[all-commits] [llvm/llvm-project] fc6300: [AMDGPU] Disable inline constants for pseudo scala...

[Carl Ritson via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: fc6300a5f7ef430e4ec86d16be0b146de7fbd16b
      https://github.com/llvm/llvm-project/commit/fc6300a5f7ef430e4ec86d16be0b146de7fbd16b
  Author: Carl Ritson <carl.ritson at amd.com>
  Date:   2024-08-17 (Sat, 17 Aug 2024)

  Changed paths:
    M llvm/lib/Target/AMDGPU/GCNSubtarget.h
    M llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
    M llvm/lib/Target/AMDGPU/SIInstrInfo.h
    A llvm/test/CodeGen/AMDGPU/pseudo-scalar-transcendental.mir

  Log Message:
  -----------
  [AMDGPU] Disable inline constants for pseudo scalar transcendentals (#104395)

Prevent operand folding from inlining constants into pseudo scalar
transcendental f16 instructions.
However still allow literal constants.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications