[llvm] [LLVM][AArch64]Use load/store with consecutive registers in SME2 or S… (PR #77665)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Feb 19 06:36:16 PST 2024
https://github.com/CarolineConcatto updated https://github.com/llvm/llvm-project/pull/77665
>From 75c621bd18667664a4263ab4e81d169be0563614 Mon Sep 17 00:00:00 2001
From: Caroline Concatto <caroline.concatto at arm.com>
Date: Wed, 10 Jan 2024 17:23:04 +0000
Subject: [PATCH 1/2] [LLVM][AArch64]Use load/store with consecutive registers
in SME2 or SVE2.1 for spill/fill
When possible the spill/fill register in Frame Lowering uses the ld/st
consecutive pairs available in sme or sve2.1.
---
.../Target/AArch64/AArch64FrameLowering.cpp | 100 +-
.../AArch64/AArch64MachineFunctionInfo.h | 2 +
.../CodeGen/AArch64/sme2-intrinsics-ld1.ll | 1456 ++++++-----------
.../CodeGen/AArch64/sme2-intrinsics-ldnt1.ll | 1456 ++++++-----------
.../AArch64/sve2p1-intrinsics-ldst-pair.ll | 295 ++++
5 files changed, 1431 insertions(+), 1878 deletions(-)
create mode 100644 llvm/test/CodeGen/AArch64/sve2p1-intrinsics-ldst-pair.ll
diff --git a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
index caab59201a8d69..7a332bfd18c21b 100644
--- a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -1480,6 +1480,11 @@ static bool IsSVECalleeSave(MachineBasicBlock::iterator I) {
switch (I->getOpcode()) {
default:
return false;
+ case AArch64::PTRUE_C_B:
+ case AArch64::LD1B_2Z_IMM:
+ case AArch64::ST1B_2Z_IMM:
+ return I->getMF()->getSubtarget<AArch64Subtarget>().hasSVE2p1() ||
+ I->getMF()->getSubtarget<AArch64Subtarget>().hasSME2();
case AArch64::STR_ZXI:
case AArch64::STR_PXI:
case AArch64::LDR_ZXI:
@@ -2753,6 +2758,16 @@ struct RegPairInfo {
} // end anonymous namespace
+unsigned findFreePredicateAsCounterReg(MachineFunction &MF) {
+ const MachineRegisterInfo &MRI = MF.getRegInfo();
+ for (MCRegister PReg :
+ {AArch64::PN8, AArch64::PN9, AArch64::PN10, AArch64::PN11, AArch64::PN12,
+ AArch64::PN13, AArch64::PN14, AArch64::PN15}) {
+ if (!MRI.isReserved(PReg))
+ return PReg;
+ }
+ llvm_unreachable("cannot find a free predicate");
+}
static void computeCalleeSaveRegisterPairs(
MachineFunction &MF, ArrayRef<CalleeSavedInfo> CSI,
const TargetRegisterInfo *TRI, SmallVectorImpl<RegPairInfo> &RegPairs,
@@ -2763,6 +2778,7 @@ static void computeCalleeSaveRegisterPairs(
bool IsWindows = isTargetWindows(MF);
bool NeedsWinCFI = needsWinCFI(MF);
+ const auto &Subtarget = MF.getSubtarget<AArch64Subtarget>();
AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
MachineFrameInfo &MFI = MF.getFrameInfo();
CallingConv::ID CC = MF.getFunction().getCallingConv();
@@ -2831,7 +2847,11 @@ static void computeCalleeSaveRegisterPairs(
RPI.Reg2 = NextReg;
break;
case RegPairInfo::PPR:
+ break;
case RegPairInfo::ZPR:
+ if (Subtarget.hasSVE2p1() || Subtarget.hasSME2())
+ if (((RPI.Reg1 - AArch64::Z0) & 1) == 0 && (NextReg == RPI.Reg1 + 1))
+ RPI.Reg2 = NextReg;
break;
}
}
@@ -2876,7 +2896,7 @@ static void computeCalleeSaveRegisterPairs(
assert(OffsetPre % Scale == 0);
if (RPI.isScalable())
- ScalableByteOffset += StackFillDir * Scale;
+ ScalableByteOffset += StackFillDir * (RPI.isPaired() ? 2 * Scale : Scale);
else
ByteOffset += StackFillDir * (RPI.isPaired() ? 2 * Scale : Scale);
@@ -2887,9 +2907,6 @@ static void computeCalleeSaveRegisterPairs(
(IsWindows && RPI.Reg2 == AArch64::LR)))
ByteOffset += StackFillDir * 8;
- assert(!(RPI.isScalable() && RPI.isPaired()) &&
- "Paired spill/fill instructions don't exist for SVE vectors");
-
// Round up size of non-pair to pair size if we need to pad the
// callee-save area to ensure 16-byte alignment.
if (NeedGapToAlignStack && !NeedsWinCFI &&
@@ -2976,6 +2993,7 @@ bool AArch64FrameLowering::spillCalleeSavedRegisters(
}
return true;
}
+ bool PtrueCreated = false;
for (const RegPairInfo &RPI : llvm::reverse(RegPairs)) {
unsigned Reg1 = RPI.Reg1;
unsigned Reg2 = RPI.Reg2;
@@ -3010,10 +3028,10 @@ bool AArch64FrameLowering::spillCalleeSavedRegisters(
Alignment = Align(16);
break;
case RegPairInfo::ZPR:
- StrOpc = AArch64::STR_ZXI;
- Size = 16;
- Alignment = Align(16);
- break;
+ StrOpc = RPI.isPaired() ? AArch64::ST1B_2Z_IMM : AArch64::STR_ZXI;
+ Size = 16;
+ Alignment = Align(16);
+ break;
case RegPairInfo::PPR:
StrOpc = AArch64::STR_PXI;
Size = 2;
@@ -3037,19 +3055,37 @@ bool AArch64FrameLowering::spillCalleeSavedRegisters(
std::swap(Reg1, Reg2);
std::swap(FrameIdxReg1, FrameIdxReg2);
}
+
+ unsigned PnReg;
+ unsigned PairRegs;
+ if (RPI.isPaired() && RPI.isScalable()) {
+ PnReg = findFreePredicateAsCounterReg(MF);
+ PairRegs = AArch64::Z0_Z1 + (RPI.Reg1 - AArch64::Z0);
+ if (!PtrueCreated) {
+ PtrueCreated = true;
+ BuildMI(MBB, MI, DL, TII.get(AArch64::PTRUE_C_B), PnReg)
+ .setMIFlags(MachineInstr::FrameDestroy);
+ }
+ }
MachineInstrBuilder MIB = BuildMI(MBB, MI, DL, TII.get(StrOpc));
if (!MRI.isReserved(Reg1))
MBB.addLiveIn(Reg1);
if (RPI.isPaired()) {
if (!MRI.isReserved(Reg2))
MBB.addLiveIn(Reg2);
- MIB.addReg(Reg2, getPrologueDeath(MF, Reg2));
+ if (RPI.isScalable())
+ MIB.addReg(PairRegs);
+ else
+ MIB.addReg(Reg2, getPrologueDeath(MF, Reg2));
MIB.addMemOperand(MF.getMachineMemOperand(
MachinePointerInfo::getFixedStack(MF, FrameIdxReg2),
MachineMemOperand::MOStore, Size, Alignment));
}
- MIB.addReg(Reg1, getPrologueDeath(MF, Reg1))
- .addReg(AArch64::SP)
+ if (RPI.isPaired() && RPI.isScalable())
+ MIB.addReg(PnReg);
+ else
+ MIB.addReg(Reg1, getPrologueDeath(MF, Reg1));
+ MIB.addReg(AArch64::SP)
.addImm(RPI.Offset) // [sp, #offset*scale],
// where factor*scale is implicit
.setMIFlag(MachineInstr::FrameSetup);
@@ -3061,8 +3097,11 @@ bool AArch64FrameLowering::spillCalleeSavedRegisters(
// Update the StackIDs of the SVE stack slots.
