Slashdot Mirror
AMD's Fusion CPU + GPU Will Ship This Year
mr_sifter writes "Intel might have beaten AMD to the punch with a CPU featuring a built-in GPU, but it relied on a relatively crude process of simply packaging two separate dies together. AMD's long-discussed Fusion product integrates the two key components into one die, and the company is confident it will be out this year — earlier than had been expected."
Sup dawg. We herd you like processing units, so we put a processing unit in yo' processing unit so you can computer while you compute!
It doesn't really matter, any more than AMD's "proper" quad core mattered more than Intel pasting two dual-core dies together. This is really just AMD getting beaten to the punch again, and having to try to spin it in some positive way. It's great news that it will be out earlier than expected, but I think they would have been better off taking the less "beautiful" and just throwing discrete dies into a single package. Particularly as it has yet to be seen how big the market for this sort of thing is. More exciting to me is that AMD is ahead of schedule with this, so hopefully they'll be similarly ahead with their next architecture. I'm yearning for the day when AMD is back to being competitive on a clock-for-clock basis with Intel.
With IE 9 headed toward GPU assisted acceleration, these types of "hybrid" chips will make things even faster. Since AMD's main enduser is a Windows user, and IE 9 will probably be shipping later this year, these two may be made for each other.
Of course every other aspect of the system will speed up as well, but I wonder how this type of CPU/GPU package will work with after market video cards? If you want a better video card for gaming, will the siamese-twin GPU bow to the additional video card?
I'd really love it if Fusion could give us ultra-powered iPad-killing tablet PCs, complete with multi-tasking/multi-window functionality, as well as 3D acceleration. But will it be low-powered enough?
Calling Intel's offerings crude sounds like it is quoting from AMD's press release. It may be crude, but it works and was quick and cheap to implement. But does it have any disadvantages? Certainly the quote from the article doesn't seem terribly confident that the integrated offering is going to be any better:
We hope so. We've just got the silicon in and we're going through the paces right now - the engineers are taking a look at it. But it should have power and performance advantages.
Dissing a product for some technical reason that may not have any real performance penalties? That's FUD!
I, for one, welcome our new small furry not-yet-house-trained overlords!
CPUGPU, just step around it...
And all our yesterdays have lighted fools The way to dusty death. --Will
I hope so, Intel is far too dominant right now.
expandfairuse.org
With the bulk of processing power for both CPU and Graphics being concentrated in a single die, I can only imagine how hot it's going to get!
AMD Fusion was meant to compete with Larrabee which is not released. The Intel package with two separate dies is not interesting. The point of these products is to give the programmer access to the vast FP power of a graphics chip, so they can do, for instance, a large scale fft and ifft faster than a normal CPU. If this proves more powerful than Nvidia's latest Fermi (GTX 480 I believe), then expect a lot of shops to switch. Right now my workplace has a Nvidia Fermi on backorder, so it looks like this is a big market.
I want my CPU to be mostly GPU. Just enough CPU to run the apps. They don't need a lot of general purpose computation, but the graphics should be really fast. And a lot of IO among devices, especially among network, RAM and display.
--
make install -not war
In addition to the CPGPU or whatever what they're calling it, Fusion should finally catch up to (and exceed) Intel in terms of niftilicious vector instructions. For example, it should have crypto and binary-polynomial acceleration, bit-fiddling (XOP), FMA and AVX instructions. As an implementor, I'm looking forward to having new toys to play with.
I hereby place the above post in the public domain.
Does this mean CUDA support in every AMD "CPU" ?
I want to delete my account but Slashdot doesn't allow it.
Call me when they can fit 9 inches of graphics card into one of these cpu.
This is great for mobile devices and laptops but I don't think I want my CPU and GPU combined in my gaming rig. I generally upgrade my video card twice as often as my CPU. If this becomes the norm then eventually I'll either get bottlenecked or have to waste money on something I don't really need. Being forced to buy two things when I only need one is not my idea of a good thing.
But will quad core and six core chips also carry a graphics chip? And how long before the two quad core mother boards hit the streets?
Frankly we are on the edge of a serious improvement in computers.
The upcoming gnome 3.0 will not run unless you have a working driver for your graphics card. If this new chip hits the steets at the same time as gnome 3 then a lot of people will end up in trouble.
