diff --git a/llvm/lib/Transforms/Scalar/LowerMatrixIntrinsics.cpp b/llvm/lib/Transforms/Scalar/LowerMatrixIntrinsics.cpp
--- a/llvm/lib/Transforms/Scalar/LowerMatrixIntrinsics.cpp
+++ b/llvm/lib/Transforms/Scalar/LowerMatrixIntrinsics.cpp
@@ -29,15 +29,20 @@
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/IntrinsicInst.h"
+#include "llvm/IR/PatternMatch.h"
 #include "llvm/InitializePasses.h"
 #include "llvm/Pass.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Transforms/Scalar.h"
 
 using namespace llvm;
+using namespace PatternMatch;
 
 #define DEBUG_TYPE "lower-matrix-intrinsics"
 
+static cl::opt<bool> EnableShapePropagation("matrix-propagate-shape",
+                                            cl::init(true));
+
 namespace {
 
 // Given an element poitner \p BasePtr to the start of a (sub) matrix, compute
@@ -104,12 +109,25 @@
 /// LowerMatrixIntrinsics contains the methods used to lower matrix intrinsics.
 ///
 /// Currently, the lowering for each matrix intrinsic is done as follows:
-/// 1. Split the operand vectors containing an embedded matrix into a set of
-///    column vectors, based on the shape information from the intrinsic.
-/// 2. Apply the transformation described by the intrinsic on the column
-///    vectors, which yields a set of column vectors containing result matrix.
-/// 3. Embed the columns of the result matrix in a flat vector and replace all
-///    uses of the intrinsic result with it.
+/// 1. Propagate the shape information from intrinsics to connected
+/// instructions.
+/// 2. Lower instructions with shape information.
+///  2.1. Get column vectors for each argument. If we already lowered the
+///       definition of an argument, use the produced column vectors directly.
+///       If not, split the operand vector containing an embedded matrix into
+///       a set of column vectors,
+///  2.2. Lower the instruction in terms of columnwise operations, which yields
+///       a set of column vectors containing result matrix. Note that we lower
+///       all instructions that have shape information. Besides the intrinsics,
+///       this includes stores for example.
+///  2.3. Update uses of the lowered instruction. If we have shape information
+///       for a user, there is nothing to do, as we will look up the result
+///       column matrix when lowering the user. For other uses, we embed the
+///       result matrix in a flat vector and update the use.
+///  2.4. Cache the result column matrix for the instruction we lowered
+/// 3. After we lowered all instructions in a function, remove the now
+///    obsolete instructions.
+///
 class LowerMatrixIntrinsics {
   Function &Func;
   const DataLayout &DL;
@@ -130,6 +148,10 @@
     void setColumn(unsigned i, Value *V) { Columns[i] = V; }
 
     size_t getNumColumns() const { return Columns.size(); }
+    size_t getNumRows() const {
+      assert(Columns.size() > 0 && "Cannot call getNumRows without columns");
+      return cast<VectorType>(Columns[0]->getType())->getNumElements();
+    }
 
     const SmallVectorImpl<Value *> &getColumnVectors() const { return Columns; }
 
@@ -156,28 +178,73 @@
     ShapeInfo(unsigned NumRows = 0, unsigned NumColumns = 0)
         : NumRows(NumRows), NumColumns(NumColumns) {}
 
-    ShapeInfo(ConstantInt *NumRows, ConstantInt *NumColumns)
-        : NumRows(NumRows->getZExtValue()),
-          NumColumns(NumColumns->getZExtValue()) {}
+    ShapeInfo(Value *NumRows, Value *NumColumns)
+        : NumRows(cast<ConstantInt>(NumRows)->getZExtValue()),
+          NumColumns(cast<ConstantInt>(NumColumns)->getZExtValue()) {}
+
+    bool operator==(const ShapeInfo &other) {
+      return NumRows == other.NumRows && NumColumns == other.NumColumns;
+    }
+    bool operator!=(const ShapeInfo &other) { return !(*this == other); }
+
+    /// Returns true if shape-information is defined, meaning both dimensions
+    /// are != 0.
+    operator bool() const {
+      assert(NumRows == 0 || NumColumns != 0);
+      return NumRows != 0;
+    }
   };
 
+  /// Maps instructions to their shape information. The shape information
+  /// describes the shape to be used while lowering. This matches the shape of
+  /// the result value of the instruction, with the only exceptions being store
+  /// instructions and the matrix_columnwise_store intrinsics. For those, the
+  /// shape information indicates that those instructions should be lowered
+  /// using shape information as well.
+  DenseMap<Value *, ShapeInfo> ShapeMap;
+
+  /// List of instructions to remove. While lowering, we are not replacing all
+  /// users of a lowered instruction, if shape information is available and
+  /// those need to be removed after we finished lowering.
+  SmallVector<Instruction *, 16> ToRemove;
+
+  /// Map from instructions to their produced column matrix.
+  DenseMap<Value *, ColumnMatrixTy> Inst2ColumnMatrix;
+
 public:
   LowerMatrixIntrinsics(Function &F, TargetTransformInfo &TTI)
       : Func(F), DL(F.getParent()->getDataLayout()), TTI(TTI) {}
 
   /// Return the set of column vectors that a matrix value is lowered to.
   ///
-  /// We split the flat vector \p MatrixVal containing a matrix with shape \p SI
-  /// into column vectors.
+  /// If we lowered \p MatrixVal, just return the cache result column matrix.
+  /// Otherwie split the flat vector \p MatrixVal containing a matrix with
+  /// shape \p SI into column vectors.
   ColumnMatrixTy getMatrix(Value *MatrixVal, const ShapeInfo &SI,
                            IRBuilder<> Builder) {
     VectorType *VType = dyn_cast<VectorType>(MatrixVal->getType());
     assert(VType && "MatrixVal must be a vector type");
     assert(VType->getNumElements() == SI.NumRows * SI.NumColumns &&
            "The vector size must match the number of matrix elements");
+
+    // Check if we lowered MatrixVal using shape information. In that case,
+    // return the existing column matrix, if it matches the requested shape
+    // information. If there is a mis-match, embed the result in a flat
+    // vector and split it later.
+    auto Found = Inst2ColumnMatrix.find(MatrixVal);
+    if (Found != Inst2ColumnMatrix.end()) {
+      ColumnMatrixTy &M = Found->second;
+      // Return the found matrix, if its shape matches the requested shape
+      // information
+      if (SI.NumRows == M.getNumRows() && SI.NumColumns == M.getNumColumns())
+        return M;
+
+      MatrixVal = M.embedInVector(Builder);
+    }
+
+    // Otherwise split MatrixVal.
     SmallVector<Value *, 16> SplitVecs;
     Value *Undef = UndefValue::get(VType);
-
     for (unsigned MaskStart = 0; MaskStart < VType->getNumElements();
          MaskStart += SI.NumRows) {
       Constant *Mask = createSequentialMask(Builder, MaskStart, SI.NumRows, 0);
@@ -188,41 +255,144 @@
     return {SplitVecs};
   }
 
-  // Replace intrinsic calls
-  bool VisitCallInst(CallInst *Inst) {
-    if (!Inst->getCalledFunction() || !Inst->getCalledFunction()->isIntrinsic())
+  /// If \p V already has a known shape return false.  Otherwise set the shape
+  /// for instructions that support it.
+  bool setShapeInfo(Value *V, ShapeInfo Shape) {
+    assert(Shape && "Shape not set");
+    if (isa<UndefValue>(V) || !supportsShapeInfo(V))
       return false;
 
-    switch (Inst->getCalledFunction()->getIntrinsicID()) {
-    case Intrinsic::matrix_multiply:
-      LowerMultiply(Inst);
-      break;
-    case Intrinsic::matrix_transpose:
-      LowerTranspose(Inst);
-      break;
-    case Intrinsic::matrix_columnwise_load:
-      LowerColumnwiseLoad(Inst);
-      break;
-    case Intrinsic::matrix_columnwise_store:
-      LowerColumnwiseStore(Inst);
-      break;
-    default:
+    auto SIter = ShapeMap.find(V);
+    if (SIter != ShapeMap.end()) {
+      LLVM_DEBUG(dbgs() << "  not overriding existing shape: "
+                        << SIter->second.NumRows << " "
+                        << SIter->second.NumColumns << " for " << *V << "\n");
       return false;
     }
-    Inst->eraseFromParent();
+
+    ShapeMap.insert({V, Shape});
+    LLVM_DEBUG(dbgs() << "  " << Shape.NumRows << " x " << Shape.NumColumns
+                      << " for " << *V << "\n");
     return true;
   }
 
+  /// Returns true if shape information can be used for \p V. The supported
+  /// instructions must match the instructions that can be lowered by this pass.
+  bool supportsShapeInfo(Value *V) {
+    Instruction *Inst = dyn_cast<Instruction>(V);
+    if (!Inst)
+      return false;
+
+    IntrinsicInst *II = dyn_cast<IntrinsicInst>(Inst);
+    if (II)
+      switch (II->getIntrinsicID()) {
+      case Intrinsic::matrix_multiply:
+      case Intrinsic::matrix_transpose:
+      case Intrinsic::matrix_columnwise_load:
+      case Intrinsic::matrix_columnwise_store:
+        return true;
+      default:
+        return false;
+      }
+    return isa<StoreInst>(Inst);
+  }
+
+  /// Propagate the shape information of instructions to their users.
+  void propagateShapeForward() {
+    // The work list contains instructions for which we can compute the shape,
+    // either based on the information provided by matrix intrinsics or known
+    // shapes of operands.
+    SmallVector<Instruction *, 8> WorkList;
+
+    // Initialize the work list with ops carrying shape information. Initially
+    // only the shape of matrix intrinsics is known.
+    for (BasicBlock &BB : Func)
+      for (Instruction &Inst : BB) {
+        IntrinsicInst *II = dyn_cast<IntrinsicInst>(&Inst);
+        if (!II)
+          continue;
+
+        switch (II->getIntrinsicID()) {
+        case Intrinsic::matrix_multiply:
+        case Intrinsic::matrix_transpose:
+        case Intrinsic::matrix_columnwise_load:
+        case Intrinsic::matrix_columnwise_store:
+          WorkList.push_back(&Inst);
+          break;
+        default:
+          break;
+        }
+      }
+
+    // Pop an element for which we guaranteed to have at least one of the
+    // operand shapes.  Add the shape for this and then add users to the work
+    // list.
+    LLVM_DEBUG(dbgs() << "Forward-propagate shapes:\n");
+    while (!WorkList.empty()) {
+      Instruction *Inst = WorkList.back();
+      WorkList.pop_back();
+
+      // New entry, set the value and insert operands
+      bool Propagate = false;
+
+      Value *MatrixA;
+      Value *MatrixB;
+      Value *M;
+      Value *N;
+      Value *K;
+      if (match(Inst, m_Intrinsic<Intrinsic::matrix_multiply>(
+                          m_Value(MatrixA), m_Value(MatrixB), m_Value(M),
+                          m_Value(N), m_Value(K)))) {
+        Propagate = setShapeInfo(Inst, {M, K});
+      } else if (match(Inst, m_Intrinsic<Intrinsic::matrix_transpose>(
+                                 m_Value(MatrixA), m_Value(M), m_Value(N)))) {
+        // Flip dimensions.
+        Propagate = setShapeInfo(Inst, {N, M});
+      } else if (match(Inst, m_Intrinsic<Intrinsic::matrix_columnwise_store>(
+                                 m_Value(MatrixA), m_Value(), m_Value(),
+                                 m_Value(M), m_Value(N)))) {
+        Propagate = setShapeInfo(Inst, {N, M});
+      } else if (match(Inst,
+                       m_Intrinsic<Intrinsic::matrix_columnwise_load>(
+                           m_Value(), m_Value(), m_Value(M), m_Value(N)))) {
+        Propagate = setShapeInfo(Inst, {M, N});
+      } else if (match(Inst, m_Store(m_Value(MatrixA), m_Value()))) {
+        auto OpShape = ShapeMap.find(MatrixA);
+        if (OpShape != ShapeMap.end())
+          setShapeInfo(Inst, OpShape->second);
+        continue;
+      }
+
+      if (Propagate)
+        for (auto *User : Inst->users())
+          if (ShapeMap.count(User) == 0)
+            WorkList.push_back(cast<Instruction>(User));
+    }
+  }
+
   bool Visit() {
+    if (EnableShapePropagation)
+      propagateShapeForward();
+
     ReversePostOrderTraversal<Function *> RPOT(&Func);
     bool Changed = false;
     for (auto *BB : RPOT) {
       for (Instruction &Inst : make_early_inc_range(*BB)) {
+        IRBuilder<> Builder(&Inst);
+
         if (CallInst *CInst = dyn_cast<CallInst>(&Inst))
           Changed |= VisitCallInst(CInst);
+
+        Value *Op1;
+        Value *Op2;
+        if (match(&Inst, m_Store(m_Value(Op1), m_Value(Op2))))
+          Changed |= VisitStore(&Inst, Op1, Op2, Builder);
       }
     }
 
+    for (Instruction *Inst : reverse(ToRemove))
+      Inst->eraseFromParent();
+
     return Changed;
   }
 
@@ -238,6 +408,7 @@
     return Builder.CreateAlignedStore(ColumnValue, ColumnPtr, Align);
   }
 
+
   /// Turns \p BasePtr into an elementwise pointer to \p EltType.
   Value *createElementPtr(Value *BasePtr, Type *EltType, IRBuilder<> &Builder) {
     unsigned AS = cast<PointerType>(BasePtr->getType())->getAddressSpace();
@@ -245,6 +416,30 @@
     return Builder.CreatePointerCast(BasePtr, EltPtrType);
   }
 
+  /// Replace intrinsic calls
+  bool VisitCallInst(CallInst *Inst) {
+    if (!Inst->getCalledFunction() || !Inst->getCalledFunction()->isIntrinsic())
+      return false;
+
+    switch (Inst->getCalledFunction()->getIntrinsicID()) {
+    case Intrinsic::matrix_multiply:
+      LowerMultiply(Inst);
+      break;
+    case Intrinsic::matrix_transpose:
+      LowerTranspose(Inst);
+      break;
+    case Intrinsic::matrix_columnwise_load:
+      LowerColumnwiseLoad(Inst);
+      break;
+    case Intrinsic::matrix_columnwise_store:
+      LowerColumnwiseStore(Inst);
+      break;
+    default:
+      return false;
+    }
+    return true;
+  }
+
   /// Lowers llvm.matrix.columnwise.load.
   ///
   /// The intrinsic loads a matrix from memory using a stride between columns.
@@ -253,9 +448,8 @@
     Value *Ptr = Inst->getArgOperand(0);
     Value *Stride = Inst->getArgOperand(1);
     auto VType = cast<VectorType>(Inst->getType());
-    ShapeInfo Shape(cast<ConstantInt>(Inst->getArgOperand(2)),
-                    cast<ConstantInt>(Inst->getArgOperand(3)));
     Value *EltPtr = createElementPtr(Ptr, VType->getElementType(), Builder);
+    ShapeInfo Shape(Inst->getArgOperand(2), Inst->getArgOperand(3));
 
     ColumnMatrixTy Result;
     // Distance between start of one column and the start of the next
@@ -267,22 +461,14 @@
       Result.addColumn(Column);
     }
 
-    Inst->replaceAllUsesWith(Result.embedInVector(Builder));
+    finalizeLowering(Inst, Result, Builder);
   }
 
-  /// Lowers llvm.matrix.columnwise.store.
-  ///
-  /// The intrinsic store a matrix back memory using a stride between columns.
-  void LowerColumnwiseStore(CallInst *Inst) {
+  void LowerStore(Instruction *Inst, Value *Matrix, Value *Ptr, Value *Stride,
+                  ShapeInfo Shape) {
     IRBuilder<> Builder(Inst);
-    Value *Matrix = Inst->getArgOperand(0);
-    Value *Ptr = Inst->getArgOperand(1);
-    Value *Stride = Inst->getArgOperand(2);
-    ShapeInfo Shape(cast<ConstantInt>(Inst->getArgOperand(3)),
-                    cast<ConstantInt>(Inst->getArgOperand(4)));
     auto VType = cast<VectorType>(Matrix->getType());
     Value *EltPtr = createElementPtr(Ptr, VType->getElementType(), Builder);
-
     auto LM = getMatrix(Matrix, Shape, Builder);
     for (auto C : enumerate(LM.columns())) {
       Value *GEP =
@@ -290,6 +476,19 @@
                             Shape.NumRows, VType->getElementType(), Builder);
       createColumnStore(C.value(), GEP, VType->getElementType(), Builder);
     }
+
+    ToRemove.push_back(Inst);
+  }
+
+  /// Lowers llvm.matrix.columnwise.store.
+  ///
+  /// The intrinsic store a matrix back memory using a stride between columns.
+  void LowerColumnwiseStore(CallInst *Inst) {
+    Value *Matrix = Inst->getArgOperand(0);
+    Value *Ptr = Inst->getArgOperand(1);
+    Value *Stride = Inst->getArgOperand(2);
+    LowerStore(Inst, Matrix, Ptr, Stride,
+               {Inst->getArgOperand(3), Inst->getArgOperand(4)});
   }
 
   /// Extract a column vector of \p NumElts starting at index (\p I, \p J) from
@@ -345,14 +544,33 @@
     return UseFPOp ? Builder.CreateFAdd(Sum, Mul) : Builder.CreateAdd(Sum, Mul);
   }
 
+  /// Cache \p Matrix as result of \p Inst and update the uses of \p Inst. For
+  /// users with shape information, there's nothing to do: the will use the
+  /// cached value when they are lowered. For other users, \p Matrix is
+  /// flattened and the uses are updated to use it. Also marks \p Inst for
+  /// deletion.
+  void finalizeLowering(Instruction *Inst, ColumnMatrixTy Matrix,
+                        IRBuilder<> &Builder) {
+    Inst2ColumnMatrix.insert(std::make_pair(Inst, Matrix));
+
+    ToRemove.push_back(Inst);
+    Value *Flattened = nullptr;
+    for (auto I = Inst->use_begin(), E = Inst->use_end(); I != E;) {
+      Use &U = *I++;
+      if (ShapeMap.find(U.getUser()) == ShapeMap.end()) {
+        if (!Flattened)
+          Flattened = Matrix.embedInVector(Builder);
+        U.set(Flattened);
+      }
+    }
+  }
+
   /// Lowers llvm.matrix.multiply.
   void LowerMultiply(CallInst *MatMul) {
     IRBuilder<> Builder(MatMul);
     auto *EltType = cast<VectorType>(MatMul->getType())->getElementType();
-    ShapeInfo LShape(cast<ConstantInt>(MatMul->getArgOperand(2)),
-                     cast<ConstantInt>(MatMul->getArgOperand(3)));
-    ShapeInfo RShape(cast<ConstantInt>(MatMul->getArgOperand(3)),
-                     cast<ConstantInt>(MatMul->getArgOperand(4)));
+    ShapeInfo LShape(MatMul->getArgOperand(2), MatMul->getArgOperand(3));
+    ShapeInfo RShape(MatMul->getArgOperand(3), MatMul->getArgOperand(4));
 
     const ColumnMatrixTy &Lhs =
         getMatrix(MatMul->getArgOperand(0), LShape, Builder);
@@ -394,8 +612,7 @@
         Result.setColumn(J, insertVector(Result.getColumn(J), I, Sum, Builder));
       }
     }
-
-    MatMul->replaceAllUsesWith(Result.embedInVector(Builder));
+    finalizeLowering(MatMul, Result, Builder);
   }
 
   /// Lowers llvm.matrix.transpose.
@@ -404,8 +621,7 @@
     IRBuilder<> Builder(Inst);
     Value *InputVal = Inst->getArgOperand(0);
     VectorType *VectorTy = cast<VectorType>(InputVal->getType());
-    ShapeInfo ArgShape(cast<ConstantInt>(Inst->getArgOperand(1)),
-                       cast<ConstantInt>(Inst->getArgOperand(2)));
+    ShapeInfo ArgShape(Inst->getArgOperand(1), Inst->getArgOperand(2));
     ColumnMatrixTy InputMatrix = getMatrix(InputVal, ArgShape, Builder);
 
     for (unsigned Row = 0; Row < ArgShape.NumRows; ++Row) {
@@ -425,7 +641,17 @@
       Result.addColumn(ResultColumn);
     }
 
-    Inst->replaceAllUsesWith(Result.embedInVector(Builder));
+    finalizeLowering(Inst, Result, Builder);
+  }
+
+  bool VisitStore(Instruction *Inst, Value *StoredVal, Value *Ptr,
+                  IRBuilder<> &Builder) {
+    auto I = ShapeMap.find(StoredVal);
+    if (I == ShapeMap.end())
+      return false;
+
+    LowerStore(Inst, StoredVal, Ptr, Builder.getInt32(I->second.NumRows), I->second);
+    return true;
   }
 };
 } // namespace
diff --git a/llvm/test/Transforms/LowerMatrixIntrinsics/bigger-expressions-double.ll b/llvm/test/Transforms/LowerMatrixIntrinsics/bigger-expressions-double.ll
--- a/llvm/test/Transforms/LowerMatrixIntrinsics/bigger-expressions-double.ll
+++ b/llvm/test/Transforms/LowerMatrixIntrinsics/bigger-expressions-double.ll
@@ -2,15 +2,23 @@
 ; RUN: opt -lower-matrix-intrinsics -S < %s | FileCheck  %s
 ; RUN: opt -passes='lower-matrix-intrinsics' -S < %s | FileCheck %s
 
-
 define void @transpose_multiply(<9 x double>* %A.Ptr, <9 x double>* %B.Ptr, <9 x double>* %C.Ptr) {
 ; CHECK-LABEL: @transpose_multiply(
 ; CHECK-NEXT:  entry:
+
+; Load input matrixes %A and %B.
+
 ; CHECK-NEXT:    [[A:%.*]] = load <9 x double>, <9 x double>* [[A_PTR:%.*]]
 ; CHECK-NEXT:    [[B:%.*]] = load <9 x double>, <9 x double>* [[B_PTR:%.*]]
+
+; Extract columns from loaded value %A.
+
 ; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <9 x double> [[A]], <9 x double> undef, <3 x i32> <i32 0, i32 1, i32 2>
 ; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <9 x double> [[A]], <9 x double> undef, <3 x i32> <i32 3, i32 4, i32 5>
 ; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <9 x double> [[A]], <9 x double> undef, <3 x i32> <i32 6, i32 7, i32 8>
+
+; Transpose %A.
+
 ; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <3 x double> [[SPLIT]], i64 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <3 x double> undef, double [[TMP0]], i64 0
 ; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <3 x double> [[SPLIT1]], i64 0
@@ -29,192 +37,201 @@
 ; CHECK-NEXT:    [[TMP15:%.*]] = insertelement <3 x double> [[TMP13]], double [[TMP14]], i64 1
 ; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <3 x double> [[SPLIT2]], i64 2
 ; CHECK-NEXT:    [[TMP17:%.*]] = insertelement <3 x double> [[TMP15]], double [[TMP16]], i64 2
-; CHECK-NEXT:    [[TMP18:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> [[TMP11]], <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
-; CHECK-NEXT:    [[TMP19:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <6 x i32> <i32 0, i32 1, i32 2, i32 undef, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP20:%.*]] = shufflevector <6 x double> [[TMP18]], <6 x double> [[TMP19]], <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>
-; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <9 x double> [[TMP20]], <9 x double> undef, <3 x i32> <i32 0, i32 1, i32 2>
-; CHECK-NEXT:    [[SPLIT4:%.*]] = shufflevector <9 x double> [[TMP20]], <9 x double> undef, <3 x i32> <i32 3, i32 4, i32 5>
-; CHECK-NEXT:    [[SPLIT5:%.*]] = shufflevector <9 x double> [[TMP20]], <9 x double> undef, <3 x i32> <i32 6, i32 7, i32 8>
-; CHECK-NEXT:    [[SPLIT6:%.*]] = shufflevector <9 x double> [[B]], <9 x double> undef, <3 x i32> <i32 0, i32 1, i32 2>
-; CHECK-NEXT:    [[SPLIT7:%.*]] = shufflevector <9 x double> [[B]], <9 x double> undef, <3 x i32> <i32 3, i32 4, i32 5>
-; CHECK-NEXT:    [[SPLIT8:%.*]] = shufflevector <9 x double> [[B]], <9 x double> undef, <3 x i32> <i32 6, i32 7, i32 8>
-; CHECK-NEXT:    [[BLOCK:%.*]] = shufflevector <3 x double> [[SPLIT3]], <3 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP21:%.*]] = extractelement <3 x double> [[SPLIT6]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x double> undef, double [[TMP21]], i32 0
+
+; Extract columns from %B.
+
+; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <9 x double> [[B]], <9 x double> undef, <3 x i32> <i32 0, i32 1, i32 2>
+; CHECK-NEXT:    [[SPLIT4:%.*]] = shufflevector <9 x double> [[B]], <9 x double> undef, <3 x i32> <i32 3, i32 4, i32 5>
+; CHECK-NEXT:    [[SPLIT5:%.*]] = shufflevector <9 x double> [[B]], <9 x double> undef, <3 x i32> <i32 6, i32 7, i32 8>
+
+; Lower multiply(transpose(%A), %B)
+
+; CHECK-NEXT:    [[BLOCK:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <3 x double> [[SPLIT3]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x double> undef, double [[TMP18]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP22:%.*]] = fmul <1 x double> [[BLOCK]], [[SPLAT_SPLAT]]
-; CHECK-NEXT:    [[BLOCK9:%.*]] = shufflevector <3 x double> [[SPLIT4]], <3 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP23:%.*]] = extractelement <3 x double> [[SPLIT6]], i64 1
+; CHECK-NEXT:    [[TMP19:%.*]] = fmul <1 x double> [[BLOCK]], [[SPLAT_SPLAT]]
+; CHECK-NEXT:    [[BLOCK6:%.*]] = shufflevector <3 x double> [[TMP11]], <3 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <3 x double> [[SPLIT3]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT7:%.*]] = insertelement <1 x double> undef, double [[TMP20]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT8:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT7]], <1 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP21:%.*]] = fmul <1 x double> [[BLOCK6]], [[SPLAT_SPLAT8]]
+; CHECK-NEXT:    [[TMP22:%.*]] = fadd <1 x double> [[TMP19]], [[TMP21]]
+; CHECK-NEXT:    [[BLOCK9:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP23:%.*]] = extractelement <3 x double> [[SPLIT3]], i64 2
 ; CHECK-NEXT:    [[SPLAT_SPLATINSERT10:%.*]] = insertelement <1 x double> undef, double [[TMP23]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT11:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT10]], <1 x double> undef, <1 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP24:%.*]] = fmul <1 x double> [[BLOCK9]], [[SPLAT_SPLAT11]]
 ; CHECK-NEXT:    [[TMP25:%.*]] = fadd <1 x double> [[TMP22]], [[TMP24]]
-; CHECK-NEXT:    [[BLOCK12:%.*]] = shufflevector <3 x double> [[SPLIT5]], <3 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP26:%.*]] = extractelement <3 x double> [[SPLIT6]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT13:%.*]] = insertelement <1 x double> undef, double [[TMP26]], i32 0
+; CHECK-NEXT:    [[TMP26:%.*]] = shufflevector <1 x double> [[TMP25]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP27:%.*]] = shufflevector <3 x double> undef, <3 x double> [[TMP26]], <3 x i32> <i32 3, i32 1, i32 2>
+; CHECK-NEXT:    [[BLOCK12:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> undef, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[TMP28:%.*]] = extractelement <3 x double> [[SPLIT3]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT13:%.*]] = insertelement <1 x double> undef, double [[TMP28]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT14:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT13]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP27:%.*]] = fmul <1 x double> [[BLOCK12]], [[SPLAT_SPLAT14]]
-; CHECK-NEXT:    [[TMP28:%.*]] = fadd <1 x double> [[TMP25]], [[TMP27]]
-; CHECK-NEXT:    [[TMP29:%.*]] = shufflevector <1 x double> [[TMP28]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP30:%.*]] = shufflevector <3 x double> undef, <3 x double> [[TMP29]], <3 x i32> <i32 3, i32 1, i32 2>
-; CHECK-NEXT:    [[BLOCK15:%.*]] = shufflevector <3 x double> [[SPLIT3]], <3 x double> undef, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[TMP31:%.*]] = extractelement <3 x double> [[SPLIT6]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT16:%.*]] = insertelement <1 x double> undef, double [[TMP31]], i32 0
+; CHECK-NEXT:    [[TMP29:%.*]] = fmul <1 x double> [[BLOCK12]], [[SPLAT_SPLAT14]]
+; CHECK-NEXT:    [[BLOCK15:%.*]] = shufflevector <3 x double> [[TMP11]], <3 x double> undef, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[TMP30:%.*]] = extractelement <3 x double> [[SPLIT3]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT16:%.*]] = insertelement <1 x double> undef, double [[TMP30]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT17:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT16]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP32:%.*]] = fmul <1 x double> [[BLOCK15]], [[SPLAT_SPLAT17]]
-; CHECK-NEXT:    [[BLOCK18:%.*]] = shufflevector <3 x double> [[SPLIT4]], <3 x double> undef, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[TMP33:%.*]] = extractelement <3 x double> [[SPLIT6]], i64 1
+; CHECK-NEXT:    [[TMP31:%.*]] = fmul <1 x double> [[BLOCK15]], [[SPLAT_SPLAT17]]
+; CHECK-NEXT:    [[TMP32:%.*]] = fadd <1 x double> [[TMP29]], [[TMP31]]
+; CHECK-NEXT:    [[BLOCK18:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[TMP33:%.*]] = extractelement <3 x double> [[SPLIT3]], i64 2
 ; CHECK-NEXT:    [[SPLAT_SPLATINSERT19:%.*]] = insertelement <1 x double> undef, double [[TMP33]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT20:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT19]], <1 x double> undef, <1 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP34:%.*]] = fmul <1 x double> [[BLOCK18]], [[SPLAT_SPLAT20]]
 ; CHECK-NEXT:    [[TMP35:%.*]] = fadd <1 x double> [[TMP32]], [[TMP34]]
-; CHECK-NEXT:    [[BLOCK21:%.*]] = shufflevector <3 x double> [[SPLIT5]], <3 x double> undef, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[TMP36:%.*]] = extractelement <3 x double> [[SPLIT6]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT22:%.*]] = insertelement <1 x double> undef, double [[TMP36]], i32 0
+; CHECK-NEXT:    [[TMP36:%.*]] = shufflevector <1 x double> [[TMP35]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP37:%.*]] = shufflevector <3 x double> [[TMP27]], <3 x double> [[TMP36]], <3 x i32> <i32 0, i32 3, i32 2>
+; CHECK-NEXT:    [[BLOCK21:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> undef, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[TMP38:%.*]] = extractelement <3 x double> [[SPLIT3]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT22:%.*]] = insertelement <1 x double> undef, double [[TMP38]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT23:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT22]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP37:%.*]] = fmul <1 x double> [[BLOCK21]], [[SPLAT_SPLAT23]]
-; CHECK-NEXT:    [[TMP38:%.*]] = fadd <1 x double> [[TMP35]], [[TMP37]]
-; CHECK-NEXT:    [[TMP39:%.*]] = shufflevector <1 x double> [[TMP38]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP40:%.*]] = shufflevector <3 x double> [[TMP30]], <3 x double> [[TMP39]], <3 x i32> <i32 0, i32 3, i32 2>
-; CHECK-NEXT:    [[BLOCK24:%.*]] = shufflevector <3 x double> [[SPLIT3]], <3 x double> undef, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[TMP41:%.*]] = extractelement <3 x double> [[SPLIT6]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT25:%.*]] = insertelement <1 x double> undef, double [[TMP41]], i32 0
+; CHECK-NEXT:    [[TMP39:%.*]] = fmul <1 x double> [[BLOCK21]], [[SPLAT_SPLAT23]]
+; CHECK-NEXT:    [[BLOCK24:%.*]] = shufflevector <3 x double> [[TMP11]], <3 x double> undef, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[TMP40:%.*]] = extractelement <3 x double> [[SPLIT3]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT25:%.*]] = insertelement <1 x double> undef, double [[TMP40]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT26:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT25]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP42:%.*]] = fmul <1 x double> [[BLOCK24]], [[SPLAT_SPLAT26]]
-; CHECK-NEXT:    [[BLOCK27:%.*]] = shufflevector <3 x double> [[SPLIT4]], <3 x double> undef, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[TMP43:%.*]] = extractelement <3 x double> [[SPLIT6]], i64 1
+; CHECK-NEXT:    [[TMP41:%.*]] = fmul <1 x double> [[BLOCK24]], [[SPLAT_SPLAT26]]
+; CHECK-NEXT:    [[TMP42:%.*]] = fadd <1 x double> [[TMP39]], [[TMP41]]
+; CHECK-NEXT:    [[BLOCK27:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[TMP43:%.*]] = extractelement <3 x double> [[SPLIT3]], i64 2
 ; CHECK-NEXT:    [[SPLAT_SPLATINSERT28:%.*]] = insertelement <1 x double> undef, double [[TMP43]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT29:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT28]], <1 x double> undef, <1 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP44:%.*]] = fmul <1 x double> [[BLOCK27]], [[SPLAT_SPLAT29]]
 ; CHECK-NEXT:    [[TMP45:%.*]] = fadd <1 x double> [[TMP42]], [[TMP44]]
-; CHECK-NEXT:    [[BLOCK30:%.*]] = shufflevector <3 x double> [[SPLIT5]], <3 x double> undef, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[TMP46:%.*]] = extractelement <3 x double> [[SPLIT6]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT31:%.*]] = insertelement <1 x double> undef, double [[TMP46]], i32 0
+; CHECK-NEXT:    [[TMP46:%.*]] = shufflevector <1 x double> [[TMP45]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP47:%.*]] = shufflevector <3 x double> [[TMP37]], <3 x double> [[TMP46]], <3 x i32> <i32 0, i32 1, i32 3>
+; CHECK-NEXT:    [[BLOCK30:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP48:%.*]] = extractelement <3 x double> [[SPLIT4]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT31:%.*]] = insertelement <1 x double> undef, double [[TMP48]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT32:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT31]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP47:%.*]] = fmul <1 x double> [[BLOCK30]], [[SPLAT_SPLAT32]]
