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

[Konstantin Zhuravlyov via llvm-commits]

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.


https://reviews.llvm.org/D25805