makes this architecture hold promise. There's now some crazy amount of arithmetic performance available (far, far more than even the most expensive Intel chips) but without the usual high latency (and pain in the ass) trip to and grom a graphics card.

That "shit" will make the GPU suitable for a substantially broader range of problems since it removes one of the primary disadvantages.

Re:the problem is... (1)

DuckDodgers (541817) | about 4 months ago | (#45599923)

Yes, this isn't an enthusiast part, it's a budget part.

To be fair, most of the PC market is budget. We the enthusiasts are the minority. This thing will probably play Starcraft 2, Crysis 3, Battlefield Whatever, BioShock Infinite Squared, etc... well enough for someone who doesn't mind 35 fps on an HD monitor. If you want 90 fps on a 4K monitor, you'll have to move up to Core i5 + mid level or better discrete graphics card.

Dual graphics (1)

edxwelch (600979) | about 5 months ago | (#45592115)

Kavari looks good for a budget gaming PC, but I think they are being a bit optimistic about the "dual graphics" feature. This is where you pair the iGPU with a dGPU, to get better performance. AMD has never been able to get this feature to work properly. All it does is create "runt" frames, which makes the FPS look higher, but without giving any visual improvement.

http://www.tomshardware.com/reviews/dual-graphics-crossfire-benchmark,3583.html [tomshardware.com]

Kaveri is a poor version of the Xbox One chip (2, Insightful)

Anonymous Coward | about 5 months ago | (#45592367)

Kaveri should be properly compared to the chips in the PS4 and Xbone. As such, it can be said that Kaveri is significantly poorer than either.

-Kaveri is shader (graphics) weak compared to the Xbone, which itself is VERY weak compared to the PS4.
-Kaveri should be roughly CPU equivalent (multi-threaded) to the CPU power of eother console
-Kaveri is memory bandwidth weak compared to the Xbone, which itself is VERY bandwidth weak compared to the PS4
-Kaveri is a generation ahead of the Xbone in HSA/hUMA concepts, but the PS4 is a generation ahead of the Kaveri

There was ZERO reason for AMD to release a new APU that was significantly weaker than even the solution in the Xbox One, but sadly this is what the idiots at AMD are doing. The Kaveri integrated graphics are far to poor for anyone who really cares about PC gaming, reducing the worth of Kaveri to a power hungry, fairly decent 4-core CPU. The REAL Kaveri II (not the Kaveri which is coming around Xmas 2013 under the confusing name of Kaveri II) will be released around Xmas 2014 or later, and should be somewhat more powerful than the Xbox One. Kaveri II will also share the same sophisticated HSA/hUMA that is currently only found in the PS4.

And maybe by some miracle, AMD will grow a brain, and give Kaveri II a 256-bit memory bus to GDDR5 memory, not the stinking 128-bit bus to DD3 that Kaveri has.

At least Kaveri has True Audio (like the PS4 and 260/290 GPUs), and hopefully AMD's Mantle will enable PC systems using Kaveri with discrete graphics cards to still benefit from doing some work on the integrated GPU cores as well.

Kaveri is much better as PC chip (2)

hkultala (69204) | about 5 months ago | (#45592705)

- Single-thread performance matters much more than multi-thread performance, and Kaveri has almost twice the single-thread performance of the Xbone and PS4 chips.

- Memory bandwidth is expensive. You either need wide and expensive bus, or expensive low-capasity graphics DRAM which need soldering, and means you are limited to 4 GiB of memory(with the highest capasity GDDR chips out there), with zero possibility of late upgrading it, or both(and MAYBE get 8 giB of soldered memory). Though there has been rumours that Kaveri might support GDDR5, for configurations with only 4 GiB of soldered memory.

- And when you have that limited memory bandwidth, it does not make sense to waste die space on creating monster GPU which is starved by the lack of bandwidth.

- ALL the mentioned chips are of same generation. All support cache-coherent unified memory.

