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
@@ -982,9 +982,16 @@
     SmallPtrSet<Instruction *, 16> FusedInsts;
     for (CallInst *CI : MaybeFusableInsts)
       LowerMatrixMultiplyFused(CI, FusedInsts);
+
+    // Third, try to lower any dot products
+    for (CallInst *CI : MaybeFusableInsts) {
+      if (FusedInsts.find(CI) != FusedInsts.end()) // skip if already fused
+        continue;
+      lowerDotProduct(CI, FusedInsts, getFastMathFlags(CI));
+    }
     Changed = !FusedInsts.empty();
 
-    // Third, lower remaining instructions with shape information.
+    // Fourth, lower remaining instructions with shape information.
     for (Instruction *Inst : MatrixInsts) {
       if (FusedInsts.count(Inst))
         continue;
@@ -1311,6 +1318,101 @@
     }
   }
 
+  /// Special case for MatMul lowering. Prevents scalar loads of row-major
+  /// vectors Lowers to vector reduction add instead of sequential add if
+  /// reassocation is enabled.
+  void lowerDotProduct(CallInst *MatMul,
+                       SmallPtrSet<Instruction *, 16> &FusedInsts,
+                       FastMathFlags FMF) {
+    ShapeInfo LShape(MatMul->getArgOperand(2), MatMul->getArgOperand(3));
+    ShapeInfo RShape(MatMul->getArgOperand(3), MatMul->getArgOperand(4));
+
+    if (LShape.NumRows != 1 || RShape.NumColumns != 1) // not a dot product
+      return;
+
+    Value *LHS = MatMul->getArgOperand(0);
+    Value *RHS = MatMul->getArgOperand(1);
+
+    Type *ElementType = cast<VectorType>(LHS->getType())->getElementType();
+    bool IsIntVec = ElementType->isIntegerTy();
+
+    // Floating point reductions require reassocation.
+    if (!IsIntVec && !FMF.allowReassoc())
+      return;
+
+    auto IsSupportedArg = [](Value *Op, unsigned N) {
+      if (!isa<Instruction>(Op))
+        return true;
+      return match(Op, m_OneUse(m_CombineOr(
+                           m_Load(m_Value()),
+                           m_Intrinsic<Intrinsic::matrix_column_major_load>(
+                               m_Value(), m_SpecificInt(N)))));
+    };
+    if (!IsSupportedArg(RHS, RShape.NumColumns) ||
+        !IsSupportedArg(LHS, LShape.NumColumns))
+      return;
+
+    // We compare the costs of a vector.reduce.add to sequential add.
+    int AddOpCode = IsIntVec ? Instruction::Add : Instruction::FAdd;
+    FastMathFlags FMFReassoc;
+    FMFReassoc.setAllowReassoc();
+    InstructionCost ReductionCost = TTI.getArithmeticReductionCost(
+        AddOpCode, cast<VectorType>(LHS->getType()), FMFReassoc);
+    InstructionCost SequentialAddCost =
+        TTI.getArithmeticInstrCost(AddOpCode, ElementType) *
+        (LShape.NumColumns - 1);
+    if (ReductionCost >= SequentialAddCost)
+      return;
+
+    FusedInsts.insert(MatMul);
+    IRBuilder<> Builder(MatMul);
+    auto FlattenArg = [&Builder, &FusedInsts](Value *Op) -> Value * {
+      // Matmul must be the only user of loads because we don't use LowerLoad
+      // for row vectors (LowerLoad results in scalar loads and shufflevectors
+      // instead of single vector load).
+      if (!match(Op, m_CombineOr(
+                         m_Load(m_Value()),
+                         m_Intrinsic<Intrinsic::matrix_column_major_load>()))) {
+        return Op;
+      }
+      FusedInsts.insert(cast<Instruction>(Op));
+
+      // If vector uses the builtin load, lower to a LoadInst
+      Value *Ptr;
+      if (match(Op, m_Intrinsic<Intrinsic::matrix_column_major_load>(
+                        m_Value(Ptr)))) {
+        auto *NewLoad = Builder.CreateLoad(Op->getType(), Ptr);
+        Op->replaceAllUsesWith(NewLoad);
+        cast<Instruction>(Op)->eraseFromParent();
+        return NewLoad;
+      }
+      return Op;
+    };
+    LHS = FlattenArg(LHS);
+    RHS = FlattenArg(RHS);
+
+    // Insert mul/fmul and llvm.vector.reduce.fadd
+    Value *Mul =
+        IsIntVec ? Builder.CreateMul(LHS, RHS) : Builder.CreateFMul(LHS, RHS);
+
+    Value *Result;
+    if (IsIntVec)
+      Result = Builder.CreateAddReduce(Mul);
+    else {
+      Result = Builder.CreateFAddReduce(
+          ConstantFP::get(cast<VectorType>(LHS->getType())->getElementType(),
+                          0.0),
+          Mul);
+      cast<Instruction>(Result)->setFastMathFlags(FMF);
+    }
+
+    // pack scalar back into a matrix and then replace matmul inst
+    Result = Builder.CreateInsertElement(PoisonValue::get(MatMul->getType()),
+                                         Result, uint64_t(0));
+    MatMul->replaceAllUsesWith(Result);
+    MatMul->eraseFromParent();
+  }
+
   /// Compute \p Result += \p A * \p B for input matrices with left-associating
   /// addition.
