diff options
author | Joseph Huber <huberjn@outlook.com> | 2024-04-10 14:07:18 -0500 |
---|---|---|
committer | Joseph Huber <huberjn@outlook.com> | 2024-04-10 14:07:57 -0500 |
commit | fad14707b73d6387e6276507e1c5726e67f08cd6 (patch) | |
tree | ad9c0448ff9e59d1c2fff3322347703962c54dfb /libc/docs | |
parent | f81879c0f70ee5a1cf1d5b716dfd49d1a271cc2d (diff) | |
download | llvm-fad14707b73d6387e6276507e1c5726e67f08cd6.zip llvm-fad14707b73d6387e6276507e1c5726e67f08cd6.tar.gz llvm-fad14707b73d6387e6276507e1c5726e67f08cd6.tar.bz2 |
[libc] Add note to use `LIBC_GPU_BUILD=ON` as another form
Summary:
This is a shorthand to enable GPU support so it should be listed in the
docs.
Diffstat (limited to 'libc/docs')
-rw-r--r-- | libc/docs/gpu/building.rst | 7 |
1 files changed, 6 insertions, 1 deletions
diff --git a/libc/docs/gpu/building.rst b/libc/docs/gpu/building.rst index 6d94134..d3e64c6 100644 --- a/libc/docs/gpu/building.rst +++ b/libc/docs/gpu/building.rst @@ -33,7 +33,8 @@ The simplest way to build the GPU libc is to use the existing LLVM runtimes support. This will automatically handle bootstrapping an up-to-date ``clang`` compiler and using it to build the C library. The following CMake invocation will instruct it to build the ``libc`` runtime targeting both AMD and NVIDIA -GPUs. +GPUs. The ``LIBC_GPU_BUILD`` option can also be enabled to add the relevant +arguments automatically. .. code-block:: sh @@ -234,6 +235,10 @@ standard runtime build. This flag controls whether or not the libc build will generate its own headers. This must always be on when targeting the GPU. +**LIBC_GPU_BUILD**:BOOL + Shorthand for enabling GPU support. Equivalent to enabling support for both + AMDGPU and NVPTX builds for ``libc``. + **LIBC_GPU_TEST_ARCHITECTURE**:STRING Sets the architecture used to build the GPU tests for, such as ``gfx90a`` or ``sm_80`` for AMD and NVIDIA GPUs respectively. The default behavior is to |