-; CHECK-NEXT:    [[TMP48:%.*]] = fadd <1 x double> [[TMP45]], [[TMP47]]
-; CHECK-NEXT:    [[TMP49:%.*]] = shufflevector <1 x double> [[TMP48]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP50:%.*]] = shufflevector <3 x double> [[TMP40]], <3 x double> [[TMP49]], <3 x i32> <i32 0, i32 1, i32 3>
-; CHECK-NEXT:    [[BLOCK33:%.*]] = shufflevector <3 x double> [[SPLIT3]], <3 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP51:%.*]] = extractelement <3 x double> [[SPLIT7]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT34:%.*]] = insertelement <1 x double> undef, double [[TMP51]], i32 0
+; CHECK-NEXT:    [[TMP49:%.*]] = fmul <1 x double> [[BLOCK30]], [[SPLAT_SPLAT32]]
+; CHECK-NEXT:    [[BLOCK33:%.*]] = shufflevector <3 x double> [[TMP11]], <3 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP50:%.*]] = extractelement <3 x double> [[SPLIT4]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT34:%.*]] = insertelement <1 x double> undef, double [[TMP50]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT35:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT34]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP52:%.*]] = fmul <1 x double> [[BLOCK33]], [[SPLAT_SPLAT35]]
-; CHECK-NEXT:    [[BLOCK36:%.*]] = shufflevector <3 x double> [[SPLIT4]], <3 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP53:%.*]] = extractelement <3 x double> [[SPLIT7]], i64 1
+; CHECK-NEXT:    [[TMP51:%.*]] = fmul <1 x double> [[BLOCK33]], [[SPLAT_SPLAT35]]
+; CHECK-NEXT:    [[TMP52:%.*]] = fadd <1 x double> [[TMP49]], [[TMP51]]
+; CHECK-NEXT:    [[BLOCK36:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP53:%.*]] = extractelement <3 x double> [[SPLIT4]], i64 2
 ; CHECK-NEXT:    [[SPLAT_SPLATINSERT37:%.*]] = insertelement <1 x double> undef, double [[TMP53]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT38:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT37]], <1 x double> undef, <1 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP54:%.*]] = fmul <1 x double> [[BLOCK36]], [[SPLAT_SPLAT38]]
 ; CHECK-NEXT:    [[TMP55:%.*]] = fadd <1 x double> [[TMP52]], [[TMP54]]
-; CHECK-NEXT:    [[BLOCK39:%.*]] = shufflevector <3 x double> [[SPLIT5]], <3 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP56:%.*]] = extractelement <3 x double> [[SPLIT7]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT40:%.*]] = insertelement <1 x double> undef, double [[TMP56]], i32 0
+; CHECK-NEXT:    [[TMP56:%.*]] = shufflevector <1 x double> [[TMP55]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP57:%.*]] = shufflevector <3 x double> undef, <3 x double> [[TMP56]], <3 x i32> <i32 3, i32 1, i32 2>
+; CHECK-NEXT:    [[BLOCK39:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> undef, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[TMP58:%.*]] = extractelement <3 x double> [[SPLIT4]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT40:%.*]] = insertelement <1 x double> undef, double [[TMP58]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT41:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT40]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP57:%.*]] = fmul <1 x double> [[BLOCK39]], [[SPLAT_SPLAT41]]
-; CHECK-NEXT:    [[TMP58:%.*]] = fadd <1 x double> [[TMP55]], [[TMP57]]
-; CHECK-NEXT:    [[TMP59:%.*]] = shufflevector <1 x double> [[TMP58]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP60:%.*]] = shufflevector <3 x double> undef, <3 x double> [[TMP59]], <3 x i32> <i32 3, i32 1, i32 2>
-; CHECK-NEXT:    [[BLOCK42:%.*]] = shufflevector <3 x double> [[SPLIT3]], <3 x double> undef, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[TMP61:%.*]] = extractelement <3 x double> [[SPLIT7]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT43:%.*]] = insertelement <1 x double> undef, double [[TMP61]], i32 0
+; CHECK-NEXT:    [[TMP59:%.*]] = fmul <1 x double> [[BLOCK39]], [[SPLAT_SPLAT41]]
+; CHECK-NEXT:    [[BLOCK42:%.*]] = shufflevector <3 x double> [[TMP11]], <3 x double> undef, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[TMP60:%.*]] = extractelement <3 x double> [[SPLIT4]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT43:%.*]] = insertelement <1 x double> undef, double [[TMP60]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT44:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT43]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP62:%.*]] = fmul <1 x double> [[BLOCK42]], [[SPLAT_SPLAT44]]
-; CHECK-NEXT:    [[BLOCK45:%.*]] = shufflevector <3 x double> [[SPLIT4]], <3 x double> undef, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[TMP63:%.*]] = extractelement <3 x double> [[SPLIT7]], i64 1
+; CHECK-NEXT:    [[TMP61:%.*]] = fmul <1 x double> [[BLOCK42]], [[SPLAT_SPLAT44]]
+; CHECK-NEXT:    [[TMP62:%.*]] = fadd <1 x double> [[TMP59]], [[TMP61]]
+; CHECK-NEXT:    [[BLOCK45:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[TMP63:%.*]] = extractelement <3 x double> [[SPLIT4]], i64 2
 ; CHECK-NEXT:    [[SPLAT_SPLATINSERT46:%.*]] = insertelement <1 x double> undef, double [[TMP63]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT47:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT46]], <1 x double> undef, <1 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP64:%.*]] = fmul <1 x double> [[BLOCK45]], [[SPLAT_SPLAT47]]
 ; CHECK-NEXT:    [[TMP65:%.*]] = fadd <1 x double> [[TMP62]], [[TMP64]]
-; CHECK-NEXT:    [[BLOCK48:%.*]] = shufflevector <3 x double> [[SPLIT5]], <3 x double> undef, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[TMP66:%.*]] = extractelement <3 x double> [[SPLIT7]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT49:%.*]] = insertelement <1 x double> undef, double [[TMP66]], i32 0
+; CHECK-NEXT:    [[TMP66:%.*]] = shufflevector <1 x double> [[TMP65]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP67:%.*]] = shufflevector <3 x double> [[TMP57]], <3 x double> [[TMP66]], <3 x i32> <i32 0, i32 3, i32 2>
+; CHECK-NEXT:    [[BLOCK48:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> undef, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[TMP68:%.*]] = extractelement <3 x double> [[SPLIT4]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT49:%.*]] = insertelement <1 x double> undef, double [[TMP68]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT50:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT49]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP67:%.*]] = fmul <1 x double> [[BLOCK48]], [[SPLAT_SPLAT50]]
-; CHECK-NEXT:    [[TMP68:%.*]] = fadd <1 x double> [[TMP65]], [[TMP67]]
-; CHECK-NEXT:    [[TMP69:%.*]] = shufflevector <1 x double> [[TMP68]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP70:%.*]] = shufflevector <3 x double> [[TMP60]], <3 x double> [[TMP69]], <3 x i32> <i32 0, i32 3, i32 2>
-; CHECK-NEXT:    [[BLOCK51:%.*]] = shufflevector <3 x double> [[SPLIT3]], <3 x double> undef, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[TMP71:%.*]] = extractelement <3 x double> [[SPLIT7]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT52:%.*]] = insertelement <1 x double> undef, double [[TMP71]], i32 0
+; CHECK-NEXT:    [[TMP69:%.*]] = fmul <1 x double> [[BLOCK48]], [[SPLAT_SPLAT50]]
+; CHECK-NEXT:    [[BLOCK51:%.*]] = shufflevector <3 x double> [[TMP11]], <3 x double> undef, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[TMP70:%.*]] = extractelement <3 x double> [[SPLIT4]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT52:%.*]] = insertelement <1 x double> undef, double [[TMP70]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT53:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT52]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP72:%.*]] = fmul <1 x double> [[BLOCK51]], [[SPLAT_SPLAT53]]
-; CHECK-NEXT:    [[BLOCK54:%.*]] = shufflevector <3 x double> [[SPLIT4]], <3 x double> undef, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[TMP73:%.*]] = extractelement <3 x double> [[SPLIT7]], i64 1
+; CHECK-NEXT:    [[TMP71:%.*]] = fmul <1 x double> [[BLOCK51]], [[SPLAT_SPLAT53]]
+; CHECK-NEXT:    [[TMP72:%.*]] = fadd <1 x double> [[TMP69]], [[TMP71]]
+; CHECK-NEXT:    [[BLOCK54:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[TMP73:%.*]] = extractelement <3 x double> [[SPLIT4]], i64 2
 ; CHECK-NEXT:    [[SPLAT_SPLATINSERT55:%.*]] = insertelement <1 x double> undef, double [[TMP73]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT56:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT55]], <1 x double> undef, <1 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP74:%.*]] = fmul <1 x double> [[BLOCK54]], [[SPLAT_SPLAT56]]
 ; CHECK-NEXT:    [[TMP75:%.*]] = fadd <1 x double> [[TMP72]], [[TMP74]]
-; CHECK-NEXT:    [[BLOCK57:%.*]] = shufflevector <3 x double> [[SPLIT5]], <3 x double> undef, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[TMP76:%.*]] = extractelement <3 x double> [[SPLIT7]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT58:%.*]] = insertelement <1 x double> undef, double [[TMP76]], i32 0
+; CHECK-NEXT:    [[TMP76:%.*]] = shufflevector <1 x double> [[TMP75]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP77:%.*]] = shufflevector <3 x double> [[TMP67]], <3 x double> [[TMP76]], <3 x i32> <i32 0, i32 1, i32 3>
+; CHECK-NEXT:    [[BLOCK57:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP78:%.*]] = extractelement <3 x double> [[SPLIT5]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT58:%.*]] = insertelement <1 x double> undef, double [[TMP78]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT59:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT58]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP77:%.*]] = fmul <1 x double> [[BLOCK57]], [[SPLAT_SPLAT59]]
-; CHECK-NEXT:    [[TMP78:%.*]] = fadd <1 x double> [[TMP75]], [[TMP77]]
-; CHECK-NEXT:    [[TMP79:%.*]] = shufflevector <1 x double> [[TMP78]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP80:%.*]] = shufflevector <3 x double> [[TMP70]], <3 x double> [[TMP79]], <3 x i32> <i32 0, i32 1, i32 3>
-; CHECK-NEXT:    [[BLOCK60:%.*]] = shufflevector <3 x double> [[SPLIT3]], <3 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP81:%.*]] = extractelement <3 x double> [[SPLIT8]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT61:%.*]] = insertelement <1 x double> undef, double [[TMP81]], i32 0
+; CHECK-NEXT:    [[TMP79:%.*]] = fmul <1 x double> [[BLOCK57]], [[SPLAT_SPLAT59]]
+; CHECK-NEXT:    [[BLOCK60:%.*]] = shufflevector <3 x double> [[TMP11]], <3 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP80:%.*]] = extractelement <3 x double> [[SPLIT5]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT61:%.*]] = insertelement <1 x double> undef, double [[TMP80]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT62:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT61]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP82:%.*]] = fmul <1 x double> [[BLOCK60]], [[SPLAT_SPLAT62]]
-; CHECK-NEXT:    [[BLOCK63:%.*]] = shufflevector <3 x double> [[SPLIT4]], <3 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP83:%.*]] = extractelement <3 x double> [[SPLIT8]], i64 1
+; CHECK-NEXT:    [[TMP81:%.*]] = fmul <1 x double> [[BLOCK60]], [[SPLAT_SPLAT62]]
+; CHECK-NEXT:    [[TMP82:%.*]] = fadd <1 x double> [[TMP79]], [[TMP81]]
+; CHECK-NEXT:    [[BLOCK63:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP83:%.*]] = extractelement <3 x double> [[SPLIT5]], i64 2
 ; CHECK-NEXT:    [[SPLAT_SPLATINSERT64:%.*]] = insertelement <1 x double> undef, double [[TMP83]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT65:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT64]], <1 x double> undef, <1 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP84:%.*]] = fmul <1 x double> [[BLOCK63]], [[SPLAT_SPLAT65]]
 ; CHECK-NEXT:    [[TMP85:%.*]] = fadd <1 x double> [[TMP82]], [[TMP84]]
-; CHECK-NEXT:    [[BLOCK66:%.*]] = shufflevector <3 x double> [[SPLIT5]], <3 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP86:%.*]] = extractelement <3 x double> [[SPLIT8]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT67:%.*]] = insertelement <1 x double> undef, double [[TMP86]], i32 0
