Index: llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -1229,6 +1229,13 @@
       }
     }
 
+    // SVE supports unpklo/hi instructions to reduce the number of loads.
+    for (auto Op : {ISD::ZEXTLOAD, ISD::SEXTLOAD}) {
+      setLoadExtAction(Op, MVT::nxv16i64, MVT::nxv16i8, Expand);
+      setLoadExtAction(Op, MVT::nxv8i64, MVT::nxv8i16, Expand);
+      setLoadExtAction(Op, MVT::nxv4i64, MVT::nxv4i32, Expand);
+    }
+
     // SVE supports truncating stores of 64 and 128-bit vectors
     setTruncStoreAction(MVT::v2i64, MVT::v2i8, Custom);
     setTruncStoreAction(MVT::v2i64, MVT::v2i16, Custom);
Index: llvm/test/CodeGen/AArch64/sve-intrinsics-mask-loads.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/AArch64/sve-intrinsics-mask-loads.ll
@@ -0,0 +1,111 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve -asm-verbose=1 < %s | FileCheck %s
+
+define <vscale x 16 x i64> @masked_ld1b_i8_sext(<vscale x 16 x i8> *%base, <vscale x 16 x i1> %mask) {
+; CHECK-LABEL: masked_ld1b_i8_sext:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x0]
+; CHECK-NEXT:    sunpklo z1.h, z0.b
+; CHECK-NEXT:    sunpkhi z0.h, z0.b
+; CHECK-NEXT:    sunpklo z2.s, z1.h
+; CHECK-NEXT:    sunpkhi z3.s, z1.h
+; CHECK-NEXT:    sunpklo z5.s, z0.h
+; CHECK-NEXT:    sunpkhi z7.s, z0.h
+; CHECK-NEXT:    sunpklo z0.d, z2.s
+; CHECK-NEXT:    sunpkhi z1.d, z2.s
+; CHECK-NEXT:    sunpklo z2.d, z3.s
+; CHECK-NEXT:    sunpkhi z3.d, z3.s
+; CHECK-NEXT:    sunpklo z4.d, z5.s
+; CHECK-NEXT:    sunpkhi z5.d, z5.s
+; CHECK-NEXT:    sunpklo z6.d, z7.s
+; CHECK-NEXT:    sunpkhi z7.d, z7.s
+; CHECK-NEXT:    ret
+  %wide.masked.load = call <vscale x 16 x i8> @llvm.masked.load.nxv16i8.p0nxv16i8(<vscale x 16 x i8>* %base, i32 2, <vscale x 16 x i1> %mask, <vscale x 16 x i8> undef)
+  %res = sext <vscale x 16 x i8> %wide.masked.load to <vscale x 16 x i64>
+  ret <vscale x 16 x i64> %res
+}
+
+define <vscale x 16 x i64> @masked_ld1b_i8_zext(<vscale x 16 x i8> *%base, <vscale x 16 x i1> %mask) {
+; CHECK-LABEL: masked_ld1b_i8_zext:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ld1b { z0.b }, p0/z, [x0]
+; CHECK-NEXT:    uunpklo z1.h, z0.b
+; CHECK-NEXT:    uunpkhi z0.h, z0.b
+; CHECK-NEXT:    uunpklo z2.s, z1.h
+; CHECK-NEXT:    uunpkhi z3.s, z1.h
+; CHECK-NEXT:    uunpklo z5.s, z0.h
+; CHECK-NEXT:    uunpkhi z7.s, z0.h
+; CHECK-NEXT:    uunpklo z0.d, z2.s
+; CHECK-NEXT:    uunpkhi z1.d, z2.s
+; CHECK-NEXT:    uunpklo z2.d, z3.s
+; CHECK-NEXT:    uunpkhi z3.d, z3.s
+; CHECK-NEXT:    uunpklo z4.d, z5.s
+; CHECK-NEXT:    uunpkhi z5.d, z5.s
+; CHECK-NEXT:    uunpklo z6.d, z7.s
+; CHECK-NEXT:    uunpkhi z7.d, z7.s
+; CHECK-NEXT:    ret
+  %wide.masked.load = call <vscale x 16 x i8> @llvm.masked.load.nxv16i8.p0nxv16i8(<vscale x 16 x i8>* %base, i32 2, <vscale x 16 x i1> %mask, <vscale x 16 x i8> undef)
+  %res = zext <vscale x 16 x i8> %wide.masked.load to <vscale x 16 x i64>
+  ret <vscale x 16 x i64> %res
+}
+
+define <vscale x 8 x i64> @masked_ld1h_i16_sext(<vscale x 8 x i16> *%base, <vscale x 8 x i1> %mask) {
+; CHECK-LABEL: masked_ld1h_i16_sext:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x0]
+; CHECK-NEXT:    sunpklo z1.s, z0.h
+; CHECK-NEXT:    sunpkhi z3.s, z0.h
+; CHECK-NEXT:    sunpklo z0.d, z1.s
+; CHECK-NEXT:    sunpkhi z1.d, z1.s
+; CHECK-NEXT:    sunpklo z2.d, z3.s
+; CHECK-NEXT:    sunpkhi z3.d, z3.s
+; CHECK-NEXT:    ret
+  %wide.masked.load = call <vscale x 8 x i16> @llvm.masked.load.nxv8i16.p0nxv8i16(<vscale x 8 x i16>* %base, i32 2, <vscale x 8 x i1> %mask, <vscale x 8 x i16> undef)
+  %res = sext <vscale x 8 x i16> %wide.masked.load to <vscale x 8 x i64>
+  ret <vscale x 8 x i64> %res
