Index: llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -3308,6 +3308,14 @@
         !TLI.isOperationLegalOrCustom(ISD::ABS, VT) &&
         TLI.expandABS(N1.getNode(), Result, DAG, true))
       return Result;
+
+    // Fold neg(bvsplat(neg(x)) -> bvsplat(x)
+    if (N1.getOpcode() == ISD::BUILD_VECTOR &&
+        llvm::all_of(N1->ops(),
+                     [&](SDValue Op) { return Op == N1.getOperand(0); }) &&
+        N1.getOperand(0)->getOpcode() == ISD::SUB &&
+        isNullConstant(N1.getOperand(0)->getOperand(0)))
+      return DAG.getSplatBuildVector(VT, DL, N1.getOperand(0)->getOperand(1));
   }
 
   // Canonicalize (sub -1, x) -> ~x, i.e. (xor x, -1)
Index: llvm/test/CodeGen/AArch64/neon-shift-neg.ll
===================================================================
--- llvm/test/CodeGen/AArch64/neon-shift-neg.ll
+++ llvm/test/CodeGen/AArch64/neon-shift-neg.ll
@@ -4,9 +4,7 @@
 define <2 x i64> @shr64x2(<2 x i64> %a, i64 %b) {
 ; CHECK-LABEL: shr64x2:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    neg x8, x0
-; CHECK-NEXT:    dup v1.2d, x8
-; CHECK-NEXT:    neg v1.2d, v1.2d
+; CHECK-NEXT:    dup v1.2d, x0
 ; CHECK-NEXT:    sshl v0.2d, v0.2d, v1.2d
 ; CHECK-NEXT:    ret
 entry:
@@ -20,9 +18,7 @@
 define <4 x i32> @shr32x4(<4 x i32> %a, i32 %b) {
 ; CHECK-LABEL: shr32x4:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    neg w8, w0
-; CHECK-NEXT:    dup v1.4s, w8
-; CHECK-NEXT:    neg v1.4s, v1.4s
+; CHECK-NEXT:    dup v1.4s, w0
 ; CHECK-NEXT:    sshl v0.4s, v0.4s, v1.4s
 ; CHECK-NEXT:    ret
 entry:
@@ -36,9 +32,7 @@
 define <4 x i32> @shr32x4undef(<4 x i32> %a, i32 %b) {
 ; CHECK-LABEL: shr32x4undef:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    neg w8, w0
-; CHECK-NEXT:    dup v1.4s, w8
-; CHECK-NEXT:    neg v1.4s, v1.4s
+; CHECK-NEXT:    dup v1.4s, w0
 ; CHECK-NEXT:    sshl v0.4s, v0.4s, v1.4s
 ; CHECK-NEXT:    ret
 entry:
@@ -52,9 +46,7 @@
 define <8 x i16> @shr16x8(<8 x i16> %a, i16 %b) {
 ; CHECK-LABEL: shr16x8:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    neg w8, w0
-; CHECK-NEXT:    dup v1.8h, w8
-; CHECK-NEXT:    neg v1.8h, v1.8h
+; CHECK-NEXT:    dup v1.8h, w0
 ; CHECK-NEXT:    sshl v0.8h, v0.8h, v1.8h
 ; CHECK-NEXT:    ret
 entry:
@@ -68,9 +60,7 @@
 define <16 x i8> @shr8x16(<16 x i8> %a, i8 %b) {
 ; CHECK-LABEL: shr8x16:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    neg w8, w0
-; CHECK-NEXT:    dup v1.16b, w8
-; CHECK-NEXT:    neg v1.16b, v1.16b
+; CHECK-NEXT:    dup v1.16b, w0
 ; CHECK-NEXT:    sshl v0.16b, v0.16b, v1.16b
 ; CHECK-NEXT:    ret
 entry:
@@ -84,9 +74,7 @@
 define <1 x i64> @shr64x1(<1 x i64> %a, i64 %b) {
 ; CHECK-LABEL: shr64x1:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    neg x8, x0
-; CHECK-NEXT:    fmov d1, x8
-; CHECK-NEXT:    neg d1, d1
+; CHECK-NEXT:    fmov d1, x0
 ; CHECK-NEXT:    sshl d0, d0, d1
 ; CHECK-NEXT:    ret
 entry:
@@ -99,9 +87,7 @@
 define <2 x i32> @shr32x2(<2 x i32> %a, i32 %b) {
 ; CHECK-LABEL: shr32x2:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    neg w8, w0
-; CHECK-NEXT:    dup v1.2s, w8
-; CHECK-NEXT:    neg v1.2s, v1.2s
+; CHECK-NEXT:    dup v1.2s, w0
 ; CHECK-NEXT:    sshl v0.2s, v0.2s, v1.2s
 ; CHECK-NEXT:    ret
 entry:
@@ -115,9 +101,7 @@
 define <4 x i16> @shr16x4(<4 x i16> %a, i16 %b) {
 ; CHECK-LABEL: shr16x4:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    neg w8, w0
-; CHECK-NEXT:    dup v1.4h, w8
-; CHECK-NEXT:    neg v1.4h, v1.4h
+; CHECK-NEXT:    dup v1.4h, w0
 ; CHECK-NEXT:    sshl v0.4h, v0.4h, v1.4h
 ; CHECK-NEXT:    ret
 entry:
@@ -131,9 +115,7 @@
 define <8 x i8> @shr8x8(<8 x i8> %a, i8 %b) {
 ; CHECK-LABEL: shr8x8:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    neg w8, w0
-; CHECK-NEXT:    dup v1.8b, w8
-; CHECK-NEXT:    neg v1.8b, v1.8b
+; CHECK-NEXT:    dup v1.8b, w0
 ; CHECK-NEXT:    sshl v0.8b, v0.8b, v1.8b
 ; CHECK-NEXT:    ret
 entry: