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-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