From e6a586aafc2484a13921b6522423068da4317643 Mon Sep 17 00:00:00 2001
From: Cullen Rhodes <cullen.rhodes@arm.com>
Date: Tue, 19 May 2020 12:55:53 +0000
Subject: [PATCH] [AArch64][SVE] Implement vector tuple intrinsics

Summary:
This patch adds the following intrinsics for creating two-tuple,
three-tuple and four-tuple scalable vectors:

    * llvm.aarch64.sve.tuple.create2
    * llvm.aarch64.sve.tuple.create3
    * llvm.aarch64.sve.tuple.create4

As well as:

    * llvm.aarch64.sve.tuple.get
    * llvm.aarch64.sve.tuple.set

For extracting and inserting scalable vectors from vector tuples. These
intrinsics are intended to be used by the ACLE functions svcreate<n>,
svget and svset.

This patch also includes calling convention support for passing and
returning tuples of scalable vectors to/from functions.

Reviewed By: efriedma

Differential Revision: https://reviews.llvm.org/D75674
---
 include/llvm/IR/IntrinsicsAArch64.td          |  40 +
 lib/Target/AArch64/AArch64ISelLowering.cpp    |  67 ++
 .../sve-calling-convention-tuple-types.ll     | 499 +++++++++++++
 .../AArch64/sve-intrinsics-create-tuple.ll    | 706 ++++++++++++++++++
 .../sve-intrinsics-insert-extract-tuple.ll    | 243 ++++++
 5 files changed, 1555 insertions(+)
 create mode 100644 test/CodeGen/AArch64/sve-calling-convention-tuple-types.ll
 create mode 100644 test/CodeGen/AArch64/sve-intrinsics-create-tuple.ll
 create mode 100644 test/CodeGen/AArch64/sve-intrinsics-insert-extract-tuple.ll

diff --git a/include/llvm/IR/IntrinsicsAArch64.td b/include/llvm/IR/IntrinsicsAArch64.td
index 6065a8c36c2..22a3c2e6d9b 100644
--- a/include/llvm/IR/IntrinsicsAArch64.td
+++ b/include/llvm/IR/IntrinsicsAArch64.td
@@ -789,6 +789,31 @@ def llvm_nxv2f64_ty : LLVMType<nxv2f64>;
 
 let TargetPrefix = "aarch64" in {  // All intrinsics start with "llvm.aarch64.".
 
+  class AdvSIMD_SVE_Create_2Vector_Tuple
+    : Intrinsic<[llvm_anyvector_ty],
+                [llvm_anyvector_ty, LLVMMatchType<1>],
+                [IntrReadMem]>;
+
+  class AdvSIMD_SVE_Create_3Vector_Tuple
+    : Intrinsic<[llvm_anyvector_ty],
+                [llvm_anyvector_ty, LLVMMatchType<1>, LLVMMatchType<1>],
+                [IntrReadMem]>;
+
+  class AdvSIMD_SVE_Create_4Vector_Tuple
+    : Intrinsic<[llvm_anyvector_ty],
+                [llvm_anyvector_ty, LLVMMatchType<1>, LLVMMatchType<1>,
+                 LLVMMatchType<1>],
+                [IntrReadMem]>;
+
+  class AdvSIMD_SVE_Set_Vector_Tuple
+    : Intrinsic<[llvm_anyvector_ty],
+                [LLVMMatchType<0>, llvm_i32_ty, llvm_anyvector_ty],
+                [IntrReadMem, ImmArg<ArgIndex<1>>]>;
+
+  class AdvSIMD_SVE_Get_Vector_Tuple
+    : Intrinsic<[llvm_anyvector_ty], [llvm_anyvector_ty, llvm_i32_ty],
+                [IntrReadMem, IntrArgMemOnly, ImmArg<ArgIndex<1>>]>;
+
   class AdvSIMD_1Vec_PredLoad_Intrinsic
     : Intrinsic<[llvm_anyvector_ty],
                 [LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
@@ -1300,6 +1325,21 @@ class SVE_MatMul_Intrinsic
                 [LLVMMatchType<0>, LLVMSubdivide4VectorType<0>, LLVMSubdivide4VectorType<0>],
                 [IntrNoMem]>;
 
+//
+// Vector tuple creation intrinsics (ACLE)
+//
+
+def int_aarch64_sve_tuple_create2 : AdvSIMD_SVE_Create_2Vector_Tuple;
+def int_aarch64_sve_tuple_create3 : AdvSIMD_SVE_Create_3Vector_Tuple;
+def int_aarch64_sve_tuple_create4 : AdvSIMD_SVE_Create_4Vector_Tuple;
+
+//
+// Vector tuple insertion/extraction intrinsics (ACLE)
+//
+
+def int_aarch64_sve_tuple_get : AdvSIMD_SVE_Get_Vector_Tuple;
+def int_aarch64_sve_tuple_set : AdvSIMD_SVE_Set_Vector_Tuple;
+
 //
 // Loads
 //
diff --git a/lib/Target/AArch64/AArch64ISelLowering.cpp b/lib/Target/AArch64/AArch64ISelLowering.cpp
index bbacf9085bf..5488d3cb12f 100644
--- a/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -13657,6 +13657,73 @@ SDValue AArch64TargetLowering::PerformDAGCombine(SDNode *N,
                                         /*OnlyPackedOffsets=*/false);
     case Intrinsic::aarch64_sve_st1_scatter_scalar_offset:
       return performScatterStoreCombine(N, DAG, AArch64ISD::SST1_IMM);
+    case Intrinsic::aarch64_sve_tuple_get: {
+      SDLoc DL(N);
+      SDValue Chain = N->getOperand(0);
+      SDValue Src1 = N->getOperand(2);
+      SDValue Idx = N->getOperand(3);
+
+      uint64_t IdxConst = cast<ConstantSDNode>(Idx)->getZExtValue();
+      if (IdxConst > Src1->getNumOperands() - 1)
+        report_fatal_error("index larger than expected");
+
+      EVT ResVT = N->getValueType(0);
+      uint64_t NumLanes = ResVT.getVectorElementCount().Min;
+      SDValue Val =
+          DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, ResVT, Src1,
+                      DAG.getConstant(IdxConst * NumLanes, DL, MVT::i32));
+      return DAG.getMergeValues({Val, Chain}, DL);
+    }
+    case Intrinsic::aarch64_sve_tuple_set: {
+      SDLoc DL(N);
+      SDValue Chain = N->getOperand(0);
+      SDValue Tuple = N->getOperand(2);
+      SDValue Idx = N->getOperand(3);
+      SDValue Vec = N->getOperand(4);
+
+      EVT TupleVT = Tuple.getValueType();
+      uint64_t TupleLanes = TupleVT.getVectorElementCount().Min;
+
+      uint64_t IdxConst = cast<ConstantSDNode>(Idx)->getZExtValue();
+      uint64_t NumLanes = Vec.getValueType().getVectorElementCount().Min;
+
+      if ((TupleLanes % NumLanes) != 0)
+        report_fatal_error("invalid tuple vector!");
+
+      uint64_t NumVecs = TupleLanes / NumLanes;
+
+      SmallVector<SDValue, 4> Opnds;
+      for (unsigned I = 0; I < NumVecs; ++I) {
+        if (I == IdxConst)
+          Opnds.push_back(Vec);
+        else {
+          Opnds.push_back(
+              DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, Vec.getValueType(), Tuple,
+                          DAG.getConstant(I * NumLanes, DL, MVT::i32)));
+        }
+      }
+      SDValue Concat =
+          DAG.getNode(ISD::CONCAT_VECTORS, DL, Tuple.getValueType(), Opnds);
+      return DAG.getMergeValues({Concat, Chain}, DL);
+    }
+    case Intrinsic::aarch64_sve_tuple_create2:
+    case Intrinsic::aarch64_sve_tuple_create3:
+    case Intrinsic::aarch64_sve_tuple_create4: {
+      SDLoc DL(N);
+      SDValue Chain = N->getOperand(0);
+
+      SmallVector<SDValue, 4> Opnds;
+      for (unsigned I = 2; I < N->getNumOperands(); ++I)
+        Opnds.push_back(N->getOperand(I));
+
+      EVT VT = Opnds[0].getValueType();
+      EVT EltVT = VT.getVectorElementType();
+      EVT DestVT = EVT::getVectorVT(*DAG.getContext(), EltVT,
+                                    VT.getVectorElementCount() *
+                                        (N->getNumOperands() - 2));
+      SDValue Concat = DAG.getNode(ISD::CONCAT_VECTORS, DL, DestVT, Opnds);
+      return DAG.getMergeValues({Concat, Chain}, DL);
+    }
     default:
       break;
     }
diff --git a/test/CodeGen/AArch64/sve-calling-convention-tuple-types.ll b/test/CodeGen/AArch64/sve-calling-convention-tuple-types.ll
new file mode 100644
index 00000000000..6c702b64a45
--- /dev/null
+++ b/test/CodeGen/AArch64/sve-calling-convention-tuple-types.ll
@@ -0,0 +1,499 @@
+; RUN: llc -mtriple aarch64 -mattr=+sve -asm-verbose=0 < %s | FileCheck %s
+
+;
+; svint8x2_t
+;
+
+define <vscale x 32 x i8> @ret_svint8x2_t(<vscale x 16 x i8> %unused_z0, <vscale x 16 x i8> %z1, <vscale x 16 x i8> %z2) #0 {
+; CHECK-LABEL: ret_svint8x2_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 32 x i8> @llvm.aarch64.sve.tuple.create2.nxv32i8.nxv16i8(<vscale x 16 x i8> %z1, <vscale x 16 x i8> %z2)
+  ret <vscale x 32 x i8> %tuple
+}
+
+define void @call_svint8x2_t(<vscale x 16 x i8> %dummy_z0, <vscale x 16 x i8> %z1, <vscale x 16 x i8> %dummy_z2, <vscale x 16 x i8> %z3) #0 {
+; CHECK-LABEL: call_svint8x2_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z3.d
+; CHECK-NEXT: bl callee_svint8x2_t
+  %tuple = tail call <vscale x 32 x i8> @llvm.aarch64.sve.tuple.create2.nxv32i8.nxv16i8(<vscale x 16 x i8> %z1, <vscale x 16 x i8> %z3)
+  call void @callee_svint8x2_t(<vscale x 32 x i8> %tuple)
+  ret void
+}
+
+;
+; svint16x2_t
+;
+
+define <vscale x 16 x i16> @ret_svint16x2_t(<vscale x 8 x i16> %unused_z0, <vscale x 8 x i16> %z1, <vscale x 8 x i16> %z2) #0 {
+; CHECK-LABEL: ret_svint16x2_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 16 x i16> @llvm.aarch64.sve.tuple.create2.nxv16i16.nxv8i16(<vscale x 8 x i16> %z1, <vscale x 8 x i16> %z2)
+  ret <vscale x 16 x i16> %tuple
+}
+
+define void @call_svint16x2_t(<vscale x 8 x i16> %dummy_z0, <vscale x 8 x i16> %z1, <vscale x 8 x i16> %dummy_z2, <vscale x 8 x i16> %z3) #0 {
+; CHECK-LABEL: call_svint16x2_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z3.d
+; CHECK-NEXT: bl callee_svint16x2_t
+  %tuple = tail call <vscale x 16 x i16> @llvm.aarch64.sve.tuple.create2.nxv16i16.nxv8i16(<vscale x 8 x i16> %z1, <vscale x 8 x i16> %z3)
+  call void @callee_svint16x2_t(<vscale x 16 x i16> %tuple)
+  ret void
+}
+
+;
+; svint32x2_t
+;
+
+define <vscale x 8 x i32> @ret_svint32x2_t(<vscale x 4 x i32> %unused_z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2) #0 {
+; CHECK-LABEL: ret_svint32x2_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 8 x i32> @llvm.aarch64.sve.tuple.create2.nxv8i32.nxv4i32(<vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2)
+  ret <vscale x 8 x i32> %tuple
+}
+
+define void @call_svint32x2_t(<vscale x 4 x i32> %dummy_z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %dummy_z2, <vscale x 4 x i32> %z3) #0 {
+; CHECK-LABEL: call_svint32x2_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z3.d
+; CHECK-NEXT: bl callee_svint32x2_t
+  %tuple = tail call <vscale x 8 x i32> @llvm.aarch64.sve.tuple.create2.nxv8i32.nxv4i32(<vscale x 4 x i32> %z1, <vscale x 4 x i32> %z3)
+  call void @callee_svint32x2_t(<vscale x 8 x i32> %tuple)
+  ret void
+}
+
+;
+; svint64x2_t
+;
+
+define <vscale x 4 x i64> @ret_svint64x2_t(<vscale x 2 x i64> %unused_z0, <vscale x 2 x i64> %z1, <vscale x 2 x i64> %z2) #0 {
+; CHECK-LABEL: ret_svint64x2_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 4 x i64> @llvm.aarch64.sve.tuple.create2.nxv4i64.nxv2i64(<vscale x 2 x i64> %z1, <vscale x 2 x i64> %z2)
+  ret <vscale x 4 x i64> %tuple
+}
+
+define void @call_svint64x2_t(<vscale x 2 x i64> %dummy_z0, <vscale x 2 x i64> %z1, <vscale x 2 x i64> %dummy_z2, <vscale x 2 x i64> %z3) #0 {
+; CHECK-LABEL: call_svint64x2_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z3.d
+; CHECK-NEXT: bl callee_svint64x2_t
+  %tuple = tail call <vscale x 4 x i64> @llvm.aarch64.sve.tuple.create2.nxv4i64.nxv2i64(<vscale x 2 x i64> %z1, <vscale x 2 x i64> %z3)
+  call void @callee_svint64x2_t(<vscale x 4 x i64> %tuple)
+  ret void
+}
+
+;
+; svfloatx2_t
+;
+
+define <vscale x 8 x float> @ret_svfloatx2_t(<vscale x 4 x float> %unused_z0, <vscale x 4 x float> %z1, <vscale x 4 x float> %z2) #0 {
+; CHECK-LABEL: ret_svfloatx2_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 8 x float> @llvm.aarch64.sve.tuple.create2.nxv8f32.nxv4f32(<vscale x 4 x float> %z1, <vscale x 4 x float> %z2)
+  ret <vscale x 8 x float> %tuple
+}
+
+define void @call_svfloatx2_t(<vscale x 4 x float> %dummy_z0, <vscale x 4 x float> %z1, <vscale x 4 x float> %dummy_z2, <vscale x 4 x float> %z3) #0 {
+; CHECK-LABEL: call_svfloatx2_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z3.d
+; CHECK-NEXT: bl callee_svfloatx2_t
+  %tuple = tail call <vscale x 8 x float> @llvm.aarch64.sve.tuple.create2.nxv8f32.nxv4f32(<vscale x 4 x float> %z1, <vscale x 4 x float> %z3)
+  call void @callee_svfloatx2_t(<vscale x 8 x float> %tuple)
+  ret void
+}
+
+;
+; svdoublex2_t
+;
+
+define <vscale x 4 x double> @ret_svdoublex2_t(<vscale x 2 x double> %unused_z0, <vscale x 2 x double> %z1, <vscale x 2 x double> %z2) #0 {
+; CHECK-LABEL: ret_svdoublex2_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 4 x double> @llvm.aarch64.sve.tuple.create2.nxv4f64.nxv2f64(<vscale x 2 x double> %z1, <vscale x 2 x double> %z2)
+  ret <vscale x 4 x double> %tuple
+}
+
+define void @call_svdoublex2_t(<vscale x 2 x double> %dummy_z0, <vscale x 2 x double> %z1, <vscale x 2 x double> %dummy_z2, <vscale x 2 x double> %z3) #0 {
+; CHECK-LABEL: call_svdoublex2_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z3.d
+; CHECK-NEXT: bl callee_svdoublex2_t
+  %tuple = tail call <vscale x 4 x double> @llvm.aarch64.sve.tuple.create2.nxv4f64.nxv2f64(<vscale x 2 x double> %z1, <vscale x 2 x double> %z3)
+  call void @callee_svdoublex2_t(<vscale x 4 x double> %tuple)
+  ret void
+}
+
+;
+; svint8x3_t
+;
+
+define <vscale x 48 x i8> @ret_svint8x3_t(<vscale x 16 x i8> %unused_z0, <vscale x 16 x i8> %z1, <vscale x 16 x i8> %z2, <vscale x 16 x i8> %z3) #0 {
+; CHECK-LABEL: ret_svint8x3_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z3.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 48 x i8> @llvm.aarch64.sve.tuple.create3.nxv48i8.nxv16i8(<vscale x 16 x i8> %z1, <vscale x 16 x i8> %z2, <vscale x 16 x i8> %z3)
+  ret <vscale x 48 x i8> %tuple
+}
+
+define void @call_svint8x3_t(<vscale x 16 x i8> %dummy_z0, <vscale x 16 x i8> %z1, <vscale x 16 x i8> %z2, <vscale x 16 x i8> %dummy_z3, <vscale x 16 x i8> %z4) #0 {
+; CHECK-LABEL: call_svint8x3_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z4.d
+; CHECK-NEXT: bl callee_svint8x3_t
+  %tuple = tail call <vscale x 48 x i8> @llvm.aarch64.sve.tuple.create3.nxv48i8.nxv16i8(<vscale x 16 x i8> %z1, <vscale x 16 x i8> %z2, <vscale x 16 x i8> %z4)
+  call void @callee_svint8x3_t(<vscale x 48 x i8> %tuple)
+  ret void
+}
+
+;
+; svint16x3_t
+;
+
+define <vscale x 24 x i16> @ret_svint16x3_t(<vscale x 8 x i16> %unused_z0, <vscale x 8 x i16> %z1, <vscale x 8 x i16> %z2, <vscale x 8 x i16> %z3) #0 {
+; CHECK-LABEL: ret_svint16x3_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z3.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 24 x i16> @llvm.aarch64.sve.tuple.create3.nxv24i16.nxv8i16(<vscale x 8 x i16> %z1, <vscale x 8 x i16> %z2, <vscale x 8 x i16> %z3)
+  ret <vscale x 24 x i16> %tuple
+}
+
+define void @call_svint16x3_t(<vscale x 8 x i16> %dummy_z0, <vscale x 8 x i16> %z1, <vscale x 8 x i16> %z2, <vscale x 8 x i16> %dummy_z3, <vscale x 8 x i16> %z4) #0 {
+; CHECK-LABEL: call_svint16x3_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z4.d
+; CHECK-NEXT: bl callee_svint16x3_t
+  %tuple = tail call <vscale x 24 x i16> @llvm.aarch64.sve.tuple.create3.nxv24i16.nxv8i16(<vscale x 8 x i16> %z1, <vscale x 8 x i16> %z2, <vscale x 8 x i16> %z4)
+  call void @callee_svint16x3_t(<vscale x 24 x i16> %tuple)
+  ret void
+}
+
+;
+; svint32x3_t
+;
+
+define <vscale x 12 x i32> @ret_svint32x3_t(<vscale x 4 x i32> %unused_z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3) #0 {
+; CHECK-LABEL: ret_svint32x3_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z3.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 12 x i32> @llvm.aarch64.sve.tuple.create3.nxv12i32.nxv4i32(<vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3)
+  ret <vscale x 12 x i32> %tuple
+}
+
+define void @call_svint32x3_t(<vscale x 4 x i32> %dummy_z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2, <vscale x 4 x i32> %dummy_z3, <vscale x 4 x i32> %z4) #0 {
+; CHECK-LABEL: call_svint32x3_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z4.d
+; CHECK-NEXT: bl callee_svint32x3_t
+  %tuple = tail call <vscale x 12 x i32> @llvm.aarch64.sve.tuple.create3.nxv12i32.nxv4i32(<vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z4)
+  call void @callee_svint32x3_t(<vscale x 12 x i32> %tuple)
+  ret void
+}
+
+;
+; svint64x3_t
+;
+
+define <vscale x 6 x i64> @ret_svint64x3_t(<vscale x 2 x i64> %unused_z0, <vscale x 2 x i64> %z1, <vscale x 2 x i64> %z2, <vscale x 2 x i64> %z3) #0 {
+; CHECK-LABEL: ret_svint64x3_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z3.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 6 x i64> @llvm.aarch64.sve.tuple.create3.nxv6i64.nxv2i64(<vscale x 2 x i64> %z1, <vscale x 2 x i64> %z2, <vscale x 2 x i64> %z3)
+  ret <vscale x 6 x i64> %tuple
+}
+
+define void @call_svint64x3_t(<vscale x 2 x i64> %dummy_z0, <vscale x 2 x i64> %z1, <vscale x 2 x i64> %z2, <vscale x 2 x i64> %dummy_z3, <vscale x 2 x i64> %z4) #0 {
+; CHECK-LABEL: call_svint64x3_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z4.d
+; CHECK-NEXT: bl callee_svint64x3_t
+  %tuple = tail call <vscale x 6 x i64> @llvm.aarch64.sve.tuple.create3.nxv6i64.nxv2i64(<vscale x 2 x i64> %z1, <vscale x 2 x i64> %z2, <vscale x 2 x i64> %z4)
+  call void @callee_svint64x3_t(<vscale x 6 x i64> %tuple)
+  ret void
+}
+
+;
+; svfloatx3_t
+;
+
+define <vscale x 12 x float> @ret_svfloatx3_t(<vscale x 4 x float> %unused_z0, <vscale x 4 x float> %z1, <vscale x 4 x float> %z2, <vscale x 4 x float> %z3) #0 {
+; CHECK-LABEL: ret_svfloatx3_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z3.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 12 x float> @llvm.aarch64.sve.tuple.create3.nxv12f32.nxv4f32(<vscale x 4 x float> %z1, <vscale x 4 x float> %z2, <vscale x 4 x float> %z3)
+  ret <vscale x 12 x float> %tuple
+}
+
+define void @call_svfloatx3_t(<vscale x 4 x float> %dummy_z0, <vscale x 4 x float> %z1, <vscale x 4 x float> %z2, <vscale x 4 x float> %dummy_z3, <vscale x 4 x float> %z4) #0 {
+; CHECK-LABEL: call_svfloatx3_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z4.d
+; CHECK-NEXT: bl callee_svfloatx3_t
+  %tuple = tail call <vscale x 12 x float> @llvm.aarch64.sve.tuple.create3.nxv12f32.nxv4f32(<vscale x 4 x float> %z1, <vscale x 4 x float> %z2, <vscale x 4 x float> %z4)
+  call void @callee_svfloatx3_t(<vscale x 12 x float> %tuple)
+  ret void
+}
+
+;
+; svdoublex3_t
+;
+
+define <vscale x 6 x double> @ret_svdoublex3_t(<vscale x 2 x double> %unused_z0, <vscale x 2 x double> %z1, <vscale x 2 x double> %z2, <vscale x 2 x double> %z3) #0 {
+; CHECK-LABEL: ret_svdoublex3_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z3.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 6 x double> @llvm.aarch64.sve.tuple.create3.nxv6f64.nxv2f64(<vscale x 2 x double> %z1, <vscale x 2 x double> %z2, <vscale x 2 x double> %z3)
+  ret <vscale x 6 x double> %tuple
+}
+
+define void @call_svdoublex3_t(<vscale x 2 x double> %dummy_z0, <vscale x 2 x double> %z1, <vscale x 2 x double> %z2, <vscale x 2 x double> %dummy_z3, <vscale x 2 x double> %z4) #0 {
+; CHECK-LABEL: call_svdoublex3_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z4.d
+; CHECK-NEXT: bl callee_svdoublex3_t
+  %tuple = tail call <vscale x 6 x double> @llvm.aarch64.sve.tuple.create3.nxv6f64.nxv2f64(<vscale x 2 x double> %z1, <vscale x 2 x double> %z2, <vscale x 2 x double> %z4)
+  call void @callee_svdoublex3_t(<vscale x 6 x double> %tuple)
+  ret void
+}
+
+;
+; svint8x4_t
+;
+
+define <vscale x 64 x i8> @ret_svint8x4_t(<vscale x 16 x i8> %unused_z0, <vscale x 16 x i8> %z1, <vscale x 16 x i8> %z2, <vscale x 16 x i8> %z3, <vscale x 16 x i8> %z4) #0 {
+; CHECK-LABEL: ret_svint8x4_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z3.d
+; CHECK-NEXT: mov z3.d, z4.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 64 x i8> @llvm.aarch64.sve.tuple.create4.nxv64i8.nxv16i8(<vscale x 16 x i8> %z1, <vscale x 16 x i8> %z2, <vscale x 16 x i8> %z3, <vscale x 16 x i8> %z4)
+  ret <vscale x 64 x i8> %tuple
+}
+
+define void @call_svint8x4_t(<vscale x 16 x i8> %dummy_z0, <vscale x 16 x i8> %z1, <vscale x 16 x i8> %z2, <vscale x 16 x i8> %dummy_z3, <vscale x 16 x i8> %z4, <vscale x 16 x i8> %z5) #0 {
+; CHECK-LABEL: call_svint8x4_t
+; CHECK:      mov z3.d, z5.d
+; CHECK-NEXT: mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z4.d
+; CHECK-NEXT: bl callee_svint8x4_t
+  %tuple = tail call <vscale x 64 x i8> @llvm.aarch64.sve.tuple.create4.nxv64i8.nxv16i8(<vscale x 16 x i8> %z1, <vscale x 16 x i8> %z2, <vscale x 16 x i8> %z4, <vscale x 16 x i8> %z5)
+  call void @callee_svint8x4_t(<vscale x 64 x i8> %tuple)
+  ret void
+}
+
+;
+; svint16x4_t
+;
+
+define <vscale x 32 x i16> @ret_svint16x4_t(<vscale x 8 x i16> %unused_z0, <vscale x 8 x i16> %z1, <vscale x 8 x i16> %z2, <vscale x 8 x i16> %z3, <vscale x 8 x i16> %z4) #0 {
+; CHECK-LABEL: ret_svint16x4_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z3.d
+; CHECK-NEXT: mov z3.d, z4.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 32 x i16> @llvm.aarch64.sve.tuple.create4.nxv32i16.nxv8i16(<vscale x 8 x i16> %z1, <vscale x 8 x i16> %z2, <vscale x 8 x i16> %z3, <vscale x 8 x i16> %z4)
+  ret <vscale x 32 x i16> %tuple
+}
+
+define void @call_svint16x4_t(<vscale x 8 x i16> %dummy_z0, <vscale x 8 x i16> %z1, <vscale x 8 x i16> %z2, <vscale x 8 x i16> %dummy_z3, <vscale x 8 x i16> %z4, <vscale x 8 x i16> %z5) #0 {
+; CHECK-LABEL: call_svint16x4_t
+; CHECK:      mov z3.d, z5.d
+; CHECK-NEXT: mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z4.d
+; CHECK-NEXT: bl callee_svint16x4_t
+  %tuple = tail call <vscale x 32 x i16> @llvm.aarch64.sve.tuple.create4.nxv32i16.nxv8i16(<vscale x 8 x i16> %z1, <vscale x 8 x i16> %z2, <vscale x 8 x i16> %z4, <vscale x 8 x i16> %z5)
+  call void @callee_svint16x4_t(<vscale x 32 x i16> %tuple)
+  ret void
+}
+
+;
+; svint32x4_t
+;
+
+define <vscale x 16 x i32> @ret_svint32x4_t(<vscale x 4 x i32> %unused_z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3, <vscale x 4 x i32> %z4) #0 {
+; CHECK-LABEL: ret_svint32x4_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z3.d
+; CHECK-NEXT: mov z3.d, z4.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 16 x i32> @llvm.aarch64.sve.tuple.create4.nxv16i32.nxv4i32(<vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3, <vscale x 4 x i32> %z4)
+  ret <vscale x 16 x i32> %tuple
+}
+
+define void @call_svint32x4_t(<vscale x 4 x i32> %dummy_z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2, <vscale x 4 x i32> %dummy_z3, <vscale x 4 x i32> %z4, <vscale x 4 x i32> %z5) #0 {
+; CHECK-LABEL: call_svint32x4_t
+; CHECK:      mov z3.d, z5.d
+; CHECK-NEXT: mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z4.d
+; CHECK-NEXT: bl callee_svint32x4_t
+  %tuple = tail call <vscale x 16 x i32> @llvm.aarch64.sve.tuple.create4.nxv16i32.nxv4i32(<vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z4, <vscale x 4 x i32> %z5)
+  call void @callee_svint32x4_t(<vscale x 16 x i32> %tuple)
+  ret void
+}
+
+;
+; svint64x4_t
+;
+
+define <vscale x 8 x i64> @ret_svint64x4_t(<vscale x 2 x i64> %unused_z0, <vscale x 2 x i64> %z1, <vscale x 2 x i64> %z2, <vscale x 2 x i64> %z3, <vscale x 2 x i64> %z4) #0 {
+; CHECK-LABEL: ret_svint64x4_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z3.d
+; CHECK-NEXT: mov z3.d, z4.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 8 x i64> @llvm.aarch64.sve.tuple.create4.nxv8i64.nxv2i64(<vscale x 2 x i64> %z1, <vscale x 2 x i64> %z2, <vscale x 2 x i64> %z3, <vscale x 2 x i64> %z4)
+  ret <vscale x 8 x i64> %tuple
+}
+
+define void @call_svint64x4_t(<vscale x 2 x i64> %dummy_z0, <vscale x 2 x i64> %z1, <vscale x 2 x i64> %z2, <vscale x 2 x i64> %dummy_z3, <vscale x 2 x i64> %z4, <vscale x 2 x i64> %z5) #0 {
+; CHECK-LABEL: call_svint64x4_t
+; CHECK:      mov z3.d, z5.d
+; CHECK-NEXT: mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z4.d
+; CHECK-NEXT: bl callee_svint64x4_t
+  %tuple = tail call <vscale x 8 x i64> @llvm.aarch64.sve.tuple.create4.nxv8i64.nxv2i64(<vscale x 2 x i64> %z1, <vscale x 2 x i64> %z2, <vscale x 2 x i64> %z4, <vscale x 2 x i64> %z5)
+  call void @callee_svint64x4_t(<vscale x 8 x i64> %tuple)
+  ret void
+}
+
+;
+; svfloatx4_t
+;
+
+define <vscale x 16 x float> @ret_svfloatx4_t(<vscale x 4 x float> %unused_z0, <vscale x 4 x float> %z1, <vscale x 4 x float> %z2, <vscale x 4 x float> %z3, <vscale x 4 x float> %z4) #0 {
+; CHECK-LABEL: ret_svfloatx4_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z3.d
+; CHECK-NEXT: mov z3.d, z4.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 16 x float> @llvm.aarch64.sve.tuple.create4.nxv16f32.nxv4f32(<vscale x 4 x float> %z1, <vscale x 4 x float> %z2, <vscale x 4 x float> %z3, <vscale x 4 x float> %z4)
+  ret <vscale x 16 x float> %tuple
+}
+
+define void @call_svfloatx4_t(<vscale x 4 x float> %dummy_z0, <vscale x 4 x float> %z1, <vscale x 4 x float> %z2, <vscale x 4 x float> %dummy_z3, <vscale x 4 x float> %z4, <vscale x 4 x float> %z5) #0 {
+; CHECK-LABEL: call_svfloatx4_t
+; CHECK:      mov z3.d, z5.d
+; CHECK-NEXT: mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z4.d
+; CHECK-NEXT: bl callee_svfloatx4_t
+  %tuple = tail call <vscale x 16 x float> @llvm.aarch64.sve.tuple.create4.nxv16f32.nxv4f32(<vscale x 4 x float> %z1, <vscale x 4 x float> %z2, <vscale x 4 x float> %z4, <vscale x 4 x float> %z5)
+  call void @callee_svfloatx4_t(<vscale x 16 x float> %tuple)
+  ret void
+}
+
+;
+; svdoublex4_t
+;
+
+define <vscale x 8 x double> @ret_svdoublex4_t(<vscale x 2 x double> %unused_z0, <vscale x 2 x double> %z1, <vscale x 2 x double> %z2, <vscale x 2 x double> %z3, <vscale x 2 x double> %z4) #0 {
+; CHECK-LABEL: ret_svdoublex4_t
+; CHECK:      mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z3.d
+; CHECK-NEXT: mov z3.d, z4.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 8 x double> @llvm.aarch64.sve.tuple.create4.nxv8f64.nxv2f64(<vscale x 2 x double> %z1, <vscale x 2 x double> %z2, <vscale x 2 x double> %z3, <vscale x 2 x double> %z4)
+  ret <vscale x 8 x double> %tuple
+}
+
+define void @call_svdoublex4_t(<vscale x 2 x double> %dummy_z0, <vscale x 2 x double> %z1, <vscale x 2 x double> %z2, <vscale x 2 x double> %dummy_z3, <vscale x 2 x double> %z4, <vscale x 2 x double> %z5) #0 {
+; CHECK-LABEL: call_svdoublex4_t
+; CHECK:      mov z3.d, z5.d
+; CHECK-NEXT: mov z0.d, z1.d
+; CHECK-NEXT: mov z1.d, z2.d
+; CHECK-NEXT: mov z2.d, z4.d
+; CHECK-NEXT: bl callee_svdoublex4_t
+  %tuple = tail call <vscale x 8 x double> @llvm.aarch64.sve.tuple.create4.nxv8f64.nxv2f64(<vscale x 2 x double> %z1, <vscale x 2 x double> %z2, <vscale x 2 x double> %z4, <vscale x 2 x double> %z5)
+  call void @callee_svdoublex4_t(<vscale x 8 x double> %tuple)
+  ret void
+}
+
+attributes #0 = { nounwind "target-features"="+sve" }
+
+declare void @callee_svint8x2_t(<vscale x 32 x i8>)
+declare void @callee_svint16x2_t(<vscale x 16 x i16>)
+declare void @callee_svint32x2_t(<vscale x 8 x i32>)
+declare void @callee_svint64x2_t(<vscale x 4 x i64>)
+declare void @callee_svfloatx2_t(<vscale x 8 x float>)
+declare void @callee_svdoublex2_t(<vscale x 4 x double>)
+
+declare void @callee_svint8x3_t(<vscale x 48 x i8>)
+declare void @callee_svint16x3_t(<vscale x 24 x i16>)
+declare void @callee_svint32x3_t(<vscale x 12 x i32>)
+declare void @callee_svint64x3_t(<vscale x 6 x i64>)
+declare void @callee_svfloatx3_t(<vscale x 12 x float>)
+declare void @callee_svdoublex3_t(<vscale x 6 x double>)
+
+declare void @callee_svint8x4_t(<vscale x 64 x i8>)
+declare void @callee_svint16x4_t(<vscale x 32 x i16>)
+declare void @callee_svint32x4_t(<vscale x 16 x i32>)
+declare void @callee_svint64x4_t(<vscale x 8 x i64>)
+declare void @callee_svfloatx4_t(<vscale x 16 x float>)
+declare void @callee_svdoublex4_t(<vscale x 8 x double>)
+
+
+; x2
+declare <vscale x 32 x i8> @llvm.aarch64.sve.tuple.create2.nxv32i8.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
+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 8 x i32> @llvm.aarch64.sve.tuple.create2.nxv8i32.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 4 x i64> @llvm.aarch64.sve.tuple.create2.nxv4i64.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
+declare <vscale x 8 x float> @llvm.aarch64.sve.tuple.create2.nxv8f32.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 4 x double> @llvm.aarch64.sve.tuple.create2.nxv4f64.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
+
+; x3
+declare <vscale x 48 x i8> @llvm.aarch64.sve.tuple.create3.nxv48i8.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+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>)
+declare <vscale x 12 x i32> @llvm.aarch64.sve.tuple.create3.nxv12i32.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+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 12 x float> @llvm.aarch64.sve.tuple.create3.nxv12f32.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 6 x double> @llvm.aarch64.sve.tuple.create3.nxv6f64.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+
+; x4
+declare <vscale x 64 x i8> @llvm.aarch64.sve.tuple.create4.nxv64i8.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+declare <vscale x 32 x i16> @llvm.aarch64.sve.tuple.create4.nxv32i16.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 16 x i32> @llvm.aarch64.sve.tuple.create4.nxv16i32.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+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 float> @llvm.aarch64.sve.tuple.create4.nxv16f32.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 8 x double> @llvm.aarch64.sve.tuple.create4.nxv8f64.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
diff --git a/test/CodeGen/AArch64/sve-intrinsics-create-tuple.ll b/test/CodeGen/AArch64/sve-intrinsics-create-tuple.ll
new file mode 100644
index 00000000000..38b05e42b96
--- /dev/null
+++ b/test/CodeGen/AArch64/sve-intrinsics-create-tuple.ll
@@ -0,0 +1,706 @@
+; RUN: llc -mtriple aarch64 -mattr=+sve -asm-verbose=1 < %s | FileCheck %s
+
+;
+; SVCREATE2 (i8)
+;
+
+define <vscale x 16 x i8> @test_svcreate2_s8_vec0(i1 %p, <vscale x 16 x i8> %z0, <vscale x 16 x i8> %z1) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate2_s8_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 32 x i8> @llvm.aarch64.sve.tuple.create2.nxv32i8.nxv16i8(<vscale x 16 x i8> %z0, <vscale x 16 x i8> %z1)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 16 x i8> undef
+L2:
+  %extract = tail call <vscale x 16 x i8> @llvm.aarch64.sve.tuple.get.nxv16i8.nxv32i8(<vscale x 32 x i8> %tuple, i32 0)
+  ret <vscale x 16 x i8> %extract
+}
+
+define <vscale x 16 x i8> @test_svcreate2_s8_vec1(i1 %p, <vscale x 16 x i8> %z0, <vscale x 16 x i8> %z1) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate2_s8_vec1:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z1.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 32 x i8> @llvm.aarch64.sve.tuple.create2.nxv32i8.nxv16i8(<vscale x 16 x i8> %z0, <vscale x 16 x i8> %z1)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 16 x i8> undef
+L2:
+  %extract = tail call <vscale x 16 x i8> @llvm.aarch64.sve.tuple.get.nxv16i8.nxv32i8(<vscale x 32 x i8> %tuple, i32 1)
+  ret <vscale x 16 x i8> %extract
+}
+
+;
+; SVCREATE2 (i16)
+;
+
+define <vscale x 8 x i16> @test_svcreate2_s16_vec0(i1 %p, <vscale x 8 x i16> %z0, <vscale x 8 x i16> %z1) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate2_s16_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 16 x i16> @llvm.aarch64.sve.tuple.create2.nxv16i16.nxv8i16(<vscale x 8 x i16> %z0, <vscale x 8 x i16> %z1)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 8 x i16> undef
+L2:
+  %extract = tail call <vscale x 8 x i16> @llvm.aarch64.sve.tuple.get.nxv8i16.nxv16i16(<vscale x 16 x i16> %tuple, i32 0)
+  ret <vscale x 8 x i16> %extract
+}
+
+define <vscale x 8 x i16> @test_svcreate2_s16_vec1(i1 %p, <vscale x 8 x i16> %z0, <vscale x 8 x i16> %z1) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate2_s16_vec1:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z1.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 16 x i16> @llvm.aarch64.sve.tuple.create2.nxv16i16.nxv8i16(<vscale x 8 x i16> %z0, <vscale x 8 x i16> %z1)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 8 x i16> undef
+L2:
+  %extract = tail call <vscale x 8 x i16> @llvm.aarch64.sve.tuple.get.nxv8i16.nxv16i16(<vscale x 16 x i16> %tuple, i32 1)
+  ret <vscale x 8 x i16> %extract
+}
+
+;
+; SVCREATE2 (half)
+;
+
+define <vscale x 8 x half> @test_svcreate2_f16_vec0(i1 %p, <vscale x 8 x half> %z0, <vscale x 8 x half> %z1) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate2_f16_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 16 x half> @llvm.aarch64.sve.tuple.create2.nxv16f16.nxv8f16(<vscale x 8 x half> %z0, <vscale x 8 x half> %z1)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 8 x half> undef
+L2:
+  %extract = tail call <vscale x 8 x half> @llvm.aarch64.sve.tuple.get.nxv8f16.nxv16f16(<vscale x 16 x half> %tuple, i32 0)
+  ret <vscale x 8 x half> %extract
+}
+
+define <vscale x 8 x half> @test_svcreate2_f16_vec1(i1 %p, <vscale x 8 x half> %z0, <vscale x 8 x half> %z1) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate2_f16_vec1:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z1.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 16 x half> @llvm.aarch64.sve.tuple.create2.nxv16f16.nxv8f16(<vscale x 8 x half> %z0, <vscale x 8 x half> %z1)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 8 x half> undef
+L2:
+  %extract = tail call <vscale x 8 x half> @llvm.aarch64.sve.tuple.get.nxv8f16.nxv16f16(<vscale x 16 x half> %tuple, i32 1)
+  ret <vscale x 8 x half> %extract
+}
+
+;
+; SVCREATE2 (i32)
+;
+
+define <vscale x 4 x i32> @test_svcreate2_s32_vec0(i1 %p, <vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate2_s32_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 8 x i32> @llvm.aarch64.sve.tuple.create2.nxv8i32.nxv4i32(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 4 x i32> undef
+L2:
+  %extract = tail call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv4i32.nxv8i32(<vscale x 8 x i32> %tuple, i32 0)
+  ret <vscale x 4 x i32> %extract
+}
+
+define <vscale x 4 x i32> @test_svcreate2_s32_vec1(i1 %p, <vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate2_s32_vec1:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z1.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 8 x i32> @llvm.aarch64.sve.tuple.create2.nxv8i32.nxv4i32(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 4 x i32> undef
+L2:
+  %extract = tail call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv4i32.nxv8i32(<vscale x 8 x i32> %tuple, i32 1)
+  ret <vscale x 4 x i32> %extract
+}
+
+;
+; SVCREATE2 (float)
+;
+
+define <vscale x 4 x float> @test_svcreate2_f32_vec0(i1 %p, <vscale x 4 x float> %z0, <vscale x 4 x float> %z1) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate2_f32_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 8 x float> @llvm.aarch64.sve.tuple.create2.nxv8f32.nxv4f32(<vscale x 4 x float> %z0, <vscale x 4 x float> %z1)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 4 x float> undef
+L2:
+  %extract = tail call <vscale x 4 x float> @llvm.aarch64.sve.tuple.get.nxv4f32.nxv8f32(<vscale x 8 x float> %tuple, i32 0)
+  ret <vscale x 4 x float> %extract
+}
+
+define <vscale x 4 x float> @test_svcreate2_f32_vec1(i1 %p, <vscale x 4 x float> %z0, <vscale x 4 x float> %z1) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate2_f32_vec1:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z1.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 8 x float> @llvm.aarch64.sve.tuple.create2.nxv8f32.nxv4f32(<vscale x 4 x float> %z0, <vscale x 4 x float> %z1)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 4 x float> undef
+L2:
+  %extract = tail call <vscale x 4 x float> @llvm.aarch64.sve.tuple.get.nxv4f32.nxv8f32(<vscale x 8 x float> %tuple, i32 1)
+  ret <vscale x 4 x float> %extract
+}
+
+;
+; SVCREATE2 (i64)
+;
+
+define <vscale x 2 x i64> @test_svcreate2_s64_vec0(i1 %p, <vscale x 2 x i64> %z0, <vscale x 2 x i64> %z1) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate2_s64_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 4 x i64> @llvm.aarch64.sve.tuple.create2.nxv4i64.nxv2i64(<vscale x 2 x i64> %z0, <vscale x 2 x i64> %z1)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 2 x i64> undef
+L2:
+  %extract = tail call <vscale x 2 x i64> @llvm.aarch64.sve.tuple.get.nxv2i64.nxv4i64(<vscale x 4 x i64> %tuple, i32 0)
+  ret <vscale x 2 x i64> %extract
+}
+
+define <vscale x 2 x i64> @test_svcreate2_s64_vec1(i1 %p, <vscale x 2 x i64> %z0, <vscale x 2 x i64> %z1) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate2_s64_vec1:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z1.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 4 x i64> @llvm.aarch64.sve.tuple.create2.nxv4i64.nxv2i64(<vscale x 2 x i64> %z0, <vscale x 2 x i64> %z1)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 2 x i64> undef
+L2:
+  %extract = tail call <vscale x 2 x i64> @llvm.aarch64.sve.tuple.get.nxv2i64.nxv4i64(<vscale x 4 x i64> %tuple, i32 1)
+  ret <vscale x 2 x i64> %extract
+}
+
+;
+; SVCREATE2 (double)
+;
+
+define <vscale x 2 x double> @test_svcreate2_f64_vec0(i1 %p, <vscale x 2 x double> %z0, <vscale x 2 x double> %z1) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate2_f64_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 4 x double> @llvm.aarch64.sve.tuple.create2.nxv4f64.nxv2f64(<vscale x 2 x double> %z0, <vscale x 2 x double> %z1)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 2 x double> undef
+L2:
+  %extract = tail call <vscale x 2 x double> @llvm.aarch64.sve.tuple.get.nxv2f64.nxv4f64(<vscale x 4 x double> %tuple, i32 0)
+  ret <vscale x 2 x double> %extract
+}
+
+define <vscale x 2 x double> @test_svcreate2_f64_vec1(i1 %p, <vscale x 2 x double> %z0, <vscale x 2 x double> %z1) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate2_f64_vec1:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z1.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 4 x double> @llvm.aarch64.sve.tuple.create2.nxv4f64.nxv2f64(<vscale x 2 x double> %z0, <vscale x 2 x double> %z1)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 2 x double> undef
+L2:
+  %extract = tail call <vscale x 2 x double> @llvm.aarch64.sve.tuple.get.nxv2f64.nxv4f64(<vscale x 4 x double> %tuple, i32 1)
+  ret <vscale x 2 x double> %extract
+}
+
+;
+; SVCREATE3 (i8)
+;
+
+define <vscale x 16 x i8> @test_svcreate3_s8_vec0(i1 %p, <vscale x 16 x i8> %z0, <vscale x 16 x i8> %z1, <vscale x 16 x i8> %z2) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate3_s8_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 48 x i8> @llvm.aarch64.sve.tuple.create3.nxv48i8.nxv16i8(<vscale x 16 x i8> %z0, <vscale x 16 x i8> %z1, <vscale x 16 x i8> %z2)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 16 x i8> undef
+L2:
+  %extract = tail call <vscale x 16 x i8> @llvm.aarch64.sve.tuple.get.nxv16i8.nxv48i8(<vscale x 48 x i8> %tuple, i32 0)
+  ret <vscale x 16 x i8> %extract
+}
+
+define <vscale x 16 x i8> @test_svcreate3_s8_vec2(i1 %p, <vscale x 16 x i8> %z0, <vscale x 16 x i8> %z1, <vscale x 16 x i8> %z2) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate3_s8_vec2:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z2.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 48 x i8> @llvm.aarch64.sve.tuple.create3.nxv48i8.nxv16i8(<vscale x 16 x i8> %z0, <vscale x 16 x i8> %z1, <vscale x 16 x i8> %z2)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 16 x i8> undef
+L2:
+  %extract = tail call <vscale x 16 x i8> @llvm.aarch64.sve.tuple.get.nxv16i8.nxv48i8(<vscale x 48 x i8> %tuple, i32 2)
+  ret <vscale x 16 x i8> %extract
+}
+
+;
+; SVCREATE3 (i16)
+;
+
+define <vscale x 8 x i16> @test_svcreate3_s16_vec0(i1 %p, <vscale x 8 x i16> %z0, <vscale x 8 x i16> %z1, <vscale x 8 x i16> %z2) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate3_s16_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 24 x i16> @llvm.aarch64.sve.tuple.create3.nxv24i16.nxv8i16(<vscale x 8 x i16> %z0, <vscale x 8 x i16> %z1, <vscale x 8 x i16> %z2)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 8 x i16> undef
+L2:
+  %extract = tail call <vscale x 8 x i16> @llvm.aarch64.sve.tuple.get.nxv8i16.nxv24i16(<vscale x 24 x i16> %tuple, i32 0)
+  ret <vscale x 8 x i16> %extract
+}
+
+define <vscale x 8 x i16> @test_svcreate3_s16_vec2(i1 %p, <vscale x 8 x i16> %z0, <vscale x 8 x i16> %z1, <vscale x 8 x i16> %z2) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate3_s16_vec2:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z2.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 24 x i16> @llvm.aarch64.sve.tuple.create3.nxv24i16.nxv8i16(<vscale x 8 x i16> %z0, <vscale x 8 x i16> %z1, <vscale x 8 x i16> %z2)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 8 x i16> undef
+L2:
+  %extract = tail call <vscale x 8 x i16> @llvm.aarch64.sve.tuple.get.nxv8i16.nxv24i16(<vscale x 24 x i16> %tuple, i32 2)
+  ret <vscale x 8 x i16> %extract
+}
+;
+; SVCREATE3 (half)
+;
+
+define <vscale x 8 x half> @test_svcreate3_f16_vec0(i1 %p, <vscale x 8 x half> %z0, <vscale x 8 x half> %z1, <vscale x 8 x half> %z2) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate3_f16_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 24 x half> @llvm.aarch64.sve.tuple.create3.nxv24f16.nxv8f16(<vscale x 8 x half> %z0, <vscale x 8 x half> %z1, <vscale x 8 x half> %z2)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 8 x half> undef
+L2:
+  %extract = tail call <vscale x 8 x half> @llvm.aarch64.sve.tuple.get.nxv8f16.nxv24f16(<vscale x 24 x half> %tuple, i32 0)
+  ret <vscale x 8 x half> %extract
+}
+
+define <vscale x 8 x half> @test_svcreate3_f16_vec2(i1 %p, <vscale x 8 x half> %z0, <vscale x 8 x half> %z1, <vscale x 8 x half> %z2) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate3_f16_vec2:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z2.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 24 x half> @llvm.aarch64.sve.tuple.create3.nxv24f16.nxv8f16(<vscale x 8 x half> %z0, <vscale x 8 x half> %z1, <vscale x 8 x half> %z2)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 8 x half> undef
+L2:
+  %extract = tail call <vscale x 8 x half> @llvm.aarch64.sve.tuple.get.nxv8f16.nxv24f16(<vscale x 24 x half> %tuple, i32 2)
+  ret <vscale x 8 x half> %extract
+}
+
+
+;
+; SVCREATE3 (i32)
+;
+
+define <vscale x 4 x i32> @test_svcreate3_s32_vec0(i1 %p, <vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate3_s32_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 12 x i32> @llvm.aarch64.sve.tuple.create3.nxv12i32.nxv4i32(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 4 x i32> undef
+L2:
+  %extract = tail call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv4i32.nxv12i32(<vscale x 12 x i32> %tuple, i32 0)
+  ret <vscale x 4 x i32> %extract
+}
+
+define <vscale x 4 x i32> @test_svcreate3_s32_vec2(i1 %p, <vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate3_s32_vec2:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z2.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 12 x i32> @llvm.aarch64.sve.tuple.create3.nxv12i32.nxv4i32(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 4 x i32> undef
+L2:
+  %extract = tail call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv4i32.nxv12i32(<vscale x 12 x i32> %tuple, i32 2)
+  ret <vscale x 4 x i32> %extract
+}
+
+;
+; SVCREATE3 (float)
+;
+
+define <vscale x 4 x float> @test_svcreate3_f32_vec0(i1 %p, <vscale x 4 x float> %z0, <vscale x 4 x float> %z1, <vscale x 4 x float> %z2) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate3_f32_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 12 x float> @llvm.aarch64.sve.tuple.create3.nxv12f32.nxv4f32(<vscale x 4 x float> %z0, <vscale x 4 x float> %z1, <vscale x 4 x float> %z2)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 4 x float> undef
+L2:
+  %extract = tail call <vscale x 4 x float> @llvm.aarch64.sve.tuple.get.nxv4f32.nxv12f32(<vscale x 12 x float> %tuple, i32 0)
+  ret <vscale x 4 x float> %extract
+}
+
+define <vscale x 4 x float> @test_svcreate3_f32_vec2(i1 %p, <vscale x 4 x float> %z0, <vscale x 4 x float> %z1, <vscale x 4 x float> %z2) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate3_f32_vec2:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z2.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 12 x float> @llvm.aarch64.sve.tuple.create3.nxv12f32.nxv4f32(<vscale x 4 x float> %z0, <vscale x 4 x float> %z1, <vscale x 4 x float> %z2)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 4 x float> undef
+L2:
+  %extract = tail call <vscale x 4 x float> @llvm.aarch64.sve.tuple.get.nxv4f32.nxv12f32(<vscale x 12 x float> %tuple, i32 2)
+  ret <vscale x 4 x float> %extract
+}
+
+;
+; SVCREATE3 (i64)
+;
+
+define <vscale x 2 x i64> @test_svcreate3_s64_vec0(i1 %p, <vscale x 2 x i64> %z0, <vscale x 2 x i64> %z1, <vscale x 2 x i64> %z2) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate3_s64_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 6 x i64> @llvm.aarch64.sve.tuple.create3.nxv6i64.nxv2i64(<vscale x 2 x i64> %z0, <vscale x 2 x i64> %z1, <vscale x 2 x i64> %z2)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 2 x i64> undef
+L2:
+  %extract = tail call <vscale x 2 x i64> @llvm.aarch64.sve.tuple.get.nxv2i64.nxv6i64(<vscale x 6 x i64> %tuple, i32 0)
+  ret <vscale x 2 x i64> %extract
+}
+
+define <vscale x 2 x i64> @test_svcreate3_s64_vec2(i1 %p, <vscale x 2 x i64> %z0, <vscale x 2 x i64> %z1, <vscale x 2 x i64> %z2) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate3_s64_vec2:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z2.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 6 x i64> @llvm.aarch64.sve.tuple.create3.nxv6i64.nxv2i64(<vscale x 2 x i64> %z0, <vscale x 2 x i64> %z1, <vscale x 2 x i64> %z2)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 2 x i64> undef
+L2:
+  %extract = tail call <vscale x 2 x i64> @llvm.aarch64.sve.tuple.get.nxv2i64.nxv6i64(<vscale x 6 x i64> %tuple, i32 2)
+  ret <vscale x 2 x i64> %extract
+}
+
+;
+; SVCREATE3 (double)
+;
+
+define <vscale x 2 x double> @test_svcreate3_f64_vec0(i1 %p, <vscale x 2 x double> %z0, <vscale x 2 x double> %z1, <vscale x 2 x double> %z2) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate3_f64_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 6 x double> @llvm.aarch64.sve.tuple.create3.nxv6f64.nxv2f64(<vscale x 2 x double> %z0, <vscale x 2 x double> %z1, <vscale x 2 x double> %z2)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 2 x double> undef
+L2:
+  %extract = tail call <vscale x 2 x double> @llvm.aarch64.sve.tuple.get.nxv2f64.nxv6f64(<vscale x 6 x double> %tuple, i32 0)
+  ret <vscale x 2 x double> %extract
+}
+
+define <vscale x 2 x double> @test_svcreate3_f64_vec2(i1 %p, <vscale x 2 x double> %z0, <vscale x 2 x double> %z1, <vscale x 2 x double> %z2) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate3_f64_vec2:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z2.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 6 x double> @llvm.aarch64.sve.tuple.create3.nxv6f64.nxv2f64(<vscale x 2 x double> %z0, <vscale x 2 x double> %z1, <vscale x 2 x double> %z2)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 2 x double> undef
+L2:
+  %extract = tail call <vscale x 2 x double> @llvm.aarch64.sve.tuple.get.nxv2f64.nxv6f64(<vscale x 6 x double> %tuple, i32 2)
+  ret <vscale x 2 x double> %extract
+}
+
+;
+; SVCREATE4 (i8)
+;
+
+define <vscale x 16 x i8> @test_svcreate4_s8_vec0(i1 %p, <vscale x 16 x i8> %z0, <vscale x 16 x i8> %z1, <vscale x 16 x i8> %z2, <vscale x 16 x i8> %z3) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate4_s8_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 64 x i8> @llvm.aarch64.sve.tuple.create4.nxv64i8.nxv16i8(<vscale x 16 x i8> %z0, <vscale x 16 x i8> %z1, <vscale x 16 x i8> %z2, <vscale x 16 x i8> %z3)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 16 x i8> undef
+L2:
+  %extract = tail call <vscale x 16 x i8> @llvm.aarch64.sve.tuple.get.nxv16i8.nxv64i8(<vscale x 64 x i8> %tuple, i32 0)
+  ret <vscale x 16 x i8> %extract
+}
+
+define <vscale x 16 x i8> @test_svcreate4_s8_vec3(i1 %p, <vscale x 16 x i8> %z0, <vscale x 16 x i8> %z1, <vscale x 16 x i8> %z2, <vscale x 16 x i8> %z3) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate4_s8_vec3:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z3.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 64 x i8> @llvm.aarch64.sve.tuple.create4.nxv64i8.nxv16i8(<vscale x 16 x i8> %z0, <vscale x 16 x i8> %z1, <vscale x 16 x i8> %z2, <vscale x 16 x i8> %z3)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 16 x i8> undef
+L2:
+  %extract = tail call <vscale x 16 x i8> @llvm.aarch64.sve.tuple.get.nxv16i8.nxv64i8(<vscale x 64 x i8> %tuple, i32 3)
+  ret <vscale x 16 x i8> %extract
+}
+
+;
+; SVCREATE4 (i16)
+;
+
+define <vscale x 8 x i16> @test_svcreate4_s16_vec0(i1 %p, <vscale x 8 x i16> %z0, <vscale x 8 x i16> %z1, <vscale x 8 x i16> %z2, <vscale x 8 x i16> %z3) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate4_s16_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 32 x i16> @llvm.aarch64.sve.tuple.create4.nxv32i16.nxv8i16(<vscale x 8 x i16> %z0, <vscale x 8 x i16> %z1, <vscale x 8 x i16> %z2, <vscale x 8 x i16> %z3)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 8 x i16> undef