   ///
diff --git a/llvm/test/Transforms/LowerMatrixIntrinsics/dot-product-int.ll b/llvm/test/Transforms/LowerMatrixIntrinsics/dot-product-int.ll
--- a/llvm/test/Transforms/LowerMatrixIntrinsics/dot-product-int.ll
+++ b/llvm/test/Transforms/LowerMatrixIntrinsics/dot-product-int.ll
@@ -5,65 +5,10 @@
 define <1 x i32> @dotproduct_i32_v8(<8 x i32> %a, <8 x i32> %b) {
 ; CHECK-LABEL: @dotproduct_i32_v8(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <8 x i32> [[A:%.*]], <8 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 3>
-; CHECK-NEXT:    [[SPLIT4:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 4>
-; CHECK-NEXT:    [[SPLIT5:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 5>
-; CHECK-NEXT:    [[SPLIT6:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 6>
-; CHECK-NEXT:    [[SPLIT7:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 7>
-; CHECK-NEXT:    [[SPLIT8:%.*]] = shufflevector <8 x i32> [[B:%.*]], <8 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:    [[BLOCK:%.*]] = shufflevector <1 x i32> [[SPLIT]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <8 x i32> [[SPLIT8]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x i32> poison, i32 [[TMP0]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP1:%.*]] = mul <1 x i32> [[BLOCK]], [[SPLAT_SPLAT]]
-; CHECK-NEXT:    [[BLOCK9:%.*]] = shufflevector <1 x i32> [[SPLIT1]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <8 x i32> [[SPLIT8]], i64 1
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT10:%.*]] = insertelement <1 x i32> poison, i32 [[TMP2]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT11:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT10]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP3:%.*]] = mul <1 x i32> [[BLOCK9]], [[SPLAT_SPLAT11]]
-; CHECK-NEXT:    [[TMP4:%.*]] = add <1 x i32> [[TMP1]], [[TMP3]]
-; CHECK-NEXT:    [[BLOCK12:%.*]] = shufflevector <1 x i32> [[SPLIT2]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <8 x i32> [[SPLIT8]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT13:%.*]] = insertelement <1 x i32> poison, i32 [[TMP5]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT14:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT13]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP6:%.*]] = mul <1 x i32> [[BLOCK12]], [[SPLAT_SPLAT14]]
-; CHECK-NEXT:    [[TMP7:%.*]] = add <1 x i32> [[TMP4]], [[TMP6]]
-; CHECK-NEXT:    [[BLOCK15:%.*]] = shufflevector <1 x i32> [[SPLIT3]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <8 x i32> [[SPLIT8]], i64 3
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT16:%.*]] = insertelement <1 x i32> poison, i32 [[TMP8]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT17:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT16]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP9:%.*]] = mul <1 x i32> [[BLOCK15]], [[SPLAT_SPLAT17]]
-; CHECK-NEXT:    [[TMP10:%.*]] = add <1 x i32> [[TMP7]], [[TMP9]]
-; CHECK-NEXT:    [[BLOCK18:%.*]] = shufflevector <1 x i32> [[SPLIT4]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <8 x i32> [[SPLIT8]], i64 4
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT19:%.*]] = insertelement <1 x i32> poison, i32 [[TMP11]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT20:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT19]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP12:%.*]] = mul <1 x i32> [[BLOCK18]], [[SPLAT_SPLAT20]]
-; CHECK-NEXT:    [[TMP13:%.*]] = add <1 x i32> [[TMP10]], [[TMP12]]
-; CHECK-NEXT:    [[BLOCK21:%.*]] = shufflevector <1 x i32> [[SPLIT5]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <8 x i32> [[SPLIT8]], i64 5
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT22:%.*]] = insertelement <1 x i32> poison, i32 [[TMP14]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT23:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT22]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP15:%.*]] = mul <1 x i32> [[BLOCK21]], [[SPLAT_SPLAT23]]
-; CHECK-NEXT:    [[TMP16:%.*]] = add <1 x i32> [[TMP13]], [[TMP15]]
-; CHECK-NEXT:    [[BLOCK24:%.*]] = shufflevector <1 x i32> [[SPLIT6]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP17:%.*]] = extractelement <8 x i32> [[SPLIT8]], i64 6
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT25:%.*]] = insertelement <1 x i32> poison, i32 [[TMP17]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT26:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT25]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP18:%.*]] = mul <1 x i32> [[BLOCK24]], [[SPLAT_SPLAT26]]
-; CHECK-NEXT:    [[TMP19:%.*]] = add <1 x i32> [[TMP16]], [[TMP18]]
-; CHECK-NEXT:    [[BLOCK27:%.*]] = shufflevector <1 x i32> [[SPLIT7]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <8 x i32> [[SPLIT8]], i64 7
