[all-commits] [llvm/llvm-project] 6d97ca: [AMDGPU] Increase detection range for s_mov, v_cmp...

[Thomas Symalla via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 6d97ca690c4d9f59226d06e30233e247a3308e9b
      https://github.com/llvm/llvm-project/commit/6d97ca690c4d9f59226d06e30233e247a3308e9b
  Author: Thomas Symalla <thomas.symalla at amd.com>
  Date:   2022-04-08 (Fri, 08 Apr 2022)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIOptimizeExecMasking.cpp
    M llvm/test/CodeGen/AMDGPU/vcmp-saveexec-to-vcmpx.mir

  Log Message:
  -----------
  [AMDGPU] Increase detection range for s_mov, v_cmpx transformation.

We found that it might be beneficial to have the SIOptimizeExecMasking
pass detect more cases where v_cmp, s_and_saveexec patterns can be
transformed to s_mov, v_cmpx patterns. Currently, the search range
for finding a fitting v_cmp instruction is 5, however, this is doubled
to 10 here.

Reviewed By: foad

Differential Revision: https://reviews.llvm.org/D123367