[llvm] c8ba317 - [AMDGPU] Remove comment outdated by #96933

Jay Foad via llvm-commits llvm-commits at lists.llvm.org
Fri Aug 23 02:48:08 PDT 2024


Author: Jay Foad
Date: 2024-08-23T10:47:45+01:00
New Revision: c8ba31700588eabbace2af40d711e235d13ab9bf

URL: https://github.com/llvm/llvm-project/commit/c8ba31700588eabbace2af40d711e235d13ab9bf
DIFF: https://github.com/llvm/llvm-project/commit/c8ba31700588eabbace2af40d711e235d13ab9bf.diff

LOG: [AMDGPU] Remove comment outdated by #96933

Added: 
    

Modified: 
    llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp b/llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp
index a41df9606749fd..95afc3fcc8d7d1 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp
@@ -905,8 +905,7 @@ void AMDGPUAtomicOptimizerImpl::optimizeAtomic(Instruction &I,
     PHI->addIncoming(NewI, SingleLaneTerminator->getParent());
 
     // We need to broadcast the value who was the lowest active lane (the first
-    // lane) to all other lanes in the wavefront. We use an intrinsic for this,
-    // but have to handle 64-bit broadcasts with two calls to this intrinsic.
+    // lane) to all other lanes in the wavefront.
     Value *BroadcastI = nullptr;
     BroadcastI = B.CreateIntrinsic(Ty, Intrinsic::amdgcn_readfirstlane, PHI);
 


        


More information about the llvm-commits mailing list