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT28:%.*]] = insertelement <1 x i32> poison, i32 [[TMP20]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT29:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT28]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP21:%.*]] = mul <1 x i32> [[BLOCK27]], [[SPLAT_SPLAT29]]
-; CHECK-NEXT:    [[TMP22:%.*]] = add <1 x i32> [[TMP19]], [[TMP21]]
-; CHECK-NEXT:    [[TMP23:%.*]] = shufflevector <1 x i32> [[TMP22]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP24:%.*]] = shufflevector <1 x i32> undef, <1 x i32> [[TMP23]], <1 x i32> <i32 1>
-; CHECK-NEXT:    ret <1 x i32> [[TMP24]]
+; CHECK-NEXT:    [[TMP0:%.*]] = mul <8 x i32> [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <1 x i32> poison, i32 [[TMP1]], i64 0
+; CHECK-NEXT:    ret <1 x i32> [[TMP2]]
 ;
 entry:
   %c = tail call <1 x i32> @llvm.matrix.multiply.v1i32.v8i32.v8i32(<8 x i32> %a, <8 x i32> %b, i32 1, i32 8, i32 1)
@@ -77,66 +22,11 @@
 define <1 x i32> @dotproduct_i32_v8_result_used_by_inst(<8 x i32> %a, <8 x i32> %b) {
 ; CHECK-LABEL: @dotproduct_i32_v8_result_used_by_inst(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <8 x i32> [[A:%.*]], <8 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 3>
-; CHECK-NEXT:    [[SPLIT4:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 4>
-; CHECK-NEXT:    [[SPLIT5:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 5>
-; CHECK-NEXT:    [[SPLIT6:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 6>
-; CHECK-NEXT:    [[SPLIT7:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 7>
-; CHECK-NEXT:    [[SPLIT8:%.*]] = shufflevector <8 x i32> [[B:%.*]], <8 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:    [[BLOCK:%.*]] = shufflevector <1 x i32> [[SPLIT]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <8 x i32> [[SPLIT8]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x i32> poison, i32 [[TMP0]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP1:%.*]] = mul <1 x i32> [[BLOCK]], [[SPLAT_SPLAT]]
-; CHECK-NEXT:    [[BLOCK9:%.*]] = shufflevector <1 x i32> [[SPLIT1]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <8 x i32> [[SPLIT8]], i64 1
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT10:%.*]] = insertelement <1 x i32> poison, i32 [[TMP2]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT11:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT10]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP3:%.*]] = mul <1 x i32> [[BLOCK9]], [[SPLAT_SPLAT11]]
-; CHECK-NEXT:    [[TMP4:%.*]] = add <1 x i32> [[TMP1]], [[TMP3]]
-; CHECK-NEXT:    [[BLOCK12:%.*]] = shufflevector <1 x i32> [[SPLIT2]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <8 x i32> [[SPLIT8]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT13:%.*]] = insertelement <1 x i32> poison, i32 [[TMP5]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT14:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT13]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP6:%.*]] = mul <1 x i32> [[BLOCK12]], [[SPLAT_SPLAT14]]
-; CHECK-NEXT:    [[TMP7:%.*]] = add <1 x i32> [[TMP4]], [[TMP6]]
-; CHECK-NEXT:    [[BLOCK15:%.*]] = shufflevector <1 x i32> [[SPLIT3]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <8 x i32> [[SPLIT8]], i64 3
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT16:%.*]] = insertelement <1 x i32> poison, i32 [[TMP8]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT17:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT16]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP9:%.*]] = mul <1 x i32> [[BLOCK15]], [[SPLAT_SPLAT17]]
-; CHECK-NEXT:    [[TMP10:%.*]] = add <1 x i32> [[TMP7]], [[TMP9]]
-; CHECK-NEXT:    [[BLOCK18:%.*]] = shufflevector <1 x i32> [[SPLIT4]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <8 x i32> [[SPLIT8]], i64 4
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT19:%.*]] = insertelement <1 x i32> poison, i32 [[TMP11]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT20:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT19]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP12:%.*]] = mul <1 x i32> [[BLOCK18]], [[SPLAT_SPLAT20]]
-; CHECK-NEXT:    [[TMP13:%.*]] = add <1 x i32> [[TMP10]], [[TMP12]]
-; CHECK-NEXT:    [[BLOCK21:%.*]] = shufflevector <1 x i32> [[SPLIT5]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <8 x i32> [[SPLIT8]], i64 5
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT22:%.*]] = insertelement <1 x i32> poison, i32 [[TMP14]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT23:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT22]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP15:%.*]] = mul <1 x i32> [[BLOCK21]], [[SPLAT_SPLAT23]]
-; CHECK-NEXT:    [[TMP16:%.*]] = add <1 x i32> [[TMP13]], [[TMP15]]
-; CHECK-NEXT:    [[BLOCK24:%.*]] = shufflevector <1 x i32> [[SPLIT6]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP17:%.*]] = extractelement <8 x i32> [[SPLIT8]], i64 6