+L2:
+  %extract = tail call <vscale x 8 x i16> @llvm.aarch64.sve.tuple.get.nxv8i16.nxv32i16(<vscale x 32 x i16> %tuple, i32 0)
+  ret <vscale x 8 x i16> %extract
+}
+
+define <vscale x 8 x i16> @test_svcreate4_s16_vec3(i1 %p, <vscale x 8 x i16> %z0, <vscale x 8 x i16> %z1, <vscale x 8 x i16> %z2, <vscale x 8 x i16> %z3) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate4_s16_vec3:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z3.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 32 x i16> @llvm.aarch64.sve.tuple.create4.nxv32i16.nxv8i16(<vscale x 8 x i16> %z0, <vscale x 8 x i16> %z1, <vscale x 8 x i16> %z2, <vscale x 8 x i16> %z3)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 8 x i16> undef
+L2:
+  %extract = tail call <vscale x 8 x i16> @llvm.aarch64.sve.tuple.get.nxv8i16.nxv32i16(<vscale x 32 x i16> %tuple, i32 3)
+  ret <vscale x 8 x i16> %extract
+}
+
+;
+; SVCREATE4 (half)
+;
+
+define <vscale x 8 x half> @test_svcreate4_f16_vec0(i1 %p, <vscale x 8 x half> %z0, <vscale x 8 x half> %z1, <vscale x 8 x half> %z2, <vscale x 8 x half> %z3) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate4_f16_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 32 x half> @llvm.aarch64.sve.tuple.create4.nxv32f16.nxv8f16(<vscale x 8 x half> %z0, <vscale x 8 x half> %z1, <vscale x 8 x half> %z2, <vscale x 8 x half> %z3)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 8 x half> undef
+L2:
+  %extract = tail call <vscale x 8 x half> @llvm.aarch64.sve.tuple.get.nxv8f16.nxv32f16(<vscale x 32 x half> %tuple, i32 0)
+  ret <vscale x 8 x half> %extract
+}
+
+define <vscale x 8 x half> @test_svcreate4_f16_vec3(i1 %p, <vscale x 8 x half> %z0, <vscale x 8 x half> %z1, <vscale x 8 x half> %z2, <vscale x 8 x half> %z3) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate4_f16_vec3:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z3.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 32 x half> @llvm.aarch64.sve.tuple.create4.nxv32f16.nxv8f16(<vscale x 8 x half> %z0, <vscale x 8 x half> %z1, <vscale x 8 x half> %z2, <vscale x 8 x half> %z3)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 8 x half> undef
+L2:
+  %extract = tail call <vscale x 8 x half> @llvm.aarch64.sve.tuple.get.nxv8f16.nxv32f16(<vscale x 32 x half> %tuple, i32 3)
+  ret <vscale x 8 x half> %extract
+}
+
+;
+; SVCREATE4 (i32)
+;
+
+define <vscale x 4 x i32> @test_svcreate4_s32_vec0(i1 %p, <vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate4_s32_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 16 x i32> @llvm.aarch64.sve.tuple.create4.nxv16i32.nxv4i32(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 4 x i32> undef
+L2:
+  %extract = tail call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv4i32.nxv16i32(<vscale x 16 x i32> %tuple, i32 0)
+  ret <vscale x 4 x i32> %extract
+}
+
+define <vscale x 4 x i32> @test_svcreate4_s32_vec3(i1 %p, <vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate4_s32_vec3:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z3.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 16 x i32> @llvm.aarch64.sve.tuple.create4.nxv16i32.nxv4i32(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 4 x i32> undef
+L2:
+  %extract = tail call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv4i32.nxv16i32(<vscale x 16 x i32> %tuple, i32 3)
+  ret <vscale x 4 x i32> %extract
+}
+
+;
+; SVCREATE4 (float)
+;
+
+define <vscale x 4 x float> @test_svcreate4_f32_vec0(i1 %p, <vscale x 4 x float> %z0, <vscale x 4 x float> %z1, <vscale x 4 x float> %z2, <vscale x 4 x float> %z3) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate4_f32_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 16 x float> @llvm.aarch64.sve.tuple.create4.nxv16f32.nxv4f32(<vscale x 4 x float> %z0, <vscale x 4 x float> %z1, <vscale x 4 x float> %z2, <vscale x 4 x float> %z3)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 4 x float> undef
+L2:
+  %extract = tail call <vscale x 4 x float> @llvm.aarch64.sve.tuple.get.nxv4f32.nxv16f32(<vscale x 16 x float> %tuple, i32 0)
+  ret <vscale x 4 x float> %extract
+}
+
+define <vscale x 4 x float> @test_svcreate4_f32_vec3(i1 %p, <vscale x 4 x float> %z0, <vscale x 4 x float> %z1, <vscale x 4 x float> %z2, <vscale x 4 x float> %z3) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate4_f32_vec3:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z3.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 16 x float> @llvm.aarch64.sve.tuple.create4.nxv16f32.nxv4f32(<vscale x 4 x float> %z0, <vscale x 4 x float> %z1, <vscale x 4 x float> %z2, <vscale x 4 x float> %z3)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 4 x float> undef
+L2:
+  %extract = tail call <vscale x 4 x float> @llvm.aarch64.sve.tuple.get.nxv4f32.nxv16f32(<vscale x 16 x float> %tuple, i32 3)
+  ret <vscale x 4 x float> %extract
+}
+
+;
+; SVCREATE4 (i64)
+;
+
+define <vscale x 2 x i64> @test_svcreate4_s64_vec0(i1 %p, <vscale x 2 x i64> %z0, <vscale x 2 x i64> %z1, <vscale x 2 x i64> %z2, <vscale x 2 x i64> %z3) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate4_s64_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 8 x i64> @llvm.aarch64.sve.tuple.create4.nxv8i64.nxv2i64(<vscale x 2 x i64> %z0, <vscale x 2 x i64> %z1, <vscale x 2 x i64> %z2, <vscale x 2 x i64> %z3)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 2 x i64> undef
+L2:
+  %extract = tail call <vscale x 2 x i64> @llvm.aarch64.sve.tuple.get.nxv2i64.nxv8i64(<vscale x 8 x i64> %tuple, i32 0)
+  ret <vscale x 2 x i64> %extract
+}
+
+define <vscale x 2 x i64> @test_svcreate4_s64_vec3(i1 %p, <vscale x 2 x i64> %z0, <vscale x 2 x i64> %z1, <vscale x 2 x i64> %z2, <vscale x 2 x i64> %z3) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate4_s64_vec3:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z3.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 8 x i64> @llvm.aarch64.sve.tuple.create4.nxv8i64.nxv2i64(<vscale x 2 x i64> %z0, <vscale x 2 x i64> %z1, <vscale x 2 x i64> %z2, <vscale x 2 x i64> %z3)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 2 x i64> undef
+L2:
+  %extract = tail call <vscale x 2 x i64> @llvm.aarch64.sve.tuple.get.nxv2i64.nxv8i64(<vscale x 8 x i64> %tuple, i32 3)
+  ret <vscale x 2 x i64> %extract
+}
+
+;
+; SVCREATE4 (double)
+;
+
+define <vscale x 2 x double> @test_svcreate4_f64_vec0(i1 %p, <vscale x 2 x double> %z0, <vscale x 2 x double> %z1, <vscale x 2 x double> %z2, <vscale x 2 x double> %z3) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate4_f64_vec0:
+; CHECK: // %L2
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 8 x double> @llvm.aarch64.sve.tuple.create4.nxv8f64.nxv2f64(<vscale x 2 x double> %z0, <vscale x 2 x double> %z1, <vscale x 2 x double> %z2, <vscale x 2 x double> %z3)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 2 x double> undef
+L2:
+  %extract = tail call <vscale x 2 x double> @llvm.aarch64.sve.tuple.get.nxv2f64.nxv8f64(<vscale x 8 x double> %tuple, i32 0)
+  ret <vscale x 2 x double> %extract
+}
+
+define <vscale x 2 x double> @test_svcreate4_f64_vec3(i1 %p, <vscale x 2 x double> %z0, <vscale x 2 x double> %z1, <vscale x 2 x double> %z2, <vscale x 2 x double> %z3) local_unnamed_addr #0 {
+; CHECK-LABEL: test_svcreate4_f64_vec3:
+; CHECK: // %L2
+; CHECK-NEXT: mov z0.d, z3.d
+; CHECK-NEXT: ret
+  %tuple = tail call <vscale x 8 x double> @llvm.aarch64.sve.tuple.create4.nxv8f64.nxv2f64(<vscale x 2 x double> %z0, <vscale x 2 x double> %z1, <vscale x 2 x double> %z2, <vscale x 2 x double> %z3)
+  br i1 %p, label %L1, label %L2
+L1:
+  ret <vscale x 2 x double> undef
+L2:
+  %extract = tail call <vscale x 2 x double> @llvm.aarch64.sve.tuple.get.nxv2f64.nxv8f64(<vscale x 8 x double> %tuple, i32 3)
+  ret <vscale x 2 x double> %extract
+}
+
+attributes #0 = { nounwind "target-features"="+sve" }
+
+declare <vscale x 4 x double>  @llvm.aarch64.sve.tuple.create2.nxv4f64.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
+declare <vscale x 8 x float>  @llvm.aarch64.sve.tuple.create2.nxv8f32.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 16 x half>  @llvm.aarch64.sve.tuple.create2.nxv16f16.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
+declare <vscale x 4 x i64>  @llvm.aarch64.sve.tuple.create2.nxv4i64.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
+declare <vscale x 8 x i32>  @llvm.aarch64.sve.tuple.create2.nxv8i32.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
+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 32 x i8>  @llvm.aarch64.sve.tuple.create2.nxv32i8.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
+
+declare <vscale x 6 x double>  @llvm.aarch64.sve.tuple.create3.nxv6f64.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+declare <vscale x 12 x float> @llvm.aarch64.sve.tuple.create3.nxv12f32.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 24 x half> @llvm.aarch64.sve.tuple.create3.nxv24f16.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+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 12 x i32> @llvm.aarch64.sve.tuple.create3.nxv12i32.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+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>)
+declare <vscale x 48 x i8>  @llvm.aarch64.sve.tuple.create3.nxv48i8.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+
+declare <vscale x 8 x double>  @llvm.aarch64.sve.tuple.create4.nxv8f64.nxv2f64 (<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+declare <vscale x 16 x float>  @llvm.aarch64.sve.tuple.create4.nxv16f32.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 32 x half>  @llvm.aarch64.sve.tuple.create4.nxv32f16.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
