diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -4419,7 +4419,7 @@
 }
 
 static unsigned selectUmullSmull(SDNode *&N0, SDNode *&N1, SelectionDAG &DAG,
-                                 bool &IsMLA) {
+                                 SDLoc DL, bool &IsMLA) {
   bool IsN0SExt = isSignExtended(N0, DAG);
   bool IsN1SExt = isSignExtended(N1, DAG);
   if (IsN0SExt && IsN1SExt)
@@ -4428,6 +4428,23 @@
   bool IsN0ZExt = isZeroExtended(N0, DAG);
   bool IsN1ZExt = isZeroExtended(N1, DAG);
 
+  // Select SMULL if we can replace zext with sext.
+  if ((IsN0SExt && IsN1ZExt) || (IsN0ZExt && IsN1SExt)) {
+    SDValue ZextOperand;
+    if (IsN0ZExt)
+      ZextOperand = N0->getOperand(0);
+    else
+      ZextOperand = N1->getOperand(0);
+    if (DAG.SignBitIsZero(ZextOperand)) {
+      SDNode *NewSext =
+          DAG.getSExtOrTrunc(ZextOperand, DL, N0->getValueType(0)).getNode();
+      if (IsN0ZExt)
+        N0 = NewSext;
+      else
+        N1 = NewSext;
+      return AArch64ISD::SMULL;
+    }
+  }
   if (IsN0ZExt && IsN1ZExt)
     return AArch64ISD::UMULL;
 
@@ -4467,7 +4484,8 @@
   SDNode *N0 = Op.getOperand(0).getNode();
   SDNode *N1 = Op.getOperand(1).getNode();
   bool isMLA = false;
-  unsigned NewOpc = selectUmullSmull(N0, N1, DAG, isMLA);
+  SDLoc DL(Op);
+  unsigned NewOpc = selectUmullSmull(N0, N1, DAG, DL, isMLA);
 
   if (!NewOpc) {
     if (VT == MVT::v2i64)
@@ -4479,7 +4497,6 @@
   }
 
   // Legalize to a S/UMULL instruction
-  SDLoc DL(Op);
   SDValue Op0;
   SDValue Op1 = skipExtensionForVectorMULL(N1, DAG);
   if (!isMLA) {
diff --git a/llvm/test/CodeGen/AArch64/aarch64-smull.ll b/llvm/test/CodeGen/AArch64/aarch64-smull.ll
--- a/llvm/test/CodeGen/AArch64/aarch64-smull.ll
+++ b/llvm/test/CodeGen/AArch64/aarch64-smull.ll
@@ -50,14 +50,10 @@
 ; CHECK-LABEL: smull_zext_v8i8_v8i32:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    ldr d0, [x0]
-; CHECK-NEXT:    ldr q1, [x1]
+; CHECK-NEXT:    ldr q2, [x1]
 ; CHECK-NEXT:    ushll v0.8h, v0.8b, #0
-; CHECK-NEXT:    sshll v2.4s, v1.4h, #0
-; CHECK-NEXT:    sshll2 v1.4s, v1.8h, #0
-; CHECK-NEXT:    ushll2 v3.4s, v0.8h, #0
-; CHECK-NEXT:    ushll v0.4s, v0.4h, #0
-; CHECK-NEXT:    mul v1.4s, v3.4s, v1.4s
-; CHECK-NEXT:    mul v0.4s, v0.4s, v2.4s
+; CHECK-NEXT:    smull2 v1.4s, v0.8h, v2.8h
+; CHECK-NEXT:    smull v0.4s, v0.4h, v2.4h
 ; CHECK-NEXT:    ret
   %load.A = load <8 x i8>, <8 x i8>* %A
   %load.B = load <8 x i16>, <8 x i16>* %B
@@ -70,15 +66,11 @@
 define <8 x i32> @smull_zext_v8i8_v8i32_sext_first_operand(<8 x i16>* %A, <8 x i8>* %B) nounwind {
 ; CHECK-LABEL: smull_zext_v8i8_v8i32_sext_first_operand:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ldr d1, [x1]
-; CHECK-NEXT:    ldr q0, [x0]
-; CHECK-NEXT:    ushll v1.8h, v1.8b, #0
-; CHECK-NEXT:    sshll v2.4s, v0.4h, #0
-; CHECK-NEXT:    sshll2 v0.4s, v0.8h, #0
-; CHECK-NEXT:    ushll2 v3.4s, v1.8h, #0
-; CHECK-NEXT:    ushll v4.4s, v1.4h, #0
-; CHECK-NEXT:    mul v1.4s, v0.4s, v3.4s
-; CHECK-NEXT:    mul v0.4s, v2.4s, v4.4s
+; CHECK-NEXT:    ldr d0, [x1]
+; CHECK-NEXT:    ldr q2, [x0]
+; CHECK-NEXT:    ushll v0.8h, v0.8b, #0
+; CHECK-NEXT:    smull2 v1.4s, v2.8h, v0.8h
+; CHECK-NEXT:    smull v0.4s, v2.4h, v0.4h
 ; CHECK-NEXT:    ret
   %load.A = load <8 x i16>, <8 x i16>* %A
   %load.B = load <8 x i8>, <8 x i8>* %B
@@ -116,9 +108,7 @@
 ; CHECK-NEXT:    ldr s0, [x0]
 ; CHECK-NEXT:    ldr d1, [x1]
 ; CHECK-NEXT:    ushll v0.8h, v0.8b, #0
-; CHECK-NEXT:    sshll v1.4s, v1.4h, #0
-; CHECK-NEXT:    ushll v0.4s, v0.4h, #0
-; CHECK-NEXT:    mul v0.4s, v0.4s, v1.4s
+; CHECK-NEXT:    smull v0.4s, v0.4h, v1.4h
 ; CHECK-NEXT:    ret
   %load.A = load <4 x i8>, <4 x i8>* %A
   %load.B = load <4 x i16>, <4 x i16>* %B
@@ -156,16 +146,7 @@
 ; CHECK-NEXT:    ldr d0, [x0]
 ; CHECK-NEXT:    ldr d1, [x1]
 ; CHECK-NEXT:    bic v0.2s, #128, lsl #24
-; CHECK-NEXT:    sshll v1.2d, v1.2s, #0
-; CHECK-NEXT:    ushll v0.2d, v0.2s, #0
-; CHECK-NEXT:    fmov x9, d1
-; CHECK-NEXT:    fmov x10, d0
-; CHECK-NEXT:    mov x8, v1.d[1]
-; CHECK-NEXT:    mov x11, v0.d[1]
-; CHECK-NEXT:    mul x9, x10, x9
-; CHECK-NEXT:    mul x8, x11, x8
-; CHECK-NEXT:    fmov d0, x9
-; CHECK-NEXT:    mov v0.d[1], x8
+; CHECK-NEXT:    smull v0.2d, v0.2s, v1.2s
 ; CHECK-NEXT:    ret
   %load.A = load <2 x i32>, <2 x i32>* %A
   %and.A = and <2 x i32> %load.A, <i32 u0x7FFFFFFF, i32 u0x7FFFFFFF>