As PC chip, Kaveri makes much more sense:

- Software that matters on PC cannot use 8 threads. Kaveri is much faster at most software
- Weaker GPU side, ability to use cheap DDR3, and narrower memory bus makes Kaveri chip and kaveri-bases systems cheaper to manufacture
- The CPU can be socket, need to to be soldered, and the memory chips can use DIMMs instead of soldering to motherboard. Ability to upgrade something and system manufacturers to easily create different configurations.

Re:Kaveri is much better as PC chip (1)

Lonewolf666 (259450) | about 4 months ago | (#45593221)

- Memory bandwidth is expensive. You either need wide and expensive bus, or expensive low-capasity graphics DRAM which need soldering, and means you are limited to 4 GiB of memory(with the highest capasity GDDR chips out there), with zero possibility of late upgrading it, or both(and MAYBE get 8 giB of soldered memory). Though there has been rumours that Kaveri might support GDDR5, for configurations with only 4 GiB of soldered memory.

In general (not necessarily relating to Kaveri as-is) 8 giB of fast, soldered memory as in the PS4 would make sense for a PC.

The current APUs are seriously bandwidth starved. In reviews where a Phenom II with a discrete graphics card is pitted against an APU with similar clock speed and number of graphics cores, the Phenom II usually wins (except benchmarks that don't use the GPU much). Overclocking the memory helps the APU some, which is further evidence.

With PS4 style memory that problem could be solved, admittedly at the expense of being able to add more RAM. But looking back on my last three computer purchases, I always ended up doing a complete update instead of adding RAM to the existing PC. Because the CPU and GPU were also obsolete, and with a new CPU came a new mainboard with a different type of RAM.

Re:Kaveri is much better as PC chip (1)

mrchaotica (681592) | about 4 months ago | (#45595369)

In reviews where a Phenom II with a discrete graphics card is pitted against an APU with similar clock speed and number of graphics cores, the Phenom II usually wins... looking back on my last three computer purchases, I always ended up doing a complete update instead of adding RAM to the existing PC. Because the CPU and GPU were also obsolete...

Because my computer is a Phenom II, this might be the first time I add RAM to an existing PC.

Re:Kaveri is much better as PC chip (1)

Bengie (1121981) | about 4 months ago | (#45603375)

APUs are only bandwidth starved when working with large datasets. There is a huge class of work-loads that are small amounts of data but require a lot of processing. In these cases, memory bandwidth isn't the limiting factor in any way. In many of these cases, it's faster to process the data on a 80GFlops CPU than to offload to a 3TFlops discreet GPU. Now we have a 900TFlop GPU that is only a few nanoseconds away from the CPU instead of tens of microseconds.

Re:Kaveri is much better as PC chip (0)

Anonymous Coward | about 4 months ago | (#45596515)

five bucks says at least one of Sony or MS wanted kaveri's CPU for their console, but switched to Jaguar for schedule reasons...

Re:Kaveri is a poor version of the Xbox One chip (0)

Anonymous Coward | about 4 months ago | (#45593051)

There was ZERO reason for AMD to release a new APU that was significantly weaker than even the solution in the Xbox One, but sadly this is what the idiots at AMD are doing.

uh... maybe pricing?

Cache Money! (1)

DarthVain (724186) | about 4 months ago | (#45595063)

I could be wrong, but it had little to do with AMD and more to do with MS specifications.

The only difference between the graphic cores on the Xbox One and PS4 is that the PS4 uses newer DDR5 memory, while the xbox DDR3. Xbox tried to compensate for the slower memory by adding additional cache on die, however this takes up physical real estate, which forced them to use a couple less cores (in exchange for faster memory handling). To simply say one is faster/better than the other is a bit misleading.

The reason for this was that MS speculated that the new DDR5 memory would be in short supply and there would not be enough production to supply their manufacturing. Considering the PS4, if they both used it, they would have probably been correct.

So anyway you are only looking at the GPU aspect, put it is integrated with the CPU, that does include an increased amount of cache on the xbox side. I think it is a bit early to tell what real life difference it makes. Early comparisons say little to none. Given time maybe, of course by then MS may adapt their design.

I am unbiased in this as I am not buying either, at least not for some time...