+; CHECK-NEXT:    [[TMP86:%.*]] = shufflevector <1 x double> [[TMP85]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP87:%.*]] = shufflevector <3 x double> undef, <3 x double> [[TMP86]], <3 x i32> <i32 3, i32 1, i32 2>
+; CHECK-NEXT:    [[BLOCK66:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> undef, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[TMP88:%.*]] = extractelement <3 x double> [[SPLIT5]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT67:%.*]] = insertelement <1 x double> undef, double [[TMP88]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT68:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT67]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP87:%.*]] = fmul <1 x double> [[BLOCK66]], [[SPLAT_SPLAT68]]
-; CHECK-NEXT:    [[TMP88:%.*]] = fadd <1 x double> [[TMP85]], [[TMP87]]
-; CHECK-NEXT:    [[TMP89:%.*]] = shufflevector <1 x double> [[TMP88]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP90:%.*]] = shufflevector <3 x double> undef, <3 x double> [[TMP89]], <3 x i32> <i32 3, i32 1, i32 2>
-; CHECK-NEXT:    [[BLOCK69:%.*]] = shufflevector <3 x double> [[SPLIT3]], <3 x double> undef, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[TMP91:%.*]] = extractelement <3 x double> [[SPLIT8]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT70:%.*]] = insertelement <1 x double> undef, double [[TMP91]], i32 0
+; CHECK-NEXT:    [[TMP89:%.*]] = fmul <1 x double> [[BLOCK66]], [[SPLAT_SPLAT68]]
+; CHECK-NEXT:    [[BLOCK69:%.*]] = shufflevector <3 x double> [[TMP11]], <3 x double> undef, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[TMP90:%.*]] = extractelement <3 x double> [[SPLIT5]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT70:%.*]] = insertelement <1 x double> undef, double [[TMP90]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT71:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT70]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP92:%.*]] = fmul <1 x double> [[BLOCK69]], [[SPLAT_SPLAT71]]
-; CHECK-NEXT:    [[BLOCK72:%.*]] = shufflevector <3 x double> [[SPLIT4]], <3 x double> undef, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[TMP93:%.*]] = extractelement <3 x double> [[SPLIT8]], i64 1
+; CHECK-NEXT:    [[TMP91:%.*]] = fmul <1 x double> [[BLOCK69]], [[SPLAT_SPLAT71]]
+; CHECK-NEXT:    [[TMP92:%.*]] = fadd <1 x double> [[TMP89]], [[TMP91]]
+; CHECK-NEXT:    [[BLOCK72:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[TMP93:%.*]] = extractelement <3 x double> [[SPLIT5]], i64 2
 ; CHECK-NEXT:    [[SPLAT_SPLATINSERT73:%.*]] = insertelement <1 x double> undef, double [[TMP93]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT74:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT73]], <1 x double> undef, <1 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP94:%.*]] = fmul <1 x double> [[BLOCK72]], [[SPLAT_SPLAT74]]
 ; CHECK-NEXT:    [[TMP95:%.*]] = fadd <1 x double> [[TMP92]], [[TMP94]]
-; CHECK-NEXT:    [[BLOCK75:%.*]] = shufflevector <3 x double> [[SPLIT5]], <3 x double> undef, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[TMP96:%.*]] = extractelement <3 x double> [[SPLIT8]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT76:%.*]] = insertelement <1 x double> undef, double [[TMP96]], i32 0
+; CHECK-NEXT:    [[TMP96:%.*]] = shufflevector <1 x double> [[TMP95]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP97:%.*]] = shufflevector <3 x double> [[TMP87]], <3 x double> [[TMP96]], <3 x i32> <i32 0, i32 3, i32 2>
+; CHECK-NEXT:    [[BLOCK75:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> undef, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[TMP98:%.*]] = extractelement <3 x double> [[SPLIT5]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT76:%.*]] = insertelement <1 x double> undef, double [[TMP98]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT77:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT76]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP97:%.*]] = fmul <1 x double> [[BLOCK75]], [[SPLAT_SPLAT77]]
-; CHECK-NEXT:    [[TMP98:%.*]] = fadd <1 x double> [[TMP95]], [[TMP97]]
-; CHECK-NEXT:    [[TMP99:%.*]] = shufflevector <1 x double> [[TMP98]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP100:%.*]] = shufflevector <3 x double> [[TMP90]], <3 x double> [[TMP99]], <3 x i32> <i32 0, i32 3, i32 2>
-; CHECK-NEXT:    [[BLOCK78:%.*]] = shufflevector <3 x double> [[SPLIT3]], <3 x double> undef, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[TMP101:%.*]] = extractelement <3 x double> [[SPLIT8]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT79:%.*]] = insertelement <1 x double> undef, double [[TMP101]], i32 0
+; CHECK-NEXT:    [[TMP99:%.*]] = fmul <1 x double> [[BLOCK75]], [[SPLAT_SPLAT77]]
+; CHECK-NEXT:    [[BLOCK78:%.*]] = shufflevector <3 x double> [[TMP11]], <3 x double> undef, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[TMP100:%.*]] = extractelement <3 x double> [[SPLIT5]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT79:%.*]] = insertelement <1 x double> undef, double [[TMP100]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT80:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT79]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP102:%.*]] = fmul <1 x double> [[BLOCK78]], [[SPLAT_SPLAT80]]
-; CHECK-NEXT:    [[BLOCK81:%.*]] = shufflevector <3 x double> [[SPLIT4]], <3 x double> undef, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[TMP103:%.*]] = extractelement <3 x double> [[SPLIT8]], i64 1
+; CHECK-NEXT:    [[TMP101:%.*]] = fmul <1 x double> [[BLOCK78]], [[SPLAT_SPLAT80]]
+; CHECK-NEXT:    [[TMP102:%.*]] = fadd <1 x double> [[TMP99]], [[TMP101]]
+; CHECK-NEXT:    [[BLOCK81:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[TMP103:%.*]] = extractelement <3 x double> [[SPLIT5]], i64 2
 ; CHECK-NEXT:    [[SPLAT_SPLATINSERT82:%.*]] = insertelement <1 x double> undef, double [[TMP103]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT83:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT82]], <1 x double> undef, <1 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP104:%.*]] = fmul <1 x double> [[BLOCK81]], [[SPLAT_SPLAT83]]
 ; CHECK-NEXT:    [[TMP105:%.*]] = fadd <1 x double> [[TMP102]], [[TMP104]]
-; CHECK-NEXT:    [[BLOCK84:%.*]] = shufflevector <3 x double> [[SPLIT5]], <3 x double> undef, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[TMP106:%.*]] = extractelement <3 x double> [[SPLIT8]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT85:%.*]] = insertelement <1 x double> undef, double [[TMP106]], i32 0
-; CHECK-NEXT:    [[SPLAT_SPLAT86:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT85]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP107:%.*]] = fmul <1 x double> [[BLOCK84]], [[SPLAT_SPLAT86]]
-; CHECK-NEXT:    [[TMP108:%.*]] = fadd <1 x double> [[TMP105]], [[TMP107]]
-; CHECK-NEXT:    [[TMP109:%.*]] = shufflevector <1 x double> [[TMP108]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP110:%.*]] = shufflevector <3 x double> [[TMP100]], <3 x double> [[TMP109]], <3 x i32> <i32 0, i32 1, i32 3>
-; CHECK-NEXT:    [[TMP111:%.*]] = shufflevector <3 x double> [[TMP50]], <3 x double> [[TMP80]], <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
-; CHECK-NEXT:    [[TMP112:%.*]] = shufflevector <3 x double> [[TMP110]], <3 x double> undef, <6 x i32> <i32 0, i32 1, i32 2, i32 undef, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP113:%.*]] = shufflevector <6 x double> [[TMP111]], <6 x double> [[TMP112]], <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>
-; CHECK-NEXT:    store <9 x double> [[TMP113]], <9 x double>* [[C_PTR:%.*]]
+; CHECK-NEXT:    [[TMP106:%.*]] = shufflevector <1 x double> [[TMP105]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP107:%.*]] = shufflevector <3 x double> [[TMP97]], <3 x double> [[TMP106]], <3 x i32> <i32 0, i32 1, i32 3>
+
+; Store result columns.
+
+; CHECK-NEXT:    [[TMP108:%.*]] = bitcast <9 x double>* [[C_PTR:%.*]] to double*
+; CHECK-NEXT:    [[TMP109:%.*]] = bitcast double* [[TMP108]] to <3 x double>*
+; CHECK-NEXT:    store <3 x double> [[TMP47]], <3 x double>* [[TMP109]], align 8
+; CHECK-NEXT:    [[TMP110:%.*]] = getelementptr double, double* [[TMP108]], i32 3
+; CHECK-NEXT:    [[TMP111:%.*]] = bitcast double* [[TMP110]] to <3 x double>*
+; CHECK-NEXT:    store <3 x double> [[TMP77]], <3 x double>* [[TMP111]], align 8
+; CHECK-NEXT:    [[TMP112:%.*]] = getelementptr double, double* [[TMP108]], i32 6
+; CHECK-NEXT:    [[TMP113:%.*]] = bitcast double* [[TMP112]] to <3 x double>*
+; CHECK-NEXT:    store <3 x double> [[TMP107]], <3 x double>* [[TMP113]], align 8
 ; CHECK-NEXT:    ret void
 ;
+
 entry:
   %a = load <9 x double>, <9 x double>* %A.Ptr
   %b = load <9 x double>, <9 x double>* %B.Ptr
@@ -230,11 +247,20 @@
 define void @transpose_multiply_add(<9 x double>* %A.Ptr, <9 x double>* %B.Ptr, <9 x double>* %C.Ptr) {
 ; CHECK-LABEL: @transpose_multiply_add(
 ; CHECK-NEXT:  entry:
+
+; Load input matrixes %A and %B.
+
 ; CHECK-NEXT:    [[A:%.*]] = load <9 x double>, <9 x double>* [[A_PTR:%.*]]
 ; CHECK-NEXT:    [[B:%.*]] = load <9 x double>, <9 x double>* [[B_PTR:%.*]]
+
+; Extract columns from loaded value %A.
+
 ; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <9 x double> [[A]], <9 x double> undef, <3 x i32> <i32 0, i32 1, i32 2>
 ; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <9 x double> [[A]], <9 x double> undef, <3 x i32> <i32 3, i32 4, i32 5>
 ; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <9 x double> [[A]], <9 x double> undef, <3 x i32> <i32 6, i32 7, i32 8>
+
+; Transpose %A.
+
 ; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <3 x double> [[SPLIT]], i64 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <3 x double> undef, double [[TMP0]], i64 0
 ; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <3 x double> [[SPLIT1]], i64 0
@@ -253,191 +279,197 @@
 ; CHECK-NEXT:    [[TMP15:%.*]] = insertelement <3 x double> [[TMP13]], double [[TMP14]], i64 1
 ; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <3 x double> [[SPLIT2]], i64 2
 ; CHECK-NEXT:    [[TMP17:%.*]] = insertelement <3 x double> [[TMP15]], double [[TMP16]], i64 2
-; CHECK-NEXT:    [[TMP18:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> [[TMP11]], <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
-; CHECK-NEXT:    [[TMP19:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <6 x i32> <i32 0, i32 1, i32 2, i32 undef, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP20:%.*]] = shufflevector <6 x double> [[TMP18]], <6 x double> [[TMP19]], <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>
-; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <9 x double> [[TMP20]], <9 x double> undef, <3 x i32> <i32 0, i32 1, i32 2>
-; CHECK-NEXT:    [[SPLIT4:%.*]] = shufflevector <9 x double> [[TMP20]], <9 x double> undef, <3 x i32> <i32 3, i32 4, i32 5>
-; CHECK-NEXT:    [[SPLIT5:%.*]] = shufflevector <9 x double> [[TMP20]], <9 x double> undef, <3 x i32> <i32 6, i32 7, i32 8>
-; CHECK-NEXT:    [[SPLIT6:%.*]] = shufflevector <9 x double> [[B]], <9 x double> undef, <3 x i32> <i32 0, i32 1, i32 2>
-; CHECK-NEXT:    [[SPLIT7:%.*]] = shufflevector <9 x double> [[B]], <9 x double> undef, <3 x i32> <i32 3, i32 4, i32 5>
-; CHECK-NEXT:    [[SPLIT8:%.*]] = shufflevector <9 x double> [[B]], <9 x double> undef, <3 x i32> <i32 6, i32 7, i32 8>
-; CHECK-NEXT:    [[BLOCK:%.*]] = shufflevector <3 x double> [[SPLIT3]], <3 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP21:%.*]] = extractelement <3 x double> [[SPLIT6]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x double> undef, double [[TMP21]], i32 0
+
+; Extract columns from %B.
+
+; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <9 x double> [[B]], <9 x double> undef, <3 x i32> <i32 0, i32 1, i32 2>
+; CHECK-NEXT:    [[SPLIT4:%.*]] = shufflevector <9 x double> [[B]], <9 x double> undef, <3 x i32> <i32 3, i32 4, i32 5>
+; CHECK-NEXT:    [[SPLIT5:%.*]] = shufflevector <9 x double> [[B]], <9 x double> undef, <3 x i32> <i32 6, i32 7, i32 8>
+
+; Lower multiply(transpose(%A), %B)
+
+; CHECK-NEXT:    [[BLOCK:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <3 x double> [[SPLIT3]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x double> undef, double [[TMP18]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP22:%.*]] = fmul <1 x double> [[BLOCK]], [[SPLAT_SPLAT]]
