Index: llvm/lib/Transforms/Scalar/LowerMatrixIntrinsics.cpp
===================================================================
--- llvm/lib/Transforms/Scalar/LowerMatrixIntrinsics.cpp
+++ llvm/lib/Transforms/Scalar/LowerMatrixIntrinsics.cpp
@@ -105,6 +105,12 @@
   return m_CombineOr(m_Mul(L, R), m_FMul(L, R));
 }
 
+/// Match any add operation (fp or integer).
+template <typename LTy, typename RTy>
+auto m_AnyAdd(const LTy &L, const RTy &R) {
+  return m_CombineOr(m_Add(L, R), m_FAdd(L, R));
+}
+
 namespace {
 
 // Given an element pointer \p BasePtr to the start of a (sub) matrix, compute
@@ -816,6 +822,21 @@
             ReplaceAllUsesWith(I, NewInst);
             EraseFromParent(&I);
             EraseFromParent(TA);
+            // (A + B)^t -> A^t + B^t
+            // RxC RxC      CxR   CxR
+          } else if (match(TA, m_AnyAdd(m_Value(TAMA), m_Value(TAMB)))) {
+            IRBuilder<> LocalBuilder(&I);
+            NewInst = distributeTransposes(
+                TAMA, {R, C}, TAMB, {R, C}, Builder,
+                [&](Value *T0, ShapeInfo Shape0, Value *T1, ShapeInfo Shape1) {
+                  auto *FAdd = cast<Instruction>(
+                      LocalBuilder.CreateFAdd(T0, T1, "mfadd"));
+                  setShapeInfo(FAdd, Shape0);
+                  return FAdd;
+                });
+            ReplaceAllUsesWith(I, NewInst);
+            EraseFromParent(&I);
+            EraseFromParent(TA);
           }
         }
 
@@ -852,6 +873,28 @@
           if (A != B && B->use_empty())
             cast<Instruction>(B)->eraseFromParent();
         }
+        // A^t + B ^t -> (A + B)^t
+        else if (match(&I, m_FAdd(m_Value(A), m_Value(B))) &&
+                 match(A,
+                       m_Intrinsic<Intrinsic::matrix_transpose>(
+                           m_Value(AT), m_ConstantInt(R), m_ConstantInt(C))) &&
+                 match(B,
+                       m_Intrinsic<Intrinsic::matrix_transpose>(
+                           m_Value(BT), m_ConstantInt(R), m_ConstantInt(C)))) {
+          IRBuilder<> Builder(&I);
+          Value *Add = cast<Instruction>(Builder.CreateFAdd(AT, BT, "mfadd"));
+          setShapeInfo(Add, {C, R});
+          MatrixBuilder MBuilder(Builder);
+          Instruction *NewInst = MBuilder.CreateMatrixTranspose(
+              Add, C->getZExtValue(), R->getZExtValue(), "mfadd_t");
+          ReplaceAllUsesWith(I, NewInst);
+          if (I.use_empty())
+            I.eraseFromParent();
+          if (A->use_empty())
+            cast<Instruction>(A)->eraseFromParent();
+          if (A != B && B->use_empty())
+            cast<Instruction>(B)->eraseFromParent();
+        }
       }
     }
   }
Index: llvm/test/Transforms/LowerMatrixIntrinsics/after-transpose-opts.ll
===================================================================
--- llvm/test/Transforms/LowerMatrixIntrinsics/after-transpose-opts.ll
+++ llvm/test/Transforms/LowerMatrixIntrinsics/after-transpose-opts.ll
@@ -100,10 +100,9 @@
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[A:%.*]] = load <9 x double>, <9 x double>* [[APTR:%.*]], align 128
 ; CHECK-NEXT:    [[B:%.*]] = load <9 x double>, <9 x double>* [[BPTR:%.*]], align 128
-; CHECK-NEXT:    [[AT:%.*]] = call <9 x double> @llvm.matrix.transpose.v9f64(<9 x double> [[A]], i32 3, i32 3)
-; CHECK-NEXT:    [[BT:%.*]] = call <9 x double> @llvm.matrix.transpose.v9f64(<9 x double> [[B]], i32 3, i32 3)