Re:Kaveri is a poor version of the Xbox One chip (1)

DarthVain (724186) | about 4 months ago | (#45595117)

OK, I admit I didn't read too carefully. Thought you were just comparing the Xbox and PS4 situation.

However it is likely for the exact same reason. When is DDR5 coming out? Can you actually buy some? No you cannot. Why design and release something you cannot use?

Reminds me of the funny MB with two slots, one for one kind of DDR VS another. I have no doubt the have another version all ready for "release" once DDR5 become viable and common place.

Re:Kaveri is a poor version of the Xbox One chip (0)

Anonymous Coward | about 4 months ago | (#45604951)

Kaveri is shader (graphics) weak compared to the Xbone, which itself is VERY weak compared to the PS4

512 -> 768 -> 1152. Perhaps the "VERY" scream is little too strong expression here.

-Kaveri is a generation ahead of the Xbone in HSA/hUMA concepts, but the PS4 is a generation ahead of the Kaveri

Where was the announcement about PS4 HSA? I didn't see it. Xbone's scratchpad memory doesn't differentiate the console in this manner. Kaveri should be the first APU to implement HSA, as the first step towards lifting the GPU to the status of a first class citizen for the general purpose software, which the games for both consoles are definitely not.

give Kaveri II a 256-bit memory bus to GDDR5 memory, not the stinking 128-bit bus to DD3 that Kaveri has.

I'd go with DDR4 plus Xbone style reconfigurable cache/scratchpad memory to give some expandability without compromising scalability.

Article is crap and misses biggest feature! (5, Interesting)

DudemanX (44606) | about 5 months ago | (#45592521)

This is the chip that unites the CPU and GPU into one programing model with unified memory addressing. Heterogeneous System Architecture(HSA) and Heterogeneous Uniform Memory Access(HUMA) are the nice buzzword acronyms that AMD came up with but it basically removes the latency from accessing GPU resources and makes memory sharing between the CPU cores and GPU cores copy free. You can now dispatch instructions to the GPU cores almost as easily and as quickly as you do to the basic ALU/FPU/SSE units of the CPU.

Will software be written to take advantage of this though?

Will Intel eventually support it on their stuff?

Ars article on the new architecture. [arstechnica.com]

Anandtech article on the Kaveri release. [anandtech.com]

Re:Article is crap and misses biggest feature! (1)

John Allsup (987) | about 4 months ago | (#45593753)

The thing I hope to see explored is using such a chip with discrete graphics.  The ability for the on-chip GPU to access the same memory will allow some things to be optimised (but possibly not all graphics).  I imagine in future we'll see a repeat of what happened with FPU coprocessors in the late 80s onwards: (this is a rough picture, and you are advised to look up the precise details if you're interested)

1. The 386 had a discrete FPU, called the 387
2. The 486 integrated the FPU, and all subsequent x86 processors did the same.
3. Certain common FPU operations began to be implemented on CPU with special instructions (SSE etc)
4. Certain common FPU operations began to be implemented on discrete accelerator chips (GPUs).
5. GPUs started being placed first in the same package as the CPU, then subsequently more closely integrated.

I imagine in the not too distant future that GPU functionality will be as integrated with CPUs as FPUs are now, with external discrete
GPUs, possibly with lightweight general purpose CPUs to manage things, available for uses (such as gaming) where built-in GPUs are
not enough.

Re:Article is crap and misses biggest feature! (1)

LoRdTAW (99712) | about 4 months ago | (#45594805)

The x86 external FPU started with the Intel 8087 [wikipedia.org] which was launched during 1980. The 8087 was the FPU for the 8086, the first generation of x86. The 80286 followed the same logic using an external FPU, 80287.

The 386 was the first to integrate the FPU onto the CPU die in the DX line of 386's. The 386SX was a 386 without the FPU which depending on the computer/motherboard could be upgraded with a 387 coprocessor.

So:
386DX = 386+FPU
386SX = 386, no FPU

The 486 also followed the same logic offering a DX or SX version. There was an i487 FPU upgrade but it was a DX that simply disabled the 486SX and took over the CPU bus.

The Pentium was the first x86 CPU to include the FPU by default.

Re:Article is crap and misses biggest feature! (3, Insightful)

the_humeister (922869) | about 4 months ago | (#45595173)

Your history is rather off. The 386 never had an integrated FPU. 386 DX had a 32-bit bus. The 386 SX had a 16-bit bus for cost saving measures. The 486 DX was the one with the integrated FPU, and that was the first to include the FPU by default. The 486 SX had the FPU fused off.

Re:Article is crap and misses biggest feature! (1)

LoRdTAW (99712) | about 4 months ago | (#45607229)

Ah shit, you're right. I forgot that the 386 didn't have an FPU and was confused by the 486SX/DX nomenclature.

Thinking back my father had two 386's at work. One a 386DX was for CAD and now that I think of it, it had a Cyrix "Fast Math" 387 FPU. Interesting thing was it had a slot which was two 8 bit ISA slots end-to-end that was a 32 bit expansion slot. Wasn't populated but was interesting. He also had a 386SX which was used for word processing and accounting/payroll. Later on we had two 486's.

Re:Article is crap and misses biggest feature! (0)

Anonymous Coward | about 4 months ago | (#45595717)

You're wrong about the 386. Both the SX and the DX versions came without an integrated FPU. The difference between the two versions was that the 386SX had a 16-bit data bus, while the 386DX had a 32-bit data bus (similar to the difference between the 8086 and 8088).

486 was the first Intel CPU with an integrated FPU and you're right that the i487 was a 486DX in a different socket, that disabled the 486SX on the motherboard.

Re:Article is crap and misses biggest feature! (1)

higuita (129722) | about 4 months ago | (#45594425)

Actually should be the driver work to support this.

When a app asks to copy something to the GPU, it ask the GPU drivers, that can use that zero-copy/remap magic and tell the apps its done.

So yes, it should be supported out of the box if the drivers support it right.

Re:Article is crap and misses biggest feature! (1)

edxwelch (600979) | about 4 months ago | (#45595885)

Games will almost certainly make use of uniform memory for loading textures faster. That feature will make it much easier to implement "mega-textures".

still crushing Intel (0)

slashmydots (2189826) | about 4 months ago | (#45595025)

The current Richland APUs have a native memory controller that runs at 1866MHz so if you put in 9-10-9 RAM of that speed and overclock it a hair, you get graphics performance that ranks at a 6.9-7.0 in the WEI in Win7. REmember, you have to jack up the memory speed since the GPU inside the CPU is using system memory instead of GDDR5. That rating is medium speed for games. So that's around $139 for the top of the line chip and $75 for the RAM.

Now let's look at Intel's solution for a basic gaming or HD video playback style computer. Oh crap, that's still slightly inferior at a modern i3 but whatever, let's go with that for about $140. 1600MHz RAM would be about $60 (both 8GB btw) and now we need an Nvidia GT640 to come close in performance. There goes $80. Intel just got demolished. Anyone building a basic gaming PC for a kid or something or a DVR PC, that's a no brainer. (remember, video encoding + hyperthreading = bad idea).

But wait, there's more! Their 6-core non-APU chip blows away an i3 and some of their i5 processors while costing almost half. So I'd even put one into a high end gaming system with a dedicated graphics card. I really wouldn't go with Intel for anything other than multiple single-core-only processes. Why is anyone still buying Intel?

Re:still crushing Intel (1)

mrchaotica (681592) | about 4 months ago | (#45595567)

Why is anyone still buying Intel?

Power consumption.

I really like AMD (in fact, all my computers since 1999 -- except for an old iMac -- have been AMD-based), but I really, really wish I could get a (socketed, not embedded) AMD APU with less than 65W TDP (ideally, it should be something like 10-30W).

I hate that when I ask people in forums "what's the lowest power consumption solution for MythTV with commercial detection and/or MP4 reencoding?" the answer is "buy Intel."

