[all-commits] [llvm/llvm-project] 3115ad: [AMDGPU] Accept arbitrary sized sources in Calcula...

[Jeffrey Byrnes via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 3115ad8980e7d36adca95b5449db8ebf9bd94bf2
      https://github.com/llvm/llvm-project/commit/3115ad8980e7d36adca95b5449db8ebf9bd94bf2
  Author: Jeffrey Byrnes <jeffrey.byrnes at amd.com>
  Date:   2024-02-07 (Wed, 07 Feb 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/test/CodeGen/AMDGPU/idot4u.ll
    M llvm/test/CodeGen/AMDGPU/insert_vector_elt.v2i16.ll
    M llvm/test/CodeGen/AMDGPU/load-hi16.ll
    M llvm/test/CodeGen/AMDGPU/permute.ll
    M llvm/test/CodeGen/AMDGPU/permute_i8.ll

  Log Message:
  -----------
  [AMDGPU] Accept arbitrary sized sources in CalculateByteProvider (#70240)

Reland the original patch with additional commit containing fix for two
issues:

1. Attempting to bitcast using MVTs with no corresponding LLVM type.
getDWordFromOffset now works directly with the original vector to get
the corresponding elements given the DWordOffset.
2. Improper bit tracking in CalculateByteProvider for vector types using
certain ops. Previously, bit tracking for certain ops (e.g.
ISD::TRUNCATE) assumed operands were scalar types, which is not correct
since these ops have different semantics depending on vector / scalar.
CalculateByteProvider / CalculateSrcByte now exit on vector types,
handling which is a TODO.