-; CHECK-NEXT:    [[FADD:%.*]] = fadd <9 x double> [[AT]], [[BT]]
-; CHECK-NEXT:    store <9 x double> [[FADD]], <9 x double>* [[C:%.*]], align 128
+; CHECK-NEXT:    [[MFADD:%.*]] = fadd <9 x double> [[A]], [[B]]
+; CHECK-NEXT:    [[MFADD_T:%.*]] = call <9 x double> @llvm.matrix.transpose.v9f64(<9 x double> [[MFADD]], i32 3, i32 3)
+; CHECK-NEXT:    store <9 x double> [[MFADD_T]], <9 x double>* [[C:%.*]], align 128
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -122,9 +121,9 @@
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[A:%.*]] = load <9 x double>, <9 x double>* [[APTR:%.*]], align 128
 ; CHECK-NEXT:    [[B:%.*]] = load <9 x double>, <9 x double>* [[BPTR:%.*]], align 128
-; CHECK-NEXT:    [[FADD:%.*]] = fadd <9 x double> [[A]], [[B]]
-; CHECK-NEXT:    [[T:%.*]] = call <9 x double> @llvm.matrix.transpose.v9f64(<9 x double> [[FADD]], i32 3, i32 3)
-; CHECK-NEXT:    store <9 x double> [[T]], <9 x double>* [[C:%.*]], align 128
+; CHECK-NEXT:    [[MFADD1:%.*]] = fadd <9 x double> [[A]], [[B]]
+; CHECK-NEXT:    [[MFADD_T:%.*]] = call <9 x double> @llvm.matrix.transpose.v9f64(<9 x double> [[MFADD1]], i32 3, i32 3)
+; CHECK-NEXT:    store <9 x double> [[MFADD_T]], <9 x double>* [[C:%.*]], align 128
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -145,11 +144,10 @@
 ; CHECK-NEXT:    [[C:%.*]] = load <9 x double>, <9 x double>* [[CPTR:%.*]], align 128
 ; CHECK-NEXT:    [[D:%.*]] = load <9 x double>, <9 x double>* [[DPTR:%.*]], align 128
 ; CHECK-NEXT:    [[TMP0:%.*]] = call <9 x double> @llvm.matrix.multiply.v9f64.v9f64.v9f64(<9 x double> [[B]], <9 x double> [[A]], i32 3, i32 3, i32 3)
-; CHECK-NEXT:    [[TMP1:%.*]] = call <9 x double> @llvm.matrix.transpose.v9f64(<9 x double> [[TMP0]], i32 3, i32 3)
-; CHECK-NEXT:    [[TMP2:%.*]] = call <9 x double> @llvm.matrix.multiply.v9f64.v9f64.v9f64(<9 x double> [[D]], <9 x double> [[C]], i32 3, i32 3, i32 3)
-; CHECK-NEXT:    [[TMP3:%.*]] = call <9 x double> @llvm.matrix.transpose.v9f64(<9 x double> [[TMP2]], i32 3, i32 3)
-; CHECK-NEXT:    [[FADD:%.*]] = fadd <9 x double> [[TMP1]], [[TMP3]]
-; CHECK-NEXT:    store <9 x double> [[FADD]], <9 x double>* [[E:%.*]], align 128
+; CHECK-NEXT:    [[TMP1:%.*]] = call <9 x double> @llvm.matrix.multiply.v9f64.v9f64.v9f64(<9 x double> [[D]], <9 x double> [[C]], i32 3, i32 3, i32 3)
+; CHECK-NEXT:    [[MFADD:%.*]] = fadd <9 x double> [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[MFADD_T:%.*]] = call <9 x double> @llvm.matrix.transpose.v9f64(<9 x double> [[MFADD]], i32 3, i32 3)
+; CHECK-NEXT:    store <9 x double> [[MFADD_T]], <9 x double>* [[E:%.*]], align 128
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -200,17 +198,13 @@
 ; CHECK-NEXT:    [[B:%.*]] = load <9 x double>, <9 x double>* [[BPTR:%.*]], align 128
 ; CHECK-NEXT:    [[C:%.*]] = load <9 x double>, <9 x double>* [[CPTR:%.*]], align 128
 ; CHECK-NEXT:    [[D:%.*]] = load <9 x double>, <9 x double>* [[DPTR:%.*]], align 128
-; CHECK-NEXT:    [[CT:%.*]] = call <9 x double> @llvm.matrix.transpose.v9f64(<9 x double> [[C]], i32 3, i32 3)
-; CHECK-NEXT:    [[DT:%.*]] = call <9 x double> @llvm.matrix.transpose.v9f64(<9 x double> [[D]], i32 3, i32 3)
-; CHECK-NEXT:    [[TMP0:%.*]] = call <9 x double> @llvm.matrix.multiply.v9f64.v9f64.v9f64(<9 x double> [[B]], <9 x double> [[A]], i32 3, i32 3, i32 3)
-; CHECK-NEXT:    [[TMP1:%.*]] = call <9 x double> @llvm.matrix.transpose.v9f64(<9 x double> [[TMP0]], i32 3, i32 3)
