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
@@ -15316,6 +15316,40 @@
   return SDValue();
 }
 
+static bool isCheapToExtend(const SDValue &N) {
+  unsigned OC = N->getOpcode();
+  return OC == ISD::LOAD || OC == ISD::MLOAD ||
+         ISD::isConstantSplatVectorAllZeros(N.getNode());
+}
+
+static SDValue
+performSignExtendSetCCCombine(SDNode *N, TargetLowering::DAGCombinerInfo &DCI,
+                              SelectionDAG &DAG) {
+  // If we have (sext (setcc A B)) and A and B are cheap to extend,
+  // we can move the sext into the arguments and have the same result. For
+  // example, if A and B are both loads, we can make those extending loads and
+  // avoid an extra instruction. This pattern appears often in VLS code
+  // generation where the inputs to the setcc have a different size to the
+  // instruction that wants to use the result of the setcc.
+  assert(N->getOpcode() == ISD::SIGN_EXTEND &&
+         N->getOperand(0)->getOpcode() == ISD::SETCC);
+  const SDValue SetCC = N->getOperand(0);
+
+  if (isCheapToExtend(SetCC.getOperand(0)) &&
+      isCheapToExtend(SetCC.getOperand(1))) {
+    const SDValue Ext1 = DAG.getNode(ISD::SIGN_EXTEND, SDLoc(N),
+                                     N->getValueType(0), SetCC.getOperand(0));
+    const SDValue Ext2 = DAG.getNode(ISD::SIGN_EXTEND, SDLoc(N),
+                                     N->getValueType(0), SetCC.getOperand(1));
+
+    return DAG.getSetCC(
+        SDLoc(SetCC), N->getValueType(0), Ext1, Ext2,
+        cast<CondCodeSDNode>(SetCC->getOperand(2).getNode())->get());
+  }
+
+  return SDValue();
+}
+
 static SDValue performExtendCombine(SDNode *N,
                                     TargetLowering::DAGCombinerInfo &DCI,
                                     SelectionDAG &DAG) {
@@ -15334,6 +15368,11 @@
 
     return DAG.getNode(ISD::ZERO_EXTEND, SDLoc(N), N->getValueType(0), NewABD);
   }
+
+  if (N->getOpcode() == ISD::SIGN_EXTEND &&
+      N->getOperand(0)->getOpcode() == ISD::SETCC)
+    return performSignExtendSetCCCombine(N, DCI, DAG);
+
   return SDValue();
 }
 
diff --git a/llvm/test/CodeGen/AArch64/sve-fixed-length-masked-loads.ll b/llvm/test/CodeGen/AArch64/sve-fixed-length-masked-loads.ll
--- a/llvm/test/CodeGen/AArch64/sve-fixed-length-masked-loads.ll
+++ b/llvm/test/CodeGen/AArch64/sve-fixed-length-masked-loads.ll
@@ -265,12 +265,10 @@
 define <32 x i16> @masked_load_sext_v32i8i16(<32 x i8>* %ap, <32 x i8>* %bp) #0 {
 ; VBITS_GE_512-LABEL: masked_load_sext_v32i8i16:
 ; VBITS_GE_512:       // %bb.0:
-; VBITS_GE_512-NEXT:    ptrue p0.b, vl32
-; VBITS_GE_512-NEXT:    ld1b { z0.b }, p0/z, [x1]
-; VBITS_GE_512-NEXT:    cmpeq p0.b, p0/z, z0.b, #0
-; VBITS_GE_512-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_512-NEXT:    ld1sb { z0.h }, p0/z, [x0]
 ; VBITS_GE_512-NEXT:    ptrue p0.h, vl32
+; VBITS_GE_512-NEXT:    ld1sb { z0.h }, p0/z, [x1]
+; VBITS_GE_512-NEXT:    cmpeq p1.h, p0/z, z0.h, #0
+; VBITS_GE_512-NEXT:    ld1sb { z0.h }, p1/z, [x0]
 ; VBITS_GE_512-NEXT:    st1h { z0.h }, p0, [x8]
 ; VBITS_GE_512-NEXT:    ret
   %b = load <32 x i8>, <32 x i8>* %bp
@@ -283,12 +281,9 @@
 define <16 x i32> @masked_load_sext_v16i8i32(<16 x i8>* %ap, <16 x i8>* %bp) #0 {
 ; VBITS_GE_512-LABEL: masked_load_sext_v16i8i32:
 ; VBITS_GE_512:       // %bb.0:
-; VBITS_GE_512-NEXT:    ldr q0, [x1]
 ; VBITS_GE_512-NEXT:    ptrue p0.s, vl16
-; VBITS_GE_512-NEXT:    cmeq v0.16b, v0.16b, #0
-; VBITS_GE_512-NEXT:    sunpklo z0.h, z0.b
-; VBITS_GE_512-NEXT:    sunpklo z0.s, z0.h
-; VBITS_GE_512-NEXT:    cmpne p1.s, p0/z, z0.s, #0
+; VBITS_GE_512-NEXT:    ld1sb { z0.s }, p0/z, [x1]
+; VBITS_GE_512-NEXT:    cmpeq p1.s, p0/z, z0.s, #0
 ; VBITS_GE_512-NEXT:    ld1sb { z0.s }, p1/z, [x0]
 ; VBITS_GE_512-NEXT:    st1w { z0.s }, p0, [x8]
 ; VBITS_GE_512-NEXT:    ret
@@ -302,13 +297,9 @@
 define <8 x i64> @masked_load_sext_v8i8i64(<8 x i8>* %ap, <8 x i8>* %bp) #0 {
 ; VBITS_GE_512-LABEL: masked_load_sext_v8i8i64:
 ; VBITS_GE_512:       // %bb.0:
-; VBITS_GE_512-NEXT:    ldr d0, [x1]
 ; VBITS_GE_512-NEXT:    ptrue p0.d, vl8
-; VBITS_GE_512-NEXT:    cmeq v0.8b, v0.8b, #0
-; VBITS_GE_512-NEXT:    sunpklo z0.h, z0.b
-; VBITS_GE_512-NEXT:    sunpklo z0.s, z0.h
-; VBITS_GE_512-NEXT:    sunpklo z0.d, z0.s
-; VBITS_GE_512-NEXT:    cmpne p1.d, p0/z, z0.d, #0
+; VBITS_GE_512-NEXT:    ld1sb { z0.d }, p0/z, [x1]
+; VBITS_GE_512-NEXT:    cmpeq p1.d, p0/z, z0.d, #0
 ; VBITS_GE_512-NEXT:    ld1sb { z0.d }, p1/z, [x0]
 ; VBITS_GE_512-NEXT:    st1d { z0.d }, p0, [x8]
 ; VBITS_GE_512-NEXT:    ret
@@ -322,12 +313,10 @@
 define <16 x i32> @masked_load_sext_v16i16i32(<16 x i16>* %ap, <16 x i16>* %bp) #0 {
 ; VBITS_GE_512-LABEL: masked_load_sext_v16i16i32:
 ; VBITS_GE_512:       // %bb.0:
-; VBITS_GE_512-NEXT:    ptrue p0.h, vl16
-; VBITS_GE_512-NEXT:    ld1h { z0.h }, p0/z, [x1]
-; VBITS_GE_512-NEXT:    cmpeq p0.h, p0/z, z0.h, #0
-; VBITS_GE_512-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_512-NEXT:    ld1sh { z0.s }, p0/z, [x0]
 ; VBITS_GE_512-NEXT:    ptrue p0.s, vl16
+; VBITS_GE_512-NEXT:    ld1sh { z0.s }, p0/z, [x1]
+; VBITS_GE_512-NEXT:    cmpeq p1.s, p0/z, z0.s, #0
+; VBITS_GE_512-NEXT:    ld1sh { z0.s }, p1/z, [x0]
 ; VBITS_GE_512-NEXT:    st1w { z0.s }, p0, [x8]
 ; VBITS_GE_512-NEXT:    ret
   %b = load <16 x i16>, <16 x i16>* %bp
@@ -340,12 +329,9 @@
 define <8 x i64> @masked_load_sext_v8i16i64(<8 x i16>* %ap, <8 x i16>* %bp) #0 {
 ; VBITS_GE_512-LABEL: masked_load_sext_v8i16i64:
 ; VBITS_GE_512:       // %bb.0:
-; VBITS_GE_512-NEXT:    ldr q0, [x1]
 ; VBITS_GE_512-NEXT:    ptrue p0.d, vl8
-; VBITS_GE_512-NEXT:    cmeq v0.8h, v0.8h, #0
-; VBITS_GE_512-NEXT:    sunpklo z0.s, z0.h
-; VBITS_GE_512-NEXT:    sunpklo z0.d, z0.s
-; VBITS_GE_512-NEXT:    cmpne p1.d, p0/z, z0.d, #0
+; VBITS_GE_512-NEXT:    ld1sh { z0.d }, p0/z, [x1]
+; VBITS_GE_512-NEXT:    cmpeq p1.d, p0/z, z0.d, #0
 ; VBITS_GE_512-NEXT:    ld1sh { z0.d }, p1/z, [x0]
 ; VBITS_GE_512-NEXT:    st1d { z0.d }, p0, [x8]
 ; VBITS_GE_512-NEXT:    ret
@@ -359,12 +345,10 @@
 define <8 x i64> @masked_load_sext_v8i32i64(<8 x i32>* %ap, <8 x i32>* %bp) #0 {
 ; VBITS_GE_512-LABEL: masked_load_sext_v8i32i64:
 ; VBITS_GE_512:       // %bb.0:
-; VBITS_GE_512-NEXT:    ptrue p0.s, vl8
-; VBITS_GE_512-NEXT:    ld1w { z0.s }, p0/z, [x1]
-; VBITS_GE_512-NEXT:    cmpeq p0.s, p0/z, z0.s, #0
-; VBITS_GE_512-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_512-NEXT:    ld1sw { z0.d }, p0/z, [x0]
 ; VBITS_GE_512-NEXT:    ptrue p0.d, vl8
+; VBITS_GE_512-NEXT:    ld1sw { z0.d }, p0/z, [x1]
+; VBITS_GE_512-NEXT:    cmpeq p1.d, p0/z, z0.d, #0
+; VBITS_GE_512-NEXT:    ld1sw { z0.d }, p1/z, [x0]
 ; VBITS_GE_512-NEXT:    st1d { z0.d }, p0, [x8]
 ; VBITS_GE_512-NEXT:    ret
   %b = load <8 x i32>, <8 x i32>* %bp
@@ -377,12 +361,10 @@
 define <32 x i16> @masked_load_zext_v32i8i16(<32 x i8>* %ap, <32 x i8>* %bp) #0 {
 ; VBITS_GE_512-LABEL: masked_load_zext_v32i8i16:
 ; VBITS_GE_512:       // %bb.0:
-; VBITS_GE_512-NEXT:    ptrue p0.b, vl32
-; VBITS_GE_512-NEXT:    ld1b { z0.b }, p0/z, [x1]
-; VBITS_GE_512-NEXT:    cmpeq p0.b, p0/z, z0.b, #0
-; VBITS_GE_512-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_512-NEXT:    ld1b { z0.h }, p0/z, [x0]
 ; VBITS_GE_512-NEXT:    ptrue p0.h, vl32
+; VBITS_GE_512-NEXT:    ld1sb { z0.h }, p0/z, [x1]
+; VBITS_GE_512-NEXT:    cmpeq p1.h, p0/z, z0.h, #0
+; VBITS_GE_512-NEXT:    ld1b { z0.h }, p1/z, [x0]
 ; VBITS_GE_512-NEXT:    st1h { z0.h }, p0, [x8]
 ; VBITS_GE_512-NEXT:    ret
   %b = load <32 x i8>, <32 x i8>* %bp
@@ -395,12 +377,9 @@
 define <16 x i32> @masked_load_zext_v16i8i32(<16 x i8>* %ap, <16 x i8>* %bp) #0 {
 ; VBITS_GE_512-LABEL: masked_load_zext_v16i8i32:
 ; VBITS_GE_512:       // %bb.0:
-; VBITS_GE_512-NEXT:    ldr q0, [x1]
 ; VBITS_GE_512-NEXT:    ptrue p0.s, vl16
-; VBITS_GE_512-NEXT:    cmeq v0.16b, v0.16b, #0
-; VBITS_GE_512-NEXT:    sunpklo z0.h, z0.b
-; VBITS_GE_512-NEXT:    sunpklo z0.s, z0.h
-; VBITS_GE_512-NEXT:    cmpne p1.s, p0/z, z0.s, #0
+; VBITS_GE_512-NEXT:    ld1sb { z0.s }, p0/z, [x1]
+; VBITS_GE_512-NEXT:    cmpeq p1.s, p0/z, z0.s, #0
 ; VBITS_GE_512-NEXT:    ld1b { z0.s }, p1/z, [x0]
 ; VBITS_GE_512-NEXT:    st1w { z0.s }, p0, [x8]
 ; VBITS_GE_512-NEXT:    ret
@@ -414,13 +393,9 @@
 define <8 x i64> @masked_load_zext_v8i8i64(<8 x i8>* %ap, <8 x i8>* %bp) #0 {
 ; VBITS_GE_512-LABEL: masked_load_zext_v8i8i64:
 ; VBITS_GE_512:       // %bb.0:
-; VBITS_GE_512-NEXT:    ldr d0, [x1]
 ; VBITS_GE_512-NEXT:    ptrue p0.d, vl8
-; VBITS_GE_512-NEXT:    cmeq v0.8b, v0.8b, #0
-; VBITS_GE_512-NEXT:    sunpklo z0.h, z0.b
-; VBITS_GE_512-NEXT:    sunpklo z0.s, z0.h
-; VBITS_GE_512-NEXT:    sunpklo z0.d, z0.s
-; VBITS_GE_512-NEXT:    cmpne p1.d, p0/z, z0.d, #0
+; VBITS_GE_512-NEXT:    ld1sb { z0.d }, p0/z, [x1]
+; VBITS_GE_512-NEXT:    cmpeq p1.d, p0/z, z0.d, #0
 ; VBITS_GE_512-NEXT:    ld1b { z0.d }, p1/z, [x0]
 ; VBITS_GE_512-NEXT:    st1d { z0.d }, p0, [x8]
 ; VBITS_GE_512-NEXT:    ret
@@ -434,12 +409,10 @@
 define <16 x i32> @masked_load_zext_v16i16i32(<16 x i16>* %ap, <16 x i16>* %bp) #0 {
 ; VBITS_GE_512-LABEL: masked_load_zext_v16i16i32:
 ; VBITS_GE_512:       // %bb.0:
-; VBITS_GE_512-NEXT:    ptrue p0.h, vl16
-; VBITS_GE_512-NEXT:    ld1h { z0.h }, p0/z, [x1]
-; VBITS_GE_512-NEXT:    cmpeq p0.h, p0/z, z0.h, #0
-; VBITS_GE_512-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_512-NEXT:    ld1h { z0.s }, p0/z, [x0]
 ; VBITS_GE_512-NEXT:    ptrue p0.s, vl16
+; VBITS_GE_512-NEXT:    ld1sh { z0.s }, p0/z, [x1]
+; VBITS_GE_512-NEXT:    cmpeq p1.s, p0/z, z0.s, #0
+; VBITS_GE_512-NEXT:    ld1h { z0.s }, p1/z, [x0]
 ; VBITS_GE_512-NEXT:    st1w { z0.s }, p0, [x8]
 ; VBITS_GE_512-NEXT:    ret
   %b = load <16 x i16>, <16 x i16>* %bp
@@ -452,12 +425,9 @@
 define <8 x i64> @masked_load_zext_v8i16i64(<8 x i16>* %ap, <8 x i16>* %bp) #0 {
 ; VBITS_GE_512-LABEL: masked_load_zext_v8i16i64:
 ; VBITS_GE_512:       // %bb.0:
-; VBITS_GE_512-NEXT:    ldr q0, [x1]
 ; VBITS_GE_512-NEXT:    ptrue p0.d, vl8
-; VBITS_GE_512-NEXT:    cmeq v0.8h, v0.8h, #0
-; VBITS_GE_512-NEXT:    sunpklo z0.s, z0.h
-; VBITS_GE_512-NEXT:    sunpklo z0.d, z0.s
-; VBITS_GE_512-NEXT:    cmpne p1.d, p0/z, z0.d, #0
+; VBITS_GE_512-NEXT:    ld1sh { z0.d }, p0/z, [x1]
+; VBITS_GE_512-NEXT:    cmpeq p1.d, p0/z, z0.d, #0
 ; VBITS_GE_512-NEXT:    ld1h { z0.d }, p1/z, [x0]
 ; VBITS_GE_512-NEXT:    st1d { z0.d }, p0, [x8]
 ; VBITS_GE_512-NEXT:    ret
@@ -471,12 +441,10 @@
 define <8 x i64> @masked_load_zext_v8i32i64(<8 x i32>* %ap, <8 x i32>* %bp) #0 {
 ; VBITS_GE_512-LABEL: masked_load_zext_v8i32i64:
 ; VBITS_GE_512:       // %bb.0:
-; VBITS_GE_512-NEXT:    ptrue p0.s, vl8
-; VBITS_GE_512-NEXT:    ld1w { z0.s }, p0/z, [x1]
-; VBITS_GE_512-NEXT:    cmpeq p0.s, p0/z, z0.s, #0
-; VBITS_GE_512-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_512-NEXT:    ld1w { z0.d }, p0/z, [x0]
 ; VBITS_GE_512-NEXT:    ptrue p0.d, vl8
+; VBITS_GE_512-NEXT:    ld1sw { z0.d }, p0/z, [x1]
+; VBITS_GE_512-NEXT:    cmpeq p1.d, p0/z, z0.d, #0
+; VBITS_GE_512-NEXT:    ld1w { z0.d }, p1/z, [x0]
 ; VBITS_GE_512-NEXT:    st1d { z0.d }, p0, [x8]
 ; VBITS_GE_512-NEXT:    ret
   %b = load <8 x i32>, <8 x i32>* %bp
@@ -681,12 +649,10 @@
 define <128 x i16> @masked_load_sext_v128i8i16(<128 x i8>* %ap, <128 x i8>* %bp) #0 {
 ; VBITS_GE_2048-LABEL: masked_load_sext_v128i8i16:
 ; VBITS_GE_2048:       // %bb.0:
-; VBITS_GE_2048-NEXT:    ptrue p0.b, vl128
-; VBITS_GE_2048-NEXT:    ld1b { z0.b }, p0/z, [x1]
-; VBITS_GE_2048-NEXT:    cmpeq p0.b, p0/z, z0.b, #0
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    ld1sb { z0.h }, p0/z, [x0]
 ; VBITS_GE_2048-NEXT:    ptrue p0.h, vl128
+; VBITS_GE_2048-NEXT:    ld1sb { z0.h }, p0/z, [x1]
+; VBITS_GE_2048-NEXT:    cmpeq p1.h, p0/z, z0.h, #0
+; VBITS_GE_2048-NEXT:    ld1sb { z0.h }, p1/z, [x0]
 ; VBITS_GE_2048-NEXT:    st1h { z0.h }, p0, [x8]
 ; VBITS_GE_2048-NEXT:    ret
   %b = load <128 x i8>, <128 x i8>* %bp
@@ -699,13 +665,10 @@
 define <64 x i32> @masked_load_sext_v64i8i32(<64 x i8>* %ap, <64 x i8>* %bp) #0 {
 ; VBITS_GE_2048-LABEL: masked_load_sext_v64i8i32:
 ; VBITS_GE_2048:       // %bb.0:
-; VBITS_GE_2048-NEXT:    ptrue p0.b, vl64
-; VBITS_GE_2048-NEXT:    ld1b { z0.b }, p0/z, [x1]
-; VBITS_GE_2048-NEXT:    cmpeq p0.b, p0/z, z0.b, #0
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    ld1sb { z0.s }, p0/z, [x0]
 ; VBITS_GE_2048-NEXT:    ptrue p0.s, vl64
+; VBITS_GE_2048-NEXT:    ld1sb { z0.s }, p0/z, [x1]
+; VBITS_GE_2048-NEXT:    cmpeq p1.s, p0/z, z0.s, #0
+; VBITS_GE_2048-NEXT:    ld1sb { z0.s }, p1/z, [x0]
 ; VBITS_GE_2048-NEXT:    st1w { z0.s }, p0, [x8]
 ; VBITS_GE_2048-NEXT:    ret
   %b = load <64 x i8>, <64 x i8>* %bp
@@ -718,14 +681,10 @@
 define <32 x i64> @masked_load_sext_v32i8i64(<32 x i8>* %ap, <32 x i8>* %bp) #0 {
 ; VBITS_GE_2048-LABEL: masked_load_sext_v32i8i64:
 ; VBITS_GE_2048:       // %bb.0:
-; VBITS_GE_2048-NEXT:    ptrue p0.b, vl32
-; VBITS_GE_2048-NEXT:    ld1b { z0.b }, p0/z, [x1]
-; VBITS_GE_2048-NEXT:    cmpeq p0.b, p0/z, z0.b, #0
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    ld1sb { z0.d }, p0/z, [x0]
 ; VBITS_GE_2048-NEXT:    ptrue p0.d, vl32
+; VBITS_GE_2048-NEXT:    ld1sb { z0.d }, p0/z, [x1]
+; VBITS_GE_2048-NEXT:    cmpeq p1.d, p0/z, z0.d, #0
+; VBITS_GE_2048-NEXT:    ld1sb { z0.d }, p1/z, [x0]
 ; VBITS_GE_2048-NEXT:    st1d { z0.d }, p0, [x8]
 ; VBITS_GE_2048-NEXT:    ret
   %b = load <32 x i8>, <32 x i8>* %bp
@@ -738,12 +697,10 @@
 define <64 x i32> @masked_load_sext_v64i16i32(<64 x i16>* %ap, <64 x i16>* %bp) #0 {
 ; VBITS_GE_2048-LABEL: masked_load_sext_v64i16i32:
 ; VBITS_GE_2048:       // %bb.0:
-; VBITS_GE_2048-NEXT:    ptrue p0.h, vl64
-; VBITS_GE_2048-NEXT:    ld1h { z0.h }, p0/z, [x1]
-; VBITS_GE_2048-NEXT:    cmpeq p0.h, p0/z, z0.h, #0
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    ld1sh { z0.s }, p0/z, [x0]
 ; VBITS_GE_2048-NEXT:    ptrue p0.s, vl64
+; VBITS_GE_2048-NEXT:    ld1sh { z0.s }, p0/z, [x1]
+; VBITS_GE_2048-NEXT:    cmpeq p1.s, p0/z, z0.s, #0
+; VBITS_GE_2048-NEXT:    ld1sh { z0.s }, p1/z, [x0]
 ; VBITS_GE_2048-NEXT:    st1w { z0.s }, p0, [x8]
 ; VBITS_GE_2048-NEXT:    ret
   %b = load <64 x i16>, <64 x i16>* %bp
@@ -756,13 +713,10 @@
 define <32 x i64> @masked_load_sext_v32i16i64(<32 x i16>* %ap, <32 x i16>* %bp) #0 {
 ; VBITS_GE_2048-LABEL: masked_load_sext_v32i16i64:
 ; VBITS_GE_2048:       // %bb.0:
-; VBITS_GE_2048-NEXT:    ptrue p0.h, vl32
-; VBITS_GE_2048-NEXT:    ld1h { z0.h }, p0/z, [x1]
-; VBITS_GE_2048-NEXT:    cmpeq p0.h, p0/z, z0.h, #0
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    ld1sh { z0.d }, p0/z, [x0]
 ; VBITS_GE_2048-NEXT:    ptrue p0.d, vl32
+; VBITS_GE_2048-NEXT:    ld1sh { z0.d }, p0/z, [x1]
+; VBITS_GE_2048-NEXT:    cmpeq p1.d, p0/z, z0.d, #0
+; VBITS_GE_2048-NEXT:    ld1sh { z0.d }, p1/z, [x0]
 ; VBITS_GE_2048-NEXT:    st1d { z0.d }, p0, [x8]
 ; VBITS_GE_2048-NEXT:    ret
   %b = load <32 x i16>, <32 x i16>* %bp
@@ -775,12 +729,10 @@
 define <32 x i64> @masked_load_sext_v32i32i64(<32 x i32>* %ap, <32 x i32>* %bp) #0 {
 ; VBITS_GE_2048-LABEL: masked_load_sext_v32i32i64:
 ; VBITS_GE_2048:       // %bb.0:
-; VBITS_GE_2048-NEXT:    ptrue p0.s, vl32
-; VBITS_GE_2048-NEXT:    ld1w { z0.s }, p0/z, [x1]
-; VBITS_GE_2048-NEXT:    cmpeq p0.s, p0/z, z0.s, #0
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    ld1sw { z0.d }, p0/z, [x0]
 ; VBITS_GE_2048-NEXT:    ptrue p0.d, vl32
+; VBITS_GE_2048-NEXT:    ld1sw { z0.d }, p0/z, [x1]
+; VBITS_GE_2048-NEXT:    cmpeq p1.d, p0/z, z0.d, #0
+; VBITS_GE_2048-NEXT:    ld1sw { z0.d }, p1/z, [x0]
 ; VBITS_GE_2048-NEXT:    st1d { z0.d }, p0, [x8]
 ; VBITS_GE_2048-NEXT:    ret
   %b = load <32 x i32>, <32 x i32>* %bp
@@ -793,12 +745,10 @@
 define <128 x i16> @masked_load_zext_v128i8i16(<128 x i8>* %ap, <128 x i8>* %bp) #0 {
 ; VBITS_GE_2048-LABEL: masked_load_zext_v128i8i16:
 ; VBITS_GE_2048:       // %bb.0:
-; VBITS_GE_2048-NEXT:    ptrue p0.b, vl128
-; VBITS_GE_2048-NEXT:    ld1b { z0.b }, p0/z, [x1]
-; VBITS_GE_2048-NEXT:    cmpeq p0.b, p0/z, z0.b, #0
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    ld1b { z0.h }, p0/z, [x0]
 ; VBITS_GE_2048-NEXT:    ptrue p0.h, vl128
+; VBITS_GE_2048-NEXT:    ld1sb { z0.h }, p0/z, [x1]
+; VBITS_GE_2048-NEXT:    cmpeq p1.h, p0/z, z0.h, #0
+; VBITS_GE_2048-NEXT:    ld1b { z0.h }, p1/z, [x0]
 ; VBITS_GE_2048-NEXT:    st1h { z0.h }, p0, [x8]
 ; VBITS_GE_2048-NEXT:    ret
   %b = load <128 x i8>, <128 x i8>* %bp
@@ -811,13 +761,10 @@
 define <64 x i32> @masked_load_zext_v64i8i32(<64 x i8>* %ap, <64 x i8>* %bp) #0 {
 ; VBITS_GE_2048-LABEL: masked_load_zext_v64i8i32:
 ; VBITS_GE_2048:       // %bb.0:
-; VBITS_GE_2048-NEXT:    ptrue p0.b, vl64
-; VBITS_GE_2048-NEXT:    ld1b { z0.b }, p0/z, [x1]
-; VBITS_GE_2048-NEXT:    cmpeq p0.b, p0/z, z0.b, #0
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    ld1b { z0.s }, p0/z, [x0]
 ; VBITS_GE_2048-NEXT:    ptrue p0.s, vl64
+; VBITS_GE_2048-NEXT:    ld1sb { z0.s }, p0/z, [x1]
+; VBITS_GE_2048-NEXT:    cmpeq p1.s, p0/z, z0.s, #0
+; VBITS_GE_2048-NEXT:    ld1b { z0.s }, p1/z, [x0]
 ; VBITS_GE_2048-NEXT:    st1w { z0.s }, p0, [x8]
 ; VBITS_GE_2048-NEXT:    ret
   %b = load <64 x i8>, <64 x i8>* %bp
@@ -830,14 +777,10 @@
 define <32 x i64> @masked_load_zext_v32i8i64(<32 x i8>* %ap, <32 x i8>* %bp) #0 {
 ; VBITS_GE_2048-LABEL: masked_load_zext_v32i8i64:
 ; VBITS_GE_2048:       // %bb.0:
-; VBITS_GE_2048-NEXT:    ptrue p0.b, vl32
-; VBITS_GE_2048-NEXT:    ld1b { z0.b }, p0/z, [x1]
-; VBITS_GE_2048-NEXT:    cmpeq p0.b, p0/z, z0.b, #0
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    ld1b { z0.d }, p0/z, [x0]
 ; VBITS_GE_2048-NEXT:    ptrue p0.d, vl32
