[all-commits] [llvm/llvm-project] ccfb05: [CUDA] Implement experimental support for texture ...

[Artem Belevich via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: ccfb0555f76b865cf50bd354558dd00bfa7b2762
      https://github.com/llvm/llvm-project/commit/ccfb0555f76b865cf50bd354558dd00bfa7b2762
  Author: Artem Belevich <tra at google.com>
  Date:   2021-10-06 (Wed, 06 Oct 2021)

  Changed paths:
    M clang/lib/Headers/CMakeLists.txt
    M clang/lib/Headers/__clang_cuda_runtime_wrapper.h
    A clang/lib/Headers/__clang_cuda_texture_intrinsics.h
    M clang/test/Headers/Inputs/include/cuda.h
    A clang/test/Headers/Inputs/include/texture_fetch_functions.h
    A clang/test/Headers/texture_intrinsics.cu

  Log Message:
  -----------
  [CUDA] Implement experimental support for texture lookups.

The patch implements header-only support for testure lookups.

The patch has been tested on a source file with all possible combinations of
argument types supported by CUDA headers, compiled and verified that the
generated instructions and their parameters match the code generated by NVCC.
Unfortunately, compiling texture code requires CUDA headers and can't be tested
in clang itself.  The test will need to be added to the test-suite later.

While generated code compiles and seems to match NVCC, I do not have any code
that uses textures that I could test correctness of the implementation. Hence
the experimental status.

Differential Revision: https://reviews.llvm.org/D110089