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT25:%.*]] = insertelement <1 x i32> poison, i32 [[TMP17]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT26:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT25]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP18:%.*]] = mul <1 x i32> [[BLOCK24]], [[SPLAT_SPLAT26]]
-; CHECK-NEXT:    [[TMP19:%.*]] = add <1 x i32> [[TMP16]], [[TMP18]]
-; CHECK-NEXT:    [[BLOCK27:%.*]] = shufflevector <1 x i32> [[SPLIT7]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <8 x i32> [[SPLIT8]], i64 7
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT28:%.*]] = insertelement <1 x i32> poison, i32 [[TMP20]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT29:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT28]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP21:%.*]] = mul <1 x i32> [[BLOCK27]], [[SPLAT_SPLAT29]]
-; CHECK-NEXT:    [[TMP22:%.*]] = add <1 x i32> [[TMP19]], [[TMP21]]
-; CHECK-NEXT:    [[TMP23:%.*]] = shufflevector <1 x i32> [[TMP22]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP24:%.*]] = shufflevector <1 x i32> undef, <1 x i32> [[TMP23]], <1 x i32> <i32 1>
-; CHECK-NEXT:    call void @use(<1 x i32> [[TMP24]])
-; CHECK-NEXT:    ret <1 x i32> [[TMP24]]
+; CHECK-NEXT:    [[TMP0:%.*]] = mul <8 x i32> [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <1 x i32> poison, i32 [[TMP1]], i64 0
+; CHECK-NEXT:    call void @use(<1 x i32> [[TMP2]])
+; CHECK-NEXT:    ret <1 x i32> [[TMP2]]
 ;
 entry:
   %c = tail call <1 x i32> @llvm.matrix.multiply.v1i32.v8i32.v8i32(<8 x i32> %a, <8 x i32> %b, i32 1, i32 8, i32 1)
@@ -148,40 +38,10 @@
 define <1 x i32> @dotproduct_i32_v8_constvector(<8 x i32> %a) {
 ; CHECK-LABEL: @dotproduct_i32_v8_constvector(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <8 x i32> [[A:%.*]], <8 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 3>
-; CHECK-NEXT:    [[SPLIT4:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 4>
-; CHECK-NEXT:    [[SPLIT5:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 5>
-; CHECK-NEXT:    [[SPLIT6:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 6>
-; CHECK-NEXT:    [[SPLIT7:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> poison, <1 x i32> <i32 7>
-; CHECK-NEXT:    [[BLOCK:%.*]] = shufflevector <1 x i32> [[SPLIT]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP0:%.*]] = mul <1 x i32> [[BLOCK]], <i32 1>
-; CHECK-NEXT:    [[BLOCK8:%.*]] = shufflevector <1 x i32> [[SPLIT1]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP1:%.*]] = mul <1 x i32> [[BLOCK8]], <i32 2>
-; CHECK-NEXT:    [[TMP2:%.*]] = add <1 x i32> [[TMP0]], [[TMP1]]
-; CHECK-NEXT:    [[BLOCK9:%.*]] = shufflevector <1 x i32> [[SPLIT2]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP3:%.*]] = mul <1 x i32> [[BLOCK9]], <i32 3>
-; CHECK-NEXT:    [[TMP4:%.*]] = add <1 x i32> [[TMP2]], [[TMP3]]
-; CHECK-NEXT:    [[BLOCK10:%.*]] = shufflevector <1 x i32> [[SPLIT3]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP5:%.*]] = mul <1 x i32> [[BLOCK10]], <i32 4>
-; CHECK-NEXT:    [[TMP6:%.*]] = add <1 x i32> [[TMP4]], [[TMP5]]
-; CHECK-NEXT:    [[BLOCK11:%.*]] = shufflevector <1 x i32> [[SPLIT4]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP7:%.*]] = mul <1 x i32> [[BLOCK11]], <i32 5>
-; CHECK-NEXT:    [[TMP8:%.*]] = add <1 x i32> [[TMP6]], [[TMP7]]
-; CHECK-NEXT:    [[BLOCK12:%.*]] = shufflevector <1 x i32> [[SPLIT5]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP9:%.*]] = mul <1 x i32> [[BLOCK12]], <i32 6>
-; CHECK-NEXT:    [[TMP10:%.*]] = add <1 x i32> [[TMP8]], [[TMP9]]
-; CHECK-NEXT:    [[BLOCK13:%.*]] = shufflevector <1 x i32> [[SPLIT6]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP11:%.*]] = mul <1 x i32> [[BLOCK13]], <i32 7>
-; CHECK-NEXT:    [[TMP12:%.*]] = add <1 x i32> [[TMP10]], [[TMP11]]
-; CHECK-NEXT:    [[BLOCK14:%.*]] = shufflevector <1 x i32> [[SPLIT7]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP13:%.*]] = mul <1 x i32> [[BLOCK14]], <i32 8>
-; CHECK-NEXT:    [[TMP14:%.*]] = add <1 x i32> [[TMP12]], [[TMP13]]
-; CHECK-NEXT:    [[TMP15:%.*]] = shufflevector <1 x i32> [[TMP14]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP16:%.*]] = shufflevector <1 x i32> undef, <1 x i32> [[TMP15]], <1 x i32> <i32 1>
-; CHECK-NEXT:    ret <1 x i32> [[TMP16]]
+; CHECK-NEXT:    [[TMP0:%.*]] = mul <8 x i32> [[A:%.*]], <i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <1 x i32> poison, i32 [[TMP1]], i64 0
+; CHECK-NEXT:    ret <1 x i32> [[TMP2]]
 ;
 entry:
   %c = tail call <1 x i32> @llvm.matrix.multiply.v1i32.v8i32.v8i32(<8 x i32> %a, <8 x i32> <i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>, i32 1, i32 8, i32 1)
@@ -463,65 +323,10 @@
 define <1 x i64> @dotproduct_i64_v8(<8 x i64> %a, <8 x i64> %b) {
