These are the release notes for AOMP 21.0-0. AOMP uses AMD developer modifications to the upstream LLVM development trunk. These differences are managed in a branch called the "amd-staging". This branch is found in a mirror of upstream LLVM found at https://github.com/ROCm/llvm-project. The amd-staging branch is constantly changing as it merges the upstream development trunk with its downstream development updates. The AMD modifications are experimental while under review for the upstream trunk. AOMP uses a snapshot of amd-staging at the commit ids and dates listed below. AOMP also includes builds of related ROCm components. We call AOMP a "standalone" build as it does not use or require ROCm with the exception of the kernel module (amdgpu-dkms) and libdrm which are often part of the Linux distribution. AOMP is isolated from any ROCm installations by installing into /usr/lib/aomp and the use of RPATH for runtime libraries.
For AOMP 21.0-0, the last LLVM trunk commit is 9cdab16da99ad9fdb823853fbc634008229e284f on March 31, 2025. The last amd-only commit is e9b040d02cd3f5e5dae032e7d15d934ea6486d18 on April 1, 2025. These commits form a frozen branch now called "aomp-21.0-0". See https://github.com/ROCm/llvm-project/tree/aomp-21.0-0.
The integrated ROCm components for this AOMP release were built with ROCM 6.3.3 sources.
This is the 1st AOMP release based on upstream LLVM 21 development.
Changes since AOMP 20.0-2:
- In this release, the FORTRAN flang-classic compiler is replaced with the new LLVM compiler (flang-new). Flang-new is built using the LLVM 21 trunk plus changes in the amd-staging branch. In addition to improved performance flang-new, supports print and write statements in the target region to support user diagnostics. The existence of any print or write statement in the target region will trigger a service thread that could impact performance, even if the print or write statements are not executed.
- The hipfort component built with flang-new has returned to aomp. Hipfort provides FORTRAN module interfaces to the HIP API and to many other hip math libraries. There are new examples in the examples directory to demonstrate hipfort.
- Improved performance on min and max reductions using fmin and fmax functions to define the reduction.
- Replacement of the amd-stging hostexec infrastructure with the upstream offload rpc mechanism.
- A new infrastructure for executing host API's in target regions called "Emissary APIs". Emissary APIs use the offload rpc mechanism to transparently execute functions called from a target region on the host. Emissary APIs exist for print, FORTRAN runtime, MPI, and HDF5. MPI and HDF5 are currently placeholders requiring more development to make them functional. The Emissary API for print includes printf, fprintf, and asan exception reporting. The Emissary API for the FORTRAN runtime supports print, write, stop, and abort FORTRAN statements.
- In this release, all OpenMP toolchains (c, c++, and FORTRAN) use a tool called clang-linker-wrapper as the default. This is a single command generated for host and device linking. Previously a multi-step process was used by the LLVM command driver. This multi-step process is still available with the --opaque-offload-linker command line option. Since clang-linker-wrapper obscures the process of device linking --opaque-offload-linker can be used to see the transformations from heterogeneous objects to fully linked device and host executable.
- This release uses the sources from ROCM 6.3 components for non-compiler components. All llvm-project compiler components were built using the amd-staging branch with the above-mentioned commit hash.
- In this release, we started a process to cleanup the examples for the different programming models supported by the ROCm compiler. The new examples are 100% driven by Makefiles so that users can see the compiler commands and environment that they are run in. Since the examples are typically in a read-only installation directory. They can now be executed from an out-of-tree directory to avoid the need to copy them. For example "make -f /usr/lib/aomp/examples/openmp/reduction/Makefile run " will build and run the example
- A significant number of changes to the AOMP build infrastructure were done to both add flang-new build and remove flang-classic build.
- Merging non-upstream changes into the amd-staging branch now uses github pull requests. We no longer use gerrit for this purpose. Merging of github PRs still requires successful passing of psdb tests. Merging from upstream trunk is still possible and preferred.
Errata:
- The hip/lib_device example currently fails to build with a link error.