[all-commits] [llvm/llvm-project] d28370: [AArch64][SVE] Fix definition of bfloat fcvt intri...

[Paul Walker via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: d283705829ecbdf4d1c214a88166d5750f992255
      https://github.com/llvm/llvm-project/commit/d283705829ecbdf4d1c214a88166d5750f992255
  Author: Paul Walker <paul.walker at arm.com>
  Date:   2024-10-03 (Thu, 03 Oct 2024)

  Changed paths:
    M clang/include/clang/Basic/arm_sve.td
    M clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cvt-bfloat.c
    M clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cvtnt.c
    M llvm/include/llvm/IR/IntrinsicsAArch64.td
    M llvm/lib/IR/AutoUpgrade.cpp
    M llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
    M llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
    M llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
    M llvm/lib/Target/AArch64/SVEInstrFormats.td
    M llvm/test/CodeGen/AArch64/sve-intrinsics-bfloat.ll
    M llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-comb-all-active-lanes-cvt.ll
    M llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-comb-no-active-lanes-cvt.ll

  Log Message:
  -----------
  [AArch64][SVE] Fix definition of bfloat fcvt intrinsics. (#110281)

Affected intrinsics:
  llvm.aarch64.sve.fcvt.bf16f32
  llvm.aarch64.sve.fcvtnt.bf16f32
    
The named intrinsics took a predicate based on the smallest element type
when it should be based on the largest. The intrinsics have been replace
by v2 equivalents and affected code ported to use them.
    
Patch includes changes to getSVEPredicateBitCast() that ensure the
generated code for the auto-upgraded old intrinsics is unchanged.



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