[all-commits] [llvm/llvm-project] ea4e32: [llvm][RISCV] Optimize fcopysign for fixed vectors...

Brandon Wu via All-commits all-commits at lists.llvm.org
Sun May 10 08:59:42 PDT 2026


  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: ea4e329808feac0290f76ae4d9b922e74916fb9f
      https://github.com/llvm/llvm-project/commit/ea4e329808feac0290f76ae4d9b922e74916fb9f
  Author: Brandon Wu <brandon.wu at sifive.com>
  Date:   2026-05-10 (Sun, 10 May 2026)

  Changed paths:
    M llvm/lib/CodeGen/SelectionDAG/LegalizeVectorOps.cpp
    M llvm/test/CodeGen/NVPTX/f16x2-instructions.ll
    M llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vcopysign-sdnode.ll
    M llvm/test/CodeGen/Thumb2/mve-fmath.ll

  Log Message:
  -----------
  [llvm][RISCV] Optimize fcopysign for fixed vectors (#193802)

vfsgnj is not available on zvfhmin or zvfbfmin, it's expected to expand
to integer operations instead of unrolling to scalar operations.
General expandFCOPYSIGN already handles that in most of cases except for
fixed vector types that are not promotable, we need to find a better
heuristic to gate this.



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


More information about the All-commits mailing list