[PATCH] D106457: [Matrix] Fix miscompile for NT matmul if the transpose has other use

[Adam Nemet via Phabricator via llvm-commits]

anemet created this revision.
anemet added a reviewer: fhahn.
Herald added subscribers: tschuett, hiraditya.
anemet requested review of this revision.
Herald added a project: LLVM.
Herald added a subscriber: llvm-commits.

We should only add the fake lowering entry for the matrix remark if the                                        
transpose is not lowered on its own.  `MapVector::insert` is used to insert                                    
the entry during proper lowering which does not overwrite the fake entry in                                    
the map.

                                 

We actually had test coverage for this but the reference output code was                                       
wrong; it was storing undef rather than the transposed column.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D106457

Files:
  llvm/lib/Transforms/Scalar/LowerMatrixIntrinsics.cpp
  llvm/test/Transforms/LowerMatrixIntrinsics/multiply-right-transpose.ll


Index: llvm/test/Transforms/LowerMatrixIntrinsics/multiply-right-transpose.ll
===================================================================
--- llvm/test/Transforms/LowerMatrixIntrinsics/multiply-right-transpose.ll
+++ llvm/test/Transforms/LowerMatrixIntrinsics/multiply-right-transpose.ll
@@ -91,10 +91,10 @@
 ; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <3 x double> [[TMP9]], double [[TMP10]], i64 2
 ; CHECK-NEXT:    [[TMP12:%.*]] = bitcast <6 x double>* [[P:%.*]] to double*
 ; CHECK-NEXT:    [[VEC_CAST:%.*]] = bitcast double* [[TMP12]] to <3 x double>*
-; CHECK-NEXT:    store <3 x double> undef, <3 x double>* [[VEC_CAST]], align 16
+; CHECK-NEXT:    store <3 x double> [[TMP5]], <3 x double>* [[VEC_CAST]], align 16
 ; CHECK-NEXT:    [[VEC_GEP:%.*]] = getelementptr double, double* [[TMP12]], i64 3
 ; CHECK-NEXT:    [[VEC_CAST42:%.*]] = bitcast double* [[VEC_GEP]] to <3 x double>*
-; CHECK-NEXT:    store <3 x double> undef, <3 x double>* [[VEC_CAST42]], align 8
+; CHECK-NEXT:    store <3 x double> [[TMP11]], <3 x double>* [[VEC_CAST42]], align 8
 ; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <6 x double> [[A:%.*]], <6 x double> poison, <2 x i32> <i32 0, i32 1>
 ; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <6 x double> [[A]], <6 x double> poison, <2 x i32> <i32 2, i32 3>
 ; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <6 x double> [[A]], <6 x double> poison, <2 x i32> <i32 4, i32 5>
Index: llvm/lib/Transforms/Scalar/LowerMatrixIntrinsics.cpp
===================================================================
--- llvm/lib/Transforms/Scalar/LowerMatrixIntrinsics.cpp
+++ llvm/lib/Transforms/Scalar/LowerMatrixIntrinsics.cpp
@@ -1540,11 +1540,11 @@
       if (Transpose->hasOneUse()) {
         FusedInsts.insert(cast<Instruction>(Transpose));
         ToRemove.push_back(cast<Instruction>(Transpose));
+        // TODO: add a fake entry for the folded instruction so that this is
+        // included in the expression in the remark.
+        Inst2ColumnMatrix[Transpose] = MatrixTy(M, C, EltType);
       }
       finalizeLowering(MatMul, Result, Builder);
-      // TODO: add a fake entry for the folded instruction so that this is
-      // included in the expression in the remark.
-      Inst2ColumnMatrix[Transpose] = MatrixTy(M, C, EltType);
       return;
     }
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D106457.360500.patch
Type: text/x-patch
Size: 2307 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210721/800fd57b/attachment.bin>