[all-commits] [llvm/llvm-project] bc7dac: [AMDGPU] Generate checks for llvm.amdgcn.image.bvh...

[Jay Foad via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: bc7dacf58946f62eaa533ee5d43365ec6bf10e12
      https://github.com/llvm/llvm-project/commit/bc7dacf58946f62eaa533ee5d43365ec6bf10e12
  Author: Jay Foad <jay.foad at amd.com>
  Date:   2021-12-04 (Sat, 04 Dec 2021)

  Changed paths:
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.intersect_ray.ll

  Log Message:
  -----------
  [AMDGPU] Generate checks for llvm.amdgcn.image.bvh.intersect.ray

Differential Revision: https://reviews.llvm.org/D114955


  Commit: c8e84c7a5f38d46e97debba0eb1ae05f6a2fa39f
      https://github.com/llvm/llvm-project/commit/c8e84c7a5f38d46e97debba0eb1ae05f6a2fa39f
  Author: Jay Foad <jay.foad at amd.com>
  Date:   2021-12-04 (Sat, 04 Dec 2021)

  Changed paths:
    M llvm/include/llvm/IR/Intrinsics.td
    M llvm/lib/IR/Function.cpp
    M llvm/utils/TableGen/IntrinsicEmitter.cpp

  Log Message:
  -----------
  [IR,TableGen] Add support for vec3 intrinsic arguments

Add generic support for vec3 types, and in particular define
llvm_v3f32_ty which will be used by AMDGPU's
llvm.amdgcn.image.bvh.intersect.ray intrinsic.

Differential Revision: https://reviews.llvm.org/D114956


  Commit: 2774bad1124215571ab154afcb5478c78cf46344
      https://github.com/llvm/llvm-project/commit/2774bad1124215571ab154afcb5478c78cf46344
  Author: Jay Foad <jay.foad at amd.com>
  Date:   2021-12-04 (Sat, 04 Dec 2021)

  Changed paths:
    M clang/lib/CodeGen/CGBuiltin.cpp
    M clang/test/CodeGenOpenCL/builtins-amdgcn-raytracing.cl
    M llvm/include/llvm/IR/IntrinsicsAMDGPU.td
    M llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.intersect_ray.ll
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.intersect_ray.ll

  Log Message:
  -----------
  [AMDGPU] Change llvm.amdgcn.image.bvh.intersect.ray to take vec3 args

The ray_origin, ray_dir and ray_inv_dir arguments should all be vec3 to
match how the hardware instruction works.

Don't change the API of the corresponding OpenCL builtins.

Differential Revision: https://reviews.llvm.org/D115032


Compare: https://github.com/llvm/llvm-project/compare/5b94037a304e...2774bad11242