 ; CHECK-NEXT:    [[VECK:%.*]] = insertelement <9 x double> poison, double [[K:%.*]], i64 0
 ; CHECK-NEXT:    [[SPLAT:%.*]] = shufflevector <9 x double> [[VECK]], <9 x double> poison, <9 x i32> zeroinitializer
-; CHECK-NEXT:    [[KCT:%.*]] = call <9 x double> @llvm.matrix.multiply.v9f64.v9f64.v9f64(<9 x double> [[SPLAT]], <9 x double> [[CT]], i32 3, i32 3, i32 3)
-; CHECK-NEXT:    [[KCTDT:%.*]] = call <9 x double> @llvm.matrix.multiply.v9f64.v9f64.v9f64(<9 x double> [[KCT]], <9 x double> [[DT]], i32 3, i32 3, i32 3)
-; CHECK-NEXT:    [[FADD:%.*]] = fadd <9 x double> [[TMP1]], [[KCTDT]]
-; CHECK-NEXT:    [[T:%.*]] = call <9 x double> @llvm.matrix.transpose.v9f64(<9 x double> [[FADD]], i32 3, i32 3)
-; CHECK-NEXT:    store <9 x double> [[T]], <9 x double>* [[E:%.*]], align 128
+; CHECK-NEXT:    [[MMUL2:%.*]] = call <9 x double> @llvm.matrix.multiply.v9f64.v9f64.v9f64(<9 x double> [[B]], <9 x double> [[A]], i32 3, i32 3, i32 3)
+; CHECK-NEXT:    [[MMUL1:%.*]] = call <9 x double> @llvm.matrix.multiply.v9f64.v9f64.v9f64(<9 x double> [[C]], <9 x double> [[SPLAT]], i32 3, i32 3, i32 3)
+; CHECK-NEXT:    [[MMUL:%.*]] = call <9 x double> @llvm.matrix.multiply.v9f64.v9f64.v9f64(<9 x double> [[D]], <9 x double> [[MMUL1]], i32 3, i32 3, i32 3)
+; CHECK-NEXT:    [[MFADD:%.*]] = fadd <9 x double> [[MMUL2]], [[MMUL]]
+; CHECK-NEXT:    store <9 x double> [[MFADD]], <9 x double>* [[E:%.*]], align 128
 ; CHECK-NEXT:    ret void
 ;
 entry:
Index: llvm/test/Transforms/LowerMatrixIntrinsics/propagate-backward.ll
===================================================================
--- llvm/test/Transforms/LowerMatrixIntrinsics/propagate-backward.ll
+++ llvm/test/Transforms/LowerMatrixIntrinsics/propagate-backward.ll
@@ -4,35 +4,31 @@
 define <8 x double> @fadd_transpose(<8 x double> %a, <8 x double> %b) {
 ; CHECK-LABEL: @fadd_transpose(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <8 x double> [[A:%.*]], <8 x double> poison, <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <2 x i32> <i32 2, i32 3>
-; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <2 x i32> <i32 4, i32 5>
-; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <2 x i32> <i32 6, i32 7>
-; CHECK-NEXT:    [[SPLIT4:%.*]] = shufflevector <8 x double> [[B:%.*]], <8 x double> poison, <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT:    [[SPLIT5:%.*]] = shufflevector <8 x double> [[B]], <8 x double> poison, <2 x i32> <i32 2, i32 3>
-; CHECK-NEXT:    [[SPLIT6:%.*]] = shufflevector <8 x double> [[B]], <8 x double> poison, <2 x i32> <i32 4, i32 5>
-; CHECK-NEXT:    [[SPLIT7:%.*]] = shufflevector <8 x double> [[B]], <8 x double> poison, <2 x i32> <i32 6, i32 7>
-; CHECK-NEXT:    [[TMP0:%.*]] = fadd <2 x double> [[SPLIT]], [[SPLIT4]]
-; CHECK-NEXT:    [[TMP1:%.*]] = fadd <2 x double> [[SPLIT1]], [[SPLIT5]]
-; CHECK-NEXT:    [[TMP2:%.*]] = fadd <2 x double> [[SPLIT2]], [[SPLIT6]]
-; CHECK-NEXT:    [[TMP3:%.*]] = fadd <2 x double> [[SPLIT3]], [[SPLIT7]]
-; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <2 x double> [[TMP0]], i64 0
-; CHECK-NEXT:    [[TMP5:%.*]] = insertelement <4 x double> poison, double [[TMP4]], i64 0
-; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x double> [[TMP1]], i64 0
-; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x double> [[TMP5]], double [[TMP6]], i64 1
-; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <2 x double> [[TMP2]], i64 0
