[AArch64] Allow copying of SVE registers in Streaming SVE

[CarolineConcatto]

Just to check, this change depends on https://reviews.llvm.org/D118561. Correct?
That is the reason your tests are failing for now.
LLVM ERROR: Don't know how to legalize this scalable vector type
I think you need to use git-clang-format.

llvm/test/CodeGen/AArch64/sve-intrinsics-create-tuple.ll

7

I guess this is just to leave a cleaner test. Correct?

[c-rhodes]

In D118562#3284538, @CarolineConcatto wrote:

Just to check, this change depends on https://reviews.llvm.org/D118561. Correct?
That is the reason your tests are failing for now.
LLVM ERROR: Don't know how to legalize this scalable vector type

Yeah that's right, I'll add it as a parent revision.

I think you need to use git-clang-format.

I'll run it before committing if accepted.

llvm/test/CodeGen/AArch64/sve-intrinsics-create-tuple.ll

7

I guess this is just to leave a cleaner test. Correct?

Yeah I don't think local_unnamed_addr is needed for these tests.

[sdesmalen]

llvm/lib/Target/AArch64/AArch64InstrInfo.cpp

3465–3466

Can you add similar asserts for the ZPR[2,3,4]RegClass copies?

[c-rhodes]

• Run clang-format.
• Add asserts for multi-vector register classes.

[sdesmalen]

Thanks for the update, LGTM!

llvm/lib/Target/AArch64/AArch64InstrInfo.cpp

if (DestReg == AArch64::WSP || SrcReg == AArch64::WSP) {
       }
     }
     return;
   }
 
   // Copy a Predicate register by ORRing with itself.
   if (AArch64::PPRRegClass.contains(DestReg) &&
       AArch64::PPRRegClass.contains(SrcReg)) {
-    assert(Subtarget.hasSVE() && "Unexpected SVE register.");
+    assert((Subtarget.hasSVE() || Subtarget.hasStreamingSVE()) &&
+           "Unexpected SVE register.");
     BuildMI(MBB, I, DL, get(AArch64::ORR_PPzPP), DestReg)
       .addReg(SrcReg) // Pg
       .addReg(SrcReg)
       .addReg(SrcReg, getKillRegState(KillSrc));
     return;
   }
 
   // Copy a Z register by ORRing with itself.
   if (AArch64::ZPRRegClass.contains(DestReg) &&
       AArch64::ZPRRegClass.contains(SrcReg)) {
-    assert(Subtarget.hasSVE() && "Unexpected SVE register.");
+    assert((Subtarget.hasSVE() || Subtarget.hasStreamingSVE()) &&
+           "Unexpected SVE register.");
     BuildMI(MBB, I, DL, get(AArch64::ORR_ZZZ), DestReg)
       .addReg(SrcReg)
       .addReg(SrcReg, getKillRegState(KillSrc));
     return;
   }
 
   // Copy a Z register pair by copying the individual sub-registers.
   if (AArch64::ZPR2RegClass.contains(DestReg) &&
       AArch64::ZPR2RegClass.contains(SrcReg)) {
+    assert((Subtarget.hasSVE() || Subtarget.hasStreamingSVE()) &&
+           "Unexpected SVE register.");
     static const unsigned Indices[] = {AArch64::zsub0, AArch64::zsub1};
     copyPhysRegTuple(MBB, I, DL, DestReg, SrcReg, KillSrc, AArch64::ORR_ZZZ,
                      Indices);
     return;
   }
 
   // Copy a Z register triple by copying the individual sub-registers.
   if (AArch64::ZPR3RegClass.contains(DestReg) &&
       AArch64::ZPR3RegClass.contains(SrcReg)) {
+    assert((Subtarget.hasSVE() || Subtarget.hasStreamingSVE()) &&
+           "Unexpected SVE register.");
     static const unsigned Indices[] = {AArch64::zsub0, AArch64::zsub1,
                                        AArch64::zsub2};
     copyPhysRegTuple(MBB, I, DL, DestReg, SrcReg, KillSrc, AArch64::ORR_ZZZ,
                      Indices);
     return;
   }
 
   // Copy a Z register quad by copying the individual sub-registers.
   if (AArch64::ZPR4RegClass.contains(DestReg) &&
       AArch64::ZPR4RegClass.contains(SrcReg)) {
+    assert((Subtarget.hasSVE() || Subtarget.hasStreamingSVE()) &&
+           "Unexpected SVE register.");
     static const unsigned Indices[] = {AArch64::zsub0, AArch64::zsub1,
                                        AArch64::zsub2, AArch64::zsub3};
     copyPhysRegTuple(MBB, I, DL, DestReg, SrcReg, KillSrc, AArch64::ORR_ZZZ,
                      Indices);
     return;
   }
 
   if (AArch64::GPR64spRegClass.contains(DestReg) &&

llvm/test/CodeGen/AArch64/sve-intrinsics-create-tuple.ll

 ; RUN: llc -mtriple aarch64 -mattr=+sve -asm-verbose=1 < %s | FileCheck %s
+; RUN: llc -mtriple aarch64 -mattr=+streaming-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 {
+define <vscale x 16 x i8> @test_svcreate2_s8_vec0(i1 %p, <vscale x 16 x i8> %z0, <vscale x 16 x i8> %z1) #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 {
+define <vscale x 16 x i8> @test_svcreate2_s8_vec1(i1 %p, <vscale x 16 x i8> %z0, <vscale x 16 x i8> %z1) #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 {
+define <vscale x 8 x i16> @test_svcreate2_s16_vec0(i1 %p, <vscale x 8 x i16> %z0, <vscale x 8 x i16> %z1) #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 {
+define <vscale x 8 x i16> @test_svcreate2_s16_vec1(i1 %p, <vscale x 8 x i16> %z0, <vscale x 8 x i16> %z1) #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 {
+define <vscale x 8 x half> @test_svcreate2_f16_vec0(i1 %p, <vscale x 8 x half> %z0, <vscale x 8 x half> %z1) #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 {
+define <vscale x 8 x half> @test_svcreate2_f16_vec1(i1 %p, <vscale x 8 x half> %z0, <vscale x 8 x half> %z1) #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 (bfloat)
 ;
 
-define <vscale x 8 x bfloat> @test_svcreate2_bf16_vec0(i1 %p, <vscale x 8 x bfloat> %z0, <vscale x 8 x bfloat> %z1) local_unnamed_addr #1 {
+define <vscale x 8 x bfloat> @test_svcreate2_bf16_vec0(i1 %p, <vscale x 8 x bfloat> %z0, <vscale x 8 x bfloat> %z1) #1 {
 ; CHECK-LABEL: test_svcreate2_bf16_vec0:
 ; CHECK: // %L2
 ; CHECK-NEXT: ret
   %tuple = tail call <vscale x 16 x bfloat> @llvm.aarch64.sve.tuple.create2.nxv16bf16.nxv8bf16(<vscale x 8 x bfloat> %z0, <vscale x 8 x bfloat> %z1)
   br i1 %p, label %L1, label %L2
 L1:
   ret <vscale x 8 x bfloat> undef
 L2:
   %extract = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.tuple.get.nxv8bf16.nxv16bf16(<vscale x 16 x bfloat> %tuple, i32 0)
   ret <vscale x 8 x bfloat> %extract
 }
 
