Index: llvm/include/llvm/Support/TypeSize.h
===================================================================
--- llvm/include/llvm/Support/TypeSize.h
+++ llvm/include/llvm/Support/TypeSize.h
@@ -131,6 +131,20 @@
     return { MinSize / RHS, IsScalable };
   }
 
+  TypeSize &operator-=(TypeSize RHS) {
+    assert(IsScalable == RHS.IsScalable &&
+           "Subtraction using mixed scalable and fixed types");
+    MinSize -= RHS.MinSize;
+    return *this;
+  }
+
+  TypeSize &operator+=(TypeSize RHS) {
+    assert(IsScalable == RHS.IsScalable &&
+           "Addition using mixed scalable and fixed types");
+    MinSize += RHS.MinSize;
+    return *this;
+  }
+
   // Return the minimum size with the assumption that the size is exact.
   // Use in places where a scalable size doesn't make sense (e.g. non-vector
   // types, or vectors in backends which don't support scalable vectors).
Index: llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
===================================================================
--- llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
+++ llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
@@ -983,10 +983,12 @@
   unsigned IncrementSize = MemVT.getSizeInBits().getKnownMinSize() / 8;
 
   if (MemVT.isScalableVector()) {
+    SDNodeFlags Flags;
     SDValue BytesIncrement = DAG.getVScale(
         DL, Ptr.getValueType(),
         APInt(Ptr.getValueSizeInBits().getFixedSize(), IncrementSize));
     MPI = MachinePointerInfo(N->getPointerInfo().getAddrSpace());
+    Flags.setNoUnsignedWrap(true);
     Ptr = DAG.getNode(ISD::ADD, DL, Ptr.getValueType(), Ptr, BytesIncrement);
   } else {
     MPI = N->getPointerInfo().getWithOffset(IncrementSize);
@@ -4820,7 +4822,7 @@
 
   // If we have one element to load/store, return it.
   EVT RetVT = WidenEltVT;
-  if (Width == WidenEltWidth)
+  if (!Scalable && Width == WidenEltWidth)
     return RetVT;
 
   // See if there is larger legal integer than the element type to load/store.
@@ -5114,53 +5116,55 @@
   SDLoc dl(ST);
 
   EVT StVT = ST->getMemoryVT();
-  unsigned StWidth = StVT.getSizeInBits();
+  TypeSize StWidth = StVT.getSizeInBits();
   EVT ValVT = ValOp.getValueType();
-  unsigned ValWidth = ValVT.getSizeInBits();
+  TypeSize ValWidth = ValVT.getSizeInBits();
   EVT ValEltVT = ValVT.getVectorElementType();
-  unsigned ValEltWidth = ValEltVT.getSizeInBits();
+  unsigned ValEltWidth = ValEltVT.getSizeInBits().getFixedSize();
   assert(StVT.getVectorElementType() == ValEltVT);
+  assert(StVT.isScalableVector() == ValVT.isScalableVector() &&
+         "Mismatch between store and value types");
 
   int Idx = 0;          // current index to store
-  unsigned Offset = 0;  // offset from base to store
-  while (StWidth != 0) {
+
+  MachinePointerInfo MPI = ST->getPointerInfo();
+  while (StWidth.isNonZero()) {
     // Find the largest vector type we can store with.
-    EVT NewVT = FindMemType(DAG, TLI, StWidth, ValVT);
-    unsigned NewVTWidth = NewVT.getSizeInBits();
-    unsigned Increment = NewVTWidth / 8;
+    EVT NewVT = FindMemType(DAG, TLI, StWidth.getKnownMinSize(), ValVT);
+    TypeSize NewVTWidth = NewVT.getSizeInBits();
+    TypeSize Increment = NewVTWidth / 8;
     if (NewVT.isVector()) {
-      unsigned NumVTElts = NewVT.getVectorNumElements();
+      unsigned NumVTElts = NewVT.getVectorMinNumElements();
       do {
         SDValue EOp = DAG.getNode(ISD::EXTRACT_SUBVECTOR, dl, NewVT, ValOp,
                                   DAG.getVectorIdxConstant(Idx, dl));
-        StChain.push_back(DAG.getStore(
-            Chain, dl, EOp, BasePtr, ST->getPointerInfo().getWithOffset(Offset),
-            ST->getOriginalAlign(), MMOFlags, AAInfo));
+        SDValue TmpSt = DAG.getStore(Chain, dl, EOp, BasePtr, MPI,
+                                     ST->getOriginalAlign(), MMOFlags, AAInfo);
+        StChain.push_back(TmpSt);
+
         StWidth -= NewVTWidth;
-        Offset += Increment;
         Idx += NumVTElts;
-
-        BasePtr = DAG.getObjectPtrOffset(dl, BasePtr, Increment);
-      } while (StWidth != 0 && StWidth >= NewVTWidth);
+        IncrementPointer(cast<StoreSDNode>(TmpSt), NewVT, MPI, BasePtr);
+      } while (StWidth.isNonZero() && StWidth >= NewVTWidth);
     } else {
       // Cast the vector to the scalar type we can store.
-      unsigned NumElts = ValWidth / NewVTWidth;
+      unsigned NumElts = ValWidth.getFixedSize() / NewVTWidth.getFixedSize();
       EVT NewVecVT = EVT::getVectorVT(*DAG.getContext(), NewVT, NumElts);
       SDValue VecOp = DAG.getNode(ISD::BITCAST, dl, NewVecVT, ValOp);
       // Readjust index position based on new vector type.
-      Idx = Idx * ValEltWidth / NewVTWidth;
+      Idx = Idx * ValEltWidth / NewVTWidth.getFixedSize();
       do {
         SDValue EOp = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, dl, NewVT, VecOp,
                                   DAG.getVectorIdxConstant(Idx++, dl));
-        StChain.push_back(DAG.getStore(
-            Chain, dl, EOp, BasePtr, ST->getPointerInfo().getWithOffset(Offset),
-            ST->getOriginalAlign(), MMOFlags, AAInfo));
+        SDValue TmpSt = DAG.getStore(Chain, dl, EOp, BasePtr, MPI,
+                                     ST->getOriginalAlign(), MMOFlags, AAInfo);
+        StChain.push_back(TmpSt);
+
         StWidth -= NewVTWidth;
-        Offset += Increment;
-        BasePtr = DAG.getObjectPtrOffset(dl, BasePtr, Increment);
-      } while (StWidth != 0 && StWidth >= NewVTWidth);
+        IncrementPointer(cast<StoreSDNode>(TmpSt), NewVT, MPI, BasePtr);
+      } while (StWidth.isNonZero() && StWidth >= NewVTWidth);
       // Restore index back to be relative to the original widen element type.
-      Idx = Idx * NewVTWidth / ValEltWidth;
+      Idx = Idx * NewVTWidth.getFixedSize() / ValEltWidth;
     }
   }
 }
@@ -5183,8 +5187,13 @@
   // It must be true that the wide vector type is bigger than where we need to
   // store.
   assert(StVT.isVector() && ValOp.getValueType().isVector());
+  assert(StVT.isScalableVector() == ValOp.getValueType().isScalableVector());
   assert(StVT.bitsLT(ValOp.getValueType()));
 
+  if (StVT.isScalableVector())
+    report_fatal_error("Generating widen scalable vector truncating stores not "
+                       "yet supported");
+
   // For truncating stores, we can not play the tricks of chopping legal vector
   // types and bitcast it to the right type. Instead, we unroll the store.
   EVT StEltVT  = StVT.getVectorElementType();
Index: llvm/test/CodeGen/AArch64/sve-intrinsics-stores.ll
===================================================================
--- llvm/test/CodeGen/AArch64/sve-intrinsics-stores.ll
+++ llvm/test/CodeGen/AArch64/sve-intrinsics-stores.ll
@@ -437,6 +437,49 @@
 }
 
 
+; Stores (tuples)
+
+define void @store_i64_tuple3(<vscale x 6 x i64>* %out, <vscale x 2 x i64> %in1, <vscale x 2 x i64> %in2, <vscale x 2 x i64> %in3) {
+; CHECK-LABEL: store_i64_tuple3
+; CHECK:      st1d { z2.d }, p0, [x0, #2, mul vl]
+; CHECK-NEXT: st1d { z1.d }, p0, [x0, #1, mul vl]
+; CHECK-NEXT: st1d { z0.d }, p0, [x0]
+  %tuple = tail call <vscale x 6 x i64> @llvm.aarch64.sve.tuple.create3.nxv6i64.nxv2i64(<vscale x 2 x i64> %in1, <vscale x 2 x i64> %in2, <vscale x 2 x i64> %in3)
+  store <vscale x 6 x i64> %tuple, <vscale x 6 x i64>* %out
+  ret void
+}
+
+define void @store_i64_tuple4(<vscale x 8 x i64>* %out, <vscale x 2 x i64> %in1, <vscale x 2 x i64> %in2, <vscale x 2 x i64> %in3, <vscale x 2 x i64> %in4) {
+; CHECK-LABEL: store_i64_tuple4
+; CHECK:      st1d { z3.d }, p0, [x0, #3, mul vl]
+; CHECK-NEXT: st1d { z2.d }, p0, [x0, #2, mul vl]
+; CHECK-NEXT: st1d { z1.d }, p0, [x0, #1, mul vl]
+; CHECK-NEXT: st1d { z0.d }, p0, [x0]
+  %tuple = tail call <vscale x 8 x i64> @llvm.aarch64.sve.tuple.create4.nxv8i64.nxv2i64(<vscale x 2 x i64> %in1, <vscale x 2 x i64> %in2, <vscale x 2 x i64> %in3, <vscale x 2 x i64> %in4)
+  store <vscale x 8 x i64> %tuple, <vscale x 8 x i64>* %out
+  ret void
+}
+
+define void @store_i16_tuple2(<vscale x 16 x i16>* %out, <vscale x 8 x i16> %in1, <vscale x 8 x i16> %in2) {
+; CHECK-LABEL: store_i16_tuple2
+; CHECK:      st1h { z1.h }, p0, [x0, #1, mul vl]
+; CHECK-NEXT: st1h { z0.h }, p0, [x0]
+  %tuple = tail call <vscale x 16 x i16> @llvm.aarch64.sve.tuple.create2.nxv16i16.nxv8i16(<vscale x 8 x i16> %in1, <vscale x 8 x i16> %in2)
+  store <vscale x 16 x i16> %tuple, <vscale x 16 x i16>* %out
+  ret void
+}
+
+define void @store_i16_tuple3(<vscale x 24 x i16>* %out, <vscale x 8 x i16> %in1, <vscale x 8 x i16> %in2, <vscale x 8 x i16> %in3) {
+; CHECK-LABEL: store_i16_tuple3
+; CHECK:      st1h { z2.h }, p0, [x0, #2, mul vl]
+; CHECK-NEXT: st1h { z1.h }, p0, [x0, #1, mul vl]
+; CHECK-NEXT: st1h { z0.h }, p0, [x0]
+  %tuple = tail call <vscale x 24 x i16> @llvm.aarch64.sve.tuple.create3.nxv24i16.nxv8i16(<vscale x 8 x i16> %in1, <vscale x 8 x i16> %in2, <vscale x 8 x i16> %in3)
+  store <vscale x 24 x i16> %tuple, <vscale x 24 x i16>* %out
+  ret void
+}
+
+
 declare void @llvm.aarch64.sve.st2.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i1>, i8*)
 declare void @llvm.aarch64.sve.st2.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i1>, i16*)
 declare void @llvm.aarch64.sve.st2.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i1>, i32*)
@@ -473,5 +516,11 @@
 declare void @llvm.aarch64.sve.stnt1.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, float*)
 declare void @llvm.aarch64.sve.stnt1.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, double*)
 
+declare <vscale x 6 x i64> @llvm.aarch64.sve.tuple.create3.nxv6i64.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>)
+declare <vscale x 8 x i64> @llvm.aarch64.sve.tuple.create4.nxv8i64.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>)
+
+declare <vscale x 16 x i16> @llvm.aarch64.sve.tuple.create2.nxv16i16.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 24 x i16> @llvm.aarch64.sve.tuple.create3.nxv24i16.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+
 ; +bf16 is required for the bfloat version.
 attributes #0 = { "target-features"="+sve,+bf16" }