One distinct disadvantage... HEAT! even with all the die shrinks
No1 Advantage, forcing Intel to product decent graphics.
Worth noting is that Apple has invested rather heavily in technology to allow programmer use of the GPU in MacOS X. And were recently rumored to have met with high ranking persons from AMD. Seems only logical that this type of chip could find its way into some of the Apple gear.
Question is of course if it would be powerefficient enough for laptops, where space is an issue...
Actually Intel had a radical way to handle this - Larrabee. It was going to be 48 in order processors on a die with Larrabee new instructions. There was a Siggraph paper with very impressive scalability figures for a bunch of games running DirectX in software - they captured the DirectX calls from a machine with a conventional CPU and GPU and injected them into a Larrabee simulator.
This was going to be a very interesting machine - you'd have a machine with good but not great gaming performance and killer server performance - servers are naturally "embarrassingly parallel" because you can have one thread per client. A sort of x86 take on Sun's Niagra.
Of course there are problems with this sort of approach. Most current games are not very well threaded - they have a small number of threads that will run poorly on an in order CPU. So if the only chip you had was a Larrabee and it was both a CPU and a GPU the GPU part would be well balanced across multiple cores. The CPU part would likely not. You have to wonder about memory bandwidth too.
Larrabee was switched to be a GPU only and then canned.
Of course as a pure GPU it is a bit of a poor design. Real GPUs don't drag in x86 compatibility - they can implement whatever instruction set is best and nothing else. The instruction set is not publicly exposed and can change from generation to generation. You can cram a lot more than 48 cores onto a GPU and the peak performance is higher. Power consumption is lower too.
Still a modern gaming GPU is huge - there's no way you're going to cram it and a modern GPU onto a die and get something affordable. Then again CPUGPU chips are probably not aimed at gamers - there's an argument for having a CPU and a stripped down integrated GPU on one chip for netbooks like the latest Atoms do.
You could cram in a chipset too to reduce the price on netbooks.
echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
I look forward to seeing what AMD's new architecture brings. It's not really interesting thinking about it as integrating a GPU into the same space as a CPU, but creating one chip that can do more exotic types of calculations than either chip could alone and making it a available in every system. I'm also envisioning "GPU" instructions being executed where normally CPU instructions were when not in use, and vise versa, basically so everything available could be put to use.
AMD had a better architecture at the times of Athlon and Intel made "netburst" architecture, the name makes users believe that it bursts internet surfing. It was 30 stages pipeline, because it could go up with MHz and so it was good to make users think "more MHz, better cpu" (like when people buys stereos, more Watts=better sound. Yuck.) AMD was the first to release dual core desktop processors, but Intel preceded AMD with dual core Pentium 4: two single-core dies on one package. AMD was the first to release quad core desktop processors, but Intel preceded AMD with quad cores: two dual-core dies on one package. Now it is the same story with CPU+GPU. The bad thing here is that all this is done with the complicity of magazines and hardware review websites around the world.
If AMD's tradition of using the same socket type continues here, then this should be a much bigger deal than Intel's entry. It'll mean that for a very small amount of money, I can add some GPU action to the little boxes I have around where the video card I scrounged is so old it's pathetic.
The same sort of situation appears in servers. I have a bunch of AMD servers which I certainly don't want to put a graphics card in, but I might have some algorithms which would benefit from GPUs. Instant upgrade.
Now, that's not the general model for success CPU companies really need, but it's a start and would provide a capital boost while AMD goes forward on making most of thier chips fusion chips, pushing a lot of business computing into GPU dependency and therefore AMD dependency. Not bad, from AMD's perspective.
There's two sides to this coin and Intel's is pretty neat. By not having the GPU integrated into the CPU die, Intel can improve the CPU/GPU without having to redesign the entire chip. For example, any Power management improvements can be moved into the design as soon as it's ready. Another advantage for them is the fact that each die CPU and GPU are actually indepenent and can be manufactured using what ever process makes the most sense to them.
AMD's design offers a major boost to overall CPU performance simply through the fact that the integration is far deeper then Intel's. From what I've read, the Fusion ties the Stream Processors (FPU) directly to a CPU and should offer a major boost in all Math ops of the CPU and I expect that it will finally compete with Intel's latest CPU's in regards to FPU operations.