MachineFrameInfo &MFI = MF.getFrameInfo();
- if (RPI.Type == RegPairInfo::ZPR || RPI.Type == RegPairInfo::PPR)
- MFI.setStackID(RPI.FrameIdx, TargetStackID::ScalableVector);
+ if (RPI.Type == RegPairInfo::ZPR || RPI.Type == RegPairInfo::PPR) {
+ MFI.setStackID(FrameIdxReg1, TargetStackID::ScalableVector);
+ if (RPI.isPaired())
+ MFI.setStackID(FrameIdxReg2, TargetStackID::ScalableVector);
+ }
}
return true;
@@ -3082,7 +3121,8 @@ bool AArch64FrameLowering::restoreCalleeSavedRegisters(
computeCalleeSaveRegisterPairs(MF, CSI, TRI, RegPairs, hasFP(MF));
- auto EmitMI = [&](const RegPairInfo &RPI) -> MachineBasicBlock::iterator {
+ auto EmitMI = [&](const RegPairInfo &RPI,
+ bool *PtrueCreated) -> MachineBasicBlock::iterator {
unsigned Reg1 = RPI.Reg1;
unsigned Reg2 = RPI.Reg2;
@@ -3114,7 +3154,7 @@ bool AArch64FrameLowering::restoreCalleeSavedRegisters(
Alignment = Align(16);
break;
case RegPairInfo::ZPR:
- LdrOpc = AArch64::LDR_ZXI;
+ LdrOpc = RPI.isPaired() ? AArch64::LD1B_2Z_IMM : AArch64::LDR_ZXI;
Size = 16;
Alignment = Align(16);
break;
@@ -3139,15 +3179,31 @@ bool AArch64FrameLowering::restoreCalleeSavedRegisters(
std::swap(Reg1, Reg2);
std::swap(FrameIdxReg1, FrameIdxReg2);
}
+
+ unsigned PnReg;
+ unsigned PairRegs;
+ if (RPI.isPaired() && RPI.isScalable()) {
+ PnReg = findFreePredicateAsCounterReg(MF);
+ PairRegs = AArch64::Z0_Z1 + (RPI.Reg1 - AArch64::Z0);
+ if (!*PtrueCreated) {
+ *PtrueCreated = true;
+ BuildMI(MBB, MBBI, DL, TII.get(AArch64::PTRUE_C_B), PnReg)
+ .setMIFlags(MachineInstr::FrameDestroy);
+ }
+ }
+
MachineInstrBuilder MIB = BuildMI(MBB, MBBI, DL, TII.get(LdrOpc));
if (RPI.isPaired()) {
- MIB.addReg(Reg2, getDefRegState(true));
+ MIB.addReg(RPI.isScalable() ? PairRegs : Reg2, getDefRegState(true));
MIB.addMemOperand(MF.getMachineMemOperand(
MachinePointerInfo::getFixedStack(MF, FrameIdxReg2),
MachineMemOperand::MOLoad, Size, Alignment));
}
- MIB.addReg(Reg1, getDefRegState(true))
- .addReg(AArch64::SP)
+ if (RPI.isPaired() && RPI.isScalable())
+ MIB.addReg(PnReg);
+ else
+ MIB.addReg(Reg1, getDefRegState(true));
+ MIB.addReg(AArch64::SP)
.addImm(RPI.Offset) // [sp, #offset*scale]
// where factor*scale is implicit
.setMIFlag(MachineInstr::FrameDestroy);
@@ -3161,9 +3217,10 @@ bool AArch64FrameLowering::restoreCalleeSavedRegisters(
};
// SVE objects are always restored in reverse order.
+ bool PtrueCreated = false;
for (const RegPairInfo &RPI : reverse(RegPairs))
if (RPI.isScalable())
- EmitMI(RPI);
+ EmitMI(RPI, &PtrueCreated);
if (homogeneousPrologEpilog(MF, &MBB)) {
auto MIB = BuildMI(MBB, MBBI, DL, TII.get(AArch64::HOM_Epilog))
@@ -3174,13 +3231,12 @@ bool AArch64FrameLowering::restoreCalleeSavedRegisters(
}
return true;
}
-
if (ReverseCSRRestoreSeq) {
MachineBasicBlock::iterator First = MBB.end();
for (const RegPairInfo &RPI : reverse(RegPairs)) {
if (RPI.isScalable())
continue;
- MachineBasicBlock::iterator It = EmitMI(RPI);
+ MachineBasicBlock::iterator It = EmitMI(RPI, &PtrueCreated);
if (First == MBB.end())
First = It;
}
@@ -3190,7 +3246,7 @@ bool AArch64FrameLowering::restoreCalleeSavedRegisters(
for (const RegPairInfo &RPI : RegPairs) {
if (RPI.isScalable())
continue;
- (void)EmitMI(RPI);
+ (void)EmitMI(RPI, &PtrueCreated);
}
}
diff --git a/llvm/lib/Target/AArch64/AArch64MachineFunctionInfo.h b/llvm/lib/Target/AArch64/AArch64MachineFunctionInfo.h
index cd4a18bfbc23a8..b44cc8d0d0dc9b 100644
--- a/llvm/lib/Target/AArch64/AArch64MachineFunctionInfo.h
+++ b/llvm/lib/Target/AArch64/AArch64MachineFunctionInfo.h
@@ -300,6 +300,8 @@ class AArch64FunctionInfo final : public MachineFunctionInfo {
int FrameIdx = Info.getFrameIdx();
if (MFI.getStackID(FrameIdx) != TargetStackID::Default)
continue;
+ if (MFI.getStackID(Info.getFrameIdx()) == TargetStackID::ScalableVector)
+ continue;
int64_t Offset = MFI.getObjectOffset(FrameIdx);
int64_t ObjSize = MFI.getObjectSize(FrameIdx);
MinOffset = std::min<int64_t>(Offset, MinOffset);
diff --git a/llvm/test/CodeGen/AArch64/sme2-intrinsics-ld1.ll b/llvm/test/CodeGen/AArch64/sme2-intrinsics-ld1.ll
index b7119fc0825673..6c94546c9525aa 100644
--- a/llvm/test/CodeGen/AArch64/sme2-intrinsics-ld1.ll
+++ b/llvm/test/CodeGen/AArch64/sme2-intrinsics-ld1.ll
@@ -55,45 +55,31 @@ define <vscale x 32 x i8> @ld1_x2_i8_z0_z8(<vscale x 16 x i8> %unused, <vscale x
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ld1b { z0.b, z8.b }, pn8/z, [x0]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -103,20 +89,14 @@ define <vscale x 32 x i8> @ld1_x2_i8_z0_z8(<vscale x 16 x i8> %unused, <vscale x
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-16
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-2
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -130,21 +110,15 @@ define <vscale x 32 x i8> @ld1_x2_i8_z0_z8(<vscale x 16 x i8> %unused, <vscale x
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -210,45 +184,31 @@ define <vscale x 32 x i8> @ld1_x2_i8_z0_z8_scalar(<vscale x 16 x i8> %unused, <v
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ld1b { z0.b, z8.b }, pn8/z, [x0, x1]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -258,20 +218,14 @@ define <vscale x 32 x i8> @ld1_x2_i8_z0_z8_scalar(<vscale x 16 x i8> %unused, <v
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-16
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-2
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -285,21 +239,15 @@ define <vscale x 32 x i8> @ld1_x2_i8_z0_z8_scalar(<vscale x 16 x i8> %unused, <v
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -366,45 +314,31 @@ define <vscale x 16 x i16> @ld1_x2_i16_z0_z8(<vscale x 8 x i16> %unused, <vscale
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ld1h { z0.h, z8.h }, pn8/z, [x0]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -414,20 +348,14 @@ define <vscale x 16 x i16> @ld1_x2_i16_z0_z8(<vscale x 8 x i16> %unused, <vscale
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-16
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-2
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -441,21 +369,15 @@ define <vscale x 16 x i16> @ld1_x2_i16_z0_z8(<vscale x 8 x i16> %unused, <vscale
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -521,45 +443,31 @@ define <vscale x 16 x i16> @ld1_x2_i16_z0_z8_scalar(<vscale x 8 x i16> %unused,
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ld1h { z0.h, z8.h }, pn8/z, [x0, x1, lsl #1]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -569,20 +477,14 @@ define <vscale x 16 x i16> @ld1_x2_i16_z0_z8_scalar(<vscale x 8 x i16> %unused,
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-16
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-2
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -596,21 +498,15 @@ define <vscale x 16 x i16> @ld1_x2_i16_z0_z8_scalar(<vscale x 8 x i16> %unused,
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -677,45 +573,31 @@ define <vscale x 8 x i32> @ld1_x2_i32_z0_z8(<vscale x 4 x i32> %unused, <vscale
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ld1w { z0.s, z8.s }, pn8/z, [x0]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -725,20 +607,14 @@ define <vscale x 8 x i32> @ld1_x2_i32_z0_z8(<vscale x 4 x i32> %unused, <vscale
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-16
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-2
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -752,21 +628,15 @@ define <vscale x 8 x i32> @ld1_x2_i32_z0_z8(<vscale x 4 x i32> %unused, <vscale
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -832,45 +702,31 @@ define <vscale x 8 x i32> @ld1_x2_i32_z0_z8_scalar(<vscale x 4 x i32> %unused, <
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ld1w { z0.s, z8.s }, pn8/z, [x0, x1, lsl #2]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -880,20 +736,14 @@ define <vscale x 8 x i32> @ld1_x2_i32_z0_z8_scalar(<vscale x 4 x i32> %unused, <
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-16
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-2
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -907,21 +757,15 @@ define <vscale x 8 x i32> @ld1_x2_i32_z0_z8_scalar(<vscale x 4 x i32> %unused, <
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -988,45 +832,31 @@ define <vscale x 4 x i64> @ld1_x2_i64_z0_z8(<vscale x 2 x i64> %unused, <vscale
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ld1d { z0.d, z8.d }, pn8/z, [x0]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -1036,20 +866,14 @@ define <vscale x 4 x i64> @ld1_x2_i64_z0_z8(<vscale x 2 x i64> %unused, <vscale
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-16
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-2
