[all-commits] [llvm/llvm-project] a3b7b2: [X86][CodeGen] Not compress EVEX into VEX when R16...

[Shengchen Kan via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: a3b7b2d6354f622372ce6967e082869979c25ed8
      https://github.com/llvm/llvm-project/commit/a3b7b2d6354f622372ce6967e082869979c25ed8
  Author: Shengchen Kan <shengchen.kan at intel.com>
  Date:   2023-11-28 (Tue, 28 Nov 2023)

  Changed paths:
    M llvm/lib/Target/X86/X86EvexToVex.cpp
    A llvm/test/CodeGen/X86/apx/evex-to-vex.ll

  Log Message:
  -----------
  [X86][CodeGen] Not compress EVEX into VEX when R16-R31 is used (#73604)

b/c VEX prefix can not encode R16-R31.