diff --git a/llvm/lib/Target/AArch64/AArch64InstrGISel.td b/llvm/lib/Target/AArch64/AArch64InstrGISel.td
index 7322212c5bb24..fe8419301b306 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrGISel.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrGISel.td
@@ -233,6 +233,12 @@ def G_SDOT : AArch64GenericInstruction {
   let hasSideEffects = 0;
 }
 
+def G_USDOT : AArch64GenericInstruction {
+  let OutOperandList = (outs type0:$dst);
+  let InOperandList = (ins type0:$src1, type0:$src2, type0:$src3);
+  let hasSideEffects = 0;
+}
+
 // Generic instruction for the BSP pseudo. It is expanded into BSP, which
 // expands into BSL/BIT/BIF after register allocation.
 def G_BSP : AArch64GenericInstruction {
@@ -278,6 +284,7 @@ def : GINodeEquiv<G_UADDLV, AArch64uaddlv>;
 
 def : GINodeEquiv<G_UDOT, AArch64udot>;
 def : GINodeEquiv<G_SDOT, AArch64sdot>;
+def : GINodeEquiv<G_USDOT, AArch64usdot>;
 
 def : GINodeEquiv<G_EXTRACT_VECTOR_ELT, vector_extract>;
 
diff --git a/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp b/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
index 9e2d698e04ae7..05a431312472e 100644
--- a/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
+++ b/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
@@ -1855,6 +1855,8 @@ bool AArch64LegalizerInfo::legalizeIntrinsic(LegalizerHelper &Helper,
     return LowerTriOp(AArch64::G_UDOT);
   case Intrinsic::aarch64_neon_sdot:
     return LowerTriOp(AArch64::G_SDOT);
+  case Intrinsic::aarch64_neon_usdot:
+    return LowerTriOp(AArch64::G_USDOT);
   case Intrinsic::aarch64_neon_sqxtn:
     return LowerUnaryOp(TargetOpcode::G_TRUNC_SSAT_S);
   case Intrinsic::aarch64_neon_sqxtun:
diff --git a/llvm/test/CodeGen/AArch64/aarch64-matmul.ll b/llvm/test/CodeGen/AArch64/aarch64-matmul.ll
index 649d0a9bfcab4..99260f0625098 100644
--- a/llvm/test/CodeGen/AArch64/aarch64-matmul.ll
+++ b/llvm/test/CodeGen/AArch64/aarch64-matmul.ll
@@ -1,41 +1,53 @@
-; RUN: llc -mtriple=aarch64-none-linux-gnu -mattr=+neon,+i8mm < %s -o -| FileCheck %s
+; RUN: llc -mtriple aarch64-none-linux-gnu -mattr=+neon,+i8mm    < %s | FileCheck %s
+; RUN: llc -mtriple aarch64-none-linux-gnu -mattr=+neon,+i8mm -global-isel < %s | FileCheck %s
 
 define <4 x i32> @smmla.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <16 x i8> %b) {
+; CHECK-LABEL: smmla.v4i32.v16i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    smmla v0.4s, v1.16b, v2.16b
+; CHECK-NEXT:    ret
 entry:
-; CHECK-LABEL: smmla.v4i32.v16i8
-; CHECK: smmla   v0.4s, v1.16b, v2.16b
   %vmmla1.i = tail call <4 x i32> @llvm.aarch64.neon.smmla.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <16 x i8> %b)
   ret <4 x i32> %vmmla1.i
 }
 
 define <4 x i32> @ummla.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <16 x i8> %b) {
+; CHECK-LABEL: ummla.v4i32.v16i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ummla v0.4s, v1.16b, v2.16b
+; CHECK-NEXT:    ret
 entry:
-; CHECK-LABEL: ummla.v4i32.v16i8
-; CHECK: ummla   v0.4s, v1.16b, v2.16b
   %vmmla1.i = tail call <4 x i32> @llvm.aarch64.neon.ummla.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <16 x i8> %b)
   ret <4 x i32> %vmmla1.i
 }
 
 define <4 x i32> @usmmla.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <16 x i8> %b) {
+; CHECK-LABEL: usmmla.v4i32.v16i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    usmmla v0.4s, v1.16b, v2.16b
+; CHECK-NEXT:    ret
 entry:
-; CHECK-LABEL: usmmla.v4i32.v16i8
-; CHECK: usmmla   v0.4s, v1.16b, v2.16b
   %vusmmla1.i = tail call <4 x i32> @llvm.aarch64.neon.usmmla.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <16 x i8> %b) #3
   ret <4 x i32> %vusmmla1.i
 }
 