Mod me up/Mod me down: I wont frown as I've no crown
Of course there are problems with this sort of approach. Most current games are not very well threaded - they have a small number of threads that will run poorly on an in order CPU. So if the only chip you had was a Larrabee and it was both a CPU and a GPU the GPU part would be well balanced across multiple cores. The CPU part would likely not. You have to wonder about memory bandwidth too.
I believe that it was in fact memory bandwidth which killed larrabee. A GPU's memory controller is nothing like a CPU's memory controller, so trying to make a many-core CPU behave like a GPU while still also behaving like a CPU just doesnt work very well.
Modern good performing GPU's require the memory controller be specifically tailored to filling large cache blocks. Latency isnt that big of an issue. The GPU is likely to need the entire cache line, so latency is sacrificed for more bandwidth. The latency is amortized over many many operations.
CPU's on the other hand require the memory controller be tailored to filling small cache blocks. Latency is a big issue. The CPU may only want or need 4 bytes from that cache line, so latency can't be sacrificed for bandwidth. The latency may not be amortized over many operations.
"His name was James Damore."
sound / firewire / usb 3.0 still need pci / pci-e bus and mid-range and high end / muilt display cards are not dieing. Most board video can only do 1-2 DVI / HDMI out's any ways with most at 1 DVI / HDMI + 1 vga and vga is poor for big screens and does not work with HDCP. PCI-e will not die as it is also needed for TV cards (if this new cable card pc push works good then you may see many more systems with them) on board sound / sata (some boards) / usb 3.0 / Network use the pci / pci-e bus as well. 4 tuner tv cards may need pci-e x4 + usb for SDV tuner as well. On board sound is not as good as some of the add in sound cards that have good amps and other parts. On board video is ok for basic stuff and older games but it can't do high res gameing at max settings and it can take a 256 or more ram hit from system ram and that ram is slower then the ram on most video cards.
It seems like the caching issues could be fixed with prefetch instructions that can fetch bigger chunks. Which it apparently has.
Still just fetching instructions for 48 cores is a huge amount of bandwidth.
http://perilsofparallel.blogspot.com/2010/01/problem-with-larrabee.html
Let's say there are 100 processors (high end of numbers I've heard). 4 threads / processor. 2 GHz (he said the clock was measured in GHz).
That's 100 cores x 4 treads x 2 GHz x 2 bytes = 1600 GB/s.
Let's put that number in perspective:
* It's moving more than the entire contents of a 1.5 TB disk drive every second.
* It's more than 100 times the bandwidth of Intel's shiny new QuickPath system interconnect (12.8 GB/s per direction).
* It would soak up the output of 33 banks of DDR3-SDRAM, all three channels, 192 bits per channel, 48 GB/s aggregate per bank.
In other words, it's impossible.
So 48 cores needs 16 banks of DDR3-SDRAM.
echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
Meanwhile, where are those damned quad core laptop processors AMD promised? I've been waiting freaking AGES to buy a laptop with one.
how is babby formed?
If AMD puts a competetive GPU onto the CPU die, comparable to their current high-end graphics boards) then this is a really big deal. Perhaps the biggest issue with GPGPU programming is the fact that the graphics unit is at the end of a fairly narrow pipe with limited memory, and getting data to the board and back is a performance bottleneck and a pain in the butt for a programmer.
Putting the GPU on the die could mean massive bandwidth from the CPU to the hundreds of streaming processors on the GPU. It also strongly implies that the GPU will have access directly to the same memory as the CPU. Finally, it would mean that if you have a Fusion-based renderfarm then you have GPUs on the renderfarm.
This is exciting!
I love Mondays. On a Monday, anything is possible.
Somehow I doubt that AMD will be placing a bleeding edge GPU in their CPU's ... it'd kill their current market for discrete cards in the short term. :)
It's likely that the in-line GPU will be the basic GPU which is part of their chipsets.
It's gutsy enough for basic 3D acceleration & video acceleration, but power efficient, and will provide enough acceleration for older games at decent resolutions, or newer games at low resolution.
However, hybrid SLI ... that's some cool stuff right there :D