Re:still crushing Intel (0)

slashmydots (2189826) | about 4 months ago | (#45596139)

You're missing three important factors. One is that both brands downclock significantly when not in use so they're a lot closer in real world usage than you think on power consumption. Maximum TDP is just that, a maximum. That's why not many servers have AMD chips but as for desktops running normal tasks like web browsing, the CPU is reduced to a lower power state over 90% of the time.

Secondly, if it's not a laptop not many people really care. DVRs sort of make sense because of the actual heat though.

Third, to get a passmark performance rating of say 900, Intel can't do it. They need to add a dedicated GPU that puts the total TDP between the two at above an AMD solution. So AMD is actually more power efficient as a whole solution in some cases. If you want to use your DVR for moderate gaming as well, AMD will output higher performance with less heat.

Re:still crushing Intel (1)

0123456 (636235) | about 4 months ago | (#45596063)

But wait, there's more! Their 6-core non-APU chip blows away an i3 and some of their i5 processors while costing almost half.

Wow! AMD only need six cores to beat an Intel dual-core! They're totally crushing Intel, baby!

Back in the real world, if what you're saying is true, AMD woudln't be forced to sell these chips at bargain basement prices. I'm thinking of using one to replace my old Athlon X2 system, but only because it's cheap.

Re:still crushing Intel (0)

slashmydots (2189826) | about 4 months ago | (#45596291)

I don't care about principle or theory. They can have 12 cores for all I care. You know why HP has 30+% of the market? Because they're the cheapest because they undercut everyone. That's what consumers buy. If AMD can get X performance for Y price and Intel can't beat them, that's who everyone will buy.
Plus, the i5 is a quad core. The FX6300 gets a passmark rating of around 6400. The i5-3450 gets around 6450 so they're basically the same speed.
The FX is $119 and the i5 is $190.
The FX has a max TDP of 95W and the i5 is 77W and their minimum power states are almost identical.
AMD has a price per performance passmark ratio of 55.63 and Intel's is 12.36. 55.63 beats every Intel chip in existence as well.
There is very little reason to choose the i5 in this match up.

Re:still crushing Intel (1)

0123456 (636235) | about 4 months ago | (#45596887)

If AMD can get X performance for Y price and Intel can't beat them, that's who everyone will buy.

Except they don't, because AMD can't compete with Intel at anything other than the low end. Which they've traditionally done by selling big chips at low prices where the margins can't be good.

Plus, the i5 is a quad core.

You were gloating about a six-core AMD beating the i3, which is a dual core with hyperthreading. That you consider that an achievement shows how far behind AMD are right now.

The FX6300 gets a passmark rating of around 6400. The i5-3450 gets around 6450 so they're basically the same speed.

In a purely synthetic benchmark.

The FX has a max TDP of 95W and the i5 is 77W and their minimum power states are almost identical.

And my i7 has a 75W TDP.

AMD has a price per performance passmark ratio of 55.63 and Intel's is 12.36. 55.63 beats every Intel chip in existence as well.

So why don't AMD triple their price? They'd still beat Intel on price/performance for everyone who buys a computer to run Passmark.

Oh, except very few people buy computers just to run benchmarks.

Re:still crushing Intel (1)

Billly Gates (198444) | about 4 months ago | (#45597103)

It hurts me to see AMD like this.

I am typing this on a Phenom II now. Not a bad chip at the time several years ago as that could hold a candle to the i5s and i7s with just a 10% performance decrease but was less than half the price and had virtualization support for VMWare and 6 cores. I run VMWare and several apps at once so it was a reasonable compromise for me and budget friendly.

But today I would not buy an AMD chip :-(

I would buy a GPU chip which is about it as those are very competitive. I wish AMD would come to a realization like INtel did with netburst in the pentium IV and dump it for something new. If AMD is within 10% of i7 I would dump it when this machine starts showing its age more. But now it is a space heater with a leaf blower that doesn't offer me much more than what my 2.8 ghz Phenom II already has (which is still superior clock cycle per clock cycle as the steamroller!!!) WTF

Re:still crushing Intel (1)

DuckDodgers (541817) | about 4 months ago | (#45600035)

I plan on buying AMD anyway, despite its inferiority, because I think the competition is good for everyone.

