AMD Rebases Their OpenMP For Radeon GPUs Against LLVM 11

At the end of last year with ROCm 3.0 AMD introduced the AOMP compiler for OpenMP support targeting Radeon GPUs. AOMP is another downstream of LLVM Clang and on Tuesday marked the latest update.

AOMP so far has been developed independently of the LLVM Clang code-base and it remains to be seen any mainlining plans they have of getting this OpenMP offloading for Radeon GPUs upstream. Following their AOMP update in March they have now announced AOMP Release 11.0-1.

AOMP Release 11.0-1 is now tracking the LLVM Clang 11 compiler development code using their Git state as of the end of March. With this transition is also their new versioning scheme to more closely follow LLVM versioning habits.

Besides re-basing against the latest LLVM 11 development code, AOMP 11.0-1 switches from the HIP run-time built with HCC to using the new HIP run-time built on top of the ROCMclr component.

More details on AOMP for OpenMP offloading to Radeon GPUs on Linux via their GitHub project site.