 define <2 x i32> @usdot.v2i32.v8i8(<2 x i32> %r, <8 x i8> %a, <8 x i8> %b) {
+; CHECK-LABEL: usdot.v2i32.v8i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    usdot v0.2s, v1.8b, v2.8b
+; CHECK-NEXT:    ret
 entry:
-; CHECK-LABEL: usdot.v2i32.v8i8
-; CHECK: usdot   v0.2s, v1.8b, v2.8b
   %vusdot1.i = tail call <2 x i32> @llvm.aarch64.neon.usdot.v2i32.v8i8(<2 x i32> %r, <8 x i8> %a, <8 x i8> %b)
   ret <2 x i32> %vusdot1.i
 }
 
 define <2 x i32> @usdot_lane.v2i32.v8i8(<2 x i32> %r, <8 x i8> %a, <8 x i8> %b) {
+; CHECK-LABEL: usdot_lane.v2i32.v8i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    // kill: def $d2 killed $d2 def $q2
+; CHECK-NEXT:    usdot v0.2s, v1.8b, v2.4b[0]
+; CHECK-NEXT:    ret
 entry:
-; CHECK-LABEL: usdot_lane.v2i32.v8i8
-; CHECK: usdot   v0.2s, v1.8b, v2.4b[0]
   %0 = bitcast <8 x i8> %b to <2 x i32>
   %shuffle = shufflevector <2 x i32> %0, <2 x i32> undef, <2 x i32> zeroinitializer
   %1 = bitcast <2 x i32> %shuffle to <8 x i8>
@@ -44,9 +56,12 @@ entry:
 }
 
 define <2 x i32> @sudot_lane.v2i32.v8i8(<2 x i32> %r, <8 x i8> %a, <8 x i8> %b) {
+; CHECK-LABEL: sudot_lane.v2i32.v8i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    // kill: def $d2 killed $d2 def $q2
+; CHECK-NEXT:    sudot v0.2s, v1.8b, v2.4b[0]
+; CHECK-NEXT:    ret
 entry:
-; CHECK-LABEL: sudot_lane.v2i32.v8i8
-; CHECK: sudot   v0.2s, v1.8b, v2.4b[0]
   %0 = bitcast <8 x i8> %b to <2 x i32>
   %shuffle = shufflevector <2 x i32> %0, <2 x i32> undef, <2 x i32> zeroinitializer
   %1 = bitcast <2 x i32> %shuffle to <8 x i8>
@@ -55,9 +70,11 @@ entry:
 }
 
 define <2 x i32> @usdot_lane.v2i32.v16i8(<2 x i32> %r, <8 x i8> %a, <16 x i8> %b) {
+; CHECK-LABEL: usdot_lane.v2i32.v16i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    usdot v0.2s, v1.8b, v2.4b[0]
+; CHECK-NEXT:    ret
 entry:
-; CHECK-LABEL: usdot_lane.v2i32.v16i8
-; CHECK: usdot   v0.2s, v1.8b, v2.4b[0]
   %0 = bitcast <16 x i8> %b to <4 x i32>
   %shuffle = shufflevector <4 x i32> %0, <4 x i32> undef, <2 x i32> zeroinitializer
   %1 = bitcast <2 x i32> %shuffle to <8 x i8>
@@ -66,9 +83,11 @@ entry:
 }
 
 define <2 x i32> @sudot_lane.v2i32.v16i8(<2 x i32> %r, <8 x i8> %a, <16 x i8> %b) {
+; CHECK-LABEL: sudot_lane.v2i32.v16i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    sudot v0.2s, v1.8b, v2.4b[0]
+; CHECK-NEXT:    ret
 entry:
-; CHECK-LABEL: sudot_lane.v2i32.v16i8
-; CHECK: sudot   v0.2s, v1.8b, v2.4b[0]
   %0 = bitcast <16 x i8> %b to <4 x i32>
   %shuffle = shufflevector <4 x i32> %0, <4 x i32> undef, <2 x i32> zeroinitializer
   %1 = bitcast <2 x i32> %shuffle to <8 x i8>
@@ -77,17 +96,22 @@ entry:
 }
 