-; CHECK-NEXT:    [[BLOCK9:%.*]] = shufflevector <3 x double> [[SPLIT4]], <3 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP23:%.*]] = extractelement <3 x double> [[SPLIT6]], i64 1
+; CHECK-NEXT:    [[TMP19:%.*]] = fmul <1 x double> [[BLOCK]], [[SPLAT_SPLAT]]
+; CHECK-NEXT:    [[BLOCK6:%.*]] = shufflevector <3 x double> [[TMP11]], <3 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <3 x double> [[SPLIT3]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT7:%.*]] = insertelement <1 x double> undef, double [[TMP20]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT8:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT7]], <1 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP21:%.*]] = fmul <1 x double> [[BLOCK6]], [[SPLAT_SPLAT8]]
+; CHECK-NEXT:    [[TMP22:%.*]] = fadd <1 x double> [[TMP19]], [[TMP21]]
+; CHECK-NEXT:    [[BLOCK9:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP23:%.*]] = extractelement <3 x double> [[SPLIT3]], i64 2
 ; CHECK-NEXT:    [[SPLAT_SPLATINSERT10:%.*]] = insertelement <1 x double> undef, double [[TMP23]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT11:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT10]], <1 x double> undef, <1 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP24:%.*]] = fmul <1 x double> [[BLOCK9]], [[SPLAT_SPLAT11]]
 ; CHECK-NEXT:    [[TMP25:%.*]] = fadd <1 x double> [[TMP22]], [[TMP24]]
-; CHECK-NEXT:    [[BLOCK12:%.*]] = shufflevector <3 x double> [[SPLIT5]], <3 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP26:%.*]] = extractelement <3 x double> [[SPLIT6]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT13:%.*]] = insertelement <1 x double> undef, double [[TMP26]], i32 0
+; CHECK-NEXT:    [[TMP26:%.*]] = shufflevector <1 x double> [[TMP25]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP27:%.*]] = shufflevector <3 x double> undef, <3 x double> [[TMP26]], <3 x i32> <i32 3, i32 1, i32 2>
+; CHECK-NEXT:    [[BLOCK12:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> undef, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[TMP28:%.*]] = extractelement <3 x double> [[SPLIT3]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT13:%.*]] = insertelement <1 x double> undef, double [[TMP28]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT14:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT13]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP27:%.*]] = fmul <1 x double> [[BLOCK12]], [[SPLAT_SPLAT14]]
-; CHECK-NEXT:    [[TMP28:%.*]] = fadd <1 x double> [[TMP25]], [[TMP27]]
-; CHECK-NEXT:    [[TMP29:%.*]] = shufflevector <1 x double> [[TMP28]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP30:%.*]] = shufflevector <3 x double> undef, <3 x double> [[TMP29]], <3 x i32> <i32 3, i32 1, i32 2>
-; CHECK-NEXT:    [[BLOCK15:%.*]] = shufflevector <3 x double> [[SPLIT3]], <3 x double> undef, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[TMP31:%.*]] = extractelement <3 x double> [[SPLIT6]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT16:%.*]] = insertelement <1 x double> undef, double [[TMP31]], i32 0
+; CHECK-NEXT:    [[TMP29:%.*]] = fmul <1 x double> [[BLOCK12]], [[SPLAT_SPLAT14]]
+; CHECK-NEXT:    [[BLOCK15:%.*]] = shufflevector <3 x double> [[TMP11]], <3 x double> undef, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[TMP30:%.*]] = extractelement <3 x double> [[SPLIT3]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT16:%.*]] = insertelement <1 x double> undef, double [[TMP30]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT17:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT16]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP32:%.*]] = fmul <1 x double> [[BLOCK15]], [[SPLAT_SPLAT17]]
-; CHECK-NEXT:    [[BLOCK18:%.*]] = shufflevector <3 x double> [[SPLIT4]], <3 x double> undef, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[TMP33:%.*]] = extractelement <3 x double> [[SPLIT6]], i64 1
+; CHECK-NEXT:    [[TMP31:%.*]] = fmul <1 x double> [[BLOCK15]], [[SPLAT_SPLAT17]]
+; CHECK-NEXT:    [[TMP32:%.*]] = fadd <1 x double> [[TMP29]], [[TMP31]]
+; CHECK-NEXT:    [[BLOCK18:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[TMP33:%.*]] = extractelement <3 x double> [[SPLIT3]], i64 2
 ; CHECK-NEXT:    [[SPLAT_SPLATINSERT19:%.*]] = insertelement <1 x double> undef, double [[TMP33]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT20:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT19]], <1 x double> undef, <1 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP34:%.*]] = fmul <1 x double> [[BLOCK18]], [[SPLAT_SPLAT20]]
 ; CHECK-NEXT:    [[TMP35:%.*]] = fadd <1 x double> [[TMP32]], [[TMP34]]
-; CHECK-NEXT:    [[BLOCK21:%.*]] = shufflevector <3 x double> [[SPLIT5]], <3 x double> undef, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[TMP36:%.*]] = extractelement <3 x double> [[SPLIT6]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT22:%.*]] = insertelement <1 x double> undef, double [[TMP36]], i32 0
+; CHECK-NEXT:    [[TMP36:%.*]] = shufflevector <1 x double> [[TMP35]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP37:%.*]] = shufflevector <3 x double> [[TMP27]], <3 x double> [[TMP36]], <3 x i32> <i32 0, i32 3, i32 2>
+; CHECK-NEXT:    [[BLOCK21:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> undef, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[TMP38:%.*]] = extractelement <3 x double> [[SPLIT3]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT22:%.*]] = insertelement <1 x double> undef, double [[TMP38]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT23:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT22]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP37:%.*]] = fmul <1 x double> [[BLOCK21]], [[SPLAT_SPLAT23]]
-; CHECK-NEXT:    [[TMP38:%.*]] = fadd <1 x double> [[TMP35]], [[TMP37]]
-; CHECK-NEXT:    [[TMP39:%.*]] = shufflevector <1 x double> [[TMP38]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP40:%.*]] = shufflevector <3 x double> [[TMP30]], <3 x double> [[TMP39]], <3 x i32> <i32 0, i32 3, i32 2>
-; CHECK-NEXT:    [[BLOCK24:%.*]] = shufflevector <3 x double> [[SPLIT3]], <3 x double> undef, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[TMP41:%.*]] = extractelement <3 x double> [[SPLIT6]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT25:%.*]] = insertelement <1 x double> undef, double [[TMP41]], i32 0
+; CHECK-NEXT:    [[TMP39:%.*]] = fmul <1 x double> [[BLOCK21]], [[SPLAT_SPLAT23]]
+; CHECK-NEXT:    [[BLOCK24:%.*]] = shufflevector <3 x double> [[TMP11]], <3 x double> undef, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[TMP40:%.*]] = extractelement <3 x double> [[SPLIT3]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT25:%.*]] = insertelement <1 x double> undef, double [[TMP40]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT26:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT25]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP42:%.*]] = fmul <1 x double> [[BLOCK24]], [[SPLAT_SPLAT26]]
-; CHECK-NEXT:    [[BLOCK27:%.*]] = shufflevector <3 x double> [[SPLIT4]], <3 x double> undef, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[TMP43:%.*]] = extractelement <3 x double> [[SPLIT6]], i64 1
+; CHECK-NEXT:    [[TMP41:%.*]] = fmul <1 x double> [[BLOCK24]], [[SPLAT_SPLAT26]]
+; CHECK-NEXT:    [[TMP42:%.*]] = fadd <1 x double> [[TMP39]], [[TMP41]]
+; CHECK-NEXT:    [[BLOCK27:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[TMP43:%.*]] = extractelement <3 x double> [[SPLIT3]], i64 2
 ; CHECK-NEXT:    [[SPLAT_SPLATINSERT28:%.*]] = insertelement <1 x double> undef, double [[TMP43]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT29:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT28]], <1 x double> undef, <1 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP44:%.*]] = fmul <1 x double> [[BLOCK27]], [[SPLAT_SPLAT29]]
 ; CHECK-NEXT:    [[TMP45:%.*]] = fadd <1 x double> [[TMP42]], [[TMP44]]
-; CHECK-NEXT:    [[BLOCK30:%.*]] = shufflevector <3 x double> [[SPLIT5]], <3 x double> undef, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[TMP46:%.*]] = extractelement <3 x double> [[SPLIT6]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT31:%.*]] = insertelement <1 x double> undef, double [[TMP46]], i32 0
+; CHECK-NEXT:    [[TMP46:%.*]] = shufflevector <1 x double> [[TMP45]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP47:%.*]] = shufflevector <3 x double> [[TMP37]], <3 x double> [[TMP46]], <3 x i32> <i32 0, i32 1, i32 3>
+; CHECK-NEXT:    [[BLOCK30:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP48:%.*]] = extractelement <3 x double> [[SPLIT4]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT31:%.*]] = insertelement <1 x double> undef, double [[TMP48]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT32:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT31]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP47:%.*]] = fmul <1 x double> [[BLOCK30]], [[SPLAT_SPLAT32]]
-; CHECK-NEXT:    [[TMP48:%.*]] = fadd <1 x double> [[TMP45]], [[TMP47]]
-; CHECK-NEXT:    [[TMP49:%.*]] = shufflevector <1 x double> [[TMP48]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP50:%.*]] = shufflevector <3 x double> [[TMP40]], <3 x double> [[TMP49]], <3 x i32> <i32 0, i32 1, i32 3>
-; CHECK-NEXT:    [[BLOCK33:%.*]] = shufflevector <3 x double> [[SPLIT3]], <3 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP51:%.*]] = extractelement <3 x double> [[SPLIT7]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT34:%.*]] = insertelement <1 x double> undef, double [[TMP51]], i32 0
+; CHECK-NEXT:    [[TMP49:%.*]] = fmul <1 x double> [[BLOCK30]], [[SPLAT_SPLAT32]]
+; CHECK-NEXT:    [[BLOCK33:%.*]] = shufflevector <3 x double> [[TMP11]], <3 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP50:%.*]] = extractelement <3 x double> [[SPLIT4]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT34:%.*]] = insertelement <1 x double> undef, double [[TMP50]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT35:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT34]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP52:%.*]] = fmul <1 x double> [[BLOCK33]], [[SPLAT_SPLAT35]]
-; CHECK-NEXT:    [[BLOCK36:%.*]] = shufflevector <3 x double> [[SPLIT4]], <3 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP53:%.*]] = extractelement <3 x double> [[SPLIT7]], i64 1
+; CHECK-NEXT:    [[TMP51:%.*]] = fmul <1 x double> [[BLOCK33]], [[SPLAT_SPLAT35]]
+; CHECK-NEXT:    [[TMP52:%.*]] = fadd <1 x double> [[TMP49]], [[TMP51]]
+; CHECK-NEXT:    [[BLOCK36:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP53:%.*]] = extractelement <3 x double> [[SPLIT4]], i64 2
 ; CHECK-NEXT:    [[SPLAT_SPLATINSERT37:%.*]] = insertelement <1 x double> undef, double [[TMP53]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT38:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT37]], <1 x double> undef, <1 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP54:%.*]] = fmul <1 x double> [[BLOCK36]], [[SPLAT_SPLAT38]]
 ; CHECK-NEXT:    [[TMP55:%.*]] = fadd <1 x double> [[TMP52]], [[TMP54]]
-; CHECK-NEXT:    [[BLOCK39:%.*]] = shufflevector <3 x double> [[SPLIT5]], <3 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP56:%.*]] = extractelement <3 x double> [[SPLIT7]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT40:%.*]] = insertelement <1 x double> undef, double [[TMP56]], i32 0
+; CHECK-NEXT:    [[TMP56:%.*]] = shufflevector <1 x double> [[TMP55]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP57:%.*]] = shufflevector <3 x double> undef, <3 x double> [[TMP56]], <3 x i32> <i32 3, i32 1, i32 2>
+; CHECK-NEXT:    [[BLOCK39:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> undef, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[TMP58:%.*]] = extractelement <3 x double> [[SPLIT4]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT40:%.*]] = insertelement <1 x double> undef, double [[TMP58]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT41:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT40]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP57:%.*]] = fmul <1 x double> [[BLOCK39]], [[SPLAT_SPLAT41]]
-; CHECK-NEXT:    [[TMP58:%.*]] = fadd <1 x double> [[TMP55]], [[TMP57]]
-; CHECK-NEXT:    [[TMP59:%.*]] = shufflevector <1 x double> [[TMP58]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP60:%.*]] = shufflevector <3 x double> undef, <3 x double> [[TMP59]], <3 x i32> <i32 3, i32 1, i32 2>