 ; CHECK-LABEL: @dotproduct_i64_v8(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <8 x i64> [[A:%.*]], <8 x i64> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <8 x i64> [[A]], <8 x i64> poison, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <8 x i64> [[A]], <8 x i64> poison, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <8 x i64> [[A]], <8 x i64> poison, <1 x i32> <i32 3>
-; CHECK-NEXT:    [[SPLIT4:%.*]] = shufflevector <8 x i64> [[A]], <8 x i64> poison, <1 x i32> <i32 4>
-; CHECK-NEXT:    [[SPLIT5:%.*]] = shufflevector <8 x i64> [[A]], <8 x i64> poison, <1 x i32> <i32 5>
-; CHECK-NEXT:    [[SPLIT6:%.*]] = shufflevector <8 x i64> [[A]], <8 x i64> poison, <1 x i32> <i32 6>
-; CHECK-NEXT:    [[SPLIT7:%.*]] = shufflevector <8 x i64> [[A]], <8 x i64> poison, <1 x i32> <i32 7>
-; CHECK-NEXT:    [[SPLIT8:%.*]] = shufflevector <8 x i64> [[B:%.*]], <8 x i64> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:    [[BLOCK:%.*]] = shufflevector <1 x i64> [[SPLIT]], <1 x i64> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <8 x i64> [[SPLIT8]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x i64> poison, i64 [[TMP0]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <1 x i64> [[SPLAT_SPLATINSERT]], <1 x i64> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP1:%.*]] = mul <1 x i64> [[BLOCK]], [[SPLAT_SPLAT]]
-; CHECK-NEXT:    [[BLOCK9:%.*]] = shufflevector <1 x i64> [[SPLIT1]], <1 x i64> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <8 x i64> [[SPLIT8]], i64 1
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT10:%.*]] = insertelement <1 x i64> poison, i64 [[TMP2]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT11:%.*]] = shufflevector <1 x i64> [[SPLAT_SPLATINSERT10]], <1 x i64> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP3:%.*]] = mul <1 x i64> [[BLOCK9]], [[SPLAT_SPLAT11]]
-; CHECK-NEXT:    [[TMP4:%.*]] = add <1 x i64> [[TMP1]], [[TMP3]]
-; CHECK-NEXT:    [[BLOCK12:%.*]] = shufflevector <1 x i64> [[SPLIT2]], <1 x i64> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <8 x i64> [[SPLIT8]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT13:%.*]] = insertelement <1 x i64> poison, i64 [[TMP5]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT14:%.*]] = shufflevector <1 x i64> [[SPLAT_SPLATINSERT13]], <1 x i64> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP6:%.*]] = mul <1 x i64> [[BLOCK12]], [[SPLAT_SPLAT14]]
-; CHECK-NEXT:    [[TMP7:%.*]] = add <1 x i64> [[TMP4]], [[TMP6]]
-; CHECK-NEXT:    [[BLOCK15:%.*]] = shufflevector <1 x i64> [[SPLIT3]], <1 x i64> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <8 x i64> [[SPLIT8]], i64 3
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT16:%.*]] = insertelement <1 x i64> poison, i64 [[TMP8]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT17:%.*]] = shufflevector <1 x i64> [[SPLAT_SPLATINSERT16]], <1 x i64> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP9:%.*]] = mul <1 x i64> [[BLOCK15]], [[SPLAT_SPLAT17]]
-; CHECK-NEXT:    [[TMP10:%.*]] = add <1 x i64> [[TMP7]], [[TMP9]]
-; CHECK-NEXT:    [[BLOCK18:%.*]] = shufflevector <1 x i64> [[SPLIT4]], <1 x i64> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <8 x i64> [[SPLIT8]], i64 4
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT19:%.*]] = insertelement <1 x i64> poison, i64 [[TMP11]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT20:%.*]] = shufflevector <1 x i64> [[SPLAT_SPLATINSERT19]], <1 x i64> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP12:%.*]] = mul <1 x i64> [[BLOCK18]], [[SPLAT_SPLAT20]]
-; CHECK-NEXT:    [[TMP13:%.*]] = add <1 x i64> [[TMP10]], [[TMP12]]
-; CHECK-NEXT:    [[BLOCK21:%.*]] = shufflevector <1 x i64> [[SPLIT5]], <1 x i64> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <8 x i64> [[SPLIT8]], i64 5
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT22:%.*]] = insertelement <1 x i64> poison, i64 [[TMP14]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT23:%.*]] = shufflevector <1 x i64> [[SPLAT_SPLATINSERT22]], <1 x i64> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP15:%.*]] = mul <1 x i64> [[BLOCK21]], [[SPLAT_SPLAT23]]
-; CHECK-NEXT:    [[TMP16:%.*]] = add <1 x i64> [[TMP13]], [[TMP15]]
-; CHECK-NEXT:    [[BLOCK24:%.*]] = shufflevector <1 x i64> [[SPLIT6]], <1 x i64> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP17:%.*]] = extractelement <8 x i64> [[SPLIT8]], i64 6
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT25:%.*]] = insertelement <1 x i64> poison, i64 [[TMP17]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT26:%.*]] = shufflevector <1 x i64> [[SPLAT_SPLATINSERT25]], <1 x i64> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP18:%.*]] = mul <1 x i64> [[BLOCK24]], [[SPLAT_SPLAT26]]
-; CHECK-NEXT:    [[TMP19:%.*]] = add <1 x i64> [[TMP16]], [[TMP18]]
-; CHECK-NEXT:    [[BLOCK27:%.*]] = shufflevector <1 x i64> [[SPLIT7]], <1 x i64> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <8 x i64> [[SPLIT8]], i64 7
