diff --git a/llvm/lib/IR/Verifier.cpp b/llvm/lib/IR/Verifier.cpp
index a31a91766ebe..b0b9af9ff573 100644
--- a/llvm/lib/IR/Verifier.cpp
+++ b/llvm/lib/IR/Verifier.cpp
@@ -4791,6 +4791,42 @@ void Verifier::visitIntrinsicCall(Intrinsic::ID ID, CallBase &Call) {
     Assert(Size % 16 == 0, "bswap must be an even number of bytes", &Call);
     break;
   }
+  case Intrinsic::matrix_multiply:
+  case Intrinsic::matrix_transpose:
+  case Intrinsic::matrix_columnwise_load:
+  case Intrinsic::matrix_columnwise_store: {
+    ConstantInt *NumRows;
+    ConstantInt *NumColumns;
+    VectorType *TypeToCheck;
+    switch (ID) {
+    case Intrinsic::matrix_multiply:
+      NumRows = cast<ConstantInt>(Call.getArgOperand(2));
+      NumColumns = cast<ConstantInt>(Call.getArgOperand(4));
+      TypeToCheck = cast<VectorType>(Call.getType());
+      break;
+    case Intrinsic::matrix_transpose:
+      NumRows = cast<ConstantInt>(Call.getArgOperand(1));
+      NumColumns = cast<ConstantInt>(Call.getArgOperand(2));
+      TypeToCheck = cast<VectorType>(Call.getType());
+      break;
+    case Intrinsic::matrix_columnwise_load:
+      NumRows = cast<ConstantInt>(Call.getArgOperand(2));
+      NumColumns = cast<ConstantInt>(Call.getArgOperand(3));
+      TypeToCheck = cast<VectorType>(Call.getType());
+      break;
+    case Intrinsic::matrix_columnwise_store:
+      NumRows = cast<ConstantInt>(Call.getArgOperand(3));
+      NumColumns = cast<ConstantInt>(Call.getArgOperand(4));
+      TypeToCheck = cast<VectorType>(Call.getArgOperand(0)->getType());
+      break;
+    default:
+      llvm_unreachable("unexpected intrinsic");
+    }
+    Assert(TypeToCheck->getNumElements() ==
+               NumRows->getZExtValue() * NumColumns->getZExtValue(),
+           "result of a matrix operation does not fit in the returned vector");
+    break;
+  }
   };
 }
 
diff --git a/llvm/test/Verifier/matrix-intrinsics.ll b/llvm/test/Verifier/matrix-intrinsics.ll
new file mode 100644
index 000000000000..d2f23ab7894e
--- /dev/null
+++ b/llvm/test/Verifier/matrix-intrinsics.ll
@@ -0,0 +1,40 @@
+; RUN: not llvm-as < %s -o /dev/null 2>&1 | FileCheck %s
+
+declare <4 x float> @llvm.matrix.transpose.v4f32(<4 x float>, i32, i32)
+define <4 x float> @transpose(<4 x float> %m) {
+; CHECK: assembly parsed, but does not verify as correct!
+; CHECK-NEXT: result of a matrix operation does not fit in the returned vector
+; CHECK-NEXT: result of a matrix operation does not fit in the returned vector
+  %result.1 = call <4 x float> @llvm.matrix.transpose.v4f32(<4 x float> %m, i32 3, i32 2)
+  %result.2 = call <4 x float> @llvm.matrix.transpose.v4f32(<4 x float> %result.1, i32 2, i32 1)
+  ret <4 x float> %result.2
+}
+
+declare <4 x float> @llvm.matrix.multiply.v4f32.v4f32.v4f32(<4 x float>, <4 x float>, i32, i32, i32)
+define <4 x float> @multiply(<4 x float> %m) {
+; CHECK-NEXT: result of a matrix operation does not fit in the returned vector
+; CHECK-NEXT: result of a matrix operation does not fit in the returned vector
+  %result.1 = call <4 x float> @llvm.matrix.multiply.v4f32.v4f32.v4f32(<4 x float> %m, <4 x float> %m, i32 3, i32 2, i32 2)
+  %result.2 = call <4 x float> @llvm.matrix.multiply.v4f32.v4f32.v4f32(<4 x float> %result.1, <4 x float> %m, i32 2, i32 2, i32 1)
+  ret <4 x float> %result.2
+}
+
+declare <4 x float> @llvm.matrix.columnwise.load.v4f32.p0v4f32(<4 x float>*, i32, i32, i32)
+declare <6 x float> @llvm.matrix.columnwise.load.v6f32.p0v6f32(<6 x float>*, i32, i32, i32)
+define <4 x float> @columnwise_load(<4 x float>* %m, <6 x float>* %n) {
+; CHECK-NEXT: result of a matrix operation does not fit in the returned vector
+; CHECK-NEXT: result of a matrix operation does not fit in the returned vector
+  %result.1 = call <4 x float> @llvm.matrix.columnwise.load.v4f32.p0v4f32(<4 x float>* %m, i32 2, i32 1, i32 2)
+  %result.2 = call <6 x float> @llvm.matrix.columnwise.load.v6f32.p0v6f32(<6 x float>* %n, i32 2, i32 3, i32 3)
+  ret <4 x float> %result.1
+}
+
+declare void @llvm.matrix.columnwise.store.v4f32.p0v4f32(<4 x float>, <4 x float>*, i32, i32, i32)
+declare void @llvm.matrix.columnwise.store.v6f32.p0v6f32(<6 x float>, <6 x float>*, i32, i32, i32)
+define void @columnwise_store(<4 x float>* %m, <6 x float>* %n) {
+; CHECK-NEXT: result of a matrix operation does not fit in the returned vector
+; CHECK-NEXT: result of a matrix operation does not fit in the returned vector
+  call void @llvm.matrix.columnwise.store.v4f32.p0v4f32(<4 x float> zeroinitializer, <4 x float>* %m, i32 2, i32 1, i32 2)
+  call void @llvm.matrix.columnwise.store.v6f32.p0v6f32(<6 x float> zeroinitializer, <6 x float>* %n, i32 2, i32 3, i32 3)
+  ret void
+}