-define <vscale x 8 x bfloat> @test_svcreate2_bf16_vec1(i1 %p, <vscale x 8 x bfloat> %z0, <vscale x 8 x bfloat> %z1) local_unnamed_addr #1 {
+define <vscale x 8 x bfloat> @test_svcreate2_bf16_vec1(i1 %p, <vscale x 8 x bfloat> %z0, <vscale x 8 x bfloat> %z1) #1 {
 ; CHECK-LABEL: test_svcreate2_bf16_vec1:
 ; CHECK: // %L2
 ; CHECK-NEXT: mov z0.d, z1.d
 ; CHECK-NEXT: ret
   %tuple = tail call <vscale x 16 x bfloat> @llvm.aarch64.sve.tuple.create2.nxv16bf16.nxv8bf16(<vscale x 8 x bfloat> %z0, <vscale x 8 x bfloat> %z1)
   br i1 %p, label %L1, label %L2
 L1:
   ret <vscale x 8 x bfloat> undef
 L2:
   %extract = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.tuple.get.nxv8bf16.nxv16bf16(<vscale x 16 x bfloat> %tuple, i32 1)
   ret <vscale x 8 x bfloat> %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 {
+define <vscale x 4 x i32> @test_svcreate2_s32_vec0(i1 %p, <vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1) #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 {
+define <vscale x 4 x i32> @test_svcreate2_s32_vec1(i1 %p, <vscale x 4 x i32> %z0, <vscale x 4 x i32> %z1) #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 {
+define <vscale x 4 x float> @test_svcreate2_f32_vec0(i1 %p, <vscale x 4 x float> %z0, <vscale x 4 x float> %z1) #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 {
+define <vscale x 4 x float> @test_svcreate2_f32_vec1(i1 %p, <vscale x 4 x float> %z0, <vscale x 4 x float> %z1) #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 {
+define <vscale x 2 x i64> @test_svcreate2_s64_vec0(i1 %p, <vscale x 2 x i64> %z0, <vscale x 2 x i64> %z1) #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 {
+define <vscale x 2 x i64> @test_svcreate2_s64_vec1(i1 %p, <vscale x 2 x i64> %z0, <vscale x 2 x i64> %z1) #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 {
+define <vscale x 2 x double> @test_svcreate2_f64_vec0(i1 %p, <vscale x 2 x double> %z0, <vscale x 2 x double> %z1) #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 {
+define <vscale x 2 x double> @test_svcreate2_f64_vec1(i1 %p, <vscale x 2 x double> %z0, <vscale x 2 x double> %z1) #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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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 (bfloat)
 ;
 
-define <vscale x 8 x bfloat> @test_svcreate3_bf16_vec0(i1 %p, <vscale x 8 x bfloat> %z0, <vscale x 8 x bfloat> %z1, <vscale x 8 x bfloat> %z2) local_unnamed_addr #1 {
+define <vscale x 8 x bfloat> @test_svcreate3_bf16_vec0(i1 %p, <vscale x 8 x bfloat> %z0, <vscale x 8 x bfloat> %z1, <vscale x 8 x bfloat> %z2) #1 {
 ; CHECK-LABEL: test_svcreate3_bf16_vec0:
 ; CHECK: // %L2
 ; CHECK-NEXT: ret
   %tuple = tail call <vscale x 24 x bfloat> @llvm.aarch64.sve.tuple.create3.nxv24bf16.nxv8bf16(<vscale x 8 x bfloat> %z0, <vscale x 8 x bfloat> %z1, <vscale x 8 x bfloat> %z2)
   br i1 %p, label %L1, label %L2
 L1:
   ret <vscale x 8 x bfloat> undef
 L2:
   %extract = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.tuple.get.nxv8bf16.nxv24bf16(<vscale x 24 x bfloat> %tuple, i32 0)
   ret <vscale x 8 x bfloat> %extract
 }
 
-define <vscale x 8 x bfloat> @test_svcreate3_bf16_vec2(i1 %p, <vscale x 8 x bfloat> %z0, <vscale x 8 x bfloat> %z1, <vscale x 8 x bfloat> %z2) local_unnamed_addr #1 {
+define <vscale x 8 x bfloat> @test_svcreate3_bf16_vec2(i1 %p, <vscale x 8 x bfloat> %z0, <vscale x 8 x bfloat> %z1, <vscale x 8 x bfloat> %z2) #1 {
 ; CHECK-LABEL: test_svcreate3_bf16_vec2:
 ; CHECK: // %L2
 ; CHECK-NEXT: mov z0.d, z2.d
 ; CHECK-NEXT: ret
   %tuple = tail call <vscale x 24 x bfloat> @llvm.aarch64.sve.tuple.create3.nxv24bf16.nxv8bf16(<vscale x 8 x bfloat> %z0, <vscale x 8 x bfloat> %z1, <vscale x 8 x bfloat> %z2)
   br i1 %p, label %L1, label %L2
 L1:
   ret <vscale x 8 x bfloat> undef
 L2:
   %extract = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.tuple.get.nxv8bf16.nxv24bf16(<vscale x 24 x bfloat> %tuple, i32 2)
   ret <vscale x 8 x bfloat> %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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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 (bfloat)
 ;
 
