[PATCH] D106023: [AMDGPU] Mark relevant rematerializable VOP2 instructions
Matt Arsenault via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Thu Jul 15 15:09:09 PDT 2021
arsenm added inline comments.
================
Comment at: llvm/lib/Target/AMDGPU/VOP2Instructions.td:651
+let FPDPRounding = 1, isReMaterializable = 1 in {
def V_MADMK_F16 : VOP2_Pseudo <"v_madmk_f16", VOP_MADMK_F16, [], "">;
defm V_LDEXP_F16 : VOP2Inst <"v_ldexp_f16", VOP_F16_F16_I32, AMDGPUldexp>;
----------------
This preserves high bits on gfx9
================
Comment at: llvm/lib/Target/AMDGPU/VOP2Instructions.td:652
def V_MADMK_F16 : VOP2_Pseudo <"v_madmk_f16", VOP_MADMK_F16, [], "">;
defm V_LDEXP_F16 : VOP2Inst <"v_ldexp_f16", VOP_F16_F16_I32, AMDGPUldexp>;
+} // End FPDPRounding = 1, isReMaterializable = 1
----------------
This one does not (but does on gfx10)
================
Comment at: llvm/lib/Target/AMDGPU/VOP2Instructions.td:765
+let SubtargetPredicate = HasFmaakFmamkF32Insts, isReMaterializable = 1 in {
def V_FMAMK_F32 : VOP2_Pseudo<"v_fmamk_f32", VOP_MADMK_F32, [], "">;
----------------
This and the other fma flavors preserve the high bits on gfx9
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D106023/new/
https://reviews.llvm.org/D106023
More information about the llvm-commits
mailing list