Eventually, maybe 5, 10, or 15 years out, I expect Intel's competition to be high end ARM chips. But for now, AMD is it. If we the consumers let AMD fold, we had better be satisfied with buying used desktop processors because I fully expect new ones to double in price per performance compared to what they are today, just because nothing will be available as an alternative.

Re:still crushing Intel (1)

Billly Gates (198444) | about 4 months ago | (#45602601)

Dude look at the 200,000,000 XP installations still running!

x86 is here to stay forever. Windows RT failed and it is a competitive cycle where ARM can't compete.

These XP users also show there is no need to ever upgrade anymore. They work. Why change to something that does this same thing they already have??!

Chips no longer double in performance as we hit limits in physics :-(

AMD is loud and needs a big fan. A i3 core is just as competitive sadly unless you really hit every darn core for an app. My phenom II is here to stay even if it is showing its age. Shoot if core2duo and pentium IV WindowsXP users are still going fine then why should I change either?

Re:still crushing Intel (0)

Anonymous Coward | about 4 months ago | (#45601095)

For what it's worth, I've actually upgraded from a phenom II x4 about a month ago (Deneb, 955BE -> FX 8350). The only component I had to change out was the CPU itself. For most day to day stuff, both chips are fast enough, but I'm definitely seeing the difference when gaming or video encoding.

The 955 was overclocked to 3.9Ghz, with a combination of FSB and multiplier tweaks to get the memory running as fast as the controller would allow with the overclock. When gaming or encoding I was constantly up against the thermal limit (61-62'c) due to the voltage required, and core 3 would crap out if I pushed it any harder (Zalman CNPS 9900 tower cooler, 120mm intake where the optical drives are normally mounted and a 120mm exhaust in the normal position to create a wind tunnel through the system. Bottom mounted PSU).

With the FX-8350 at stock clocks I'm seeing a 20% single threaded performance boost over the oc'd Deneb, and a little under a 100% gain in encoding rates. If you're coming from a stock clocked Thuban, that should give you an idea what to expect. Running temperature is down to 42'c at full load, power consumption is down as well, and the machine's much quieter.

When it comes to games I think I'm GPU bound now (560ti @ 920mhz, 72'c load + GT430 running as a dedicated PhysX board), but I have noticed I can bump up details that were troublesome before. The phenom couldn't handle maxed shadow details in Tomb Raider or Grid 2 for example (think those are done CPU side), and texture fade-in in borderlands 2, RAGE, and basically any UE3 based game has vanished.

Not saying it will be worth it for everyone, but for a single component upgrade it was worth it for me. Converting to Intel would have cost at a minimum twice as much (budgeting £150 for the chip, plus another £150 for the requisite motherboard) to get to the same level of performance.
If you were in a position where you'd have to replace the motherboard or were building from scratch though, the math would work out better on the Intel side.

Re:still crushing Intel (1)

Billly Gates (198444) | about 4 months ago | (#45602545)

Not worth it for a 20% boast.

I upgraded to an ATI 7850 and notice da significant boost.

My goal was a 5 year plan so in 2015 is when I will upgrade. I got an SSD, ATI 7850, and 16 gigs of higher speed ram. Yes my processor is 2.6 ghz but that is the only part left and the T edition is a little bit faster.

In the old days I would upgrade at 100% performance increase. Today it is I/O. I am sure Tom Raider would run fine under medium to high on it if I disable an effect or 2. No biggie for the extra cost.

Re:still crushing Intel (1)

slashmydots (2189826) | about 4 months ago | (#45607529)

What is your way of measuring speed that's superior than the rest of the internet then? The FX6300 ties or beats it in every other category and test style imaginable as well.
You're also forgetting that processors are practically a non-issue these days. If you had an i7 system with a 1TB drive and an Athlon X2 AM3 Regor 260 system with an SSD, the AMD system would feel faster doing just about anything realistic like web browsing and opening software. Intel fanboys are just buying high performance chips that are above anything AMD can made for bragging rights and shiny number. In reality, they just built an unbalanced system with too fast of a CPU.