-; CHECK-NEXT:    [[BLOCK42:%.*]] = shufflevector <3 x double> [[SPLIT3]], <3 x double> undef, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[TMP61:%.*]] = extractelement <3 x double> [[SPLIT7]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT43:%.*]] = insertelement <1 x double> undef, double [[TMP61]], i32 0
+; CHECK-NEXT:    [[TMP59:%.*]] = fmul <1 x double> [[BLOCK39]], [[SPLAT_SPLAT41]]
+; CHECK-NEXT:    [[BLOCK42:%.*]] = shufflevector <3 x double> [[TMP11]], <3 x double> undef, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[TMP60:%.*]] = extractelement <3 x double> [[SPLIT4]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT43:%.*]] = insertelement <1 x double> undef, double [[TMP60]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT44:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT43]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP62:%.*]] = fmul <1 x double> [[BLOCK42]], [[SPLAT_SPLAT44]]
-; CHECK-NEXT:    [[BLOCK45:%.*]] = shufflevector <3 x double> [[SPLIT4]], <3 x double> undef, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[TMP63:%.*]] = extractelement <3 x double> [[SPLIT7]], i64 1
+; CHECK-NEXT:    [[TMP61:%.*]] = fmul <1 x double> [[BLOCK42]], [[SPLAT_SPLAT44]]
+; CHECK-NEXT:    [[TMP62:%.*]] = fadd <1 x double> [[TMP59]], [[TMP61]]
+; CHECK-NEXT:    [[BLOCK45:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[TMP63:%.*]] = extractelement <3 x double> [[SPLIT4]], i64 2
 ; CHECK-NEXT:    [[SPLAT_SPLATINSERT46:%.*]] = insertelement <1 x double> undef, double [[TMP63]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT47:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT46]], <1 x double> undef, <1 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP64:%.*]] = fmul <1 x double> [[BLOCK45]], [[SPLAT_SPLAT47]]
 ; CHECK-NEXT:    [[TMP65:%.*]] = fadd <1 x double> [[TMP62]], [[TMP64]]
-; CHECK-NEXT:    [[BLOCK48:%.*]] = shufflevector <3 x double> [[SPLIT5]], <3 x double> undef, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[TMP66:%.*]] = extractelement <3 x double> [[SPLIT7]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT49:%.*]] = insertelement <1 x double> undef, double [[TMP66]], i32 0
+; CHECK-NEXT:    [[TMP66:%.*]] = shufflevector <1 x double> [[TMP65]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP67:%.*]] = shufflevector <3 x double> [[TMP57]], <3 x double> [[TMP66]], <3 x i32> <i32 0, i32 3, i32 2>
+; CHECK-NEXT:    [[BLOCK48:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> undef, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[TMP68:%.*]] = extractelement <3 x double> [[SPLIT4]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT49:%.*]] = insertelement <1 x double> undef, double [[TMP68]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT50:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT49]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP67:%.*]] = fmul <1 x double> [[BLOCK48]], [[SPLAT_SPLAT50]]
-; CHECK-NEXT:    [[TMP68:%.*]] = fadd <1 x double> [[TMP65]], [[TMP67]]
-; CHECK-NEXT:    [[TMP69:%.*]] = shufflevector <1 x double> [[TMP68]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP70:%.*]] = shufflevector <3 x double> [[TMP60]], <3 x double> [[TMP69]], <3 x i32> <i32 0, i32 3, i32 2>
-; CHECK-NEXT:    [[BLOCK51:%.*]] = shufflevector <3 x double> [[SPLIT3]], <3 x double> undef, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[TMP71:%.*]] = extractelement <3 x double> [[SPLIT7]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT52:%.*]] = insertelement <1 x double> undef, double [[TMP71]], i32 0
+; CHECK-NEXT:    [[TMP69:%.*]] = fmul <1 x double> [[BLOCK48]], [[SPLAT_SPLAT50]]
+; CHECK-NEXT:    [[BLOCK51:%.*]] = shufflevector <3 x double> [[TMP11]], <3 x double> undef, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[TMP70:%.*]] = extractelement <3 x double> [[SPLIT4]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT52:%.*]] = insertelement <1 x double> undef, double [[TMP70]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT53:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT52]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP72:%.*]] = fmul <1 x double> [[BLOCK51]], [[SPLAT_SPLAT53]]
-; CHECK-NEXT:    [[BLOCK54:%.*]] = shufflevector <3 x double> [[SPLIT4]], <3 x double> undef, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[TMP73:%.*]] = extractelement <3 x double> [[SPLIT7]], i64 1
+; CHECK-NEXT:    [[TMP71:%.*]] = fmul <1 x double> [[BLOCK51]], [[SPLAT_SPLAT53]]
+; CHECK-NEXT:    [[TMP72:%.*]] = fadd <1 x double> [[TMP69]], [[TMP71]]
+; CHECK-NEXT:    [[BLOCK54:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[TMP73:%.*]] = extractelement <3 x double> [[SPLIT4]], i64 2
 ; CHECK-NEXT:    [[SPLAT_SPLATINSERT55:%.*]] = insertelement <1 x double> undef, double [[TMP73]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT56:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT55]], <1 x double> undef, <1 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP74:%.*]] = fmul <1 x double> [[BLOCK54]], [[SPLAT_SPLAT56]]
 ; CHECK-NEXT:    [[TMP75:%.*]] = fadd <1 x double> [[TMP72]], [[TMP74]]
-; CHECK-NEXT:    [[BLOCK57:%.*]] = shufflevector <3 x double> [[SPLIT5]], <3 x double> undef, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[TMP76:%.*]] = extractelement <3 x double> [[SPLIT7]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT58:%.*]] = insertelement <1 x double> undef, double [[TMP76]], i32 0
+; CHECK-NEXT:    [[TMP76:%.*]] = shufflevector <1 x double> [[TMP75]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP77:%.*]] = shufflevector <3 x double> [[TMP67]], <3 x double> [[TMP76]], <3 x i32> <i32 0, i32 1, i32 3>
+; CHECK-NEXT:    [[BLOCK57:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP78:%.*]] = extractelement <3 x double> [[SPLIT5]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT58:%.*]] = insertelement <1 x double> undef, double [[TMP78]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT59:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT58]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP77:%.*]] = fmul <1 x double> [[BLOCK57]], [[SPLAT_SPLAT59]]
-; CHECK-NEXT:    [[TMP78:%.*]] = fadd <1 x double> [[TMP75]], [[TMP77]]
-; CHECK-NEXT:    [[TMP79:%.*]] = shufflevector <1 x double> [[TMP78]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP80:%.*]] = shufflevector <3 x double> [[TMP70]], <3 x double> [[TMP79]], <3 x i32> <i32 0, i32 1, i32 3>
-; CHECK-NEXT:    [[BLOCK60:%.*]] = shufflevector <3 x double> [[SPLIT3]], <3 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP81:%.*]] = extractelement <3 x double> [[SPLIT8]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT61:%.*]] = insertelement <1 x double> undef, double [[TMP81]], i32 0
+; CHECK-NEXT:    [[TMP79:%.*]] = fmul <1 x double> [[BLOCK57]], [[SPLAT_SPLAT59]]
+; CHECK-NEXT:    [[BLOCK60:%.*]] = shufflevector <3 x double> [[TMP11]], <3 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP80:%.*]] = extractelement <3 x double> [[SPLIT5]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT61:%.*]] = insertelement <1 x double> undef, double [[TMP80]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT62:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT61]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP82:%.*]] = fmul <1 x double> [[BLOCK60]], [[SPLAT_SPLAT62]]
-; CHECK-NEXT:    [[BLOCK63:%.*]] = shufflevector <3 x double> [[SPLIT4]], <3 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP83:%.*]] = extractelement <3 x double> [[SPLIT8]], i64 1
+; CHECK-NEXT:    [[TMP81:%.*]] = fmul <1 x double> [[BLOCK60]], [[SPLAT_SPLAT62]]
+; CHECK-NEXT:    [[TMP82:%.*]] = fadd <1 x double> [[TMP79]], [[TMP81]]
+; CHECK-NEXT:    [[BLOCK63:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP83:%.*]] = extractelement <3 x double> [[SPLIT5]], i64 2
 ; CHECK-NEXT:    [[SPLAT_SPLATINSERT64:%.*]] = insertelement <1 x double> undef, double [[TMP83]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT65:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT64]], <1 x double> undef, <1 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP84:%.*]] = fmul <1 x double> [[BLOCK63]], [[SPLAT_SPLAT65]]
 ; CHECK-NEXT:    [[TMP85:%.*]] = fadd <1 x double> [[TMP82]], [[TMP84]]
-; CHECK-NEXT:    [[BLOCK66:%.*]] = shufflevector <3 x double> [[SPLIT5]], <3 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP86:%.*]] = extractelement <3 x double> [[SPLIT8]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT67:%.*]] = insertelement <1 x double> undef, double [[TMP86]], i32 0
+; CHECK-NEXT:    [[TMP86:%.*]] = shufflevector <1 x double> [[TMP85]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP87:%.*]] = shufflevector <3 x double> undef, <3 x double> [[TMP86]], <3 x i32> <i32 3, i32 1, i32 2>
+; CHECK-NEXT:    [[BLOCK66:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> undef, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[TMP88:%.*]] = extractelement <3 x double> [[SPLIT5]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT67:%.*]] = insertelement <1 x double> undef, double [[TMP88]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT68:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT67]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP87:%.*]] = fmul <1 x double> [[BLOCK66]], [[SPLAT_SPLAT68]]
-; CHECK-NEXT:    [[TMP88:%.*]] = fadd <1 x double> [[TMP85]], [[TMP87]]
-; CHECK-NEXT:    [[TMP89:%.*]] = shufflevector <1 x double> [[TMP88]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP90:%.*]] = shufflevector <3 x double> undef, <3 x double> [[TMP89]], <3 x i32> <i32 3, i32 1, i32 2>
-; CHECK-NEXT:    [[BLOCK69:%.*]] = shufflevector <3 x double> [[SPLIT3]], <3 x double> undef, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[TMP91:%.*]] = extractelement <3 x double> [[SPLIT8]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT70:%.*]] = insertelement <1 x double> undef, double [[TMP91]], i32 0
+; CHECK-NEXT:    [[TMP89:%.*]] = fmul <1 x double> [[BLOCK66]], [[SPLAT_SPLAT68]]
+; CHECK-NEXT:    [[BLOCK69:%.*]] = shufflevector <3 x double> [[TMP11]], <3 x double> undef, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[TMP90:%.*]] = extractelement <3 x double> [[SPLIT5]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT70:%.*]] = insertelement <1 x double> undef, double [[TMP90]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT71:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT70]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP92:%.*]] = fmul <1 x double> [[BLOCK69]], [[SPLAT_SPLAT71]]
-; CHECK-NEXT:    [[BLOCK72:%.*]] = shufflevector <3 x double> [[SPLIT4]], <3 x double> undef, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[TMP93:%.*]] = extractelement <3 x double> [[SPLIT8]], i64 1
+; CHECK-NEXT:    [[TMP91:%.*]] = fmul <1 x double> [[BLOCK69]], [[SPLAT_SPLAT71]]
+; CHECK-NEXT:    [[TMP92:%.*]] = fadd <1 x double> [[TMP89]], [[TMP91]]
+; CHECK-NEXT:    [[BLOCK72:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[TMP93:%.*]] = extractelement <3 x double> [[SPLIT5]], i64 2
 ; CHECK-NEXT:    [[SPLAT_SPLATINSERT73:%.*]] = insertelement <1 x double> undef, double [[TMP93]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT74:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT73]], <1 x double> undef, <1 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP94:%.*]] = fmul <1 x double> [[BLOCK72]], [[SPLAT_SPLAT74]]
 ; CHECK-NEXT:    [[TMP95:%.*]] = fadd <1 x double> [[TMP92]], [[TMP94]]
-; CHECK-NEXT:    [[BLOCK75:%.*]] = shufflevector <3 x double> [[SPLIT5]], <3 x double> undef, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[TMP96:%.*]] = extractelement <3 x double> [[SPLIT8]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT76:%.*]] = insertelement <1 x double> undef, double [[TMP96]], i32 0
+; CHECK-NEXT:    [[TMP96:%.*]] = shufflevector <1 x double> [[TMP95]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP97:%.*]] = shufflevector <3 x double> [[TMP87]], <3 x double> [[TMP96]], <3 x i32> <i32 0, i32 3, i32 2>
