AMD is offering a free OpenCL for CPU beta download as part of the ATI Stream SDK v2.0 Beta Program. The Stream SDK allows you to take advantage of GPGPU computing and develop your applications in a high-level language - OpenCL. It allows you to divide software workloads between different hardware elements such as multi-core CPUs, GPUs, and DSPs.
Below is a video of a 4P six-core AMD Opteron processor-based system (24 total cores) running an OpenCL-based, fluid/particle simulation. The demo runs through enabling progressively more CPU cores and you see the performance scaling. Impressive.
Normally you think of just the GPU for this kind of computational processing. But reality is you need both the GPU and CPU for optimal performance and OpenCL provides this. I stole the quote form an AMD blog:
“Of course no application runs entirely on the GPU. Beyond the obvious need for CPUs to drive execution, most mainstream applications are heterogeneous in nature. They have some functions that accelerate well on multicore CPUs, and others that are perfectly suited for a GPU’s data parallel architecture. A good development platform needs to take that into account - this is the difference between GPGPU as a niche accelerator and GPGPU as a new baseline feature, ready for tomorrow’s systems and applications.”
As many predicted, AMD showed off OpenCL-accelerated Havok gaming physics at the 2009 Game Developers Conference. Specifically the demo showed OpenCL- accelerated Havok Cloth, a runtime and toolset that lets developers add physically simulated cloth to their games. The GDC demo, duplicated in these official videos shows the acceleration applied to realistic motion of garments like skirts, capes, shirts, trousers and coats, as well other deformable items like hair.
OpenCL is the first cross-platform and open technology designed to exploit the horsepower in multi-core CPUs and GPUs (or other processors).
GPU Cafe notes that the FireStream 9270 will be released Q1 2009. What makes this interesting to me, beside the performance, is the listed support for OpenCL. AMD is embracing this parallel processing standard in a big way. I wonder how long it will be before mainstream CAD and 3D Viz software vendors can determine how to use OpenCL to accelerate their computations.
If you are into the specs and numbers race, here's some of the relevant info:
Currently the highest performing HPC processor outperforming Nvidia's Tesla C1060 by 28% (single-precision at 1.2 TFLOPS) and 207% (double-precision at 240 GFLOPS) at peak compute rates (but in real life, the API will make a big difference here).
The first public demonstration of OpenCL functionality was given by AMD at Siggraph Asia 2008. OpenCL is the new vendor-independent standard designed to extract high performance parallel computing out of GPUs, DSPs and multicore CPUs. Basically the idea is that you can write your core computational code in OpenCL and voila! - your code scales to whatever processors are available. OpenCL will greatly improve speed and responsiveness for a wide spectrum of applications from entertainment to scientific and 3D visualization.
The FirePro / FireStream teams created a screen capture of this particle & fluid simulation demo showing OpenCL functionality - embedded below. As you can see when you run it, initially the demo only uses one core of a Dragon-based system (quad-core Phenom II). As the additional cores are enabled the simulation compute time is cut in half!
Note: Set the embedded video to display at hi-quality to see more detail - it takes a while to load - but it is worth it (once you start the video, select HQ from the bottom right up-arrow of the video)
More details
CPU-optimized runtime based on the publicly available OpenCL specification from the Khronos Group designed to optimally run compute kernels on multi-core systems with linear scaling
Powdertoy is a combined particle & fluid simulator written by Stanislaw Skowronek
- Particles can change state (Snow melting into water)
- Particles affect the state of the fluid (Heat increases pressure)
- Fluid state affects the particles (Particle movement)
Computationally dense portions of the original C code ported to compute kernels in just a couple of hours
Yellow bar on right represents the time spent in all the compute kernels
- grey material used to write "powder toy" at the beginning of the video is "metal" which later melts
- AMD logo is drawn in a material that "clones" what ever touches it first, which in the video is a flammable gas (the yellow particles)
- after igniting the gas, the air near the logo rapidly heats up and expands, causing the outflow of fire particles.
The last part of the video shows the affect of enabling multiple cores. The video capture software prevents the forth core from being used by the runtime
Interested in more technical info about OpenCL and Stream Computing? Check out these papers:
Today the OpenCL CPU+GPU compute standard was ratified by the Khronos Group and AMD announced that it is making good progress on its OpenCL-compliant offering and plans to release a developer version of the ATI Stream SDK v1.4 with support for OpenCL 1.0 for content developers in the first half of 2009. Working from early specifications of OpenCL, AMD’s engineering team has already started running code on its initial implementation.
OpenCL (Open Computing Language), a way to extract computing performance out of GPUs and multicore CPUs in an architecture-independent way. In other words, programmers can use the GPU as a data-parallel coprocessor without having to go through a specialized graphics API like OpenGL or DirectX. OpenCL is designed to address more than GPGPU (general-purpose computing on graphics processing units). It is really a way to enable a broad range of parallel architectures that includes GPUs, multicore CPUs, Larrabee, and even DSPs, to greatly improve speed and responsiveness for a wide spectrum of applications from entertainment to scientific and 3D visualization.
The new ATI Stream SDK 1.4 will add finer grain data type support, graphics API interoperability, multi-GPU support and support for Radeon HD 4870 X2 and several ATI FirePro 3D graphics accelerators
HPC has a blog post on the fast track release of OpenCL (Open Computing Language), a way to extract computing performance out of GPUs and multicore CPUs in an architecture-independent way. OpenCL is designed to address more than GPGPU (general-purpose computing on graphics processing units). It is really a way to enable a broad range of parallel architectures that includes GPUs, multicore CPUs, Larrabee, and even DSPs. Both AMD (with Stream Computing) and Nvidia (with CUDA) strongly support the OpenCL move.
Version 1.0 of OpenCL is on a fast track release schedule for early December at SIGGRAPH Asia 2008 in Singapore. OpenCL is a low level API that should be applicable to high-end workstations, desktop computers, handhelds and embedded devices.
FireUser.com is a community resource for CAD, visualization, 3D, video and engineering professionals to learn about the latest acceleration and display technologies and news with a focus on the AMD FirePro workstation graphics line.
If you are into the specs and numbers race, here's some of the relevant info:
