Index: llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -2371,6 +2371,16 @@
     return DAG.getVScale(DL, VT, C0 + C1);
   }
 
+  // fold a+vscale(c1)+vscale(c2) -> a+vscale(c1+c2)
+  if ((N0.getOpcode() == ISD::ADD) &&
+      (N0.getOperand(1).getOpcode() == ISD::VSCALE) &&
+      (N1.getOpcode() == ISD::VSCALE)) {
+    auto VS0 = N0.getOperand(1)->getConstantOperandAPInt(0);
+    auto VS1 = N1->getConstantOperandAPInt(0);
+    auto VS = DAG.getVScale(DL, VT, VS0 + VS1);
+    return DAG.getNode(ISD::ADD, DL, VT, N0.getOperand(0), VS);
+  }
+
   return SDValue();
 }
 
Index: llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
===================================================================
--- llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
+++ llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
@@ -1538,10 +1538,24 @@
                    MMOFlags, AAInfo);
 
   unsigned IncrementSize = LoMemVT.getSizeInBits()/8;
-  Ptr = DAG.getObjectPtrOffset(dl, Ptr, IncrementSize);
+
+  SDValue BytesIncrement;
+  MachinePointerInfo MPI;
+  if (LoVT.isScalableVector()) {
+    BytesIncrement = DAG.getVScale(
+        dl, Ptr.getValueType(),
+        APInt(Ptr.getValueType().getSizeInBits().getKnownMinSize(),
+              IncrementSize));
+    MPI = LD->getPointerInfo();
+    Ptr = DAG.getNode(ISD::ADD, dl, Ptr.getValueType(), Ptr, BytesIncrement);
+  } else {
+    BytesIncrement = DAG.getConstant(IncrementSize, dl, Ptr.getValueType());
+    MPI = LD->getPointerInfo().getWithOffset(IncrementSize);
+    Ptr = DAG.getObjectPtrOffset(dl, Ptr, IncrementSize);
+  }
+
   Hi = DAG.getLoad(ISD::UNINDEXED, ExtType, HiVT, dl, Ch, Ptr, Offset,
-                   LD->getPointerInfo().getWithOffset(IncrementSize), HiMemVT,
-                   LD->getOriginalAlign(), MMOFlags, AAInfo);
+                   MPI, HiMemVT, LD->getOriginalAlign(), MMOFlags, AAInfo);
 
   // Build a factor node to remember that this load is independent of the
   // other one.
Index: llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
===================================================================
--- llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
+++ llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
@@ -1675,8 +1675,15 @@
 
   multiclass unpred_load<PatFrag Load, ValueType Ty, Instruction RegImmInst,
                          Instruction PTrue> {
-    def : Pat<(Ty (Load  (am_sve_fi GPR64sp:$base, simm4s1:$offset))),
-              (RegImmInst (PTrue 31), GPR64sp:$base, simm4s1:$offset)>;
+    let AddedComplexity = 1 in {
+      def _imm: Pat<(Ty (Load  (am_sve_indexed_s4 GPR64sp:$base, simm4s1:$offset))),
+                    (RegImmInst (PTrue 31), GPR64sp:$base, simm4s1:$offset)>;
+    }
+
+    let AddedComplexity = 2 in {
+      def _fi : Pat<(Ty (Load  (am_sve_fi GPR64sp:$base, simm4s1:$offset))),
+                    (RegImmInst (PTrue 31), GPR64sp:$base, simm4s1:$offset)>;
+    }
 
     def : Pat<(Ty (Load GPR64:$base)),
               (RegImmInst (PTrue 31), GPR64:$base, (i64 0))>;
Index: llvm/test/CodeGen/AArch64/sve-ldst.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/AArch64/sve-ldst.ll
@@ -0,0 +1,55 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
+
+; LOAD
+
+define <vscale x 4 x i16> @load_promote_4i8(<vscale x 4 x i16>* %a) {
+; CHECK-LABEL: load_promote_4i8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    ld1h { z0.s }, p0/z, [x0]
+; CHECK-NEXT:    ret
+  %load = load <vscale x 4 x i16>, <vscale x 4 x i16>* %a
+  ret <vscale x 4 x i16> %load
+}
+
+define <vscale x 16 x i16> @load_split_i16(<vscale x 16 x i16>* %a) {
+; CHECK-LABEL: load_split_i16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.h
+; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x0]
+; CHECK-NEXT:    ld1h { z1.h }, p0/z, [x0, #1, mul vl]
+; CHECK-NEXT:    ret
+  %load = load <vscale x 16 x i16>, <vscale x 16 x i16>* %a
+  ret <vscale x 16 x i16> %load
+}
+
+define <vscale x 32 x i16> @load_split_32i16(<vscale x 32 x i16>* %a) {
+; CHECK-LABEL: load_split_32i16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.h
+; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x0]
+; CHECK-NEXT:    ld1h { z1.h }, p0/z, [x0, #1, mul vl]
+; CHECK-NEXT:    ld1h { z2.h }, p0/z, [x0, #2, mul vl]
+; CHECK-NEXT:    ld1h { z3.h }, p0/z, [x0, #3, mul vl]
+; CHECK-NEXT:    ret
+  %load = load <vscale x 32 x i16>, <vscale x 32 x i16>* %a
+  ret <vscale x 32 x i16> %load
+}
+
+define <vscale x 16 x i64> @load_split_16i64(<vscale x 16 x i64>* %a) {
+; CHECK-LABEL: load_split_16i64:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0]
+; CHECK-NEXT:    ld1d { z1.d }, p0/z, [x0, #1, mul vl]
+; CHECK-NEXT:    ld1d { z2.d }, p0/z, [x0, #2, mul vl]
+; CHECK-NEXT:    ld1d { z3.d }, p0/z, [x0, #3, mul vl]
+; CHECK-NEXT:    ld1d { z4.d }, p0/z, [x0, #4, mul vl]
+; CHECK-NEXT:    ld1d { z5.d }, p0/z, [x0, #5, mul vl]
+; CHECK-NEXT:    ld1d { z6.d }, p0/z, [x0, #6, mul vl]
+; CHECK-NEXT:    ld1d { z7.d }, p0/z, [x0, #7, mul vl]
+; CHECK-NEXT:    ret
+  %load = load <vscale x 16 x i64>, <vscale x 16 x i64>* %a
+  ret <vscale x 16 x i64> %load
+}