+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 i32> @llvm.aarch64.sve.tuple.create4.nxv16i32.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 32 x i16> @llvm.aarch64.sve.tuple.create4.nxv32i16.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 64 x i8>  @llvm.aarch64.sve.tuple.create4.nxv64i8.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.tuple.get.nxv16i8.nxv32i8(<vscale x 32 x i8>, i32 immarg)
+declare <vscale x 16 x i8> @llvm.aarch64.sve.tuple.get.nxv16i8.nxv48i8(<vscale x 48 x i8>, i32 immarg)
+declare <vscale x 16 x i8> @llvm.aarch64.sve.tuple.get.nxv16i8.nxv64i8(<vscale x 64 x i8>, i32 immarg)
+
+declare <vscale x 8 x i16> @llvm.aarch64.sve.tuple.get.nxv8i16.nxv16i16(<vscale x 16 x i16>, i32 immarg)
+declare <vscale x 8 x i16> @llvm.aarch64.sve.tuple.get.nxv8i16.nxv24i16(<vscale x 24 x i16>, i32 immarg)
+declare <vscale x 8 x i16> @llvm.aarch64.sve.tuple.get.nxv8i16.nxv32i16(<vscale x 32 x i16>, i32 immarg)
+
+declare <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv4i32.nxv8i32(<vscale x 8 x i32>, i32 immarg)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv4i32.nxv12i32(<vscale x 12 x i32>, i32 immarg)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv4i32.nxv16i32(<vscale x 16 x i32>, i32 immarg)
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.tuple.get.nxv2i64.nxv4i64(<vscale x 4 x i64>, i32 immarg)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.tuple.get.nxv2i64.nxv6i64(<vscale x 6 x i64>, i32 immarg)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.tuple.get.nxv2i64.nxv8i64(<vscale x 8 x i64>, i32 immarg)
+
+declare <vscale x 8 x half> @llvm.aarch64.sve.tuple.get.nxv8f16.nxv16f16(<vscale x 16 x half>, i32 immarg)
+declare <vscale x 8 x half> @llvm.aarch64.sve.tuple.get.nxv8f16.nxv24f16(<vscale x 24 x half>, i32 immarg)
+declare <vscale x 8 x half> @llvm.aarch64.sve.tuple.get.nxv8f16.nxv32f16(<vscale x 32 x half>, i32 immarg)
+
+declare <vscale x 4 x float> @llvm.aarch64.sve.tuple.get.nxv4f32.nxv8f32(<vscale x 8 x float>, i32 immarg)
+declare <vscale x 4 x float> @llvm.aarch64.sve.tuple.get.nxv4f32.nxv12f32(<vscale x 12 x float>, i32 immarg)
+declare <vscale x 4 x float> @llvm.aarch64.sve.tuple.get.nxv4f32.nxv16f32(<vscale x 16 x float>, i32 immarg)
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.tuple.get.nxv2f64.nxv4f64(<vscale x 4 x double>, i32 immarg)
+declare <vscale x 2 x double> @llvm.aarch64.sve.tuple.get.nxv2f64.nxv6f64(<vscale x 6 x double>, i32 immarg)
+declare <vscale x 2 x double> @llvm.aarch64.sve.tuple.get.nxv2f64.nxv8f64(<vscale x 8 x double>, i32 immarg)
diff --git a/test/CodeGen/AArch64/sve-intrinsics-insert-extract-tuple.ll b/test/CodeGen/AArch64/sve-intrinsics-insert-extract-tuple.ll
new file mode 100644
index 00000000000..287f7245dce
--- /dev/null
+++ b/test/CodeGen/AArch64/sve-intrinsics-insert-extract-tuple.ll
@@ -0,0 +1,243 @@
+; RUN: llc -mtriple aarch64 -mattr=+sve -asm-verbose=0 < %s | FileCheck %s
+
+; All these tests create a vector tuple, insert z5 into one of the elements,
+; and finally extracts that element from the wide vector to return it.  These
+; checks ensure that z5 is always the value that is returned.
+
+;
+; Insert into two element tuples
+;
+
+; tuple:      { tuple2.res0, tuple2.res1 }
+; insert z5:  {     z5     , tuple2.res1 }
+; extract z5:       ^^
+define <vscale x 4 x i32> @set_tuple2_nxv8i32_elt0(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1,
+                                                   <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3,
+                                                   <vscale x 4 x i32> %z4, <vscale x 4 x i32> %z5) #0 {
+  ; CHECK-LABEL: set_tuple2_nxv8i32_elt0:
+  ; CHECK-NEXT:  mov     z0.d, z5.d
+  ; CHECK-NEXT:  ret
+  %tuple = call <vscale x 8 x i32> @llvm.aarch64.sve.tuple.create2.nxv8i32.nxv4i32(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1)
+  %ins = call <vscale x 8 x i32> @llvm.aarch64.sve.tuple.set.nxv8i32.nxv4i32(<vscale x 8 x i32> %tuple, i32 0, <vscale x 4 x i32> %z5)
+  %ext = call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv8i32(<vscale x 8 x i32> %ins, i32 0)
+  ret <vscale x 4 x i32> %ext
+}
+
+; tuple:       { tuple2.res0, tuple2.res1 }
+; insert z5:   { tuple2.res0,     z5      }
+; extract z5:                     ^^
+define <vscale x 4 x i32> @set_tuple2_nxv8i32_elt1(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1,
+                                                   <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3,
+                                                   <vscale x 4 x i32> %z4, <vscale x 4 x i32> %z5) #0 {
+  ; CHECK-LABEL: set_tuple2_nxv8i32_elt1:
+  ; CHECK-NEXT:  mov     z0.d, z5.d
+  ; CHECK-NEXT:  ret
+  %tuple = call <vscale x 8 x i32> @llvm.aarch64.sve.tuple.create2.nxv8i32.nxv4i32(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1)
+  %ins = call <vscale x 8 x i32> @llvm.aarch64.sve.tuple.set.nxv8i32.nxv4i32(<vscale x 8 x i32> %tuple, i32 1, <vscale x 4 x i32> %z5)
+  %ext = call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv8i32(<vscale x 8 x i32> %ins, i32 1)
+  ret <vscale x 4 x i32> %ext
+}
+
+; This test checks the elements _not_ being set aren't changed.
+
+; tuple:       { tuple2.res0, tuple2.res1 }
+; insert z5:   { tuple2.res0,     z5      }
+; extract z0:         ^^
+define <vscale x 4 x i32> @set_tuple2_nxv8i32_elt1_ret_elt0(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1,
+                                                            <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3,
+                                                            <vscale x 4 x i32> %z4, <vscale x 4 x i32> %z5) #0 {
+  ; CHECK-LABEL: set_tuple2_nxv8i32_elt1_ret_elt0:
+  ; CHECK-NEXT:  ret
+  %tuple = call <vscale x 8 x i32> @llvm.aarch64.sve.tuple.create2.nxv8i32.nxv4i32(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1)
+  %ins = call <vscale x 8 x i32> @llvm.aarch64.sve.tuple.set.nxv8i32.nxv4i32(<vscale x 8 x i32> %tuple, i32 1, <vscale x 4 x i32> %z5)
+  %ext = call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv8i32(<vscale x 8 x i32> %ins, i32 0)
+  ret <vscale x 4 x i32> %ext
+}
+
+; Test extract of tuple passed into function
+define <vscale x 4 x i32> @get_tuple2_nxv8i32_elt1(<vscale x 8 x i32> %tuple) #0 {
+  ; CHECK-LABEL: get_tuple2_nxv8i32_elt1:
+  ; CHECK-NEXT:  mov     z0.d, z1.d
+  ; CHECK-NEXT:  ret
+  %ext = call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv8i32(<vscale x 8 x i32> %tuple, i32 1)
+  ret <vscale x 4 x i32> %ext
+}
+
+;
+; Insert into three element tuples
+;
+
+; tuple:       { tuple3.res0, tuple3.res1, tuple3.res2 }
+; insert z5:   {     z5     , tuple3.res0, tuple3.res2 }
+; extract z5:        ^^
+define <vscale x 4 x i32> @set_tuple3_nxv12i32_elt0(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1,
+                                                    <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3,
+                                                    <vscale x 4 x i32> %z4, <vscale x 4 x i32> %z5) #0 {
+  ; CHECK-LABEL: set_tuple3_nxv12i32_elt0:
+  ; CHECK-NEXT:  mov     z0.d, z5.d
+  ; CHECK-NEXT:  ret
+  %tuple = call <vscale x 12 x i32> @llvm.aarch64.sve.tuple.create3.nxv12i32.nxv4i32(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2)
+  %ins = call <vscale x 12 x i32> @llvm.aarch64.sve.tuple.set.nxv12i32.nxv4i32(<vscale x 12 x i32> %tuple, i32 0, <vscale x 4 x i32> %z5)
+  %ext = call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv12i32(<vscale x 12 x i32> %ins, i32 0)
+  ret <vscale x 4 x i32> %ext
+}
+
+; tuple:       { tuple3.res0, tuple3.res1, tuple3.res2 }
+; insert z5:   { tuple3.res0,     z5     , tuple3.res2 }
+; extract z5:                     ^^
+define <vscale x 4 x i32> @set_tuple3_nxv12i32_elt1(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1,
+                                                    <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3,
+                                                    <vscale x 4 x i32> %z4, <vscale x 4 x i32> %z5) #0 {
+  ; CHECK-LABEL: set_tuple3_nxv12i32_elt1:
+  ; CHECK-NEXT:  mov     z0.d, z5.d
+  ; CHECK-NEXT:  ret
+  %tuple = call <vscale x 12 x i32> @llvm.aarch64.sve.tuple.create3.nxv12i32.nxv4i32(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2)
+  %ins = call <vscale x 12 x i32> @llvm.aarch64.sve.tuple.set.nxv12i32.nxv4i32(<vscale x 12 x i32> %tuple, i32 1, <vscale x 4 x i32> %z5)
+  %ext = call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv12i32(<vscale x 12 x i32> %ins, i32 1)
+  ret <vscale x 4 x i32> %ext
+}
+
+; tuple:       { tuple3.res0, tuple3.res1, tuple3.res2 }
+; insert z5:   { tuple3.res0, tuple3.res1,     z5      }
+; extract z5:                                  ^^
+define <vscale x 4 x i32> @set_tuple3_nxv12i32_elt2(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1,
+                                                    <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3,
+                                                    <vscale x 4 x i32> %z4, <vscale x 4 x i32> %z5) #0 {
+  ; CHECK-LABEL: set_tuple3_nxv12i32_elt2:
+  ; CHECK-NEXT:  mov     z0.d, z5.d
+  ; CHECK-NEXT:  ret
+  %tuple = call <vscale x 12 x i32> @llvm.aarch64.sve.tuple.create3.nxv12i32.nxv4i32(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2)
+  %ins = call <vscale x 12 x i32> @llvm.aarch64.sve.tuple.set.nxv12i32.nxv4i32(<vscale x 12 x i32> %tuple, i32 2, <vscale x 4 x i32> %z5)
+  %ext = call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv12i32(<vscale x 12 x i32> %ins, i32 2)
+  ret <vscale x 4 x i32> %ext
+}
+
+; This test checks the elements _not_ being set aren't changed.
