AMD Shares New Information On Future GPUs

At its Fusion Development Summit this week, AMD discussed the concepts and capabilities it's targeting for future generations of AMD graphics cards. The company isn't sharing any specific architectural features, but even the general information it handed out is interesting.

Demers began by talking about the history of ATI's graphics card and the evolution of the company's GPU design. When ATI originally designed its DX9 hardware, it designed its vertex shaders to use a VLIW5 (Very Long Instruction Word) implementation. Back in such halcyon days of yore, Nvidia's programmable G80 was scarcely a twinkle in David Kirk's eye. Pixel and vertex shaders were two different animals. ATI's VLIW5 approach allowed the vertex shader to handle four simple operations, with a dedicated fifth unit that could handle more complex tasks.

AMD stuck with a VLIW5 approach until it launched Cayman last year. With Cayman, AMD adopted VLIW4. Instead of four simple operations with an option for a complex 5th, VLIW4 uses three of its four simple units to perform a complex operation. This increased design efficiency and allowed AMD to increase the number of SIMD blocks per die. Future discrete GPUs (and Fusion products) will be built around what AMD is calling a compute unit (CU). AMD's video explores the difference between the new CU architecture and the VLIW5/VLIW4 designs that came before it in some detail; we've kept our own discussion at a fairly high level.

AMD's long-term Fusion roadmap

Demers made it clear that while gaming and pure graphics performance remain important to AMD, many of the improvements the company is planning to introduce are aimed at boosting GPU compute performance. Nvidia took the same general approach when it built Fermi. Granted, the GF100 had more than its share of growing pains, but it proved that its possible to improve gaming and GPU compute capabilities at the same time without sacrificing one for the other.

AMD's long term goal is to integrate the GPU and CPU into a single cohesive unit. Future Fusion parts (and discrete GPUs) will add support for C, C++, and other high-level languages. Eventually, CPU and GPU will share x86 virtual memory (64 bit x86 pointers will be understood by the GPU). The GPU will also have its own address translation caches, cache coherence between the two parts will be maintained, and all of these features will be accessible if a discrete GPU is paired with a traditional CPU.

The new compute unit structure.

It'll be a year or more until we see a Fusion chip or discrete GPU that leverages these new technologies; AMD has stated that the first generation of Bulldozer chips that integrate GPUs will *not* use the tech we've been discussing. It's also noteworthy that many of the technologies AMD has adopted here first showed up in Fermi. Then again, AMD's own presentation indirectly addresses this issue. Up until now, AMD has focused on first matching, then challenging NV's game performance. If gaming were the only important issue, the company's VLIW4 and VLIW5 designs would've been sufficient. AMD is moving to adopt certain technologies precisely because it wants to compete in the GPGPU / HPC markets.

Via:  AMD
OptimusPrimeTime 3 years ago

"AMD I dont wanna hear yada yada about something thats at least a year away, Does anyone know the actual Bulldozer release date?


schmich 3 years ago

They said Q3 (even for desktop now) so most likely September if things go well.

realneil 3 years ago

Bulldozer please?

pwrntspd 3 years ago

This should be interesting...i wonder if this is going to be another step to CPU-GPU integration where the GPU will take up more of the parallel and floating point calculations? Theres a decent article about this over at Anandtech as well.

CNguyen 3 years ago

Bulldozer will probably be released in Q3 2011, ... I'm guessing either late August or September. It'll be a while, so just save up your money :)

ThunderBird 3 years ago

Sounds like AMD is on the right track now if they can continue to execute.

Joel H 3 years ago


Keep your eye on Q3.

Joel H 3 years ago


To some degree. It'll be several years before we see Fusion products as tightly coupled as the ones Demers discussed in this presentation. We *won't* see this design in the first generaion of Biulldozer Fusion chips. Those cores will tip up in 9-12 months, as compared to the Q3 ship date for standard Bulldozer parts.

AKwyn 3 years ago

AMD's plan to merge the CPU and the GPU together are interesting, and it's really going to be interesting to see how they perform when placed up with NVIDIA's Kepler series (if they do manage to be released on time.)

Pretty interesting way to do things according to AMD's schematics.

Post a Comment
or Register to comment