[PATCH] D106023: [AMDGPU] Mark relevant rematerializable VOP2 instructions

[Matt Arsenault via Phabricator via llvm-commits]

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