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT28:%.*]] = insertelement <1 x i64> poison, i64 [[TMP20]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT29:%.*]] = shufflevector <1 x i64> [[SPLAT_SPLATINSERT28]], <1 x i64> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP21:%.*]] = mul <1 x i64> [[BLOCK27]], [[SPLAT_SPLAT29]]
-; CHECK-NEXT:    [[TMP22:%.*]] = add <1 x i64> [[TMP19]], [[TMP21]]
-; CHECK-NEXT:    [[TMP23:%.*]] = shufflevector <1 x i64> [[TMP22]], <1 x i64> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP24:%.*]] = shufflevector <1 x i64> undef, <1 x i64> [[TMP23]], <1 x i32> <i32 1>
-; CHECK-NEXT:    ret <1 x i64> [[TMP24]]
+; CHECK-NEXT:    [[TMP0:%.*]] = mul <8 x i64> [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <1 x i64> poison, i64 [[TMP1]], i64 0
+; CHECK-NEXT:    ret <1 x i64> [[TMP2]]
 ;
 entry:
   %c = tail call <1 x i64> @llvm.matrix.multiply.v1i64.v8i64.v8i64(<8 x i64> %a, <8 x i64> %b, i32 1, i32 8, i32 1)
@@ -533,88 +338,12 @@
 define <1 x i32> @intrinsic_column_major_load_dot_product_i32_v8(ptr %lhs_address, ptr %rhs_address) {
 ; CHECK-LABEL: @intrinsic_column_major_load_dot_product_i32_v8(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[COL_LOAD:%.*]] = load <8 x i32>, ptr [[LHS_ADDRESS:%.*]], align 4
-; CHECK-NEXT:    [[COL_LOAD1:%.*]] = load <1 x i32>, ptr [[RHS_ADDRESS:%.*]], align 4
-; CHECK-NEXT:    [[VEC_GEP:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 1
-; CHECK-NEXT:    [[COL_LOAD2:%.*]] = load <1 x i32>, ptr [[VEC_GEP]], align 4
-; CHECK-NEXT:    [[VEC_GEP3:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 2
-; CHECK-NEXT:    [[COL_LOAD4:%.*]] = load <1 x i32>, ptr [[VEC_GEP3]], align 4
-; CHECK-NEXT:    [[VEC_GEP5:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 3
-; CHECK-NEXT:    [[COL_LOAD6:%.*]] = load <1 x i32>, ptr [[VEC_GEP5]], align 4
-; CHECK-NEXT:    [[VEC_GEP7:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 4
-; CHECK-NEXT:    [[COL_LOAD8:%.*]] = load <1 x i32>, ptr [[VEC_GEP7]], align 4
-; CHECK-NEXT:    [[VEC_GEP9:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 5
-; CHECK-NEXT:    [[COL_LOAD10:%.*]] = load <1 x i32>, ptr [[VEC_GEP9]], align 4
-; CHECK-NEXT:    [[VEC_GEP11:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 6
-; CHECK-NEXT:    [[COL_LOAD12:%.*]] = load <1 x i32>, ptr [[VEC_GEP11]], align 4
-; CHECK-NEXT:    [[VEC_GEP13:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 7
-; CHECK-NEXT:    [[COL_LOAD14:%.*]] = load <1 x i32>, ptr [[VEC_GEP13]], align 4
-; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <8 x i32> [[COL_LOAD]], <8 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[SPLIT15:%.*]] = shufflevector <8 x i32> [[COL_LOAD]], <8 x i32> poison, <1 x i32> <i32 1>
-; CHECK-NEXT:    [[SPLIT16:%.*]] = shufflevector <8 x i32> [[COL_LOAD]], <8 x i32> poison, <1 x i32> <i32 2>
-; CHECK-NEXT:    [[SPLIT17:%.*]] = shufflevector <8 x i32> [[COL_LOAD]], <8 x i32> poison, <1 x i32> <i32 3>
-; CHECK-NEXT:    [[SPLIT18:%.*]] = shufflevector <8 x i32> [[COL_LOAD]], <8 x i32> poison, <1 x i32> <i32 4>
-; CHECK-NEXT:    [[SPLIT19:%.*]] = shufflevector <8 x i32> [[COL_LOAD]], <8 x i32> poison, <1 x i32> <i32 5>
-; CHECK-NEXT:    [[SPLIT20:%.*]] = shufflevector <8 x i32> [[COL_LOAD]], <8 x i32> poison, <1 x i32> <i32 6>
-; CHECK-NEXT:    [[SPLIT21:%.*]] = shufflevector <8 x i32> [[COL_LOAD]], <8 x i32> poison, <1 x i32> <i32 7>
-; CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <1 x i32> [[COL_LOAD1]], <1 x i32> [[COL_LOAD2]], <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <1 x i32> [[COL_LOAD4]], <1 x i32> [[COL_LOAD6]], <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <1 x i32> [[COL_LOAD8]], <1 x i32> [[COL_LOAD10]], <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <1 x i32> [[COL_LOAD12]], <1 x i32> [[COL_LOAD14]], <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <2 x i32> [[TMP0]], <2 x i32> [[TMP1]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT:    [[TMP5:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> [[TMP3]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT:    [[TMP6:%.*]] = shufflevector <4 x i32> [[TMP4]], <4 x i32> [[TMP5]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:    [[SPLIT22:%.*]] = shufflevector <8 x i32> [[TMP6]], <8 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:    [[BLOCK:%.*]] = shufflevector <1 x i32> [[SPLIT]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <8 x i32> [[SPLIT22]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x i32> poison, i32 [[TMP7]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP8:%.*]] = mul <1 x i32> [[BLOCK]], [[SPLAT_SPLAT]]
-; CHECK-NEXT:    [[BLOCK23:%.*]] = shufflevector <1 x i32> [[SPLIT15]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP9:%.*]] = extractelement <8 x i32> [[SPLIT22]], i64 1
