Index: llvm/lib/Target/AArch64/AArch64ISelLowering.h
===================================================================
--- llvm/lib/Target/AArch64/AArch64ISelLowering.h
+++ llvm/lib/Target/AArch64/AArch64ISelLowering.h
@@ -240,6 +240,9 @@
   UABD,
   SABD,
 
+  // Unsigned Add Long Pairwise
+  UADDLP,
+
   // udot/sdot instructions
   UDOT,
   SDOT,
Index: llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -2110,6 +2110,7 @@
     MAKE_CASE(AArch64ISD::INDEX_VECTOR)
     MAKE_CASE(AArch64ISD::UABD)
     MAKE_CASE(AArch64ISD::SABD)
+    MAKE_CASE(AArch64ISD::UADDLP)
     MAKE_CASE(AArch64ISD::CALL_RVMARKER)
   }
 #undef MAKE_CASE
@@ -4078,6 +4079,10 @@
     return DAG.getNode(Opcode, dl, Op.getValueType(), Op.getOperand(1),
                        Op.getOperand(2));
   }
+  case Intrinsic::aarch64_neon_uaddlp: {
+    unsigned Opcode = AArch64ISD::UADDLP;
+    return DAG.getNode(Opcode, dl, Op.getValueType(), Op.getOperand(1));
+  }
   case Intrinsic::aarch64_neon_sdot:
   case Intrinsic::aarch64_neon_udot:
   case Intrinsic::aarch64_sve_sdot:
@@ -11981,13 +11986,102 @@
   return DAG.getNode(AArch64ISD::CMGEz, SDLoc(N), VT, Shift.getOperand(0));
 }
 
+// Given a vecreduce_add node, detect the below pattern and convert it to the
+// node sequence with UABDL, UADB and UADDLP.
+//
+// i32 vecreduce_add(
+//  v16i32 abs(
+//    v16i32 sub(
+//      v16i32 zero_extend(v16i8 a), v16i32 zero_extend(v16i8 b))))
+// =================>
+// i32 vecreduce_add(
+//   v4i32 UADDLP(
+//     v8i16 add(
+//       v8i16 zext(
+//         v8i8 UABD low8:v16i8 a, low8:v16i8 b
+//       v8i16 zext(
+//         v8i8 UABD high8:v16i8 a, high8:v16i8 b
+static SDValue performVecReduceAddCombineWithUADALP(SDNode *N,
+                                                    SelectionDAG &DAG) {
+  // Assumed i32 vecreduce_add
+  if (N->getValueType(0) != MVT::i32)
+    return SDValue();
+
+  SDValue VecReduceOp0 = N->getOperand(0);
+  unsigned Opcode = VecReduceOp0.getOpcode();
+  // Assumed v16i32 abs
+  if (Opcode != ISD::ABS || VecReduceOp0->getValueType(0) != MVT::v16i32)
+    return SDValue();
+
+  SDValue ABS = VecReduceOp0;
+  SDValue ABSOp0 = ABS->getOperand(0);
+  Opcode = ABSOp0.getOpcode();
+  // Assumed v16i32 sub
+  if (Opcode != ISD::SUB || ABSOp0->getValueType(0) != MVT::v16i32)
+    return SDValue();
+
+  SDValue SUB = ABSOp0;
+  SDValue SUBOp0 = SUB->getOperand(0);
+  SDValue SUBOp1 = SUB->getOperand(1);
+  unsigned Opcode0 = SUBOp0.getOpcode();
+  unsigned Opcode1 = SUBOp1.getOpcode();
+  // Assumed v16i32 zext
+  if (Opcode0 != ISD::ZERO_EXTEND || Opcode1 != ISD::ZERO_EXTEND ||
+      SUBOp0->getValueType(0) != MVT::v16i32 ||
+      SUBOp1->getValueType(0) != MVT::v16i32)
+    return SDValue();
+
+  SDValue ZEXT0 = SUBOp0;
+  SDValue ZEXT1 = SUBOp1;
+  SDValue ZEXT0Op0 = ZEXT0->getOperand(0);
+  SDValue ZEXT1Op0 = ZEXT1->getOperand(0);
+  // Assumed zext's operand has v16i8 type
+  if (ZEXT0Op0->getValueType(0) != MVT::v16i8 ||
+      ZEXT1Op0->getValueType(0) != MVT::v16i8)
+    return SDValue();
+
+  // Pattern is dectected. Let's convert it to sequence of nodes.
+  SDLoc DL(N);
+
+  // First, create the node pattern of UABDL.
+  SDValue UABDHigh8Op0 =
+      DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, MVT::v8i8, ZEXT0Op0,
+                  DAG.getConstant(8, DL, MVT::i64));
+  SDValue UABDHigh8Op1 =
+      DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, MVT::v8i8, ZEXT1Op0,
+                  DAG.getConstant(8, DL, MVT::i64));
+  SDValue UABDHigh8 =
+      DAG.getNode(AArch64ISD::UABD, DL, MVT::v8i8, UABDHigh8Op0, UABDHigh8Op1);
+  SDValue UABDL = DAG.getNode(ISD::ZERO_EXTEND, DL, MVT::v8i16, UABDHigh8);
+
+  // Second, create the node pattern of UABAL.
+  SDValue UABDLo8Op0 = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, MVT::v8i8,
+                                   ZEXT0Op0, DAG.getConstant(0, DL, MVT::i64));
+  SDValue UABDLo8Op1 = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, MVT::v8i8,
+                                   ZEXT1Op0, DAG.getConstant(0, DL, MVT::i64));
+  SDValue UABDLo8 =
+      DAG.getNode(AArch64ISD::UABD, DL, MVT::v8i8, UABDLo8Op0, UABDLo8Op1);
+  SDValue ZExtUABD = DAG.getNode(ISD::ZERO_EXTEND, DL, MVT::v8i16, UABDLo8);
+  SDValue UABAL = DAG.getNode(ISD::ADD, DL, MVT::v8i16, UABDL, ZExtUABD);
+
+  // Third, create the node of UADDLP.
+  SDValue UADDLPOp0 = UABAL;
+  SDValue UADDLP = DAG.getNode(AArch64ISD::UADDLP, DL, MVT::v4i32, UADDLPOp0);
+
+  // Fourth, create the node of VECREDUCE_ADD.
+  return DAG.getNode(ISD::VECREDUCE_ADD, DL, MVT::i32, UADDLP);
+}
+
 // Turn a v8i8/v16i8 extended vecreduce into a udot/sdot and vecreduce
 //   vecreduce.add(ext(A)) to vecreduce.add(DOT(zero, A, one))
 //   vecreduce.add(mul(ext(A), ext(B))) to vecreduce.add(DOT(zero, A, B))
 static SDValue performVecReduceAddCombine(SDNode *N, SelectionDAG &DAG,
                                           const AArch64Subtarget *ST) {
+  if (!ST->hasDotProd())
+    return performVecReduceAddCombineWithUADALP(N, DAG);
+
   SDValue Op0 = N->getOperand(0);
-  if (!ST->hasDotProd() || N->getValueType(0) != MVT::i32 ||
+  if (N->getValueType(0) != MVT::i32 ||
       Op0.getValueType().getVectorElementType() != MVT::i32)
     return SDValue();
 
Index: llvm/lib/Target/AArch64/AArch64InstrInfo.td
===================================================================
--- llvm/lib/Target/AArch64/AArch64InstrInfo.td
+++ llvm/lib/Target/AArch64/AArch64InstrInfo.td
@@ -271,6 +271,8 @@
 def SDT_AArch64TLSDescCall : SDTypeProfile<0, -2, [SDTCisPtrTy<0>,
                                                  SDTCisPtrTy<1>]>;
 
+def SDT_AArch64uaddlp : SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>]>;
+
 def SDT_AArch64ldp : SDTypeProfile<2, 1, [SDTCisVT<0, i64>, SDTCisSameAs<0, 1>, SDTCisPtrTy<2>]>;
 def SDT_AArch64stp : SDTypeProfile<0, 3, [SDTCisVT<0, i64>, SDTCisSameAs<0, 1>, SDTCisPtrTy<2>]>;
 def SDT_AArch64stnp : SDTypeProfile<0, 3, [SDTCisVT<0, v4i32>, SDTCisSameAs<0, 1>, SDTCisPtrTy<2>]>;
@@ -587,6 +589,11 @@
                                [(AArch64sabd_n node:$lhs, node:$rhs),
                                 (int_aarch64_neon_sabd node:$lhs, node:$rhs)]>;
 
+def AArch64uaddlp_n : SDNode<"AArch64ISD::UADDLP", SDT_AArch64uaddlp>;
+def AArch64uaddlp   : PatFrags<(ops node:$src),
+                               [(AArch64uaddlp_n node:$src),
+                                (int_aarch64_neon_uaddlp node:$src)]>;
+
 def SDT_AArch64SETTAG : SDTypeProfile<0, 2, [SDTCisPtrTy<0>, SDTCisPtrTy<1>]>;
 def AArch64stg : SDNode<"AArch64ISD::STG", SDT_AArch64SETTAG, [SDNPHasChain, SDNPMayStore, SDNPMemOperand]>;
 def AArch64stzg : SDNode<"AArch64ISD::STZG", SDT_AArch64SETTAG, [SDNPHasChain, SDNPMayStore, SDNPMemOperand]>;
@@ -4178,9 +4185,8 @@
 defm SQXTUN : SIMDMixedTwoVector<1, 0b10010, "sqxtun", int_aarch64_neon_sqxtun>;
 defm SUQADD : SIMDTwoVectorBHSDTied<0, 0b00011, "suqadd",int_aarch64_neon_suqadd>;
 defm UADALP : SIMDLongTwoVectorTied<1, 0b00110, "uadalp",
-       BinOpFrag<(add node:$LHS, (int_aarch64_neon_uaddlp node:$RHS))> >;
-defm UADDLP : SIMDLongTwoVector<1, 0b00010, "uaddlp",
-                    int_aarch64_neon_uaddlp>;
+       BinOpFrag<(add node:$LHS, (AArch64uaddlp node:$RHS))> >;
+defm UADDLP : SIMDLongTwoVector<1, 0b00010, "uaddlp", AArch64uaddlp>;
 defm UCVTF  : SIMDTwoVectorIntToFP<1, 0, 0b11101, "ucvtf", uint_to_fp>;
 defm UQXTN  : SIMDMixedTwoVector<1, 0b10100, "uqxtn", int_aarch64_neon_uqxtn>;
 defm URECPE : SIMDTwoVectorS<0, 1, 0b11100, "urecpe", int_aarch64_neon_urecpe>;
Index: llvm/test/CodeGen/AArch64/neon-sad.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/AArch64/neon-sad.ll
@@ -0,0 +1,29 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple aarch64-none-linux-gnu < %s | FileCheck %s
+
+declare <16 x i32> @llvm.abs.v16i32(<16 x i32>, i1 immarg)
+declare i32 @llvm.vector.reduce.add.v16i32(<16 x i32>)
+
+define i32 @test_sad_v16i8(i8* nocapture readonly %a, i8* nocapture readonly %b) {
+; CHECK-LABEL: test_sad_v16i8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ldr q0, [x0]
+; CHECK-NEXT:    ldr q1, [x1]
+; CHECK-NEXT:    uabdl v2.8h, v1.8b, v0.8b
+; CHECK-NEXT:    uabal2 v2.8h, v1.16b, v0.16b
+; CHECK-NEXT:    uaddlp v0.4s, v2.8h
+; CHECK-NEXT:    addv s0, v0.4s
+; CHECK-NEXT:    fmov w0, s0
+; CHECK-NEXT:    ret
+entry:
+  %0 = bitcast i8* %a to <16 x i8>*
+  %1 = load <16 x i8>, <16 x i8>* %0
+  %2 = zext <16 x i8> %1 to <16 x i32>
+  %3 = bitcast i8* %b to <16 x i8>*
+  %4 = load <16 x i8>, <16 x i8>* %3
+  %5 = zext <16 x i8> %4 to <16 x i32>
+  %6 = sub nsw <16 x i32> %5, %2
+  %7 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> %6, i1 true)
+  %8 = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> %7)
+  ret i32 %8
+}