chipStar
OpenCL-Wrapper
chipStar | OpenCL-Wrapper | |
---|---|---|
4 | 7 | |
147 | 263 | |
4.8% | - | |
9.7 | 5.7 | |
7 days ago | 7 days ago | |
C++ | C++ | |
GNU General Public License v3.0 or later | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
chipStar
-
AMD Funded a Drop-In CUDA Implementation Built on ROCm: It's Open-Source
There is already a work-in-progress implementation of HIP on top of OpenCL https://github.com/CHIP-SPV/chipStar and the Mesa RustiCL folks are quite interested in getting that to run on top of Vulkan.
-
Vcc – The Vulkan Clang Compiler
chipStar (formerly CHIP-SPV) might also be worth checking out: https://github.com/CHIP-SPV/chipStar
It compiles CUDA/HIP C++ to SPIR-V that can run on top of OpenCL or Level Zero. (It does require OpenCL's compute flavored SPIR-V, instead of graphics flavored SPIR-V as seen in OpenGL or Vulkan. I also think it requires some OpenCL extensions that are currently exclusive to Intel NEO, but should on paper be coming to Mesa's rusticl implementation too.
- ChipStar: Run CUDA/Hip on SPIR-V via OpenCL/Level Zero
-
In the next 5 years, what do you think can push OpenCL adoption?
Regarding the second item (CUDA to OpenCL), have a look at hipstar: https://github.com/CHIP-SPV/hipstar
OpenCL-Wrapper
-
What 8x AMD Instinct MI200 GPUs can do with a combined 512GB VRAM: Bell 222 Helicopter in FluidX3D CFD - 10 Billion Cells, 75k Time Steps, 71TB vizualized - 6.4 hours compute+rendering with OpenCL
In case you go with OpenCL, start here: https://github.com/ProjectPhysX/OpenCL-Wrapper
-
In the next 5 years, what do you think can push OpenCL adoption?
I've also open-sourced an OpenCL-Wrapper to eliminate all of the boilerplate code that otherwise comes with the OpenCL C++ bindings and lower the entry barrier. Especially for larger projects, the biolerplate code becomes really offputting, and I solved it entirely.
-
What's your main programming language?
Somewhat unusual these days, but I mainly use OpenCL C. It's seems cumbersome and hard to learn at first, but becomes much more easy to use with the right tools. Once you master it, it whipes the floor with CPU programming; it's not unusual to see 100x speedup on a GPU compared to multithreaded CPU code at the same energy consumption. It's just as fast as CUDA - as efficient as the microarchitecture allows - but compatible with literally all GPU/CPU hardware of the last decade. No need to waste time on code porting if the next supercomputer has GPUs from a different vendor, it just runs out-of-the-box. Ideal for scientific compute!
-
How do you allocate more than 4GB of memory for OpenCL in A770 16GB?
I added this to my OpenCL-Wrapper in this commit, so anything built on top of it, such as FluidX3D, works on Arc out-of-the-box. Additionally, I fixed Intel's wrong VRAM capacity reporting on Arc in this patch.
-
New project - Which framework/libraries to use ?
Try OpenCL. You only need to implement the code once (in a vectorized form) and it works cross-platform on all GPUs and all CPUs, even on FPGAs. Performance is exactly as good as CUDA. There is still no rivaling framework today, although SYCL is starting to become a viable alternative.
- Want to to learn OpenCL on C++ without the painful clutter that comes with the C++ bindings? My lightweight OpenCL-Wrapper makes it super simple. Automatically select the fastest GPU in 1 line. Create Host+Device Buffers and Kernels in 1 line. It even automatically tracks Device memory allocation.
-
Most user friendly way to write OpenCL kernels.
I have found that OpenCL-Wrapper from PhysX has a great solution to this : https://github.com/ProjectPhysX/OpenCL-Wrapper/
What are some alternatives?
FluidX3D - The fastest and most memory efficient lattice Boltzmann CFD software, running on all GPUs via OpenCL.
Cgml - GPU-targeted vendor-agnostic AI library for Windows, and Mistral model implementation.
OpenCL-examples - Simple OpenCL examples for exploiting GPU computing
hipDNN - A thin wrapper around miOpen and cuDNN
intel-extension-for-tensorflow - Intel® Extension for TensorFlow*
llvm - Intel staging area for llvm.org contribution. Home for Intel LLVM-based projects.
dolfinx - Next generation FEniCS problem solving environment
VectorVisor - VectorVisor is a vectorizing binary translator for GPUs, designed to make it easy to run many copies of a single-threaded WebAssembly program in parallel using GPUs
cccl - CUDA C++ Core Libraries