Index: llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -9428,13 +9428,13 @@
 }
 
 // Fold sext/zext of index into index type.
-bool refineIndexType(MaskedScatterSDNode *MSC, SDValue &Index, bool Scaled,
-                     SelectionDAG &DAG) {
+bool refineIndexType(MaskedGatherScatterSDNode *MGS, SDValue &Index,
+                     bool Scaled, SelectionDAG &DAG) {
   const TargetLowering &TLI = DAG.getTargetLoweringInfo();
   SDValue Op = Index.getOperand(0);
 
   if (Index.getOpcode() == ISD::ZERO_EXTEND) {
-    MSC->setIndexType(Scaled ? ISD::UNSIGNED_SCALED : ISD::UNSIGNED_UNSCALED);
+    MGS->setIndexType(Scaled ? ISD::UNSIGNED_SCALED : ISD::UNSIGNED_UNSCALED);
     if (TLI.shouldRemoveExtendFromGSIndex(Op.getValueType())) {
       Index = Op;
       return true;
@@ -9442,7 +9442,7 @@
   }
 
   if (Index.getOpcode() == ISD::SIGN_EXTEND) {
-    MSC->setIndexType(Scaled ? ISD::SIGNED_SCALED : ISD::SIGNED_UNSCALED);
+    MGS->setIndexType(Scaled ? ISD::SIGNED_SCALED : ISD::SIGNED_UNSCALED);
     if (TLI.shouldRemoveExtendFromGSIndex(Op.getValueType())) {
       Index = Op;
       return true;
@@ -9511,11 +9511,30 @@
 SDValue DAGCombiner::visitMGATHER(SDNode *N) {
   MaskedGatherSDNode *MGT = cast<MaskedGatherSDNode>(N);
   SDValue Mask = MGT->getMask();
+  SDValue Chain = MGT->getChain();
+  SDValue Index = MGT->getIndex();
+  SDValue Scale = MGT->getScale();
+  SDValue PassThru = MGT->getPassThru();
+  SDValue BasePtr = MGT->getBasePtr();
   SDLoc DL(N);
 
   // Zap gathers with a zero mask.
   if (ISD::isBuildVectorAllZeros(Mask.getNode()))
-    return CombineTo(N, MGT->getPassThru(), MGT->getChain());
+    return CombineTo(N, PassThru, MGT->getChain());
+
+  if (refineUniformBase(BasePtr, Index, DAG)) {
+    SDValue Ops[] = {Chain, PassThru, Mask, BasePtr, Index, Scale};
+    return DAG.getMaskedGather(DAG.getVTList(N->getValueType(0), MVT::Other),
+                               PassThru.getValueType(), DL, Ops,
+                               MGT->getMemOperand(), MGT->getIndexType());
+  }
+
+  if (refineIndexType(MGT, Index, MGT->isIndexScaled(), DAG)) {
+    SDValue Ops[] = {Chain, PassThru, Mask, BasePtr, Index, Scale};
+    return DAG.getMaskedGather(DAG.getVTList(N->getValueType(0), MVT::Other),
+                               PassThru.getValueType(), DL, Ops,
+                               MGT->getMemOperand(), MGT->getIndexType());
+  }
 
   return SDValue();
 }
Index: llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
===================================================================
--- llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -4416,7 +4416,7 @@
   if (!UniformBase) {
     Base = DAG.getConstant(0, sdl, TLI.getPointerTy(DAG.getDataLayout()));
     Index = getValue(Ptr);
-    IndexType = ISD::SIGNED_SCALED;
+    IndexType = ISD::SIGNED_UNSCALED;
     Scale = DAG.getTargetConstant(1, sdl, TLI.getPointerTy(DAG.getDataLayout()));
   }
   SDValue Ops[] = { Root, Src0, Mask, Base, Index, Scale };
Index: llvm/test/CodeGen/AArch64/sve-masked-gather-32b-signed-unscaled.ll
===================================================================
--- llvm/test/CodeGen/AArch64/sve-masked-gather-32b-signed-unscaled.ll
+++ llvm/test/CodeGen/AArch64/sve-masked-gather-32b-signed-unscaled.ll
@@ -20,12 +20,7 @@
 define <vscale x 2 x i64> @masked_gather_nxv2i16(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2i16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ptrue p1.d
-; CHECK-NEXT:    sxtw z0.d, p1/m, z0.d
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x8, z0.d, lsl #1]
+; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0, z0.d, sxtw]
 ; CHECK-NEXT:    and z0.d, z0.d, #0xffff
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i32> %offsets
@@ -38,12 +33,7 @@
 define <vscale x 2 x i64> @masked_gather_nxv2i32(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2i32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ptrue p1.d
-; CHECK-NEXT:    sxtw z0.d, p1/m, z0.d
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x8, z0.d, lsl #2]
+; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0, z0.d, sxtw]
 ; CHECK-NEXT:    and z0.d, z0.d, #0xffffffff
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i32> %offsets
@@ -56,12 +46,7 @@
 define <vscale x 2 x i64> @masked_gather_nxv2i64(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2i64:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ptrue p1.d
-; CHECK-NEXT:    sxtw z0.d, p1/m, z0.d
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8, z0.d, lsl #3]
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0, z0.d, sxtw]
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i32> %offsets
   %ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x i64*>
@@ -72,12 +57,7 @@
 define <vscale x 2 x half> @masked_gather_nxv2f16(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2f16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ptrue p1.d
-; CHECK-NEXT:    sxtw z0.d, p1/m, z0.d
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x8, z0.d, lsl #1]
+; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0, z0.d, sxtw]
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i32> %offsets
   %ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x half*>
@@ -88,12 +68,7 @@
 define <vscale x 2 x float> @masked_gather_nxv2f32(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2f32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ptrue p1.d
-; CHECK-NEXT:    sxtw z0.d, p1/m, z0.d
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x8, z0.d, lsl #2]
+; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0, z0.d, sxtw]
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i32> %offsets
   %ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x float*>
@@ -104,12 +79,7 @@
 define <vscale x 2 x double> @masked_gather_nxv2f64(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2f64:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ptrue p1.d
-; CHECK-NEXT:    sxtw z0.d, p1/m, z0.d
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8, z0.d, lsl #3]
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0, z0.d, sxtw]
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i32> %offsets
   %ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x double*>
@@ -133,13 +103,9 @@
 define <vscale x 2 x i64> @masked_sgather_nxv2i16(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_sgather_nxv2i16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ptrue p1.d
-; CHECK-NEXT:    sxtw z0.d, p1/m, z0.d
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x8, z0.d, lsl #1]
-; CHECK-NEXT:    sxth z0.d, p1/m, z0.d
+; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0, z0.d, sxtw]
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    sxth z0.d, p0/m, z0.d
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i32> %offsets
   %ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x i16*>
@@ -151,13 +117,9 @@
 define <vscale x 2 x i64> @masked_sgather_nxv2i32(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_sgather_nxv2i32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ptrue p1.d
-; CHECK-NEXT:    sxtw z0.d, p1/m, z0.d
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x8, z0.d, lsl #2]
-; CHECK-NEXT:    sxtw z0.d, p1/m, z0.d
+; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0, z0.d, sxtw]
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    sxtw z0.d, p0/m, z0.d
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i32> %offsets
   %ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x i32*>
@@ -185,18 +147,7 @@
 define <vscale x 4 x i32> @masked_gather_nxv4i16(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv4i16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    sunpklo z2.d, z0.s
-; CHECK-NEXT:    sunpkhi z0.d, z0.s
-; CHECK-NEXT:    pfalse p1.b
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z2.d, z1.d, z2.d
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    zip2 p2.s, p0.s, p1.s
-; CHECK-NEXT:    zip1 p0.s, p0.s, p1.s
-; CHECK-NEXT:    ld1h { z0.d }, p2/z, [x8, z0.d, lsl #1]
-; CHECK-NEXT:    ld1h { z1.d }, p0/z, [x8, z2.d, lsl #1]
-; CHECK-NEXT:    uzp1 z0.s, z1.s, z0.s
+; CHECK-NEXT:    ld1h { z0.s }, p0/z, [x0, z0.s, sxtw]
 ; CHECK-NEXT:    and z0.s, z0.s, #0xffff
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 4 x i32> %offsets
@@ -209,18 +160,7 @@
 define <vscale x 4 x i32> @masked_gather_nxv4i32(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv4i32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    sunpklo z2.d, z0.s
-; CHECK-NEXT:    sunpkhi z0.d, z0.s
-; CHECK-NEXT:    pfalse p1.b
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z2.d, z1.d, z2.d
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    zip2 p2.s, p0.s, p1.s
-; CHECK-NEXT:    zip1 p0.s, p0.s, p1.s
-; CHECK-NEXT:    ld1w { z0.d }, p2/z, [x8, z0.d, lsl #2]
-; CHECK-NEXT:    ld1w { z1.d }, p0/z, [x8, z2.d, lsl #2]
-; CHECK-NEXT:    uzp1 z0.s, z1.s, z0.s
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x0, z0.s, sxtw]
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 4 x i32> %offsets
   %ptrs = bitcast <vscale x 4 x i8*> %byte_ptrs to <vscale x 4 x i32*>
@@ -231,18 +171,7 @@
 define <vscale x 4 x half> @masked_gather_nxv4f16(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv4f16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    sunpklo z2.d, z0.s
-; CHECK-NEXT:    sunpkhi z0.d, z0.s
-; CHECK-NEXT:    pfalse p1.b
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z2.d, z1.d, z2.d
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    zip2 p2.s, p0.s, p1.s
-; CHECK-NEXT:    zip1 p0.s, p0.s, p1.s
-; CHECK-NEXT:    ld1h { z0.d }, p2/z, [x8, z0.d, lsl #1]
-; CHECK-NEXT:    ld1h { z1.d }, p0/z, [x8, z2.d, lsl #1]
-; CHECK-NEXT:    uzp1 z0.s, z1.s, z0.s
+; CHECK-NEXT:    ld1h { z0.s }, p0/z, [x0, z0.s, sxtw]
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 4 x i32> %offsets
   %ptrs = bitcast <vscale x 4 x i8*> %byte_ptrs to <vscale x 4 x half*>
@@ -253,18 +182,7 @@
 define <vscale x 4 x float> @masked_gather_nxv4f32(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv4f32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    sunpklo z2.d, z0.s
-; CHECK-NEXT:    sunpkhi z0.d, z0.s
-; CHECK-NEXT:    pfalse p1.b
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z2.d, z1.d, z2.d
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    zip2 p2.s, p0.s, p1.s
-; CHECK-NEXT:    zip1 p0.s, p0.s, p1.s
-; CHECK-NEXT:    ld1w { z0.d }, p2/z, [x8, z0.d, lsl #2]
-; CHECK-NEXT:    ld1w { z1.d }, p0/z, [x8, z2.d, lsl #2]
-; CHECK-NEXT:    uzp1 z0.s, z1.s, z0.s
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x0, z0.s, sxtw]
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 4 x i32> %offsets
   %ptrs = bitcast <vscale x 4 x i8*> %byte_ptrs to <vscale x 4 x float*>
@@ -288,19 +206,8 @@
 define <vscale x 4 x i32> @masked_sgather_nxv4i16(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: masked_sgather_nxv4i16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    sunpklo z2.d, z0.s
-; CHECK-NEXT:    sunpkhi z0.d, z0.s
-; CHECK-NEXT:    pfalse p1.b
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z2.d, z1.d, z2.d
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    zip2 p2.s, p0.s, p1.s
-; CHECK-NEXT:    zip1 p0.s, p0.s, p1.s
-; CHECK-NEXT:    ld1h { z0.d }, p2/z, [x8, z0.d, lsl #1]
-; CHECK-NEXT:    ld1h { z1.d }, p0/z, [x8, z2.d, lsl #1]
+; CHECK-NEXT:    ld1h { z0.s }, p0/z, [x0, z0.s, sxtw]
 ; CHECK-NEXT:    ptrue p0.s
-; CHECK-NEXT:    uzp1 z0.s, z1.s, z0.s
 ; CHECK-NEXT:    sxth z0.s, p0/m, z0.s
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 4 x i32> %offsets
Index: llvm/test/CodeGen/AArch64/sve-masked-gather-32b-unsigned-scaled.ll
===================================================================
--- llvm/test/CodeGen/AArch64/sve-masked-gather-32b-unsigned-scaled.ll
+++ llvm/test/CodeGen/AArch64/sve-masked-gather-32b-unsigned-scaled.ll
@@ -8,7 +8,7 @@
 define <vscale x 2 x i64> @masked_gather_nxv2i16(i16* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2i16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0, z0.d, sxtw #1]
+; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0, z0.d, uxtw #1]
 ; CHECK-NEXT:    and z0.d, z0.d, #0xffff
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
@@ -21,7 +21,7 @@
 define <vscale x 2 x i64> @masked_gather_nxv2i32(i32* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2i32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0, z0.d, sxtw #2]
+; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0, z0.d, uxtw #2]
 ; CHECK-NEXT:    and z0.d, z0.d, #0xffffffff
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
@@ -34,7 +34,7 @@
 define <vscale x 2 x i64> @masked_gather_nxv2i64(i64* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2i64:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0, z0.d, sxtw #3]
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0, z0.d, uxtw #3]
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
   %ptrs = getelementptr i64, i64* %base, <vscale x 2 x i64> %offsets.zext
@@ -45,7 +45,7 @@
 define <vscale x 2 x half> @masked_gather_nxv2f16(half* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2f16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0, z0.d, sxtw #1]
+; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0, z0.d, uxtw #1]
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
   %ptrs = getelementptr half, half* %base, <vscale x 2 x i64> %offsets.zext
@@ -56,7 +56,7 @@
 define <vscale x 2 x float> @masked_gather_nxv2f32(float* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2f32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0, z0.d, sxtw #2]
+; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0, z0.d, uxtw #2]
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
   %ptrs = getelementptr float, float* %base, <vscale x 2 x i64> %offsets.zext
@@ -67,7 +67,7 @@
 define <vscale x 2 x double> @masked_gather_nxv2f64(double* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2f64:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0, z0.d, sxtw #3]
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0, z0.d, uxtw #3]
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
   %ptrs = getelementptr double, double* %base, <vscale x 2 x i64> %offsets.zext
@@ -78,7 +78,7 @@
 define <vscale x 2 x i64> @masked_sgather_nxv2i16(i16* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_sgather_nxv2i16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0, z0.d, sxtw #1]
+; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0, z0.d, uxtw #1]
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    sxth z0.d, p0/m, z0.d
 ; CHECK-NEXT:    ret
@@ -92,7 +92,7 @@
 define <vscale x 2 x i64> @masked_sgather_nxv2i32(i32* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_sgather_nxv2i32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0, z0.d, sxtw #2]
+; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0, z0.d, uxtw #2]
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    sxtw z0.d, p0/m, z0.d
 ; CHECK-NEXT:    ret
@@ -110,14 +110,7 @@
 define <vscale x 4 x i32> @masked_gather_nxv4i16(i16* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv4i16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    pfalse p1.b
-; CHECK-NEXT:    uunpklo z1.d, z0.s
-; CHECK-NEXT:    uunpkhi z0.d, z0.s
-; CHECK-NEXT:    zip2 p2.s, p0.s, p1.s
-; CHECK-NEXT:    zip1 p0.s, p0.s, p1.s
-; CHECK-NEXT:    ld1h { z0.d }, p2/z, [x0, z0.d, sxtw #1]
-; CHECK-NEXT:    ld1h { z1.d }, p0/z, [x0, z1.d, sxtw #1]
-; CHECK-NEXT:    uzp1 z0.s, z1.s, z0.s
+; CHECK-NEXT:    ld1h { z0.s }, p0/z, [x0, z0.s, uxtw #1]
 ; CHECK-NEXT:    and z0.s, z0.s, #0xffff
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
@@ -130,14 +123,7 @@
 define <vscale x 4 x i32> @masked_gather_nxv4i32(i32* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv4i32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    pfalse p1.b
-; CHECK-NEXT:    uunpklo z1.d, z0.s
-; CHECK-NEXT:    uunpkhi z0.d, z0.s
-; CHECK-NEXT:    zip2 p2.s, p0.s, p1.s
-; CHECK-NEXT:    zip1 p0.s, p0.s, p1.s
-; CHECK-NEXT:    ld1w { z0.d }, p2/z, [x0, z0.d, sxtw #2]
-; CHECK-NEXT:    ld1w { z1.d }, p0/z, [x0, z1.d, sxtw #2]
-; CHECK-NEXT:    uzp1 z0.s, z1.s, z0.s
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x0, z0.s, uxtw #2]
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
   %ptrs = getelementptr i32, i32* %base, <vscale x 4 x i64> %offsets.zext
@@ -148,14 +134,7 @@
 define <vscale x 4 x half> @masked_gather_nxv4f16(half* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv4f16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    pfalse p1.b
-; CHECK-NEXT:    uunpklo z1.d, z0.s
-; CHECK-NEXT:    uunpkhi z0.d, z0.s
-; CHECK-NEXT:    zip2 p2.s, p0.s, p1.s
-; CHECK-NEXT:    zip1 p0.s, p0.s, p1.s
-; CHECK-NEXT:    ld1h { z0.d }, p2/z, [x0, z0.d, sxtw #1]
-; CHECK-NEXT:    ld1h { z1.d }, p0/z, [x0, z1.d, sxtw #1]
-; CHECK-NEXT:    uzp1 z0.s, z1.s, z0.s
+; CHECK-NEXT:    ld1h { z0.s }, p0/z, [x0, z0.s, uxtw #1]
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
   %ptrs = getelementptr half, half* %base, <vscale x 4 x i64> %offsets.zext
@@ -166,14 +145,7 @@
 define <vscale x 4 x float> @masked_gather_nxv4f32(float* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv4f32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    pfalse p1.b
-; CHECK-NEXT:    uunpklo z1.d, z0.s
-; CHECK-NEXT:    uunpkhi z0.d, z0.s
-; CHECK-NEXT:    zip2 p2.s, p0.s, p1.s
-; CHECK-NEXT:    zip1 p0.s, p0.s, p1.s
-; CHECK-NEXT:    ld1w { z0.d }, p2/z, [x0, z0.d, sxtw #2]
-; CHECK-NEXT:    ld1w { z1.d }, p0/z, [x0, z1.d, sxtw #2]
-; CHECK-NEXT:    uzp1 z0.s, z1.s, z0.s
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x0, z0.s, uxtw #2]
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
   %ptrs = getelementptr float, float* %base, <vscale x 4 x i64> %offsets.zext
@@ -184,15 +156,8 @@
 define <vscale x 4 x i32> @masked_sgather_nxv4i16(i16* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: masked_sgather_nxv4i16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    pfalse p1.b
-; CHECK-NEXT:    uunpklo z1.d, z0.s
-; CHECK-NEXT:    uunpkhi z0.d, z0.s
-; CHECK-NEXT:    zip2 p2.s, p0.s, p1.s
-; CHECK-NEXT:    zip1 p0.s, p0.s, p1.s
-; CHECK-NEXT:    ld1h { z0.d }, p2/z, [x0, z0.d, sxtw #1]
-; CHECK-NEXT:    ld1h { z1.d }, p0/z, [x0, z1.d, sxtw #1]
+; CHECK-NEXT:    ld1h { z0.s }, p0/z, [x0, z0.s, uxtw #1]
 ; CHECK-NEXT:    ptrue p0.s
-; CHECK-NEXT:    uzp1 z0.s, z1.s, z0.s
 ; CHECK-NEXT:    sxth z0.s, p0/m, z0.s
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
Index: llvm/test/CodeGen/AArch64/sve-masked-gather-32b-unsigned-unscaled.ll
===================================================================
--- llvm/test/CodeGen/AArch64/sve-masked-gather-32b-unsigned-unscaled.ll
+++ llvm/test/CodeGen/AArch64/sve-masked-gather-32b-unsigned-unscaled.ll
@@ -8,7 +8,7 @@
 define <vscale x 2 x i64> @masked_gather_nxv2i8(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2i8:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ld1b { z0.d }, p0/z, [x0, z0.d, sxtw]
+; CHECK-NEXT:    ld1b { z0.d }, p0/z, [x0, z0.d, uxtw]
 ; CHECK-NEXT:    and z0.d, z0.d, #0xff
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
@@ -21,11 +21,7 @@
 define <vscale x 2 x i64> @masked_gather_nxv2i16(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2i16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    and z0.d, z0.d, #0xffffffff
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x8, z0.d, lsl #1]
+; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0, z0.d, uxtw]
 ; CHECK-NEXT:    and z0.d, z0.d, #0xffff
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
@@ -39,11 +35,7 @@
 define <vscale x 2 x i64> @masked_gather_nxv2i32(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2i32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    and z0.d, z0.d, #0xffffffff
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x8, z0.d, lsl #2]
+; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0, z0.d, uxtw]
 ; CHECK-NEXT:    and z0.d, z0.d, #0xffffffff
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
@@ -57,11 +49,7 @@
 define <vscale x 2 x i64> @masked_gather_nxv2i64(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2i64:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    and z0.d, z0.d, #0xffffffff
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8, z0.d, lsl #3]
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0, z0.d, uxtw]
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets.zext
@@ -73,11 +61,7 @@
 define <vscale x 2 x half> @masked_gather_nxv2f16(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2f16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    and z0.d, z0.d, #0xffffffff
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x8, z0.d, lsl #1]
+; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0, z0.d, uxtw]
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets.zext
@@ -89,11 +73,7 @@
 define <vscale x 2 x float> @masked_gather_nxv2f32(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2f32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    and z0.d, z0.d, #0xffffffff
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x8, z0.d, lsl #2]
+; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0, z0.d, uxtw]
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets.zext
@@ -105,11 +85,7 @@
 define <vscale x 2 x double> @masked_gather_nxv2f64(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2f64:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    and z0.d, z0.d, #0xffffffff
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8, z0.d, lsl #3]
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0, z0.d, uxtw]
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets.zext
@@ -121,7 +97,7 @@
 define <vscale x 2 x i64> @masked_sgather_nxv2i8(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_sgather_nxv2i8:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ld1b { z0.d }, p0/z, [x0, z0.d, sxtw]
+; CHECK-NEXT:    ld1b { z0.d }, p0/z, [x0, z0.d, uxtw]
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    sxtb z0.d, p0/m, z0.d
 ; CHECK-NEXT:    ret
@@ -135,11 +111,7 @@
 define <vscale x 2 x i64> @masked_sgather_nxv2i16(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_sgather_nxv2i16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    and z0.d, z0.d, #0xffffffff
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x8, z0.d, lsl #1]
+; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0, z0.d, uxtw]
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    sxth z0.d, p0/m, z0.d
 ; CHECK-NEXT:    ret
@@ -154,11 +126,7 @@
 define <vscale x 2 x i64> @masked_sgather_nxv2i32(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_sgather_nxv2i32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    and z0.d, z0.d, #0xffffffff
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x8, z0.d, lsl #2]
+; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0, z0.d, uxtw]
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    sxtw z0.d, p0/m, z0.d
 ; CHECK-NEXT:    ret
@@ -177,14 +145,7 @@
 define <vscale x 4 x i32> @masked_gather_nxv4i8(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv4i8:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    pfalse p1.b
-; CHECK-NEXT:    uunpklo z1.d, z0.s
-; CHECK-NEXT:    uunpkhi z0.d, z0.s
-; CHECK-NEXT:    zip2 p2.s, p0.s, p1.s
-; CHECK-NEXT:    zip1 p0.s, p0.s, p1.s
-; CHECK-NEXT:    ld1b { z0.d }, p2/z, [x0, z0.d, sxtw]
-; CHECK-NEXT:    ld1b { z1.d }, p0/z, [x0, z1.d, sxtw]
-; CHECK-NEXT:    uzp1 z0.s, z1.s, z0.s
+; CHECK-NEXT:    ld1b { z0.s }, p0/z, [x0, z0.s, uxtw]
 ; CHECK-NEXT:    and z0.s, z0.s, #0xff
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
@@ -197,18 +158,7 @@
 define <vscale x 4 x i32> @masked_gather_nxv4i16(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv4i16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    uunpkhi z2.d, z0.s
-; CHECK-NEXT:    uunpklo z0.d, z0.s
-; CHECK-NEXT:    pfalse p1.b
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    add z1.d, z1.d, z2.d
-; CHECK-NEXT:    zip2 p2.s, p0.s, p1.s
-; CHECK-NEXT:    zip1 p0.s, p0.s, p1.s
-; CHECK-NEXT:    ld1h { z1.d }, p2/z, [x8, z1.d, lsl #1]
-; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x8, z0.d, lsl #1]
-; CHECK-NEXT:    uzp1 z0.s, z0.s, z1.s
+; CHECK-NEXT:    ld1h { z0.s }, p0/z, [x0, z0.s, uxtw]
 ; CHECK-NEXT:    and z0.s, z0.s, #0xffff
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
@@ -222,18 +172,7 @@
 define <vscale x 4 x i32> @masked_gather_nxv4i32(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv4i32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    uunpkhi z2.d, z0.s
-; CHECK-NEXT:    uunpklo z0.d, z0.s
-; CHECK-NEXT:    pfalse p1.b
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    add z1.d, z1.d, z2.d
-; CHECK-NEXT:    zip2 p2.s, p0.s, p1.s
-; CHECK-NEXT:    zip1 p0.s, p0.s, p1.s
-; CHECK-NEXT:    ld1w { z1.d }, p2/z, [x8, z1.d, lsl #2]
-; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x8, z0.d, lsl #2]
-; CHECK-NEXT:    uzp1 z0.s, z0.s, z1.s
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x0, z0.s, uxtw]
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 4 x i64> %offsets.zext
@@ -245,18 +184,7 @@
 define <vscale x 4 x half> @masked_gather_nxv4f16(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv4f16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    uunpkhi z2.d, z0.s
-; CHECK-NEXT:    uunpklo z0.d, z0.s
-; CHECK-NEXT:    pfalse p1.b
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    add z1.d, z1.d, z2.d
-; CHECK-NEXT:    zip2 p2.s, p0.s, p1.s
-; CHECK-NEXT:    zip1 p0.s, p0.s, p1.s
-; CHECK-NEXT:    ld1h { z1.d }, p2/z, [x8, z1.d, lsl #1]
-; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x8, z0.d, lsl #1]
-; CHECK-NEXT:    uzp1 z0.s, z0.s, z1.s
+; CHECK-NEXT:    ld1h { z0.s }, p0/z, [x0, z0.s, uxtw]
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 4 x i64> %offsets.zext
@@ -268,18 +196,7 @@
 define <vscale x 4 x float> @masked_gather_nxv4f32(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv4f32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    uunpkhi z2.d, z0.s
-; CHECK-NEXT:    uunpklo z0.d, z0.s
-; CHECK-NEXT:    pfalse p1.b
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    add z1.d, z1.d, z2.d
-; CHECK-NEXT:    zip2 p2.s, p0.s, p1.s
-; CHECK-NEXT:    zip1 p0.s, p0.s, p1.s
-; CHECK-NEXT:    ld1w { z1.d }, p2/z, [x8, z1.d, lsl #2]
-; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x8, z0.d, lsl #2]
-; CHECK-NEXT:    uzp1 z0.s, z0.s, z1.s
+; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x0, z0.s, uxtw]
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 4 x i64> %offsets.zext
@@ -291,15 +208,8 @@
 define <vscale x 4 x i32> @masked_sgather_nxv4i8(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: masked_sgather_nxv4i8:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    pfalse p1.b
-; CHECK-NEXT:    uunpklo z1.d, z0.s
-; CHECK-NEXT:    uunpkhi z0.d, z0.s
-; CHECK-NEXT:    zip2 p2.s, p0.s, p1.s
-; CHECK-NEXT:    zip1 p0.s, p0.s, p1.s
-; CHECK-NEXT:    ld1b { z0.d }, p2/z, [x0, z0.d, sxtw]
-; CHECK-NEXT:    ld1b { z1.d }, p0/z, [x0, z1.d, sxtw]
+; CHECK-NEXT:    ld1b { z0.s }, p0/z, [x0, z0.s, uxtw]
 ; CHECK-NEXT:    ptrue p0.s
-; CHECK-NEXT:    uzp1 z0.s, z1.s, z0.s
 ; CHECK-NEXT:    sxtb z0.s, p0/m, z0.s
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
@@ -312,19 +222,8 @@
 define <vscale x 4 x i32> @masked_sgather_nxv4i16(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
 ; CHECK-LABEL: masked_sgather_nxv4i16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    uunpkhi z2.d, z0.s
-; CHECK-NEXT:    uunpklo z0.d, z0.s
-; CHECK-NEXT:    pfalse p1.b
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    add z1.d, z1.d, z2.d
-; CHECK-NEXT:    zip2 p2.s, p0.s, p1.s
-; CHECK-NEXT:    zip1 p0.s, p0.s, p1.s
-; CHECK-NEXT:    ld1h { z1.d }, p2/z, [x8, z1.d, lsl #1]
-; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x8, z0.d, lsl #1]
+; CHECK-NEXT:    ld1h { z0.s }, p0/z, [x0, z0.s, uxtw]
 ; CHECK-NEXT:    ptrue p0.s
-; CHECK-NEXT:    uzp1 z0.s, z0.s, z1.s
 ; CHECK-NEXT:    sxth z0.s, p0/m, z0.s
 ; CHECK-NEXT:    ret
   %offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
Index: llvm/test/CodeGen/AArch64/sve-masked-gather-64b-unscaled.ll
===================================================================
--- llvm/test/CodeGen/AArch64/sve-masked-gather-64b-unscaled.ll
+++ llvm/test/CodeGen/AArch64/sve-masked-gather-64b-unscaled.ll
@@ -16,10 +16,7 @@
 define <vscale x 2 x i64> @masked_gather_nxv2i16(i8* %base, <vscale x 2 x i64> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2i16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x8, z0.d, lsl #1]
+; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0, z0.d]
 ; CHECK-NEXT:    and z0.d, z0.d, #0xffff
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets
@@ -32,10 +29,7 @@
 define <vscale x 2 x i64> @masked_gather_nxv2i32(i8* %base, <vscale x 2 x i64> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2i32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x8, z0.d, lsl #2]
+; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0, z0.d]
 ; CHECK-NEXT:    and z0.d, z0.d, #0xffffffff
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets
@@ -48,10 +42,7 @@
 define <vscale x 2 x i64> @masked_gather_nxv2i64(i8* %base, <vscale x 2 x i64> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2i64:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8, z0.d, lsl #3]
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0, z0.d]
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets
   %ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x i64*>
@@ -62,10 +53,7 @@
 define <vscale x 2 x half> @masked_gather_nxv2f16(i8* %base, <vscale x 2 x i64> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2f16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x8, z0.d, lsl #1]
+; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0, z0.d]
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets
   %ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x half*>
@@ -76,10 +64,7 @@
 define <vscale x 2 x float> @masked_gather_nxv2f32(i8* %base, <vscale x 2 x i64> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2f32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x8, z0.d, lsl #2]
+; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0, z0.d]
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets
   %ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x float*>
@@ -90,10 +75,7 @@
 define <vscale x 2 x double> @masked_gather_nxv2f64(i8* %base, <vscale x 2 x i64> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2f64:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x8, z0.d, lsl #3]
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0, z0.d]
 ; CHECK-NEXT:    ret
   %byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets
   %ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x double*>
@@ -117,10 +99,7 @@
 define <vscale x 2 x i64> @masked_sgather_nxv2i16(i8* %base, <vscale x 2 x i64> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_sgather_nxv2i16:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x8, z0.d, lsl #1]
+; CHECK-NEXT:    ld1h { z0.d }, p0/z, [x0, z0.d]
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    sxth z0.d, p0/m, z0.d
 ; CHECK-NEXT:    ret
@@ -134,10 +113,7 @@
 define <vscale x 2 x i64> @masked_sgather_nxv2i32(i8* %base, <vscale x 2 x i64> %offsets, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_sgather_nxv2i32:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov z1.d, x0
-; CHECK-NEXT:    mov x8, xzr
-; CHECK-NEXT:    add z0.d, z1.d, z0.d
-; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x8, z0.d, lsl #2]
+; CHECK-NEXT:    ld1w { z0.d }, p0/z, [x0, z0.d]
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    sxtw z0.d, p0/m, z0.d
 ; CHECK-NEXT:    ret
Index: llvm/test/CodeGen/AArch64/sve-masked-gather-legalize.ll
===================================================================
--- llvm/test/CodeGen/AArch64/sve-masked-gather-legalize.ll
+++ llvm/test/CodeGen/AArch64/sve-masked-gather-legalize.ll
@@ -7,7 +7,7 @@
 define <vscale x 2 x i32> @masked_gather_nxv2i32(<vscale x 2 x i32*> %ptrs, <vscale x 2 x i1> %mask) {
 ; CHECK-LABEL: masked_gather_nxv2i32:
 ; CHECK-DAG: mov x8, xzr
-; CHECK-DAG: ld1w { z0.d }, p0/z, [x8, z0.d, lsl #2]
+; CHECK-DAG: ld1w { z0.d }, p0/z, [x8, z0.d]
 ; CHECK:     ret
   %data = call <vscale x 2 x i32> @llvm.masked.gather.nxv2i32(<vscale x 2 x i32*> %ptrs, i32 4, <vscale x 2 x i1> %mask, <vscale x 2 x i32> undef)
   ret <vscale x 2 x i32> %data
Index: llvm/test/CodeGen/X86/masked_gather_scatter.ll
===================================================================
--- llvm/test/CodeGen/X86/masked_gather_scatter.ll
+++ llvm/test/CodeGen/X86/masked_gather_scatter.ll
@@ -765,45 +765,41 @@
 define <16 x float> @test14(float* %base, i32 %ind, <16 x float*> %vec) {
 ; KNL_64-LABEL: test14:
 ; KNL_64:       # %bb.0:
-; KNL_64-NEXT:    vpbroadcastq %xmm0, %zmm0
-; KNL_64-NEXT:    vmovd %esi, %xmm1
-; KNL_64-NEXT:    vpbroadcastd %xmm1, %ymm1
-; KNL_64-NEXT:    vpmovsxdq %ymm1, %zmm1
-; KNL_64-NEXT:    vpsllq $2, %zmm1, %zmm1
-; KNL_64-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
+; KNL_64-NEXT:    vmovq %xmm0, %rax
+; KNL_64-NEXT:    vmovd %esi, %xmm0
+; KNL_64-NEXT:    vpbroadcastd %xmm0, %ymm0
+; KNL_64-NEXT:    vpmovsxdq %ymm0, %zmm0
+; KNL_64-NEXT:    vpsllq $2, %zmm0, %zmm0
 ; KNL_64-NEXT:    kxnorw %k0, %k0, %k1
-; KNL_64-NEXT:    vgatherqps (,%zmm0), %ymm1 {%k1}
+; KNL_64-NEXT:    vgatherqps (%rax,%zmm0), %ymm1 {%k1}
 ; KNL_64-NEXT:    vinsertf64x4 $1, %ymm1, %zmm1, %zmm0
 ; KNL_64-NEXT:    retq
 ;
 ; KNL_32-LABEL: test14:
 ; KNL_32:       # %bb.0:
-; KNL_32-NEXT:    vpbroadcastd %xmm0, %zmm0
+; KNL_32-NEXT:    vmovd %xmm0, %eax
 ; KNL_32-NEXT:    vpslld $2, {{[0-9]+}}(%esp){1to16}, %zmm1
-; KNL_32-NEXT:    vpaddd %zmm1, %zmm0, %zmm1
 ; KNL_32-NEXT:    kxnorw %k0, %k0, %k1
-; KNL_32-NEXT:    vgatherdps (,%zmm1), %zmm0 {%k1}
+; KNL_32-NEXT:    vgatherdps (%eax,%zmm1), %zmm0 {%k1}
 ; KNL_32-NEXT:    retl
 ;
 ; SKX-LABEL: test14:
 ; SKX:       # %bb.0:
-; SKX-NEXT:    vpbroadcastq %xmm0, %zmm0
-; SKX-NEXT:    vpbroadcastd %esi, %ymm1
-; SKX-NEXT:    vpmovsxdq %ymm1, %zmm1
-; SKX-NEXT:    vpsllq $2, %zmm1, %zmm1
-; SKX-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
+; SKX-NEXT:    vmovq %xmm0, %rax
+; SKX-NEXT:    vpbroadcastd %esi, %ymm0
+; SKX-NEXT:    vpmovsxdq %ymm0, %zmm0
+; SKX-NEXT:    vpsllq $2, %zmm0, %zmm0
 ; SKX-NEXT:    kxnorw %k0, %k0, %k1
-; SKX-NEXT:    vgatherqps (,%zmm0), %ymm1 {%k1}
+; SKX-NEXT:    vgatherqps (%rax,%zmm0), %ymm1 {%k1}
 ; SKX-NEXT:    vinsertf64x4 $1, %ymm1, %zmm1, %zmm0
 ; SKX-NEXT:    retq
 ;
 ; SKX_32-LABEL: test14:
 ; SKX_32:       # %bb.0:
-; SKX_32-NEXT:    vpbroadcastd %xmm0, %zmm0
+; SKX_32-NEXT:    vmovd %xmm0, %eax
 ; SKX_32-NEXT:    vpslld $2, {{[0-9]+}}(%esp){1to16}, %zmm1
-; SKX_32-NEXT:    vpaddd %zmm1, %zmm0, %zmm1
 ; SKX_32-NEXT:    kxnorw %k0, %k0, %k1
-; SKX_32-NEXT:    vgatherdps (,%zmm1), %zmm0 {%k1}
+; SKX_32-NEXT:    vgatherdps (%eax,%zmm1), %zmm0 {%k1}
 ; SKX_32-NEXT:    retl
 
   %broadcast.splatinsert = insertelement <16 x float*> %vec, float* %base, i32 1