Scheduling for a miracle (0)

Anonymous Coward | about 4 months ago | (#45595493)

Having seen it go wrong, I cringe when I hear of companies that depend on a "home run" or Hail-Mary "immaculate reception". Personally I'd love it if AMD was wildly successful. Intel is coasting without significant competition.

Core questions (1)

anne on E. mouse cow (867445) | about 4 months ago | (#45597949)

the A10-7700K will be a 384-core part.

Can some of these cores work on game AI whilst others handle graphics, or can they only work on one task all at once? Could they do game AI at all? And can programmers program for gpu cores cross-platform or is it still one brand at a time?

Re:Core questions (0)

Anonymous Coward | about 4 months ago | (#45601335)

GPU cores aren't well suited for AI - they don't like branching (if statements) much. They're great for pure compute tasks though (TressFX or PhysX style code, for example).

You'd use them for split taks the same way those example do - render frame, switch to compute, run compute, switch back to render, start new frame. Basically, time slicing, like we do on single core CPUs.

'DirectCompute' is cross brand, as is OpenCL. The brand specific solutions sometimes have advantages - either in support (getting the board manufacturers to help with troubleshooting on an AAA title) or straight up performance advantages.

APU nifty (1)

Bengie (1121981) | about 4 months ago | (#45603635)

I was doing some reading on Mantle, and there's some interesting things I noted. One of the things about Mantle is you can create "task" queues. You register a queue with some consumer, be that the CPU or a GPU. Registering the queue is a system call, but the queue itself is in user land. Each task is a data structure that contains a few things, several of them were stuff that I was less interested in, but a few stood out. One was a pointer to a function and another was a pointer to some data.

The way this sounds to work is your CPU can do some work, then package it up in a nice area in memory and enqueue a function pointer and data pointer into this queue. The GPU will then be notified without any system calls, then it will at its leisure, look at the function pointer and start executing the code against the data pointer, which is probably your matrix of data to crunch.

Here comes another cool part. Once the GPU is done crunching this data, it can do the same thing back at the CPU because the GPU can have queues registered against the CPU. This means the CPU and GPU and ping-pong work back and forth with little effort.

How does the GPU/CPU get notified? Well, it just so happens that these tasks are 64bytes, the size of a cache line. This means the cache-coherency protocol could easily notify the device when a queue has work ready, effectively having a hardware accelerated event system. I'm sure there are other more traditional ways to do this for non IGPs.

Since both the GPU and CPU use the same protected memory, there is no data copying the programmer needs to be aware of, it's all transparent. All pointers naturally work. Not only that, but the GPU can cause page faults, so data sets no longer must fit into GPU memory, but can actually be stored in system memory, or event better, swapped out. I'm not saying swapping is good, just that it's much easier to handle than a programmer manually doing memory management.

Even more good news. These GPUs are full C/C++ capable. No funny custom languages to use, good old C. Nothing says "I like to work with buffers of data and pointers" than C.

Do the biggest reason Mantle will help is because it can completely by-pass system calls and allow producer-consumer queues and use event notification for when work is ready. Mantle is supposed to be GPU independent, so Nvidia should also be able to implement it, but without tight GPU integration, I'm not sure it will be as efficient, but still better than system calls.

What can happen now is a network of task queues connecting the CPU, IGP, and any other GPUs. If you have more than one GPU, each GPU can have it's own queue. You can actually register as many queues as you want, which means an 8 core CPU will probably one queue for each core for each device. This could be a first great attempt at unifying GPUs and CPUs into one massive processing system.

Dice has some interesting stuff about how they can get BF4 efficiently using 90%-95% of an 8 core CPU while offloading lots of work to the GPU and IGP. Better use of multi-core CPUs, lower latency, higher throughput, what's not to like? The design looks good, the idea sounds awesome, now we wait for the implementation. No matter what happens, I see this eventually being the future, be it Mantle or some other API.
Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Sign up for Slashdot Newsletters
Create a Slashdot Account

Loading...