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.
Hi, can you please provide a pre-built package as a tarball? The RPMs are not relocatable and want to install on a shared network path so all users on a...
Below a pure-C minimal failing example showing an increase in memory consumption when multiple omp-offloading shared objects are called back to back from Python https://github.com/devitocodes/devito/tree/patch-omp-off-leakage/tests/omp-mfe the MFE files are hosted...
I suggest adding the topic `fortran-compiler` in the About section.
I added the following to this [repo's OMPT example](https://github.com/ROCm-Developer-Tools/aomp/blob/4585647781c82648002c7955d6f5dfa1a8f57532/examples/tools/ompt/veccopy-ompt-target-tracing/callbacks.h): ``` int initial_device = omp_get_initial_device(); printf("initial device_num = %d\n", initial_device); #pragma omp target data map(to: i) device(3) { #pragma omp target...
I added the following to this [repo's OMPT example](https://github.com/ROCm-Developer-Tools/aomp/blob/4585647781c82648002c7955d6f5dfa1a8f57532/examples/tools/ompt/veccopy-ompt-target-tracing/callbacks.h): ``` #pragma omp target data map(tofrom: initial_device) { int a; #pragma omp target { for(int i=0; i
See #160 figure. Currently every asynchronous transfer and kernel_dispatch within a target offload has single_wait_scaquire (synchronization) right after. It should be nice to optimize them by enqueuing H2D, kernel_dispatch, D2H...
I'm using AOMP 11.7-1 STANDALONE compiled from source on Arch Linux. When compiling OpenMP code with a custom mapper I always get a memory access fault. The following code is...
