Skip to content

Conversation

@justinfargnoli
Copy link
Contributor

Delete dead code that checks for NVPTX::IMOV16rr.

@justinfargnoli justinfargnoli self-assigned this Nov 5, 2024
@justinfargnoli justinfargnoli marked this pull request as ready for review November 5, 2024 02:12
@llvmbot
Copy link
Member

llvmbot commented Nov 5, 2024

@llvm/pr-subscribers-backend-nvptx

Author: Justin Fargnoli (justinfargnoli)

Changes

Delete dead code that checks for NVPTX::IMOV16rr.


Full diff: https://github.com/llvm/llvm-project/pull/114913.diff

1 Files Affected:

  • (modified) llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp (-4)
diff --git a/llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp b/llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp
index d32be9cd9bf7c0..8e73efd013fa88 100644
--- a/llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp
+++ b/llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp
@@ -5602,10 +5602,6 @@ static SDValue PerformANDCombine(SDNode *N,
     Val = Val->getOperand(0);
   }
 
-  if (Val->isMachineOpcode() && Val->getMachineOpcode() == NVPTX::IMOV16rr) {
-    Val = Val->getOperand(0);
-  }
-
   if (Val->getOpcode() == NVPTXISD::LoadV2 ||
       Val->getOpcode() == NVPTXISD::LoadV4) {
     ConstantSDNode *MaskCnst = dyn_cast<ConstantSDNode>(Mask);

Copy link
Member

@AlexMaclean AlexMaclean left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, thanks

@justinfargnoli justinfargnoli merged commit 9a5e5a6 into llvm:main Nov 5, 2024
12 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants