[all-commits] [llvm/llvm-project] 65e424: [CostModel][X86] Adjust i32/i64 to f32/f64 scalar ...

[Simon Pilgrim via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 65e4240fa10848d3b201429ab5a1bfb2eb02c7ad
      https://github.com/llvm/llvm-project/commit/65e4240fa10848d3b201429ab5a1bfb2eb02c7ad
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2021-07-05 (Mon, 05 Jul 2021)

  Changed paths:
    M llvm/lib/Target/X86/X86TargetTransformInfo.cpp
    M llvm/test/Analysis/CostModel/X86/sitofp.ll
    M llvm/test/Analysis/CostModel/X86/uitofp.ll
    M llvm/test/Transforms/SLPVectorizer/X86/sitofp-inseltpoison.ll
    M llvm/test/Transforms/SLPVectorizer/X86/sitofp.ll
    M llvm/test/Transforms/SLPVectorizer/X86/uitofp.ll

  Log Message:
  -----------
  [CostModel][X86] Adjust i32/i64 to f32/f64 scalar based on llvm-mca reports (+ Agner).

Older SSE targets have slower gpr->fpu scalar conversions - we also need to account for uitofp i32 > f32/f64 being lowered as sitofp i64 -> f32/f64


  Commit: 5db826e4ce63a4d45a4695e5486841d08b86cd24
      https://github.com/llvm/llvm-project/commit/5db826e4ce63a4d45a4695e5486841d08b86cd24
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2021-07-05 (Mon, 05 Jul 2021)

  Changed paths:
    M llvm/lib/Target/X86/X86TargetTransformInfo.cpp
    M llvm/test/Analysis/CostModel/X86/insert-extract-at-zero-inseltpoison.ll
    M llvm/test/Analysis/CostModel/X86/insert-extract-at-zero.ll
    M llvm/test/Analysis/CostModel/X86/vector-extract.ll
    M llvm/test/Analysis/CostModel/X86/vector-insert-inseltpoison.ll
    M llvm/test/Analysis/CostModel/X86/vector-insert.ll

  Log Message:
  -----------
  [CostModel][X86] Handle costs for insert/extractelement with non-immediate indices via stack

Determine the insert/extractelement costs when performing this as a sequence of aliased loads+stores via the stack.


Compare: https://github.com/llvm/llvm-project/compare/3d3c0ed9323b...5db826e4ce63