[PATCH] D25805: [AMDGPU] Perform uchar to float combine for ISD::SINT_TO_FP

Konstantin Zhuravlyov via llvm-commits llvm-commits at lists.llvm.org
Fri Oct 21 10:46:30 PDT 2016

kzhuravl added inline comments.

Comment at: lib/Target/AMDGPU/SIISelLowering.cpp:3525-3527
+    if (Src.getOpcode() == ISD::ZERO_EXTEND &&
+        Src.getOperand(0).getOpcode() == ISD::SRL)
+      Src = Src.getOperand(0);
tstellarAMD wrote:
> I think calling simplifyDemandedBits either here or in performUCharToFloat combine will eliminate the need for this code.
In this case, simplifyDemandedBits will replace zero_extend with any_extend.


More information about the llvm-commits mailing list