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT24:%.*]] = insertelement <1 x i32> poison, i32 [[TMP9]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT25:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT24]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP10:%.*]] = mul <1 x i32> [[BLOCK23]], [[SPLAT_SPLAT25]]
-; CHECK-NEXT:    [[TMP11:%.*]] = add <1 x i32> [[TMP8]], [[TMP10]]
-; CHECK-NEXT:    [[BLOCK26:%.*]] = shufflevector <1 x i32> [[SPLIT16]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <8 x i32> [[SPLIT22]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT27:%.*]] = insertelement <1 x i32> poison, i32 [[TMP12]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT28:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT27]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP13:%.*]] = mul <1 x i32> [[BLOCK26]], [[SPLAT_SPLAT28]]
-; CHECK-NEXT:    [[TMP14:%.*]] = add <1 x i32> [[TMP11]], [[TMP13]]
-; CHECK-NEXT:    [[BLOCK29:%.*]] = shufflevector <1 x i32> [[SPLIT17]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP15:%.*]] = extractelement <8 x i32> [[SPLIT22]], i64 3
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT30:%.*]] = insertelement <1 x i32> poison, i32 [[TMP15]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT31:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT30]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP16:%.*]] = mul <1 x i32> [[BLOCK29]], [[SPLAT_SPLAT31]]
-; CHECK-NEXT:    [[TMP17:%.*]] = add <1 x i32> [[TMP14]], [[TMP16]]
-; CHECK-NEXT:    [[BLOCK32:%.*]] = shufflevector <1 x i32> [[SPLIT18]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <8 x i32> [[SPLIT22]], i64 4
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT33:%.*]] = insertelement <1 x i32> poison, i32 [[TMP18]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT34:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT33]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP19:%.*]] = mul <1 x i32> [[BLOCK32]], [[SPLAT_SPLAT34]]
-; CHECK-NEXT:    [[TMP20:%.*]] = add <1 x i32> [[TMP17]], [[TMP19]]
-; CHECK-NEXT:    [[BLOCK35:%.*]] = shufflevector <1 x i32> [[SPLIT19]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP21:%.*]] = extractelement <8 x i32> [[SPLIT22]], i64 5
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT36:%.*]] = insertelement <1 x i32> poison, i32 [[TMP21]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT37:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT36]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP22:%.*]] = mul <1 x i32> [[BLOCK35]], [[SPLAT_SPLAT37]]
-; CHECK-NEXT:    [[TMP23:%.*]] = add <1 x i32> [[TMP20]], [[TMP22]]
-; CHECK-NEXT:    [[BLOCK38:%.*]] = shufflevector <1 x i32> [[SPLIT20]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP24:%.*]] = extractelement <8 x i32> [[SPLIT22]], i64 6
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT39:%.*]] = insertelement <1 x i32> poison, i32 [[TMP24]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT40:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT39]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP25:%.*]] = mul <1 x i32> [[BLOCK38]], [[SPLAT_SPLAT40]]
-; CHECK-NEXT:    [[TMP26:%.*]] = add <1 x i32> [[TMP23]], [[TMP25]]
-; CHECK-NEXT:    [[BLOCK41:%.*]] = shufflevector <1 x i32> [[SPLIT21]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP27:%.*]] = extractelement <8 x i32> [[SPLIT22]], i64 7
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT42:%.*]] = insertelement <1 x i32> poison, i32 [[TMP27]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT43:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT42]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP28:%.*]] = mul <1 x i32> [[BLOCK41]], [[SPLAT_SPLAT43]]
-; CHECK-NEXT:    [[TMP29:%.*]] = add <1 x i32> [[TMP26]], [[TMP28]]
-; CHECK-NEXT:    [[TMP30:%.*]] = shufflevector <1 x i32> [[TMP29]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP31:%.*]] = shufflevector <1 x i32> undef, <1 x i32> [[TMP30]], <1 x i32> <i32 1>
-; CHECK-NEXT:    ret <1 x i32> [[TMP31]]
+; CHECK-NEXT:    [[TMP0:%.*]] = load <8 x i32>, ptr [[LHS_ADDRESS:%.*]], align 32
+; CHECK-NEXT:    [[TMP1:%.*]] = load <8 x i32>, ptr [[RHS_ADDRESS:%.*]], align 32
+; CHECK-NEXT:    [[TMP2:%.*]] = mul <8 x i32> [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> [[TMP2]])
+; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <1 x i32> poison, i32 [[TMP3]], i64 0
+; CHECK-NEXT:    ret <1 x i32> [[TMP4]]
 ;
 entry:
   %lhs = tail call <8 x i32> @llvm.matrix.column.major.load.v8i32.i64(ptr nonnull align 4 %lhs_address, i64 8, i1 false, i32 8, i32 1)
@@ -740,56 +469,12 @@
 define <1 x i16> @LoadInst_dot_product_i16_v6(ptr %lhs_address, ptr %rhs_address) {
 ; CHECK-LABEL: @LoadInst_dot_product_i16_v6(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[COL_LOAD:%.*]] = load <1 x i16>, ptr [[LHS_ADDRESS:%.*]], align 16
-; CHECK-NEXT:    [[VEC_GEP:%.*]] = getelementptr i16, ptr [[LHS_ADDRESS]], i64 1