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -1063,21 +887,15 @@ define <vscale x 4 x i64> @ld1_x2_i64_z0_z8(<vscale x 2 x i64> %unused, <vscale
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1143,45 +961,31 @@ define <vscale x 4 x i64> @ld1_x2_i64_z0_z8_scalar(<vscale x 2 x i64> %unused, <
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ld1d { z0.d, z8.d }, pn8/z, [x0, x1, lsl #3]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -1191,20 +995,14 @@ define <vscale x 4 x i64> @ld1_x2_i64_z0_z8_scalar(<vscale x 2 x i64> %unused, <
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-16
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-2
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -1218,21 +1016,15 @@ define <vscale x 4 x i64> @ld1_x2_i64_z0_z8_scalar(<vscale x 2 x i64> %unused, <
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1301,46 +1093,32 @@ define <vscale x 64 x i8> @ld1_x4_i8_z0_z4_z8_z12(<vscale x 16 x i8> %unused, <v
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ld1b { z0.b, z4.b, z8.b, z12.b }, pn8/z, [x0]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1351,19 +1129,14 @@ define <vscale x 64 x i8> @ld1_x4_i8_z0_z4_z8_z12(<vscale x 16 x i8> %unused, <v
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-15
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #14, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-4
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -1381,20 +1154,15 @@ define <vscale x 64 x i8> @ld1_x4_i8_z0_z4_z8_z12(<vscale x 16 x i8> %unused, <v
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1466,46 +1234,32 @@ define <vscale x 64 x i8> @ld1_x4_i8_z0_z4_z8_z12_scalar(<vscale x 16 x i8> %unu
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ld1b { z0.b, z4.b, z8.b, z12.b }, pn8/z, [x0, x1]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1516,19 +1270,14 @@ define <vscale x 64 x i8> @ld1_x4_i8_z0_z4_z8_z12_scalar(<vscale x 16 x i8> %unu
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-15
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #14, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-4
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -1546,20 +1295,15 @@ define <vscale x 64 x i8> @ld1_x4_i8_z0_z4_z8_z12_scalar(<vscale x 16 x i8> %unu
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1632,46 +1376,32 @@ define <vscale x 32 x i16> @ld1_x4_i16_z0_z4_z8_z12(<vscale x 8 x i16> %unused,
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ld1h { z0.h, z4.h, z8.h, z12.h }, pn8/z, [x0]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1682,19 +1412,14 @@ define <vscale x 32 x i16> @ld1_x4_i16_z0_z4_z8_z12(<vscale x 8 x i16> %unused,
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-15
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #14, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-4
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -1712,20 +1437,15 @@ define <vscale x 32 x i16> @ld1_x4_i16_z0_z4_z8_z12(<vscale x 8 x i16> %unused,
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1798,46 +1518,32 @@ define <vscale x 32 x i16> @ld1_x4_i16_z0_z4_z8_z12_scalar(<vscale x 8 x i16> %u
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ld1h { z0.h, z4.h, z8.h, z12.h }, pn8/z, [x0, x1, lsl #1]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1848,19 +1554,14 @@ define <vscale x 32 x i16> @ld1_x4_i16_z0_z4_z8_z12_scalar(<vscale x 8 x i16> %u
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-15
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #14, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-4
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -1878,20 +1579,15 @@ define <vscale x 32 x i16> @ld1_x4_i16_z0_z4_z8_z12_scalar(<vscale x 8 x i16> %u
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1964,46 +1660,32 @@ define <vscale x 16 x i32> @ld1_x4_i32_z0_z4_z8_z12(<vscale x 4 x i32> %unused,
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ld1w { z0.s, z4.s, z8.s, z12.s }, pn8/z, [x0]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -2014,19 +1696,14 @@ define <vscale x 16 x i32> @ld1_x4_i32_z0_z4_z8_z12(<vscale x 4 x i32> %unused,
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-15
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #14, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-4
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -2044,20 +1721,15 @@ define <vscale x 16 x i32> @ld1_x4_i32_z0_z4_z8_z12(<vscale x 4 x i32> %unused,
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -2130,46 +1802,32 @@ define <vscale x 16 x i32> @ld1_x4_i32_z0_z4_z8_z12_scalar(<vscale x 4 x i32> %u
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ld1w { z0.s, z4.s, z8.s, z12.s }, pn8/z, [x0, x1, lsl #2]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -2180,19 +1838,14 @@ define <vscale x 16 x i32> @ld1_x4_i32_z0_z4_z8_z12_scalar(<vscale x 4 x i32> %u
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-15
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #14, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-4
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -2210,20 +1863,15 @@ define <vscale x 16 x i32> @ld1_x4_i32_z0_z4_z8_z12_scalar(<vscale x 4 x i32> %u
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -2296,46 +1944,32 @@ define <vscale x 8 x i64> @ld1_x4_i64_z0_z4_z8_z12(<vscale x 2 x i64> %unused, <
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ld1d { z0.d, z4.d, z8.d, z12.d }, pn8/z, [x0]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -2346,19 +1980,14 @@ define <vscale x 8 x i64> @ld1_x4_i64_z0_z4_z8_z12(<vscale x 2 x i64> %unused, <
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-15
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #14, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-4
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -2376,20 +2005,15 @@ define <vscale x 8 x i64> @ld1_x4_i64_z0_z4_z8_z12(<vscale x 2 x i64> %unused, <
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -2462,46 +2086,32 @@ define <vscale x 8 x i64> @ld1_x4_i64_z0_z4_z8_z12_scalar(<vscale x 2 x i64> %un
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ld1d { z0.d, z4.d, z8.d, z12.d }, pn8/z, [x0, x1, lsl #3]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -2512,19 +2122,14 @@ define <vscale x 8 x i64> @ld1_x4_i64_z0_z4_z8_z12_scalar(<vscale x 2 x i64> %un
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-15
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #14, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-4
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -2542,20 +2147,15 @@ define <vscale x 8 x i64> @ld1_x4_i64_z0_z4_z8_z12_scalar(<vscale x 2 x i64> %un
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
diff --git a/llvm/test/CodeGen/AArch64/sme2-intrinsics-ldnt1.ll b/llvm/test/CodeGen/AArch64/sme2-intrinsics-ldnt1.ll
index 1fb251a4f628e9..1df619a40ef3fa 100644
--- a/llvm/test/CodeGen/AArch64/sme2-intrinsics-ldnt1.ll
+++ b/llvm/test/CodeGen/AArch64/sme2-intrinsics-ldnt1.ll
@@ -8,45 +8,31 @@ define <vscale x 32 x i8> @ldnt1_x2_i8_z0_z8(<vscale x 16 x i8> %unused, <vscale
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ldnt1b { z0.b, z8.b }, pn8/z, [x0]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -56,20 +42,14 @@ define <vscale x 32 x i8> @ldnt1_x2_i8_z0_z8(<vscale x 16 x i8> %unused, <vscale
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-16
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-2
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -83,21 +63,15 @@ define <vscale x 32 x i8> @ldnt1_x2_i8_z0_z8(<vscale x 16 x i8> %unused, <vscale
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -116,45 +90,31 @@ define <vscale x 32 x i8> @ldnt1_x2_i8_z0_z8_scalar(<vscale x 16 x i8> %unused,
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ldnt1b { z0.b, z8.b }, pn8/z, [x0, x1]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -164,20 +124,14 @@ define <vscale x 32 x i8> @ldnt1_x2_i8_z0_z8_scalar(<vscale x 16 x i8> %unused,
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-16
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-2
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -191,21 +145,15 @@ define <vscale x 32 x i8> @ldnt1_x2_i8_z0_z8_scalar(<vscale x 16 x i8> %unused,
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -225,45 +173,31 @@ define <vscale x 16 x i16> @ldnt1_x2_i16_z0_z8(<vscale x 8 x i16> %unused, <vsca
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ldnt1h { z0.h, z8.h }, pn8/z, [x0]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -273,20 +207,14 @@ define <vscale x 16 x i16> @ldnt1_x2_i16_z0_z8(<vscale x 8 x i16> %unused, <vsca