-define <vscale x 8 x bfloat> @test_svcreate4_bf16_vec0(i1 %p, <vscale x 8 x bfloat> %z0, <vscale x 8 x bfloat> %z1, <vscale x 8 x bfloat> %z2, <vscale x 8 x bfloat> %z3) local_unnamed_addr #1 {
+define <vscale x 8 x bfloat> @test_svcreate4_bf16_vec0(i1 %p, <vscale x 8 x bfloat> %z0, <vscale x 8 x bfloat> %z1, <vscale x 8 x bfloat> %z2, <vscale x 8 x bfloat> %z3) #1 {
 ; CHECK-LABEL: test_svcreate4_bf16_vec0:
 ; CHECK: // %L2
 ; CHECK-NEXT: ret
   %tuple = tail call <vscale x 32 x bfloat> @llvm.aarch64.sve.tuple.create4.nxv32bf16.nxv8bf16(<vscale x 8 x bfloat> %z0, <vscale x 8 x bfloat> %z1, <vscale x 8 x bfloat> %z2, <vscale x 8 x bfloat> %z3)
   br i1 %p, label %L1, label %L2
 L1:
   ret <vscale x 8 x bfloat> undef
 L2:
   %extract = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.tuple.get.nxv8bf16.nxv32bf16(<vscale x 32 x bfloat> %tuple, i32 0)
   ret <vscale x 8 x bfloat> %extract
 }
 
-define <vscale x 8 x bfloat> @test_svcreate4_bf16_vec3(i1 %p, <vscale x 8 x bfloat> %z0, <vscale x 8 x bfloat> %z1, <vscale x 8 x bfloat> %z2, <vscale x 8 x bfloat> %z3) local_unnamed_addr #1 {
+define <vscale x 8 x bfloat> @test_svcreate4_bf16_vec3(i1 %p, <vscale x 8 x bfloat> %z0, <vscale x 8 x bfloat> %z1, <vscale x 8 x bfloat> %z2, <vscale x 8 x bfloat> %z3) #1 {
 ; CHECK-LABEL: test_svcreate4_bf16_vec3:
 ; CHECK: // %L2
 ; CHECK-NEXT: mov z0.d, z3.d
 ; CHECK-NEXT: ret
   %tuple = tail call <vscale x 32 x bfloat> @llvm.aarch64.sve.tuple.create4.nxv32bf16.nxv8bf16(<vscale x 8 x bfloat> %z0, <vscale x 8 x bfloat> %z1, <vscale x 8 x bfloat> %z2, <vscale x 8 x bfloat> %z3)
   br i1 %p, label %L1, label %L2
 L1:
   ret <vscale x 8 x bfloat> undef
 L2:
   %extract = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.tuple.get.nxv8bf16.nxv32bf16(<vscale x 32 x bfloat> %tuple, i32 3)
   ret <vscale x 8 x bfloat> %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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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 {
+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) #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" }
+attributes #0 = { nounwind }
 ; +bf16 is required for the bfloat version.
-attributes #1 = { nounwind "target-features"="+sve,+bf16" }
+attributes #1 = { nounwind "target-features"="+bf16" }
 
 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 16 x bfloat>  @llvm.aarch64.sve.tuple.create2.nxv16bf16.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
 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>)

llvm/test/CodeGen/AArch64/sve-intrinsics-insert-extract-tuple.ll

 ; RUN: llc -mtriple aarch64 -mattr=+sve -asm-verbose=0 < %s | FileCheck %s
+; RUN: llc -mtriple aarch64 -mattr=+streaming-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
 ;

 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" }
+attributes #0 = { nounwind }
 
 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)

llvm/test/CodeGen/AArch64/sve-intrinsics-pred-operations.ll

 ; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+streaming-sve < %s | FileCheck %s
 
 ;
 ; BRKA
 ;
 
 define <vscale x 16 x i1> @brka_m_b8(<vscale x 16 x i1> %inactive, <vscale x 16 x i1> %pg, <vscale x 16 x i1> %a) {
 ; CHECK-LABEL: brka_m_b8:
 ; CHECK: brka p0.b, p1/m, p2.b