 define <4 x i32> @usdot.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <16 x i8> %b) {
+; CHECK-LABEL: usdot.v4i32.v16i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    usdot v0.4s, v1.16b, v2.16b
+; CHECK-NEXT:    ret
 entry:
-; CHECK-LABEL: usdot.v4i32.v16i8
-; CHECK: usdot   v0.4s, v1.16b, v2.16b
   %vusdot1.i = tail call <4 x i32> @llvm.aarch64.neon.usdot.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <16 x i8> %b) #3
   ret <4 x i32> %vusdot1.i
 }
 
 define <4 x i32> @usdot_lane.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <8 x i8> %b) {
+; CHECK-LABEL: usdot_lane.v4i32.v16i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    // kill: def $d2 killed $d2 def $q2
+; CHECK-NEXT:    usdot v0.4s, v1.16b, v2.4b[0]
+; CHECK-NEXT:    ret
 entry:
-; CHECK-LABEL: usdot_lane.v4i32.v16i8
-; CHECK: usdot   v0.4s, v1.16b, v2.4b[0]
   %0 = bitcast <8 x i8> %b to <2 x i32>
   %shuffle = shufflevector <2 x i32> %0, <2 x i32> undef, <4 x i32> zeroinitializer
   %1 = bitcast <4 x i32> %shuffle to <16 x i8>
@@ -96,9 +120,12 @@ entry:
 }
 
 define <4 x i32> @sudot_lane.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <8 x i8> %b) {
+; CHECK-LABEL: sudot_lane.v4i32.v16i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    // kill: def $d2 killed $d2 def $q2
+; CHECK-NEXT:    sudot v0.4s, v1.16b, v2.4b[0]
+; CHECK-NEXT:    ret
 entry:
-; CHECK-LABEL: sudot_lane.v4i32.v16i8
-; CHECK: sudot   v0.4s, v1.16b, v2.4b[0]
   %0 = bitcast <8 x i8> %b to <2 x i32>
   %shuffle = shufflevector <2 x i32> %0, <2 x i32> undef, <4 x i32> zeroinitializer
   %1 = bitcast <4 x i32> %shuffle to <16 x i8>
@@ -107,9 +134,11 @@ entry:
 }
 
 define <4 x i32> @usdot_laneq.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <16 x i8> %b) {
+; CHECK-LABEL: usdot_laneq.v4i32.v16i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    usdot v0.4s, v1.16b, v2.4b[0]
+; CHECK-NEXT:    ret
 entry:
-; CHECK-LABEL: usdot_laneq.v4i32.v16i8
-; CHECK: usdot   v0.4s, v1.16b, v2.4b[0]
   %0 = bitcast <16 x i8> %b to <4 x i32>
   %shuffle = shufflevector <4 x i32> %0, <4 x i32> undef, <4 x i32> zeroinitializer
   %1 = bitcast <4 x i32> %shuffle to <16 x i8>
@@ -118,9 +147,11 @@ entry:
 }
 
 define <4 x i32> @sudot_laneq.v4i32.v16i8(<4 x i32> %r, <16 x i8> %a, <16 x i8> %b) {
+; CHECK-LABEL: sudot_laneq.v4i32.v16i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    sudot v0.4s, v1.16b, v2.4b[0]
+; CHECK-NEXT:    ret
 entry:
-; CHECK-LABEL: sudot_laneq.v4i32.v16i8
-; CHECK: sudot   v0.4s, v1.16b, v2.4b[0]
   %0 = bitcast <16 x i8> %b to <4 x i32>
   %shuffle = shufflevector <4 x i32> %0, <4 x i32> undef, <4 x i32> zeroinitializer
   %1 = bitcast <4 x i32> %shuffle to <16 x i8>
@@ -134,3 +165,6 @@ declare <4 x i32> @llvm.aarch64.neon.usmmla.v4i32.v16i8(<4 x i32>, <16 x i8>, <1
 declare <2 x i32> @llvm.aarch64.neon.usdot.v2i32.v8i8(<2 x i32>, <8 x i8>, <8 x i8>) #2
 declare <4 x i32> @llvm.aarch64.neon.usdot.v4i32.v16i8(<4 x i32>, <16 x i8>, <16 x i8>) #2
 
+;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
+; CHECK-GI: {{.*}}
+; CHECK-SD: {{.*}}