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-16
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-2
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -300,21 +228,15 @@ define <vscale x 16 x i16> @ldnt1_x2_i16_z0_z8(<vscale x 8 x i16> %unused, <vsca
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -333,45 +255,31 @@ define <vscale x 16 x i16> @ldnt1_x2_i16_z0_z8_scalar(<vscale x 8 x i16> %unused
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ldnt1h { z0.h, z8.h }, pn8/z, [x0, x1, lsl #1]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -381,20 +289,14 @@ define <vscale x 16 x i16> @ldnt1_x2_i16_z0_z8_scalar(<vscale x 8 x i16> %unused
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-16
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-2
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -408,21 +310,15 @@ define <vscale x 16 x i16> @ldnt1_x2_i16_z0_z8_scalar(<vscale x 8 x i16> %unused
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -442,45 +338,31 @@ define <vscale x 8 x i32> @ldnt1_x2_i32_z0_z8(<vscale x 4 x i32> %unused, <vscal
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ldnt1w { z0.s, z8.s }, pn8/z, [x0]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -490,20 +372,14 @@ define <vscale x 8 x i32> @ldnt1_x2_i32_z0_z8(<vscale x 4 x i32> %unused, <vscal
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-16
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-2
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -517,21 +393,15 @@ define <vscale x 8 x i32> @ldnt1_x2_i32_z0_z8(<vscale x 4 x i32> %unused, <vscal
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -550,45 +420,31 @@ define <vscale x 8 x i32> @ldnt1_x2_i32_z0_z8_scalar(<vscale x 4 x i32> %unused,
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ldnt1w { z0.s, z8.s }, pn8/z, [x0, x1, lsl #2]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -598,20 +454,14 @@ define <vscale x 8 x i32> @ldnt1_x2_i32_z0_z8_scalar(<vscale x 4 x i32> %unused,
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-16
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-2
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -625,21 +475,15 @@ define <vscale x 8 x i32> @ldnt1_x2_i32_z0_z8_scalar(<vscale x 4 x i32> %unused,
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -659,45 +503,31 @@ define <vscale x 4 x i64> @ldnt1_x2_i64_z0_z8(<vscale x 2 x i64> %unused, <vscal
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ldnt1d { z0.d, z8.d }, pn8/z, [x0]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -707,20 +537,14 @@ define <vscale x 4 x i64> @ldnt1_x2_i64_z0_z8(<vscale x 2 x i64> %unused, <vscal
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-16
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-2
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -734,21 +558,15 @@ define <vscale x 4 x i64> @ldnt1_x2_i64_z0_z8(<vscale x 2 x i64> %unused, <vscal
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -767,45 +585,31 @@ define <vscale x 4 x i64> @ldnt1_x2_i64_z0_z8_scalar(<vscale x 2 x i64> %unused,
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ldnt1d { z0.d, z8.d }, pn8/z, [x0, x1, lsl #3]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -815,20 +619,14 @@ define <vscale x 4 x i64> @ldnt1_x2_i64_z0_z8_scalar(<vscale x 2 x i64> %unused,
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-16
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-2
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -842,21 +640,15 @@ define <vscale x 4 x i64> @ldnt1_x2_i64_z0_z8_scalar(<vscale x 2 x i64> %unused,
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -876,46 +668,32 @@ define <vscale x 64 x i8> @ldnt1_x4_i8_z0_z4_z8_z12(<vscale x 16 x i8> %unused,
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ldnt1b { z0.b, z4.b, z8.b, z12.b }, pn8/z, [x0]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -926,19 +704,14 @@ define <vscale x 64 x i8> @ldnt1_x4_i8_z0_z4_z8_z12(<vscale x 16 x i8> %unused,
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-15
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #14, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-4
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -956,20 +729,15 @@ define <vscale x 64 x i8> @ldnt1_x4_i8_z0_z4_z8_z12(<vscale x 16 x i8> %unused,
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -992,46 +760,32 @@ define <vscale x 64 x i8> @ldnt1_x4_i8_z0_z4_z8_z12_scalar(<vscale x 16 x i8> %u
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ldnt1b { z0.b, z4.b, z8.b, z12.b }, pn8/z, [x0, x1]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1042,19 +796,14 @@ define <vscale x 64 x i8> @ldnt1_x4_i8_z0_z4_z8_z12_scalar(<vscale x 16 x i8> %u
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-15
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #14, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-4
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -1072,20 +821,15 @@ define <vscale x 64 x i8> @ldnt1_x4_i8_z0_z4_z8_z12_scalar(<vscale x 16 x i8> %u
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1109,46 +853,32 @@ define <vscale x 32 x i16> @ldnt1_x4_i16_z0_z4_z8_z12(<vscale x 8 x i16> %unused
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ldnt1h { z0.h, z4.h, z8.h, z12.h }, pn8/z, [x0]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1159,19 +889,14 @@ define <vscale x 32 x i16> @ldnt1_x4_i16_z0_z4_z8_z12(<vscale x 8 x i16> %unused
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-15
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #14, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-4
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -1189,20 +914,15 @@ define <vscale x 32 x i16> @ldnt1_x4_i16_z0_z4_z8_z12(<vscale x 8 x i16> %unused
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1225,46 +945,32 @@ define <vscale x 32 x i16> @ldnt1_x4_i16_z0_z4_z8_z12_scalar(<vscale x 8 x i16>
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ldnt1h { z0.h, z4.h, z8.h, z12.h }, pn8/z, [x0, x1, lsl #1]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1275,19 +981,14 @@ define <vscale x 32 x i16> @ldnt1_x4_i16_z0_z4_z8_z12_scalar(<vscale x 8 x i16>
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-15
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #14, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-4
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -1305,20 +1006,15 @@ define <vscale x 32 x i16> @ldnt1_x4_i16_z0_z4_z8_z12_scalar(<vscale x 8 x i16>
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1342,46 +1038,32 @@ define <vscale x 16 x i32> @ldnt1_x4_i32_z0_z4_z8_z12(<vscale x 4 x i32> %unused
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ldnt1w { z0.s, z4.s, z8.s, z12.s }, pn8/z, [x0]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1392,19 +1074,14 @@ define <vscale x 16 x i32> @ldnt1_x4_i32_z0_z4_z8_z12(<vscale x 4 x i32> %unused
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-15
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #14, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-4
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -1422,20 +1099,15 @@ define <vscale x 16 x i32> @ldnt1_x4_i32_z0_z4_z8_z12(<vscale x 4 x i32> %unused
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1458,46 +1130,32 @@ define <vscale x 16 x i32> @ldnt1_x4_i32_z0_z4_z8_z12_scalar(<vscale x 4 x i32>
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ldnt1w { z0.s, z4.s, z8.s, z12.s }, pn8/z, [x0, x1, lsl #2]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1508,19 +1166,14 @@ define <vscale x 16 x i32> @ldnt1_x4_i32_z0_z4_z8_z12_scalar(<vscale x 4 x i32>
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-15
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #14, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-4
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -1538,20 +1191,15 @@ define <vscale x 16 x i32> @ldnt1_x4_i32_z0_z4_z8_z12_scalar(<vscale x 4 x i32>
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1575,46 +1223,32 @@ define <vscale x 8 x i64> @ldnt1_x4_i64_z0_z4_z8_z12(<vscale x 2 x i64> %unused,
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ldnt1d { z0.d, z4.d, z8.d, z12.d }, pn8/z, [x0]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1625,19 +1259,14 @@ define <vscale x 8 x i64> @ldnt1_x4_i64_z0_z4_z8_z12(<vscale x 2 x i64> %unused,
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-15
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #14, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-4
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -1655,20 +1284,15 @@ define <vscale x 8 x i64> @ldnt1_x4_i64_z0_z4_z8_z12(<vscale x 2 x i64> %unused,
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1691,46 +1315,32 @@ define <vscale x 8 x i64> @ldnt1_x4_i64_z0_z4_z8_z12_scalar(<vscale x 2 x i64> %
; STRIDED-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; STRIDED-NEXT: addvl sp, sp, #-17
; STRIDED-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #22, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #26, mul vl] // 32-byte Folded Spill
+; STRIDED-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #30, mul vl] // 32-byte Folded Spill
; STRIDED-NEXT: mov p8.b, p0.b
-; STRIDED-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z12, [sp, #12, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z11, [sp, #13, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z10, [sp, #14, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z9, [sp, #15, mul vl] // 16-byte Folded Spill
-; STRIDED-NEXT: str z8, [sp, #16, mul vl] // 16-byte Folded Spill
; STRIDED-NEXT: ldnt1d { z0.d, z4.d, z8.d, z12.d }, pn8/z, [x0, x1, lsl #3]
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; STRIDED-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ptrue pn8.b
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
-; STRIDED-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1741,19 +1351,14 @@ define <vscale x 8 x i64> @ldnt1_x4_i64_z0_z4_z8_z12_scalar(<vscale x 2 x i64> %
; CONTIGUOUS-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-15
; CONTIGUOUS-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; CONTIGUOUS-NEXT: str z23, [sp, #1, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z22, [sp, #2, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z21, [sp, #3, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z20, [sp, #4, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z19, [sp, #5, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z18, [sp, #6, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z17, [sp, #7, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z16, [sp, #8, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z15, [sp, #9, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z14, [sp, #10, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #6, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #10, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #14, mul vl] // 32-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #18, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z13, [sp, #11, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z11, [sp, #12, mul vl] // 16-byte Folded Spill
-; CONTIGUOUS-NEXT: str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CONTIGUOUS-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
; CONTIGUOUS-NEXT: str z9, [sp, #14, mul vl] // 16-byte Folded Spill
; CONTIGUOUS-NEXT: addvl sp, sp, #-4
; CONTIGUOUS-NEXT: mov p8.b, p0.b
@@ -1771,20 +1376,15 @@ define <vscale x 8 x i64> @ldnt1_x4_i64_z0_z4_z8_z12_scalar(<vscale x 2 x i64> %
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ptrue pn8.b
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
diff --git a/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-ldst-pair.ll b/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-ldst-pair.ll
new file mode 100644
index 00000000000000..c7f38861102c00
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-ldst-pair.ll
@@ -0,0 +1,295 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sme -verify-machineinstrs < %s | FileCheck %s --check-prefixes=NOPAIR
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=NOPAIR
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sme2 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=PAIR
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2p1 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=PAIR
+
+
+declare void @my_func()
+
+define void @fbyte(<vscale x 16 x i8> %v) {
+; NOPAIR-LABEL: fbyte:
+; NOPAIR: // %bb.0:
+; NOPAIR-NEXT: stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
+; NOPAIR-NEXT: addvl sp, sp, #-18
+; NOPAIR-NEXT: str p15, [sp, #4, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p14, [sp, #5, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p13, [sp, #6, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p12, [sp, #7, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p11, [sp, #8, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p10, [sp, #9, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p9, [sp, #10, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p8, [sp, #11, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p7, [sp, #12, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p6, [sp, #13, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p5, [sp, #14, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p4, [sp, #15, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str z23, [sp, #2, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z22, [sp, #3, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z21, [sp, #4, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z20, [sp, #5, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z19, [sp, #6, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z18, [sp, #7, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z17, [sp, #8, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z16, [sp, #9, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z15, [sp, #10, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z14, [sp, #11, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z13, [sp, #12, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z12, [sp, #13, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z11, [sp, #14, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z10, [sp, #15, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z9, [sp, #16, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z8, [sp, #17, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 144 * VG
+; NOPAIR-NEXT: .cfi_offset w30, -8
+; NOPAIR-NEXT: .cfi_offset w29, -16
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x48, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 16 - 8 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x49, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 16 - 16 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 16 - 24 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4b, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x60, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d11 @ cfa - 16 - 32 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4c, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x58, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d12 @ cfa - 16 - 40 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4d, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x50, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d13 @ cfa - 16 - 48 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 16 - 56 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 16 - 64 * VG
+; NOPAIR-NEXT: bl my_func
+; NOPAIR-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: addvl sp, sp, #18
+; NOPAIR-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; NOPAIR-NEXT: ret
+;
+; PAIR-LABEL: fbyte:
+; PAIR: // %bb.0:
+; PAIR-NEXT: stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
+; PAIR-NEXT: addvl sp, sp, #-18
+; PAIR-NEXT: str p8, [sp, #11, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: ptrue pn8.b
+; PAIR-NEXT: str p15, [sp, #4, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #4, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #8, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: str p14, [sp, #5, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #12, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #16, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: str p13, [sp, #6, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #20, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: str p12, [sp, #7, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #28, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: str p11, [sp, #8, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p10, [sp, #9, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p9, [sp, #10, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p7, [sp, #12, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p6, [sp, #13, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p5, [sp, #14, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p4, [sp, #15, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #32, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 144 * VG
+; PAIR-NEXT: .cfi_offset w30, -8
+; PAIR-NEXT: .cfi_offset w29, -16
+; PAIR-NEXT: .cfi_escape 0x10, 0x48, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 16 - 8 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x49, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 16 - 16 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 16 - 24 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4b, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x60, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d11 @ cfa - 16 - 32 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4c, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x58, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d12 @ cfa - 16 - 40 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4d, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x50, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d13 @ cfa - 16 - 48 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 16 - 56 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 16 - 64 * VG
+; PAIR-NEXT: bl my_func
+; PAIR-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ptrue pn8.b
+; PAIR-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #4, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #8, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #12, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #16, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #20, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #28, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #32, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: addvl sp, sp, #18
+; PAIR-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; PAIR-NEXT: ret
+ call void @my_func()
+ ret void
+}
+
+define void @fhalf(<vscale x 8 x half> %v) {
+; NOPAIR-LABEL: fhalf:
+; NOPAIR: // %bb.0:
+; NOPAIR-NEXT: stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
+; NOPAIR-NEXT: addvl sp, sp, #-18
+; NOPAIR-NEXT: str p15, [sp, #4, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p14, [sp, #5, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p13, [sp, #6, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p12, [sp, #7, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p11, [sp, #8, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p10, [sp, #9, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p9, [sp, #10, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p8, [sp, #11, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p7, [sp, #12, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p6, [sp, #13, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p5, [sp, #14, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p4, [sp, #15, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str z23, [sp, #2, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z22, [sp, #3, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z21, [sp, #4, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z20, [sp, #5, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z19, [sp, #6, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z18, [sp, #7, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z17, [sp, #8, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z16, [sp, #9, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z15, [sp, #10, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z14, [sp, #11, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z13, [sp, #12, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z12, [sp, #13, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z11, [sp, #14, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z10, [sp, #15, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z9, [sp, #16, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z8, [sp, #17, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 144 * VG
+; NOPAIR-NEXT: .cfi_offset w30, -8
+; NOPAIR-NEXT: .cfi_offset w29, -16
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x48, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 16 - 8 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x49, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 16 - 16 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 16 - 24 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4b, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x60, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d11 @ cfa - 16 - 32 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4c, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x58, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d12 @ cfa - 16 - 40 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4d, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x50, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d13 @ cfa - 16 - 48 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 16 - 56 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 16 - 64 * VG
+; NOPAIR-NEXT: bl my_func
+; NOPAIR-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: addvl sp, sp, #18
+; NOPAIR-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; NOPAIR-NEXT: ret
+;
+; PAIR-LABEL: fhalf:
+; PAIR: // %bb.0:
+; PAIR-NEXT: stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
+; PAIR-NEXT: addvl sp, sp, #-18
+; PAIR-NEXT: str p8, [sp, #11, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: ptrue pn8.b
+; PAIR-NEXT: str p15, [sp, #4, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #4, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #8, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: str p14, [sp, #5, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #12, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #16, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: str p13, [sp, #6, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #20, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: str p12, [sp, #7, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #28, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: str p11, [sp, #8, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p10, [sp, #9, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p9, [sp, #10, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p7, [sp, #12, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p6, [sp, #13, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p5, [sp, #14, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p4, [sp, #15, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #32, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 144 * VG
+; PAIR-NEXT: .cfi_offset w30, -8
+; PAIR-NEXT: .cfi_offset w29, -16
+; PAIR-NEXT: .cfi_escape 0x10, 0x48, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 16 - 8 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x49, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 16 - 16 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 16 - 24 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4b, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x60, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d11 @ cfa - 16 - 32 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4c, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x58, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d12 @ cfa - 16 - 40 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4d, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x50, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d13 @ cfa - 16 - 48 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 16 - 56 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 16 - 64 * VG
+; PAIR-NEXT: bl my_func
+; PAIR-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ptrue pn8.b
+; PAIR-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #4, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #8, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #12, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #16, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #20, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #28, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #32, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: addvl sp, sp, #18
+; PAIR-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; PAIR-NEXT: ret
+ call void @my_func()
+ ret void
+}
+
+
+
>From b66d3cee6f0212f30f188a43a0679c5dc559e542 Mon Sep 17 00:00:00 2001
From: Caroline Concatto <caroline.concatto at arm.com>
Date: Wed, 10 Jan 2024 17:23:04 +0000
Subject: [PATCH 2/2] [LLVM][AArch64]Use load/store with consecutive registers
in SME2 or SVE2.1 for spill/fill
When possible the spill/fill register in Frame Lowering uses the ld/st
consecutive pairs available in sme or sve2.1.
