[all-commits] [llvm/llvm-project] ae33cb: [X86][SSE] LowerVectorAllZeroTest - add support fo...

[Simon Pilgrim via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: ae33cbc49408c90cef0b1246a7bae59bd467c93b
      https://github.com/llvm/llvm-project/commit/ae33cbc49408c90cef0b1246a7bae59bd467c93b
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2020-06-15 (Mon, 15 Jun 2020)

  Changed paths:
    M llvm/lib/Target/X86/X86ISelLowering.cpp
    M llvm/test/CodeGen/X86/ptest.ll

  Log Message:
  -----------
  [X86][SSE] LowerVectorAllZeroTest - add support for >256-bit vectors

Reduce by splitting the vector until we reach the target size for PTEST/MOVMSK_PCMPEQ. There might be some cases where AVX512 can perform this with 512-bit vectors but so far I haven't encountered any such pattern that reaches LowerVectorAllZeroTest.

Prep work for D81547