[all-commits] [llvm/llvm-project] fc02d9: [X86] Add cost table entry for v2i32->v2f64 fp_to_...

[topperc via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: fc02d9f3c6b709a241eb3963366fa6aa09c1ee21
      https://github.com/llvm/llvm-project/commit/fc02d9f3c6b709a241eb3963366fa6aa09c1ee21
  Author: Craig Topper <craig.topper at gmail.com>
  Date:   2020-04-26 (Sun, 26 Apr 2020)

  Changed paths:
    M llvm/lib/Target/X86/X86TargetTransformInfo.cpp

  Log Message:
  -----------
  [X86] Add cost table entry for v2i32->v2f64 fp_to_uint with avx512.

We're currently getting this from the default implementation. But
I don't like how the cost model came to this answer and I might
be making some changes there.


  Commit: 5f2ea709800ca51cf08986c9e44943d5db05619f
      https://github.com/llvm/llvm-project/commit/5f2ea709800ca51cf08986c9e44943d5db05619f
  Author: Craig Topper <craig.topper at gmail.com>
  Date:   2020-04-26 (Sun, 26 Apr 2020)

  Changed paths:
    M llvm/test/Analysis/CostModel/X86/fptosi.ll
    M llvm/test/Analysis/CostModel/X86/fptoui.ll
    M llvm/test/Analysis/CostModel/X86/sitofp.ll
    M llvm/test/Analysis/CostModel/X86/uitofp.ll

  Log Message:
  -----------
  [X86] Add cost model tests for conversions between <2 x float> and integers.

For all but 2 x i32 we were starting from 4 x float.


Compare: https://github.com/llvm/llvm-project/compare/8000d506afcd...5f2ea709800c