[all-commits] [llvm/llvm-project] e933c0: [X86] Add fadd/fsub/fmul tests showing failure to ...

[Simon Pilgrim via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: e933c05cd2cb97974cfca9544ebbdb9af349d602
      https://github.com/llvm/llvm-project/commit/e933c05cd2cb97974cfca9544ebbdb9af349d602
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2024-03-26 (Tue, 26 Mar 2024)

  Changed paths:
    M llvm/test/CodeGen/X86/widen_fadd.ll
    M llvm/test/CodeGen/X86/widen_fmul.ll
    M llvm/test/CodeGen/X86/widen_fsub.ll

  Log Message:
  -----------
  [X86] Add fadd/fsub/fmul tests showing failure to concat operands together and perform as a wider vector

We don't want to concat fadd/fsub/fmul if both operands would need concatenating (as the fp op is usually cheaper than the concat), but if at least one operand is free to concat (i.e. constant or extracted from a wider vector), then we should try to concat the fp op.


  Commit: d18bee2313ab8274fad386b1c0227316bf4238b2
      https://github.com/llvm/llvm-project/commit/d18bee2313ab8274fad386b1c0227316bf4238b2
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2024-03-26 (Tue, 26 Mar 2024)

  Changed paths:
    M llvm/lib/Target/X86/X86ISelLowering.cpp
    M llvm/test/CodeGen/X86/widen_fadd.ll
    M llvm/test/CodeGen/X86/widen_fmul.ll
    M llvm/test/CodeGen/X86/widen_fsub.ll

  Log Message:
  -----------
  [X86] combineConcatVectorOps - concatenate FADD/FSUB/FMUL ops if we don't increase the number of INSERT_SUBVECTOR nodes.

FADD/FSUB/FMUL are usually less port-bound than INSERT_SUBVECTOR, so only concatenate if it reduces the instruction count and doesn't introduce extra INSERT_SUBVECTOR nodes.


Compare: https://github.com/llvm/llvm-project/compare/06bb8c9f202e...d18bee2313ab

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