llvm
AdaptiveCpp
llvm | AdaptiveCpp | |
---|---|---|
10 | 19 | |
1,165 | 1,046 | |
3.9% | 2.8% | |
10.0 | 9.7 | |
about 2 hours ago | 1 day ago | |
C++ | ||
GNU General Public License v3.0 or later | BSD 2-clause "Simplified" License |
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.
llvm
-
Vcc – The Vulkan Clang Compiler
Intel's modern compilers (icx, icpx) are clang-based. There is an open-source version [1], and the closed-source version is built atop of this with extra closed-source special sauce.
AOCC and ROCm are also based on LLVM/clang.
[1] https://github.com/intel/llvm
-
device::aspects ?
You are not missing anything spec-wise, it is just that particular version of the compiler/runtime doesn't support that query. Support for it was added in intel/llvm#7937 and it should be available in the next oneAPI release.
-
How to install OpenCL for AMD CPU?
Install the Intel OpenCL CPU Runtime. AMD CPUs are x86-64 too, so they work just like Intel CPUs do. Afaik, performance is significantly better than with POCL. This also works with EPYC, like the new 96-core Genoa.
-
Modern Software Development Tools and oneAPI Part 2
The Meson build system Version: 1.0.0 Source dir: /var/home/sri/Projects/simple-oneapi Build dir: /var/home/sri/Projects/simple-oneapi/builddir Build type: native build Project name: simple-oneapi Project version: 0.1.0 C compiler for the host machine: clang (clang 16.0.0 "clang version 16.0.0 (https://github.com/intel/llvm 08be083e07b1fd6437267e26adb92f1b647d57dd)") C linker for the host machine: clang ld.bfd 2.34 C++ compiler for the host machine: clang++ (clang 16.0.0 "clang version 16.0.0 (https://github.com/intel/llvm 08be083e07b1fd6437267e26adb92f1b647d57dd)") C++ linker for the host machine: clang++ ld.bfd 2.34 Host machine cpu family: x86_64 Host machine cpu: x86_64 Build targets in project: 1 Found ninja-1.11.1.git.kitware.jobserver-1 at /var/home/sri/.local/bin/ninja
-
Modern Software Development Tools and oneAPI Part 1
$ sudo mkdir -p /opt/intel $ sudo mkdir -p /etc/OpenCL/vendors/intel_fpgaemu.icd $ cd /tmp $ wget https://github.com/intel/llvm/releases/download/2022-WW50/oclcpuexp-2022.15.12.0.01_rel.tar.gz $ wget https://github.com/intel/llvm/releases/download/2022-WW50/fpgaemu-2022.15.12.0.01_rel.tar.gz $ sudo bash # cd /opt/intel # mkdir oclfpgaemu- # cd oclfpgaemu- # tar xvfpz /tmp/fpgaemu-2022.15.12.0.01_rel.tar.gz # cd .. # mkdir oclcpuexp_ # cd oclcpuexp- # tar xvfpz /tmp/oclcpuexp- # cd ..
-
Cross Platform Computing Framework?
oneAPI includes an implementation of SYCL called DPC++. This implementation supports Intel, Nvidia and AMD GPUs (currently for Nvidia and AMD you need to build the support from the source) but oneAPI also includes some libraries too like oneDNN and oneMKL that use SYCL.
-
Does an actually general purpose GPGPU solution exist?
Yes, you can use multiple backends with the same compiled binary. For example you can use DPC++ with Nvidia, AMD and Intel GPU at the same time. ComputeCpp also has the ability to output a binary that can target multiple targets. Each backend generates the ISA for each GPU, and then the SYCL runtime chooses the right one at execution time. There is no ODR violation because each GPU executable is stored on separate ELF sections and loaded at runtime : the C++ linker does not see them. The code doesn't need to have any layers, the only changes you might (but don't have to) make are to optimize for specific processor features.
-
Why Does SYCL Have Different Implementations, and What Version to Use for GPGPU Computing(With Slower CPU Mode for Testing/No Gpu Machines)?
Intel LLVM SYCL oneAPI DPC++ - an open source implementation of SYCL that is being contributed to the LLVM project
-
How to set up Intel oneAPI?
I'm using intel cpu, and after reading this i'm just curious can i set this up with portage? Are there any ebuilds to build this? Do i need whole toolchain from intel site (3Gb+) or just 300 mb tar from their github?