+; CHECK-NEXT:    [[BLOCK75:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> undef, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[TMP98:%.*]] = extractelement <3 x double> [[SPLIT5]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT76:%.*]] = insertelement <1 x double> undef, double [[TMP98]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT77:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT76]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP97:%.*]] = fmul <1 x double> [[BLOCK75]], [[SPLAT_SPLAT77]]
-; CHECK-NEXT:    [[TMP98:%.*]] = fadd <1 x double> [[TMP95]], [[TMP97]]
-; CHECK-NEXT:    [[TMP99:%.*]] = shufflevector <1 x double> [[TMP98]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP100:%.*]] = shufflevector <3 x double> [[TMP90]], <3 x double> [[TMP99]], <3 x i32> <i32 0, i32 3, i32 2>
-; CHECK-NEXT:    [[BLOCK78:%.*]] = shufflevector <3 x double> [[SPLIT3]], <3 x double> undef, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[TMP101:%.*]] = extractelement <3 x double> [[SPLIT8]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT79:%.*]] = insertelement <1 x double> undef, double [[TMP101]], i32 0
+; CHECK-NEXT:    [[TMP99:%.*]] = fmul <1 x double> [[BLOCK75]], [[SPLAT_SPLAT77]]
+; CHECK-NEXT:    [[BLOCK78:%.*]] = shufflevector <3 x double> [[TMP11]], <3 x double> undef, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[TMP100:%.*]] = extractelement <3 x double> [[SPLIT5]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT79:%.*]] = insertelement <1 x double> undef, double [[TMP100]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT80:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT79]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP102:%.*]] = fmul <1 x double> [[BLOCK78]], [[SPLAT_SPLAT80]]
-; CHECK-NEXT:    [[BLOCK81:%.*]] = shufflevector <3 x double> [[SPLIT4]], <3 x double> undef, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[TMP103:%.*]] = extractelement <3 x double> [[SPLIT8]], i64 1
+; CHECK-NEXT:    [[TMP101:%.*]] = fmul <1 x double> [[BLOCK78]], [[SPLAT_SPLAT80]]
+; CHECK-NEXT:    [[TMP102:%.*]] = fadd <1 x double> [[TMP99]], [[TMP101]]
+; CHECK-NEXT:    [[BLOCK81:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> undef, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[TMP103:%.*]] = extractelement <3 x double> [[SPLIT5]], i64 2
 ; CHECK-NEXT:    [[SPLAT_SPLATINSERT82:%.*]] = insertelement <1 x double> undef, double [[TMP103]], i32 0
 ; CHECK-NEXT:    [[SPLAT_SPLAT83:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT82]], <1 x double> undef, <1 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP104:%.*]] = fmul <1 x double> [[BLOCK81]], [[SPLAT_SPLAT83]]
 ; CHECK-NEXT:    [[TMP105:%.*]] = fadd <1 x double> [[TMP102]], [[TMP104]]
-; CHECK-NEXT:    [[BLOCK84:%.*]] = shufflevector <3 x double> [[SPLIT5]], <3 x double> undef, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[TMP106:%.*]] = extractelement <3 x double> [[SPLIT8]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT85:%.*]] = insertelement <1 x double> undef, double [[TMP106]], i32 0
-; CHECK-NEXT:    [[SPLAT_SPLAT86:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT85]], <1 x double> undef, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP107:%.*]] = fmul <1 x double> [[BLOCK84]], [[SPLAT_SPLAT86]]
-; CHECK-NEXT:    [[TMP108:%.*]] = fadd <1 x double> [[TMP105]], [[TMP107]]
-; CHECK-NEXT:    [[TMP109:%.*]] = shufflevector <1 x double> [[TMP108]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP110:%.*]] = shufflevector <3 x double> [[TMP100]], <3 x double> [[TMP109]], <3 x i32> <i32 0, i32 1, i32 3>
-; CHECK-NEXT:    [[TMP111:%.*]] = shufflevector <3 x double> [[TMP50]], <3 x double> [[TMP80]], <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
-; CHECK-NEXT:    [[TMP112:%.*]] = shufflevector <3 x double> [[TMP110]], <3 x double> undef, <6 x i32> <i32 0, i32 1, i32 2, i32 undef, i32 undef, i32 undef>
-; CHECK-NEXT:    [[TMP113:%.*]] = shufflevector <6 x double> [[TMP111]], <6 x double> [[TMP112]], <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>
+
+;  Embed result of multiply into flat vector.
+
+; CHECK-NEXT:    [[TMP106:%.*]] = shufflevector <1 x double> [[TMP105]], <1 x double> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP107:%.*]] = shufflevector <3 x double> [[TMP97]], <3 x double> [[TMP106]], <3 x i32> <i32 0, i32 1, i32 3>
+; CHECK-NEXT:    [[TMP108:%.*]] = shufflevector <3 x double> [[TMP47]], <3 x double> [[TMP77]], <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
+; CHECK-NEXT:    [[TMP109:%.*]] = shufflevector <3 x double> [[TMP107]], <3 x double> undef, <6 x i32> <i32 0, i32 1, i32 2, i32 undef, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP110:%.*]] = shufflevector <6 x double> [[TMP108]], <6 x double> [[TMP109]], <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>
+
+; Load %C and add result of multiply.
+
 ; CHECK-NEXT:    [[C:%.*]] = load <9 x double>, <9 x double>* [[C_PTR:%.*]]
-; CHECK-NEXT:    [[RES:%.*]] = fadd <9 x double> [[C]], [[TMP113]]
+; CHECK-NEXT:    [[RES:%.*]] = fadd <9 x double> [[C]], [[TMP110]]
 ; CHECK-NEXT:    store <9 x double> [[RES]], <9 x double>* [[C_PTR]]
 ; CHECK-NEXT:    ret void
 ;
@@ -452,4 +484,3 @@
   store <9 x double> %res, <9 x double>* %C.Ptr
   ret void
 }
-
diff --git a/llvm/test/Transforms/LowerMatrixIntrinsics/propagate-forward.ll b/llvm/test/Transforms/LowerMatrixIntrinsics/propagate-forward.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/LowerMatrixIntrinsics/propagate-forward.ll
@@ -0,0 +1,44 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -lower-matrix-intrinsics -S < %s | FileCheck  %s
+; RUN: opt -passes='lower-matrix-intrinsics' -S < %s | FileCheck %s
+
+; Check that we do not emit shufflevectors to flatten the result of the
+; transpose and store the columns directly.
+define void @transpose_store(<8 x double> %a, <8 x double>* %Ptr) {
+; CHECK-LABEL: @transpose_store(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <8 x double> [[A:%.*]], <8 x double> undef, <2 x i32> <i32 0, i32 1>
+; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <8 x double> [[A]], <8 x double> undef, <2 x i32> <i32 2, i32 3>
+; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <8 x double> [[A]], <8 x double> undef, <2 x i32> <i32 4, i32 5>
+; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <8 x double> [[A]], <8 x double> undef, <2 x i32> <i32 6, i32 7>
+; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <2 x double> [[SPLIT]], i64 0
+; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x double> undef, double [[TMP0]], i64 0
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[SPLIT1]], i64 0
+; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <4 x double> [[TMP1]], double [[TMP2]], i64 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <2 x double> [[SPLIT2]], i64 0
+; CHECK-NEXT:    [[TMP5:%.*]] = insertelement <4 x double> [[TMP3]], double [[TMP4]], i64 2
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x double> [[SPLIT3]], i64 0
+; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x double> [[TMP5]], double [[TMP6]], i64 3
+; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <2 x double> [[SPLIT]], i64 1
+; CHECK-NEXT:    [[TMP9:%.*]] = insertelement <4 x double> undef, double [[TMP8]], i64 0
+; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <2 x double> [[SPLIT1]], i64 1
+; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <4 x double> [[TMP9]], double [[TMP10]], i64 1
+; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <2 x double> [[SPLIT2]], i64 1
+; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <4 x double> [[TMP11]], double [[TMP12]], i64 2
+; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <2 x double> [[SPLIT3]], i64 1
+; CHECK-NEXT:    [[TMP15:%.*]] = insertelement <4 x double> [[TMP13]], double [[TMP14]], i64 3
+; CHECK-NEXT:    [[TMP16:%.*]] = bitcast <8 x double>* [[PTR:%.*]] to double*
+; CHECK-NEXT:    [[TMP17:%.*]] = bitcast double* [[TMP16]] to <4 x double>*
+; CHECK-NEXT:    store <4 x double> [[TMP7]], <4 x double>* [[TMP17]], align 8
+; CHECK-NEXT:    [[TMP18:%.*]] = getelementptr double, double* [[TMP16]], i32 4
+; CHECK-NEXT:    [[TMP19:%.*]] = bitcast double* [[TMP18]] to <4 x double>*
+; CHECK-NEXT:    store <4 x double> [[TMP15]], <4 x double>* [[TMP19]], align 8
+; CHECK-NEXT:    ret void
+;
+entry:
+  %c  = call <8 x double> @llvm.matrix.transpose(<8 x double> %a, i32 2, i32 4)
+  store <8 x double> %c, <8 x double>* %Ptr
+  ret void
+}
+
+declare <8 x double> @llvm.matrix.transpose(<8 x double>, i32, i32)
diff --git a/llvm/test/Transforms/LowerMatrixIntrinsics/propagate-mixed-users.ll b/llvm/test/Transforms/LowerMatrixIntrinsics/propagate-mixed-users.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/LowerMatrixIntrinsics/propagate-mixed-users.ll
@@ -0,0 +1,53 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -lower-matrix-intrinsics -S < %s | FileCheck %s
+; RUN: opt -passes='lower-matrix-intrinsics' -S < %s | FileCheck %s
+
+; Currently we only lower stores with shape information, but need to embed the
+; matrix in a flat vector for function calls and returns.
+define <8 x double> @strided_load_4x4(<8 x double> %in, <8 x double>* %Ptr) {
+; CHECK-LABEL: @strided_load_4x4(
+; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <8 x double> [[IN:%.*]], <8 x double> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <8 x double> [[IN]], <8 x double> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x double> [[SPLIT]], i64 0
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x double> undef, double [[TMP1]], i64 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 0
+; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <2 x double> [[TMP2]], double [[TMP3]], i64 1
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x double> [[SPLIT]], i64 1
+; CHECK-NEXT:    [[TMP6:%.*]] = insertelement <2 x double> undef, double [[TMP5]], i64 0
+; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 1
+; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <2 x double> [[TMP6]], double [[TMP7]], i64 1
+; CHECK-NEXT:    [[TMP9:%.*]] = extractelement <4 x double> [[SPLIT]], i64 2
+; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <2 x double> undef, double [[TMP9]], i64 0
+; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 2
+; CHECK-NEXT:    [[TMP12:%.*]] = insertelement <2 x double> [[TMP10]], double [[TMP11]], i64 1
+; CHECK-NEXT:    [[TMP13:%.*]] = extractelement <4 x double> [[SPLIT]], i64 3
+; CHECK-NEXT:    [[TMP14:%.*]] = insertelement <2 x double> undef, double [[TMP13]], i64 0
+; CHECK-NEXT:    [[TMP15:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 3
+; CHECK-NEXT:    [[TMP16:%.*]] = insertelement <2 x double> [[TMP14]], double [[TMP15]], i64 1
+; CHECK-NEXT:    [[TMP17:%.*]] = shufflevector <2 x double> [[TMP4]], <2 x double> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[TMP18:%.*]] = shufflevector <2 x double> [[TMP12]], <2 x double> [[TMP16]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[TMP19:%.*]] = shufflevector <4 x double> [[TMP17]], <4 x double> [[TMP18]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:    [[TMP20:%.*]] = bitcast <8 x double>* [[PTR:%.*]] to double*
+; CHECK-NEXT:    [[TMP21:%.*]] = bitcast double* [[TMP20]] to <2 x double>*
+; CHECK-NEXT:    store <2 x double> [[TMP4]], <2 x double>* [[TMP21]], align 8
+; CHECK-NEXT:    [[TMP22:%.*]] = getelementptr double, double* [[TMP20]], i32 2
+; CHECK-NEXT:    [[TMP23:%.*]] = bitcast double* [[TMP22]] to <2 x double>*
+; CHECK-NEXT:    store <2 x double> [[TMP8]], <2 x double>* [[TMP23]], align 8
+; CHECK-NEXT:    [[TMP24:%.*]] = getelementptr double, double* [[TMP20]], i32 4
+; CHECK-NEXT:    [[TMP25:%.*]] = bitcast double* [[TMP24]] to <2 x double>*
+; CHECK-NEXT:    store <2 x double> [[TMP12]], <2 x double>* [[TMP25]], align 8
+; CHECK-NEXT:    [[TMP26:%.*]] = getelementptr double, double* [[TMP20]], i32 6
+; CHECK-NEXT:    [[TMP27:%.*]] = bitcast double* [[TMP26]] to <2 x double>*
+; CHECK-NEXT:    store <2 x double> [[TMP16]], <2 x double>* [[TMP27]], align 8
+; CHECK-NEXT:    call void @foo(<8 x double> [[TMP19]])
+; CHECK-NEXT:    ret <8 x double> [[TMP19]]
+;
+  %transposed = call <8 x double> @llvm.matrix.transpose(<8 x double> %in, i32 4, i32 2)
+  store <8 x double> %transposed, <8 x double>* %Ptr
+  call void @foo(<8 x double> %transposed)
+  ret <8 x double> %transposed
+}
+
+declare <8 x double> @llvm.matrix.transpose(<8 x double>, i32, i32)
+
+declare void @foo(<8 x double>)