-; CHECK-NEXT:    [[TMP9:%.*]] = insertelement <4 x double> [[TMP7]], double [[TMP8]], i64 2
-; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <2 x double> [[TMP3]], i64 0
-; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <4 x double> [[TMP9]], double [[TMP10]], i64 3
-; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <2 x double> [[TMP0]], i64 1
-; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <4 x double> poison, double [[TMP12]], i64 0
-; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <2 x double> [[TMP1]], i64 1
-; CHECK-NEXT:    [[TMP15:%.*]] = insertelement <4 x double> [[TMP13]], double [[TMP14]], i64 1
-; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <2 x double> [[TMP2]], i64 1
-; CHECK-NEXT:    [[TMP17:%.*]] = insertelement <4 x double> [[TMP15]], double [[TMP16]], i64 2
-; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <2 x double> [[TMP3]], i64 1
-; CHECK-NEXT:    [[TMP19:%.*]] = insertelement <4 x double> [[TMP17]], double [[TMP18]], i64 3
-; CHECK-NEXT:    [[TMP20:%.*]] = shufflevector <4 x double> [[TMP11]], <4 x double> [[TMP19]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <8 x double> [[A:%.*]], <8 x double> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <8 x double> [[B:%.*]], <8 x double> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[SPLIT4:%.*]] = shufflevector <8 x double> [[B]], <8 x double> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:    [[TMP0:%.*]] = fadd <4 x double> [[SPLIT]], [[SPLIT3]]
+; CHECK-NEXT:    [[TMP1:%.*]] = fadd <4 x double> [[SPLIT2]], [[SPLIT4]]
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x double> [[TMP0]], i64 0
+; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <2 x double> poison, double [[TMP2]], i64 0
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x double> [[TMP1]], i64 0
+; CHECK-NEXT:    [[TMP5:%.*]] = insertelement <2 x double> [[TMP3]], double [[TMP4]], i64 1
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x double> [[TMP0]], i64 1
+; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <2 x double> poison, double [[TMP6]], i64 0
+; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <4 x double> [[TMP1]], i64 1
+; CHECK-NEXT:    [[TMP9:%.*]] = insertelement <2 x double> [[TMP7]], double [[TMP8]], i64 1
+; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <4 x double> [[TMP0]], i64 2
+; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <2 x double> poison, double [[TMP10]], i64 0
+; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <4 x double> [[TMP1]], i64 2
+; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <2 x double> [[TMP11]], double [[TMP12]], i64 1
+; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <4 x double> [[TMP0]], i64 3
+; CHECK-NEXT:    [[TMP15:%.*]] = insertelement <2 x double> poison, double [[TMP14]], i64 0
+; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <4 x double> [[TMP1]], i64 3
+; CHECK-NEXT:    [[TMP17:%.*]] = insertelement <2 x double> [[TMP15]], double [[TMP16]], i64 1
+; CHECK-NEXT:    [[TMP18:%.*]] = shufflevector <2 x double> [[TMP5]], <2 x double> [[TMP9]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[TMP19:%.*]] = shufflevector <2 x double> [[TMP13]], <2 x double> [[TMP17]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[TMP20:%.*]] = shufflevector <4 x double> [[TMP18]], <4 x double> [[TMP19]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; CHECK-NEXT:    ret <8 x double> [[TMP20]]
 ;
 entry:
@@ -48,40 +44,43 @@