- Benchmarking Division and Libdivide on Apple M1 and Intel AVX512
AdaptiveCpp
-
What Every Developer Should Know About GPU Computing
Sapphire Rapids is a CPU.
AMD's primary focus for a GPU software ecosystem these days seems to be implementing CUDA with s/cuda/hip, so AMD directly supports and encourages running GPU software written in CUDA on AMD GPUs.
The only implementation for sycl on AMD GPUs that I can find is a hobby project that apparently is not allowed to use either the 'hip' or 'sycl' names. https://github.com/AdaptiveCpp/AdaptiveCpp
-
AMD May Get Across the CUDA Moat
Not natively, but AdaptiveCpp (previously hiSycl, then OpenSycl) has a single source single compiler pass, where they basically store LLVM IR as an intermediate representation.
https://github.com/AdaptiveCpp/AdaptiveCpp/blob/develop/doc/...
Performance penalty was within ew precents, at least according to the paper (figure 9 and 10)
-
Offloading standard C++ PSTL to Intel, NVIDIA and AMD GPUs with AdaptiveCpp
AdaptiveCpp (formerly known as hipSYCL) is an independent, open source, clang-based heterogeneous C++ compiler project. I thought some of you might be interested in knowing that we recently added support to offload standard C++ parallel STL algorithms to GPUs from all major vendors. E.g.:
-
AMD's HIPRT Working Its Way To Blender With ~25% Faster Rendering
In fact SYCL was initially called hipSYCL because it is based on AMD's ROCm/HIP. AMD had hipSYCL code running on the Frontier supercomputer four years ago at least and continues to support it.
-
hipSYCL can now generate a binary that runs on any Intel/NVIDIA/AMD GPU - in a single compiler pass. It is now the first single-pass SYCL compiler, and the first with unified code representation across backends.
Apple Silicon support through Metal is something that is actively discussed in hipSYCL. See https://github.com/illuhad/hipSYCL/issues/864 https://github.com/illuhad/hipSYCL/issues/460 (loooong discussion)
-
Bringing Nvidia® and AMD support to oneAPI
But really, the DPC++ part of oneAPI (which is many APIs) is just SYCL + extensions, and there are several other SYCL implementations which have already featured CUDA and Hip (AMD) support for a long time. The most popular and widely-used is hipSYCL, which we've been using in an HPC context on NV hardware for over 4 years now.
-
Intel oneAPI 2023 Released - AMD & NVIDIA Plugins Available
Unfortunately, the AMD and Nvidia plugins are proprietary. AMD users are probably better served with hipSYCL, if they somehow find an application using SYCL...
-
There is framework for everything.
Also, you might want to take a look at an implementation like hipSYCL :)
-
The Next Platform: "Intel Takes The SYCL To Nvidia's CUDA With Migration Tool"
Yup. SYCL is the future: https://github.com/illuhad/hipSYCL
-
Phoronix: "Intel's Vulkan Linux Driver Adds Experimental Mesh Shader Support For DG2/Alchemist"
ROCm is completely independent from these. It's a compute stack containing an OpenCL implementation for Radeon GPUs, plus a CUDA-like language called HIP which can be compiled to either device code for Radeon GPUs or to PTX to work with Nvidia GPUs. However, some researchers also created hipSYCL that allows SYCL to run atop HIP; you can think of it like DXVK - the program contains the DirectX/SYCL API, and DXVK/hipSYCL converts it to Vulkan/HIP (with one difference - DXVK does the conversion at runtime, while hipSYCL does it at compile time).
What are some alternatives?
pocl - pocl - Portable Computing Language
ROCm - AMD ROCm™ Software - GitHub Home [Moved to: https://github.com/ROCm/ROCm]
oneTBB - oneAPI Threading Building Blocks (oneTBB)
HIP-CPU - An implementation of HIP that works on CPUs, across OSes.
meson - The Meson Build System
triSYCL - Generic system-wide modern C++ for heterogeneous platforms with SYCL from Khronos Group
OCL-SDK
HIP - HIP: C++ Heterogeneous-Compute Interface for Portability
featuresupport
cuda-api-wrappers - Thin C++-flavored header-only wrappers for core CUDA APIs: Runtime, Driver, NVRTC, NVTX.
Hackintosh-Intel - Hackintosh Intel
cuda_memtest - Fork of CUDA GPU memtest :eyeglasses: