[all-commits] [llvm/llvm-project] 31b62a: [AMDGPU] Fix codegen of image intrinsics for g16 a...

[David Stuttard via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 31b62aa162b464efadef942a801706127dd8a443
      https://github.com/llvm/llvm-project/commit/31b62aa162b464efadef942a801706127dd8a443
  Author: David Stuttard <david.stuttard at amd.com>
  Date:   2021-05-14 (Fri, 14 May 2021)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
    M llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.sample.a16.dim.ll
    A llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.sample.g16.a16.dim.ll

  Log Message:
  -----------
  [AMDGPU] Fix codegen of image intrinsics for g16 and a16

For gfx10 gradient (g16) and address (a16) can be independent. Previous
implementation assumed that a16 implied g16.

There are some other changes that fix the verification (as well as asm/disasm)
that are required for the included test to pass - the XFAIL will be removed in
those changes.

This also includes required fixes for GlobalISel

Differential Revision: https://reviews.llvm.org/D102066

Change-Id: I7d171cc90994de05f41669b66a6d0ffa2ed05d09