aomp
aomp copied to clipboard
ROCm
AOMP is an open source Clang/LLVM based compiler with added support for the OpenMP® API on Radeon™ GPUs. Use this repository for releases, issues, documentation, packaging, and examples.
It seems that offload plugin or down to hsa creates additional thread to communicate with the GPU. Such additional thread seems floating around and competing with regular OpenMP threads. It...
On a gfx906 device, I observe the following bandwidth for the two examples. Users may be confused with bandwidth inconsistency. Thanks. ./omp_band Starting omp_band Time 1.209406 for copy host to...
Add test for USM mode when mixing hip and openmp but only openmp requires hw support for xnack
For the repository https://github.com/zjin-lcf/oneAPI-DirectProgramming, the examples, which fail on an AMD GPU (gfx906), are listed below. The HIP version for each kernel may help when running both HIP and OMP...
Added OMPT callbacks to veccopy. This is intended to work with https://github.com/ROCm-Developer-Tools/llvm-project/pull/175 Do not merge this PR, this is experimental, intended to demonstrate simple OMPT callbacks. OMPT target tests will...
Hello, the following code compiles and works fine with GNU, Intel, NVIDIA, and NAG. It is however not fully working with flang-12 or flang-13 that comes with AMD ROCm: integer,...
Add test for omp_is_coarse_grain_mem_region libomptarget API.
I am trying to run a openMP program on a instance with AMD EPYC 7R32 CPU/ V520 GPU. This is on a AWS shared instance. I installed AOMP 11.12.0 and...