+; VBITS_GE_2048-NEXT:    ld1sb { z0.d }, p0/z, [x1]
+; VBITS_GE_2048-NEXT:    cmpeq p1.d, p0/z, z0.d, #0
+; VBITS_GE_2048-NEXT:    ld1b { z0.d }, p1/z, [x0]
 ; VBITS_GE_2048-NEXT:    st1d { z0.d }, p0, [x8]
 ; VBITS_GE_2048-NEXT:    ret
   %b = load <32 x i8>, <32 x i8>* %bp
@@ -850,12 +793,10 @@
 define <64 x i32> @masked_load_zext_v64i16i32(<64 x i16>* %ap, <64 x i16>* %bp) #0 {
 ; VBITS_GE_2048-LABEL: masked_load_zext_v64i16i32:
 ; VBITS_GE_2048:       // %bb.0:
-; VBITS_GE_2048-NEXT:    ptrue p0.h, vl64
-; VBITS_GE_2048-NEXT:    ld1h { z0.h }, p0/z, [x1]
-; VBITS_GE_2048-NEXT:    cmpeq p0.h, p0/z, z0.h, #0
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    ld1h { z0.s }, p0/z, [x0]
 ; VBITS_GE_2048-NEXT:    ptrue p0.s, vl64
+; VBITS_GE_2048-NEXT:    ld1sh { z0.s }, p0/z, [x1]
+; VBITS_GE_2048-NEXT:    cmpeq p1.s, p0/z, z0.s, #0
+; VBITS_GE_2048-NEXT:    ld1h { z0.s }, p1/z, [x0]
 ; VBITS_GE_2048-NEXT:    st1w { z0.s }, p0, [x8]
 ; VBITS_GE_2048-NEXT:    ret
   %b = load <64 x i16>, <64 x i16>* %bp
@@ -868,13 +809,10 @@
 define <32 x i64> @masked_load_zext_v32i16i64(<32 x i16>* %ap, <32 x i16>* %bp) #0 {
 ; VBITS_GE_2048-LABEL: masked_load_zext_v32i16i64:
 ; VBITS_GE_2048:       // %bb.0:
-; VBITS_GE_2048-NEXT:    ptrue p0.h, vl32
-; VBITS_GE_2048-NEXT:    ld1h { z0.h }, p0/z, [x1]
-; VBITS_GE_2048-NEXT:    cmpeq p0.h, p0/z, z0.h, #0
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    ld1h { z0.d }, p0/z, [x0]
 ; VBITS_GE_2048-NEXT:    ptrue p0.d, vl32
+; VBITS_GE_2048-NEXT:    ld1sh { z0.d }, p0/z, [x1]
+; VBITS_GE_2048-NEXT:    cmpeq p1.d, p0/z, z0.d, #0
+; VBITS_GE_2048-NEXT:    ld1h { z0.d }, p1/z, [x0]
 ; VBITS_GE_2048-NEXT:    st1d { z0.d }, p0, [x8]
 ; VBITS_GE_2048-NEXT:    ret
   %b = load <32 x i16>, <32 x i16>* %bp
@@ -887,12 +825,10 @@
 define <32 x i64> @masked_load_zext_v32i32i64(<32 x i32>* %ap, <32 x i32>* %bp) #0 {
 ; VBITS_GE_2048-LABEL: masked_load_zext_v32i32i64:
 ; VBITS_GE_2048:       // %bb.0:
-; VBITS_GE_2048-NEXT:    ptrue p0.s, vl32
-; VBITS_GE_2048-NEXT:    ld1w { z0.s }, p0/z, [x1]
-; VBITS_GE_2048-NEXT:    cmpeq p0.s, p0/z, z0.s, #0
-; VBITS_GE_2048-NEXT:    punpklo p0.h, p0.b
-; VBITS_GE_2048-NEXT:    ld1w { z0.d }, p0/z, [x0]
 ; VBITS_GE_2048-NEXT:    ptrue p0.d, vl32
+; VBITS_GE_2048-NEXT:    ld1sw { z0.d }, p0/z, [x1]
+; VBITS_GE_2048-NEXT:    cmpeq p1.d, p0/z, z0.d, #0
+; VBITS_GE_2048-NEXT:    ld1w { z0.d }, p1/z, [x0]
 ; VBITS_GE_2048-NEXT:    st1d { z0.d }, p0, [x8]
 ; VBITS_GE_2048-NEXT:    ret
   %b = load <32 x i32>, <32 x i32>* %bp