================
@@ -6093,12 +6150,16 @@
SITargetLowering::EmitInstrWithCustomInserter(MachineInstr &MI,
return lowerWaveReduce(MI, *BB, *getSubtarget(), AMDGPU::S_ADD_U64_PSEUDO);
case AMDGPU::WAVE_REDUCE_FADD_PSEUDO_F32:
return lowerWaveReduce(MI, *BB, *getSubtarget(), AMDGPU::V_ADD_F32_e64);
+ case AMDGPU::WAVE_REDUCE_FADD_PSEUDO_F64:
+ return lowerWaveReduce(MI, *BB, *getSubtarget(), AMDGPU::V_ADD_F64_e64);
case AMDGPU::WAVE_REDUCE_SUB_PSEUDO_I32:
return lowerWaveReduce(MI, *BB, *getSubtarget(), AMDGPU::S_SUB_I32);
case AMDGPU::WAVE_REDUCE_SUB_PSEUDO_U64:
return lowerWaveReduce(MI, *BB, *getSubtarget(), AMDGPU::S_SUB_U64_PSEUDO);
case AMDGPU::WAVE_REDUCE_FSUB_PSEUDO_F32:
return lowerWaveReduce(MI, *BB, *getSubtarget(), AMDGPU::V_SUB_F32_e64);
+ case AMDGPU::WAVE_REDUCE_FSUB_PSEUDO_F64:
+ return lowerWaveReduce(MI, *BB, *getSubtarget(), AMDGPU::V_SUB_F32_e32);
----------------
easyonaadit wrote:
Right,
As an alternative idea, I could pass the `WAVE_REDUCE_FSUB_PSEUDO_F64` opcode
itself, as it is only going to be used in the switch statements and not for
codegen, but then it ruins the uniformity of the code.
Should I use that instead?
https://github.com/llvm/llvm-project/pull/170812
_______________________________________________
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