-; CHECK-NEXT:    [[COL_LOAD1:%.*]] = load <1 x i16>, ptr [[VEC_GEP]], align 2
-; CHECK-NEXT:    [[VEC_GEP2:%.*]] = getelementptr i16, ptr [[LHS_ADDRESS]], i64 2
-; CHECK-NEXT:    [[COL_LOAD3:%.*]] = load <1 x i16>, ptr [[VEC_GEP2]], align 4
-; CHECK-NEXT:    [[VEC_GEP4:%.*]] = getelementptr i16, ptr [[LHS_ADDRESS]], i64 3
-; CHECK-NEXT:    [[COL_LOAD5:%.*]] = load <1 x i16>, ptr [[VEC_GEP4]], align 2
-; CHECK-NEXT:    [[VEC_GEP6:%.*]] = getelementptr i16, ptr [[LHS_ADDRESS]], i64 4
-; CHECK-NEXT:    [[COL_LOAD7:%.*]] = load <1 x i16>, ptr [[VEC_GEP6]], align 8
-; CHECK-NEXT:    [[VEC_GEP8:%.*]] = getelementptr i16, ptr [[LHS_ADDRESS]], i64 5
-; CHECK-NEXT:    [[COL_LOAD9:%.*]] = load <1 x i16>, ptr [[VEC_GEP8]], align 2
-; CHECK-NEXT:    [[COL_LOAD10:%.*]] = load <6 x i16>, ptr [[RHS_ADDRESS:%.*]], align 16
-; CHECK-NEXT:    [[BLOCK:%.*]] = shufflevector <1 x i16> [[COL_LOAD]], <1 x i16> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <6 x i16> [[COL_LOAD10]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x i16> poison, i16 [[TMP0]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <1 x i16> [[SPLAT_SPLATINSERT]], <1 x i16> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP1:%.*]] = mul <1 x i16> [[BLOCK]], [[SPLAT_SPLAT]]
-; CHECK-NEXT:    [[BLOCK11:%.*]] = shufflevector <1 x i16> [[COL_LOAD1]], <1 x i16> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <6 x i16> [[COL_LOAD10]], i64 1
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT12:%.*]] = insertelement <1 x i16> poison, i16 [[TMP2]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT13:%.*]] = shufflevector <1 x i16> [[SPLAT_SPLATINSERT12]], <1 x i16> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP3:%.*]] = mul <1 x i16> [[BLOCK11]], [[SPLAT_SPLAT13]]
-; CHECK-NEXT:    [[TMP4:%.*]] = add <1 x i16> [[TMP1]], [[TMP3]]
-; CHECK-NEXT:    [[BLOCK14:%.*]] = shufflevector <1 x i16> [[COL_LOAD3]], <1 x i16> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <6 x i16> [[COL_LOAD10]], i64 2
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT15:%.*]] = insertelement <1 x i16> poison, i16 [[TMP5]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT16:%.*]] = shufflevector <1 x i16> [[SPLAT_SPLATINSERT15]], <1 x i16> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP6:%.*]] = mul <1 x i16> [[BLOCK14]], [[SPLAT_SPLAT16]]
-; CHECK-NEXT:    [[TMP7:%.*]] = add <1 x i16> [[TMP4]], [[TMP6]]
-; CHECK-NEXT:    [[BLOCK17:%.*]] = shufflevector <1 x i16> [[COL_LOAD5]], <1 x i16> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <6 x i16> [[COL_LOAD10]], i64 3
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT18:%.*]] = insertelement <1 x i16> poison, i16 [[TMP8]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT19:%.*]] = shufflevector <1 x i16> [[SPLAT_SPLATINSERT18]], <1 x i16> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP9:%.*]] = mul <1 x i16> [[BLOCK17]], [[SPLAT_SPLAT19]]
-; CHECK-NEXT:    [[TMP10:%.*]] = add <1 x i16> [[TMP7]], [[TMP9]]
-; CHECK-NEXT:    [[BLOCK20:%.*]] = shufflevector <1 x i16> [[COL_LOAD7]], <1 x i16> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <6 x i16> [[COL_LOAD10]], i64 4
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT21:%.*]] = insertelement <1 x i16> poison, i16 [[TMP11]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT22:%.*]] = shufflevector <1 x i16> [[SPLAT_SPLATINSERT21]], <1 x i16> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP12:%.*]] = mul <1 x i16> [[BLOCK20]], [[SPLAT_SPLAT22]]
-; CHECK-NEXT:    [[TMP13:%.*]] = add <1 x i16> [[TMP10]], [[TMP12]]
-; CHECK-NEXT:    [[BLOCK23:%.*]] = shufflevector <1 x i16> [[COL_LOAD9]], <1 x i16> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <6 x i16> [[COL_LOAD10]], i64 5
-; CHECK-NEXT:    [[SPLAT_SPLATINSERT24:%.*]] = insertelement <1 x i16> poison, i16 [[TMP14]], i64 0
-; CHECK-NEXT:    [[SPLAT_SPLAT25:%.*]] = shufflevector <1 x i16> [[SPLAT_SPLATINSERT24]], <1 x i16> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP15:%.*]] = mul <1 x i16> [[BLOCK23]], [[SPLAT_SPLAT25]]
-; CHECK-NEXT:    [[TMP16:%.*]] = add <1 x i16> [[TMP13]], [[TMP15]]
-; CHECK-NEXT:    [[TMP17:%.*]] = shufflevector <1 x i16> [[TMP16]], <1 x i16> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP18:%.*]] = shufflevector <1 x i16> undef, <1 x i16> [[TMP17]], <1 x i32> <i32 1>
-; CHECK-NEXT:    ret <1 x i16> [[TMP18]]
+; CHECK-NEXT:    [[LHS:%.*]] = load <6 x i16>, ptr [[LHS_ADDRESS:%.*]], align 16
+; CHECK-NEXT:    [[RHS:%.*]] = load <6 x i16>, ptr [[RHS_ADDRESS:%.*]], align 16
+; CHECK-NEXT:    [[TMP0:%.*]] = mul <6 x i16> [[LHS]], [[RHS]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call i16 @llvm.vector.reduce.add.v6i16(<6 x i16> [[TMP0]])
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <1 x i16> poison, i16 [[TMP1]], i64 0
+; CHECK-NEXT:    ret <1 x i16> [[TMP2]]
 ;
 entry:
   %lhs = load <6 x i16>, ptr %lhs_address