 ; CHECK-NEXT:    [[VEC_CAST:%.*]] = bitcast double* [[TMP0]] to <2 x double>*
 ; CHECK-NEXT:    [[COL_LOAD:%.*]] = load <2 x double>, <2 x double>* [[VEC_CAST]], align 8
 ; CHECK-NEXT:    [[VEC_GEP:%.*]] = getelementptr double, double* [[TMP0]], i64 2
-; CHECK-NEXT:    [[VEC_CAST1:%.*]] = bitcast double* [[VEC_GEP]] to <2 x double>*
-; CHECK-NEXT:    [[COL_LOAD2:%.*]] = load <2 x double>, <2 x double>* [[VEC_CAST1]], align 8
-; CHECK-NEXT:    [[VEC_GEP3:%.*]] = getelementptr double, double* [[TMP0]], i64 4
-; CHECK-NEXT:    [[VEC_CAST4:%.*]] = bitcast double* [[VEC_GEP3]] to <2 x double>*
-; CHECK-NEXT:    [[COL_LOAD5:%.*]] = load <2 x double>, <2 x double>* [[VEC_CAST4]], align 8
-; CHECK-NEXT:    [[VEC_GEP6:%.*]] = getelementptr double, double* [[TMP0]], i64 6
-; CHECK-NEXT:    [[VEC_CAST7:%.*]] = bitcast double* [[VEC_GEP6]] to <2 x double>*
-; CHECK-NEXT:    [[COL_LOAD8:%.*]] = load <2 x double>, <2 x double>* [[VEC_CAST7]], align 8
-; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <8 x double> [[B:%.*]], <8 x double> poison, <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT:    [[SPLIT9:%.*]] = shufflevector <8 x double> [[B]], <8 x double> poison, <2 x i32> <i32 2, i32 3>
-; CHECK-NEXT:    [[SPLIT10:%.*]] = shufflevector <8 x double> [[B]], <8 x double> poison, <2 x i32> <i32 4, i32 5>
-; CHECK-NEXT:    [[SPLIT11:%.*]] = shufflevector <8 x double> [[B]], <8 x double> poison, <2 x i32> <i32 6, i32 7>
-; CHECK-NEXT:    [[TMP1:%.*]] = fadd <2 x double> [[COL_LOAD]], [[SPLIT]]
-; CHECK-NEXT:    [[TMP2:%.*]] = fadd <2 x double> [[COL_LOAD2]], [[SPLIT9]]
-; CHECK-NEXT:    [[TMP3:%.*]] = fadd <2 x double> [[COL_LOAD5]], [[SPLIT10]]
-; CHECK-NEXT:    [[TMP4:%.*]] = fadd <2 x double> [[COL_LOAD8]], [[SPLIT11]]
-; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <2 x double> [[TMP1]], i64 0
-; CHECK-NEXT:    [[TMP6:%.*]] = insertelement <4 x double> poison, double [[TMP5]], i64 0
-; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <2 x double> [[TMP2]], i64 0
-; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <4 x double> [[TMP6]], double [[TMP7]], i64 1
-; CHECK-NEXT:    [[TMP9:%.*]] = extractelement <2 x double> [[TMP3]], i64 0
-; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <4 x double> [[TMP8]], double [[TMP9]], i64 2
-; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <2 x double> [[TMP4]], i64 0
-; CHECK-NEXT:    [[TMP12:%.*]] = insertelement <4 x double> [[TMP10]], double [[TMP11]], i64 3
-; CHECK-NEXT:    [[TMP13:%.*]] = extractelement <2 x double> [[TMP1]], i64 1
-; CHECK-NEXT:    [[TMP14:%.*]] = insertelement <4 x double> poison, double [[TMP13]], i64 0
-; CHECK-NEXT:    [[TMP15:%.*]] = extractelement <2 x double> [[TMP2]], i64 1
-; CHECK-NEXT:    [[TMP16:%.*]] = insertelement <4 x double> [[TMP14]], double [[TMP15]], i64 1
-; CHECK-NEXT:    [[TMP17:%.*]] = extractelement <2 x double> [[TMP3]], i64 1
-; CHECK-NEXT:    [[TMP18:%.*]] = insertelement <4 x double> [[TMP16]], double [[TMP17]], i64 2
-; CHECK-NEXT:    [[TMP19:%.*]] = extractelement <2 x double> [[TMP4]], i64 1
-; CHECK-NEXT:    [[TMP20:%.*]] = insertelement <4 x double> [[TMP18]], double [[TMP19]], i64 3
-; CHECK-NEXT:    [[TMP21:%.*]] = shufflevector <4 x double> [[TMP12]], <4 x double> [[TMP20]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:    ret <8 x double> [[TMP21]]
+; CHECK-NEXT:    [[VEC_CAST2:%.*]] = bitcast double* [[VEC_GEP]] to <2 x double>*