---
.../Target/AArch64/AArch64FrameLowering.cpp | 46 +-
llvm/test/CodeGen/AArch64/active_lane_mask.ll | 2 +-
.../framelayout-sve-calleesaves-fix.mir | 2 +-
llvm/test/CodeGen/AArch64/framelayout-sve.mir | 42 +-
.../sme-streaming-compatible-interface.ll | 104 +-
.../AArch64/sme-streaming-interface.ll | 104 +-
.../CodeGen/AArch64/sme2-intrinsics-ld1.ll | 480 ++---
.../CodeGen/AArch64/sme2-intrinsics-ldnt1.ll | 480 ++---
.../test/CodeGen/AArch64/stack-probing-sve.ll | 80 +-
llvm/test/CodeGen/AArch64/sve-alloca.ll | 52 +-
.../sve-breakdown-scalable-vectortype.ll | 84 +-
.../AArch64/sve-callee-save-restore-pairs.ll | 295 +++
.../AArch64/sve-calling-convention-mixed.ll | 104 +-
llvm/test/CodeGen/AArch64/sve-fptosi-sat.ll | 12 +-
llvm/test/CodeGen/AArch64/sve-fptoui-sat.ll | 12 +-
llvm/test/CodeGen/AArch64/sve-pred-arith.ll | 16 +-
llvm/test/CodeGen/AArch64/sve-tailcall.ll | 108 +-
llvm/test/CodeGen/AArch64/sve-trunc.ll | 4 +-
.../AArch64/sve2p1-intrinsics-ldst-pair.ll | 176 +-
llvm/test/CodeGen/AArch64/unwind-preserved.ll | 216 +-
mir.mir | 1874 +++++++++++++++++
21 files changed, 3234 insertions(+), 1059 deletions(-)
create mode 100644 llvm/test/CodeGen/AArch64/sve-callee-save-restore-pairs.ll
create mode 100644 mir.mir
diff --git a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
index 7a332bfd18c21b..c24ab36f4f12d2 100644
--- a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -2733,7 +2733,7 @@ struct RegPairInfo {
unsigned Reg2 = AArch64::NoRegister;
int FrameIdx;
int Offset;
- enum RegType { GPR, FPR64, FPR128, PPR, ZPR } Type;
+ enum RegType { GPR, FPR64, FPR128, ZPR, PPR } Type;
RegPairInfo() = default;
@@ -2758,16 +2758,23 @@ struct RegPairInfo {
} // end anonymous namespace
-unsigned findFreePredicateAsCounterReg(MachineFunction &MF) {
- const MachineRegisterInfo &MRI = MF.getRegInfo();
+static unsigned findFreePredicateAsCounterReg(MachineBasicBlock *MBB) {
+ MachineFunction *MF = MBB->getParent();
+
+ const AArch64Subtarget &Subtarget = MF->getSubtarget<AArch64Subtarget>();
+ const AArch64RegisterInfo &TRI = *Subtarget.getRegisterInfo();
+ LivePhysRegs LiveRegs(TRI);
+ getLiveRegsForEntryMBB(LiveRegs, *MBB);
+
+ const MachineRegisterInfo &MRI = MF->getRegInfo();
for (MCRegister PReg :
{AArch64::PN8, AArch64::PN9, AArch64::PN10, AArch64::PN11, AArch64::PN12,
- AArch64::PN13, AArch64::PN14, AArch64::PN15}) {
- if (!MRI.isReserved(PReg))
+ AArch64::PN13, AArch64::PN14, AArch64::PN15}){
return PReg;
}
- llvm_unreachable("cannot find a free predicate");
+ llvm_unreachable("No predicated register free");
}
+
static void computeCalleeSaveRegisterPairs(
MachineFunction &MF, ArrayRef<CalleeSavedInfo> CSI,
const TargetRegisterInfo *TRI, SmallVectorImpl<RegPairInfo> &RegPairs,
@@ -3056,17 +3063,18 @@ bool AArch64FrameLowering::spillCalleeSavedRegisters(
std::swap(FrameIdxReg1, FrameIdxReg2);
}
- unsigned PnReg;
unsigned PairRegs;
+ unsigned PnReg;
if (RPI.isPaired() && RPI.isScalable()) {
- PnReg = findFreePredicateAsCounterReg(MF);
PairRegs = AArch64::Z0_Z1 + (RPI.Reg1 - AArch64::Z0);
if (!PtrueCreated) {
PtrueCreated = true;
+ PnReg = findFreePredicateAsCounterReg(&MBB);
BuildMI(MBB, MI, DL, TII.get(AArch64::PTRUE_C_B), PnReg)
- .setMIFlags(MachineInstr::FrameDestroy);
+ .setMIFlags(MachineInstr::FrameSetup);
}
}
+
MachineInstrBuilder MIB = BuildMI(MBB, MI, DL, TII.get(StrOpc));
if (!MRI.isReserved(Reg1))
MBB.addLiveIn(Reg1);
@@ -3120,9 +3128,8 @@ bool AArch64FrameLowering::restoreCalleeSavedRegisters(
DL = MBBI->getDebugLoc();
computeCalleeSaveRegisterPairs(MF, CSI, TRI, RegPairs, hasFP(MF));
-
- auto EmitMI = [&](const RegPairInfo &RPI,
- bool *PtrueCreated) -> MachineBasicBlock::iterator {
+ bool PtrueCreated = false;
+ auto EmitMI = [&, PtrueCreated = false](const RegPairInfo &RPI) mutable -> MachineBasicBlock::iterator {
unsigned Reg1 = RPI.Reg1;
unsigned Reg2 = RPI.Reg2;
@@ -3183,10 +3190,10 @@ bool AArch64FrameLowering::restoreCalleeSavedRegisters(
unsigned PnReg;
unsigned PairRegs;
if (RPI.isPaired() && RPI.isScalable()) {
- PnReg = findFreePredicateAsCounterReg(MF);
PairRegs = AArch64::Z0_Z1 + (RPI.Reg1 - AArch64::Z0);
- if (!*PtrueCreated) {
- *PtrueCreated = true;
+ if (!PtrueCreated) {
+ PtrueCreated = true;
+ PnReg = findFreePredicateAsCounterReg(&MBB);
BuildMI(MBB, MBBI, DL, TII.get(AArch64::PTRUE_C_B), PnReg)
.setMIFlags(MachineInstr::FrameDestroy);
}
@@ -3217,10 +3224,9 @@ bool AArch64FrameLowering::restoreCalleeSavedRegisters(
};
// SVE objects are always restored in reverse order.