+}
+
+define <vscale x 8 x i64> @masked_ld1h_i16_zext(<vscale x 8 x i16> *%base, <vscale x 8 x i1> %mask) {
+; CHECK-LABEL: masked_ld1h_i16_zext:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x0]
+; CHECK-NEXT:    uunpklo z1.s, z0.h
+; CHECK-NEXT:    uunpkhi z3.s, z0.h
+; CHECK-NEXT:    uunpklo z0.d, z1.s
+; CHECK-NEXT:    uunpkhi z1.d, z1.s
+; CHECK-NEXT:    uunpklo z2.d, z3.s
+; CHECK-NEXT:    uunpkhi z3.d, z3.s
+; CHECK-NEXT:    ret
+  %wide.masked.load = call <vscale x 8 x i16> @llvm.masked.load.nxv8i16.p0nxv8i16(<vscale x 8 x i16>* %base, i32 2, <vscale x 8 x i1> %mask, <vscale x 8 x i16> undef)
+  %res = zext <vscale x 8 x i16> %wide.masked.load to <vscale x 8 x i64>
+  ret <vscale x 8 x i64> %res
+}
+
+define <vscale x 4 x i64> @masked_ld1w_i32_sext(<vscale x 4 x i32> *%base, <vscale x 4 x i1> %mask) {
+; CHECK-LABEL: masked_ld1w_i32_sext:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ld1w { z1.s }, p0/z, [x0]
+; CHECK-NEXT:    sunpklo z0.d, z1.s
+; CHECK-NEXT:    sunpkhi z1.d, z1.s
+; CHECK-NEXT:    ret
+  %wide.masked.load = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* %base, i32 4, <vscale x 4 x i1> %mask, <vscale x 4 x i32> undef)
+  %res = sext <vscale x 4 x i32> %wide.masked.load to <vscale x 4 x i64>
+  ret <vscale x 4 x i64> %res
+}
+
+define <vscale x 4 x i64> @masked_ld1w_i32_zext(<vscale x 4 x i32> *%base, <vscale x 4 x i1> %mask) {
+; CHECK-LABEL: masked_ld1w_i32_zext:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ld1w { z1.s }, p0/z, [x0]
+; CHECK-NEXT:    uunpklo z0.d, z1.s
+; CHECK-NEXT:    uunpkhi z1.d, z1.s
+; CHECK-NEXT:    ret
+  %wide.masked.load = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* %base, i32 4, <vscale x 4 x i1> %mask, <vscale x 4 x i32> undef)
+  %res = zext <vscale x 4 x i32> %wide.masked.load to <vscale x 4 x i64>
+  ret <vscale x 4 x i64> %res
+}
+
+declare <vscale x 16 x i8> @llvm.masked.load.nxv16i8.p0nxv16i8(<vscale x 16 x i8>*, i32 immarg, <vscale x 16 x i1>, <vscale x 16 x i8>)
+declare <vscale x 8 x i16> @llvm.masked.load.nxv8i16.p0nxv8i16(<vscale x 8 x i16>*, i32 immarg, <vscale x 8 x i1>, <vscale x 8 x i16>)
+declare <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>*, i32 immarg, <vscale x 4 x i1>, <vscale x 4 x i32>)
+
Index: llvm/test/CodeGen/AArch64/sve-masked-ldst-zext.ll
===================================================================
--- llvm/test/CodeGen/AArch64/sve-masked-ldst-zext.ll
+++ llvm/test/CodeGen/AArch64/sve-masked-ldst-zext.ll
@@ -79,17 +79,14 @@
 ; Return type requires splitting
 define <vscale x 8 x i64> @masked_zload_nxv8i16(<vscale x 8 x i16>* %a, <vscale x 8 x i1> %mask) {
 ; CHECK-LABEL: masked_zload_nxv8i16:
-; CHECK:       punpklo p1.h, p0.b
-; CHECK-NEXT:  punpkhi p0.h, p0.b
-; CHECK-NEXT:  punpklo p2.h, p1.b
-; CHECK-NEXT:  punpkhi p1.h, p1.b
-; CHECK-NEXT:  ld1h { z0.d }, p2/z, [x0]
-; CHECK-NEXT:  punpklo p2.h, p0.b
-; CHECK-NEXT:  punpkhi p0.h, p0.b
-; CHECK-NEXT:  ld1h { z1.d }, p1/z, [x0, #1, mul vl]
-; CHECK-NEXT:  ld1h { z2.d }, p2/z, [x0, #2, mul vl]
-; CHECK-NEXT:  ld1h { z3.d }, p0/z, [x0, #3, mul vl]
-; CHECK-NEXT:  ret
+; CHECK:         ld1h { z0.h }, p0/z, [x0]
+; CHECK-NEXT:    uunpklo z1.s, z0.h
+; CHECK-NEXT:    uunpkhi z3.s, z0.h
+; CHECK-NEXT:    uunpklo z0.d, z1.s
+; CHECK-NEXT:    uunpkhi z1.d, z1.s
+; CHECK-NEXT:    uunpklo z2.d, z3.s
+; CHECK-NEXT:    uunpkhi z3.d, z3.s
+; CHECK-NEXT:    ret
   %load = call <vscale x 8 x i16> @llvm.masked.load.nxv8i16(<vscale x 8 x i16>* %a, i32 2, <vscale x 8 x i1> %mask, <vscale x 8 x i16> undef)
   %ext = zext <vscale x 8 x i16> %load to <vscale x 8 x i64>
   ret <vscale x 8 x i64> %ext