+
+; tuple:       { tuple3.res0, tuple3.res1, tuple3.res2 }
+; insert z5:   { tuple3.res0,     z5     , tuple3.res2 }
+; extract z2:                                  ^^
+define <vscale x 4 x i32> @set_tuple3_nxv12i32_elt1_ret_elt2(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1,
+                                                             <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3,
+                                                             <vscale x 4 x i32> %z4, <vscale x 4 x i32> %z5) #0 {
+  ; CHECK-LABEL: set_tuple3_nxv12i32_elt1_ret_elt2:
+  ; CHECK-NEXT:  mov     z0.d, z2.d
+  ; CHECK-NEXT:  ret
+  %tuple = call <vscale x 12 x i32> @llvm.aarch64.sve.tuple.create3.nxv12i32.nxv4i32(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2)
+  %ins = call <vscale x 12 x i32> @llvm.aarch64.sve.tuple.set.nxv12i32.nxv4i32(<vscale x 12 x i32> %tuple, i32 1, <vscale x 4 x i32> %z5)
+  %ext = call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv12i32(<vscale x 12 x i32> %ins, i32 2)
+  ret <vscale x 4 x i32> %ext
+}
+
+; Test extract of tuple passed into function
+define <vscale x 4 x i32> @get_tuple3_nxv12i32_elt2(<vscale x 4 x i32> %z0, <vscale x 12 x i32> %tuple) #0 {
+  ; CHECK-LABEL: get_tuple3_nxv12i32_elt2:
+  ; CHECK-NEXT:  mov     z0.d, z3.d
+  ; CHECK-NEXT:  ret
+  %ext = call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv12i32(<vscale x 12 x i32> %tuple, i32 2)
+  ret <vscale x 4 x i32> %ext
+}
+
+;
+; Insert into four element tuples
+;
+
+; tuple:       { tuple4.res0, tuple4.res1, tuple4.res2, tuple4.res3 }
+; insert z5:   {     z5     , tuple4.res1, tuple4.res2, tuple4.res3 }
+; extract z5:        ^^
+define <vscale x 4 x i32> @set_tuple4_nxv16i32_elt0(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1,
+                                                    <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3,
+                                                    <vscale x 4 x i32> %z4, <vscale x 4 x i32> %z5) #0 {
+  ; CHECK-LABEL: set_tuple4_nxv16i32_elt0:
+  ; CHECK-NEXT:  mov     z0.d, z5.d
+  ; CHECK-NEXT:  ret
+  %tuple = tail call <vscale x 16 x i32> @llvm.aarch64.sve.tuple.create4.nxv16i32.nxv4i32(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3)
+  %ins = call <vscale x 16 x i32> @llvm.aarch64.sve.tuple.set.nxv16i32.nxv4i32(<vscale x 16 x i32> %tuple, i32 0, <vscale x 4 x i32> %z5)
+  %ext = call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv16i32(<vscale x 16 x i32> %ins, i32 0)
+  ret <vscale x 4 x i32> %ext
+}
+
+; tuple:       { tuple4.res0, tuple4.res1, tuple4.res2, tuple4.res3 }
+; insert z5:   { tuple4.res0,     z5     , tuple4.res2, tuple4.res3 }
+; extract z5:                     ^^
+define <vscale x 4 x i32> @set_tuple4_nxv16i32_elt1(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1,
+                                                    <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3,
+                                                    <vscale x 4 x i32> %z4, <vscale x 4 x i32> %z5) #0 {
+  ; CHECK-LABEL: set_tuple4_nxv16i32_elt1:
+  ; CHECK-NEXT:  mov     z0.d, z5.d
+  ; CHECK-NEXT:  ret
+  %tuple = tail call <vscale x 16 x i32> @llvm.aarch64.sve.tuple.create4.nxv16i32.nxv4i32(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3)
+  %ins = call <vscale x 16 x i32> @llvm.aarch64.sve.tuple.set.nxv16i32.nxv4i32(<vscale x 16 x i32> %tuple, i32 1, <vscale x 4 x i32> %z5)
+  %ext = call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv16i32(<vscale x 16 x i32> %ins, i32 1)
+  ret <vscale x 4 x i32> %ext
+}
+
+; tuple:       { tuple4.res0, tuple4.res1, tuple4.res2, tuple4.res3 }
+; insert z5:   { tuple4.res0, tuple4.res1,     z5     , tuple4.res3 }
+; extract z5:                                  ^^
+define <vscale x 4 x i32> @set_tuple4_nxv16i32_elt2(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1,
+                                                    <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3,
+                                                    <vscale x 4 x i32> %z4, <vscale x 4 x i32> %z5) #0 {
+  ; CHECK-LABEL: set_tuple4_nxv16i32_elt2:
+  ; CHECK-NEXT:  mov     z0.d, z5.d
+  ; CHECK-NEXT:  ret
+  %tuple = tail call <vscale x 16 x i32> @llvm.aarch64.sve.tuple.create4.nxv16i32.nxv4i32(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3)
+  %ins = call <vscale x 16 x i32> @llvm.aarch64.sve.tuple.set.nxv16i32.nxv4i32(<vscale x 16 x i32> %tuple, i32 2, <vscale x 4 x i32> %z5)
+  %ext = call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv16i32(<vscale x 16 x i32> %ins, i32 2)
+  ret <vscale x 4 x i32> %ext
+}
+
+; tuple:       { tuple4.res0, tuple4.res1, tuple4.res2, tuple4.res3 }
+; insert z5:   { tuple4.res0, tuple4.res1, tuple4.res2,     z5      }
+; extract z5:                                               ^^
+define <vscale x 4 x i32> @set_tuple4_nxv16i32_elt3(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1,
+                                                    <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3,
+                                                    <vscale x 4 x i32> %z4, <vscale x 4 x i32> %z5) #0 {
+  ; CHECK-LABEL: set_tuple4_nxv16i32_elt3:
+  ; CHECK-NEXT:  mov     z0.d, z5.d
+  ; CHECK-NEXT:  ret
+  %tuple = tail call <vscale x 16 x i32> @llvm.aarch64.sve.tuple.create4.nxv16i32.nxv4i32(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3)
+  %ins = call <vscale x 16 x i32> @llvm.aarch64.sve.tuple.set.nxv16i32.nxv4i32(<vscale x 16 x i32> %tuple, i32 3, <vscale x 4 x i32> %z5)
+  %ext = call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv16i32(<vscale x 16 x i32> %ins, i32 3)
+  ret <vscale x 4 x i32> %ext
+}
+
+; This test checks the elements _not_ being set aren't changed.
+
+; tuple:       { tuple4.res0, tuple4.res1, tuple4.res2, tuple4.res3 }
+; insert z5:   { tuple4.res0, tuple4.res1, tuple4.res2,     z5      }
+; extract z2:                                               ^^
+define <vscale x 4 x i32> @set_tuple4_nxv16i32_elt3_ret_elt2(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1,
+                                                             <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3,
+                                                             <vscale x 4 x i32> %z4, <vscale x 4 x i32> %z5) #0 {
+  ; CHECK-LABEL: set_tuple4_nxv16i32_elt3_ret_elt2:
+  ; CHECK-NEXT:  mov     z0.d, z2.d
+  ; CHECK-NEXT:  ret
+  %tuple = tail call <vscale x 16 x i32> @llvm.aarch64.sve.tuple.create4.nxv16i32.nxv4i32(<vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1, <vscale x 4 x i32> %z2, <vscale x 4 x i32> %z3)
+  %ins = call <vscale x 16 x i32> @llvm.aarch64.sve.tuple.set.nxv16i32.nxv4i32(<vscale x 16 x i32> %tuple, i32 3, <vscale x 4 x i32> %z5)
+  %ext = call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv16i32(<vscale x 16 x i32> %ins, i32 2)
+  ret <vscale x 4 x i32> %ext
+}
+
+; Test extract of tuple passed into function
+define <vscale x 4 x i32> @get_tuple4_nxv16i32_elt3(<vscale x 16 x i32> %tuple) #0 {
+  ; CHECK-LABEL: get_tuple4_nxv16i32_elt3:
+  ; CHECK-NEXT:  mov     z0.d, z3.d
+  ; CHECK-NEXT:  ret
+  %ext = call <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv16i32(<vscale x 16 x i32> %tuple, i32 3)
+  ret <vscale x 4 x i32> %ext
+}
+
+attributes #0 = { nounwind "target-features"="+sve" }
+
+declare <vscale x 8 x i32>  @llvm.aarch64.sve.tuple.create2.nxv8i32.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 8 x i32> @llvm.aarch64.sve.tuple.set.nxv8i32.nxv4i32(<vscale x 8 x i32>, i32, <vscale x 4 x i32>)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv8i32(<vscale x 8 x i32>, i32)
+
+declare <vscale x 12 x i32> @llvm.aarch64.sve.tuple.create3.nxv12i32.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 12 x i32> @llvm.aarch64.sve.tuple.set.nxv12i32.nxv4i32(<vscale x 12 x i32>, i32, <vscale x 4 x i32>)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv12i32(<vscale x 12 x i32>, i32)
+
+declare <vscale x 16 x i32> @llvm.aarch64.sve.tuple.create4.nxv16i32.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 16 x i32> @llvm.aarch64.sve.tuple.set.nxv16i32.nxv4i32(<vscale x 16 x i32>, i32, <vscale x 4 x i32>)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.tuple.get.nxv16i32(<vscale x 16 x i32>, i32)