[all-commits] [llvm/llvm-project] 62fca6: [CostModel][X86][AVX2] Improve 256-bit vector non-...

[Simon Pilgrim via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 62fca69a704cc4883736698b781f63f59e7fa7b2
      https://github.com/llvm/llvm-project/commit/62fca69a704cc4883736698b781f63f59e7fa7b2
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2021-05-20 (Thu, 20 May 2021)

  Changed paths:
    M llvm/lib/Target/X86/X86TargetTransformInfo.cpp
    M llvm/test/Analysis/CostModel/X86/div.ll
    M llvm/test/Analysis/CostModel/X86/fshl.ll
    M llvm/test/Analysis/CostModel/X86/fshr.ll
    M llvm/test/Analysis/CostModel/X86/rem.ll
    M llvm/test/Analysis/CostModel/X86/vshift-ashr-cost-inseltpoison.ll
    M llvm/test/Analysis/CostModel/X86/vshift-ashr-cost.ll
    M llvm/test/Analysis/CostModel/X86/vshift-lshr-cost-inseltpoison.ll
    M llvm/test/Analysis/CostModel/X86/vshift-lshr-cost.ll
    M llvm/test/Analysis/CostModel/X86/vshift-shl-cost-inseltpoison.ll
    M llvm/test/Analysis/CostModel/X86/vshift-shl-cost.ll

  Log Message:
  -----------
  [CostModel][X86][AVX2] Improve 256-bit vector non-uniform shifts costs

Haswell, Excavator and early Ryzen all have slower 256-bit non-uniform vector shifts (confirmed on AMDSoG/Agner/instlatx64 and llvm models) - so bump the worst case costs accordingly.

Noticed while investigating PR50364