+; CHECK-NEXT:    [[COL_LOAD3:%.*]] = load <2 x double>, <2 x double>* [[VEC_CAST2]], align 8
+; CHECK-NEXT:    [[VEC_GEP4:%.*]] = getelementptr double, double* [[TMP0]], i64 4
+; CHECK-NEXT:    [[VEC_CAST5:%.*]] = bitcast double* [[VEC_GEP4]] to <2 x double>*
+; CHECK-NEXT:    [[COL_LOAD6:%.*]] = load <2 x double>, <2 x double>* [[VEC_CAST5]], align 8
+; CHECK-NEXT:    [[VEC_GEP7:%.*]] = getelementptr double, double* [[TMP0]], i64 6
+; CHECK-NEXT:    [[VEC_CAST8:%.*]] = bitcast double* [[VEC_GEP7]] to <2 x double>*
+; CHECK-NEXT:    [[COL_LOAD9:%.*]] = load <2 x double>, <2 x double>* [[VEC_CAST8]], align 8
+; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <2 x double> [[COL_LOAD]], <2 x double> [[COL_LOAD3]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <2 x double> [[COL_LOAD6]], <2 x double> [[COL_LOAD9]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <4 x double> [[TMP1]], <4 x double> [[TMP2]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <8 x double> [[TMP3]], <8 x double> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[SPLIT10:%.*]] = shufflevector <8 x double> [[TMP3]], <8 x double> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:    [[SPLIT11:%.*]] = shufflevector <8 x double> [[B:%.*]], <8 x double> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[SPLIT12:%.*]] = shufflevector <8 x double> [[B]], <8 x double> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:    [[TMP4:%.*]] = fadd <4 x double> [[SPLIT]], [[SPLIT11]]
+; CHECK-NEXT:    [[TMP5:%.*]] = fadd <4 x double> [[SPLIT10]], [[SPLIT12]]
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x double> [[TMP4]], i64 0
+; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <2 x double> poison, double [[TMP6]], i64 0
+; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <4 x double> [[TMP5]], i64 0
+; CHECK-NEXT:    [[TMP9:%.*]] = insertelement <2 x double> [[TMP7]], double [[TMP8]], i64 1
+; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <4 x double> [[TMP4]], i64 1
+; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <2 x double> poison, double [[TMP10]], i64 0
+; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <4 x double> [[TMP5]], i64 1
+; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <2 x double> [[TMP11]], double [[TMP12]], i64 1
+; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <4 x double> [[TMP4]], i64 2
+; CHECK-NEXT:    [[TMP15:%.*]] = insertelement <2 x double> poison, double [[TMP14]], i64 0
+; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <4 x double> [[TMP5]], i64 2
+; CHECK-NEXT:    [[TMP17:%.*]] = insertelement <2 x double> [[TMP15]], double [[TMP16]], i64 1
+; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <4 x double> [[TMP4]], i64 3
+; CHECK-NEXT:    [[TMP19:%.*]] = insertelement <2 x double> poison, double [[TMP18]], i64 0
+; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <4 x double> [[TMP5]], i64 3
+; CHECK-NEXT:    [[TMP21:%.*]] = insertelement <2 x double> [[TMP19]], double [[TMP20]], i64 1
+; CHECK-NEXT:    [[TMP22:%.*]] = shufflevector <2 x double> [[TMP9]], <2 x double> [[TMP13]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[TMP23:%.*]] = shufflevector <2 x double> [[TMP17]], <2 x double> [[TMP21]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[TMP24:%.*]] = shufflevector <4 x double> [[TMP22]], <4 x double> [[TMP23]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:    ret <8 x double> [[TMP24]]
 ;