- bool PtrueCreated = false;
- for (const RegPairInfo &RPI : reverse(RegPairs))
+ for (const RegPairInfo &RPI : RegPairs)
if (RPI.isScalable())
- EmitMI(RPI, &PtrueCreated);
+ EmitMI(RPI);
if (homogeneousPrologEpilog(MF, &MBB)) {
auto MIB = BuildMI(MBB, MBBI, DL, TII.get(AArch64::HOM_Epilog))
@@ -3236,7 +3242,7 @@ bool AArch64FrameLowering::restoreCalleeSavedRegisters(
for (const RegPairInfo &RPI : reverse(RegPairs)) {
if (RPI.isScalable())
continue;
- MachineBasicBlock::iterator It = EmitMI(RPI, &PtrueCreated);
+ MachineBasicBlock::iterator It = EmitMI(RPI);
if (First == MBB.end())
First = It;
}
@@ -3246,7 +3252,7 @@ bool AArch64FrameLowering::restoreCalleeSavedRegisters(
for (const RegPairInfo &RPI : RegPairs) {
if (RPI.isScalable())
continue;
- (void)EmitMI(RPI, &PtrueCreated);
+ (void)EmitMI(RPI);
}
}
diff --git a/llvm/test/CodeGen/AArch64/active_lane_mask.ll b/llvm/test/CodeGen/AArch64/active_lane_mask.ll
index a65c5d66677946..15a61910fb1009 100644
--- a/llvm/test/CodeGen/AArch64/active_lane_mask.ll
+++ b/llvm/test/CodeGen/AArch64/active_lane_mask.ll
@@ -191,8 +191,8 @@ define <vscale x 32 x i1> @lane_mask_nxv32i1_i32(i32 %index, i32 %TC) {
; CHECK-NEXT: uzp1 p3.h, p3.h, p4.h
; CHECK-NEXT: cmphi p0.s, p0/z, z25.s, z1.s
; CHECK-NEXT: uzp1 p4.h, p5.h, p6.h
-; CHECK-NEXT: ldr p6, [sp, #5, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p6, [sp, #5, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: uzp1 p2.h, p2.h, p0.h
; CHECK-NEXT: uzp1 p0.b, p1.b, p3.b
; CHECK-NEXT: uzp1 p1.b, p4.b, p2.b
diff --git a/llvm/test/CodeGen/AArch64/framelayout-sve-calleesaves-fix.mir b/llvm/test/CodeGen/AArch64/framelayout-sve-calleesaves-fix.mir
index 3dba21d59b4087..aed31450736191 100644
--- a/llvm/test/CodeGen/AArch64/framelayout-sve-calleesaves-fix.mir
+++ b/llvm/test/CodeGen/AArch64/framelayout-sve-calleesaves-fix.mir
@@ -19,8 +19,8 @@
; CHECK-NEXT: // implicit-def: $p4
; CHECK-NEXT: addvl sp, sp, #1
; CHECK-NEXT: .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG
- ; CHECK-NEXT: ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #1, mul vl] // 16-byte Folded Reload
+ ; CHECK-NEXT: ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #2
; CHECK-NEXT: .cfi_def_cfa wsp, 16
; CHECK-NEXT: .cfi_restore z8
diff --git a/llvm/test/CodeGen/AArch64/framelayout-sve.mir b/llvm/test/CodeGen/AArch64/framelayout-sve.mir
index 213d7919e4a727..8bfd12067d77c9 100644
--- a/llvm/test/CodeGen/AArch64/framelayout-sve.mir
+++ b/llvm/test/CodeGen/AArch64/framelayout-sve.mir
@@ -710,9 +710,9 @@ body: |
# CHECK: $sp = frame-destroy ADDXri $sp, 32, 0
# CHECK-NEXT: frame-destroy CFI_INSTRUCTION escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22
-# CHECK: $p6 = frame-destroy LDR_PXI $sp, 5
-# CHECK: $p5 = frame-destroy LDR_PXI $sp, 6
# CHECK: $p4 = frame-destroy LDR_PXI $sp, 7
+# CHECK: $p5 = frame-destroy LDR_PXI $sp, 6
+# CHECK: $p6 = frame-destroy LDR_PXI $sp, 5
# CHECK: $sp = frame-destroy ADDVL_XXI $sp, 1
# CHECK-NEXT: frame-destroy CFI_INSTRUCTION def_cfa $wsp, 16
# CHECK-NEXT: early-clobber $sp, $fp = frame-destroy LDRXpost $sp, 16 :: (load (s64) from %stack.4)
@@ -772,9 +772,9 @@ body: |
# CHECK: $sp = frame-destroy ADDXri $sp, 32, 0
# CHECK-NEXT: frame-destroy CFI_INSTRUCTION escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0x2e, 0x00, 0x1e, 0x22
-# CHECK-NEXT: $z10 = frame-destroy LDR_ZXI $sp, 0
-# CHECK-NEXT: $z9 = frame-destroy LDR_ZXI $sp, 1
# CHECK-NEXT: $z8 = frame-destroy LDR_ZXI $sp, 2
+# CHECK-NEXT: $z9 = frame-destroy LDR_ZXI $sp, 1
+# CHECK-NEXT: $z10 = frame-destroy LDR_ZXI $sp, 0
# CHECK-NEXT: $sp = frame-destroy ADDVL_XXI $sp, 3
# CHECK-NEXT: frame-destroy CFI_INSTRUCTION def_cfa $wsp, 16
# CHECK-NEXT: frame-destroy CFI_INSTRUCTION restore $z8
@@ -873,14 +873,14 @@ body: |
# CHECK-NEXT: frame-destroy CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x20, 0x22, 0x11, 0x98, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22
# CHECK: $sp = frame-destroy ADDVL_XXI $sp, 1
# CHECK-NEXT: frame-destroy CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x20, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22
-# CHECK: $p15 = frame-destroy LDR_PXI $sp, 4
-# CHECK: $p14 = frame-destroy LDR_PXI $sp, 5
-# CHECK: $p5 = frame-destroy LDR_PXI $sp, 14
-# CHECK: $p4 = frame-destroy LDR_PXI $sp, 15
-# CHECK: $z23 = frame-destroy LDR_ZXI $sp, 2
-# CHECK: $z22 = frame-destroy LDR_ZXI $sp, 3
-# CHECK: $z9 = frame-destroy LDR_ZXI $sp, 16
# CHECK: $z8 = frame-destroy LDR_ZXI $sp, 17
+# CHECK: $z9 = frame-destroy LDR_ZXI $sp, 16
+# CHECK: $z22 = frame-destroy LDR_ZXI $sp, 3
+# CHECK: $z23 = frame-destroy LDR_ZXI $sp, 2
+# CHECK: $p4 = frame-destroy LDR_PXI $sp, 15
+# CHECK: $p5 = frame-destroy LDR_PXI $sp, 14
+# CHECK: $p14 = frame-destroy LDR_PXI $sp, 5
+# CHECK: $p15 = frame-destroy LDR_PXI $sp, 4
# CHECK: $sp = frame-destroy ADDVL_XXI $sp, 18
# CHECK-NEXT: frame-destroy CFI_INSTRUCTION def_cfa $wsp, 32
# CHECK-NEXT: frame-destroy CFI_INSTRUCTION restore $z8
@@ -1037,14 +1037,14 @@ body: |
# CHECK-NEXT: $sp = frame-setup ANDXri killed $[[TMP]]
# CHECK: $sp = frame-destroy ADDVL_XXI $fp, -18
-# CHECK-NEXT: $p15 = frame-destroy LDR_PXI $sp, 4
-# CHECK-NEXT: $p14 = frame-destroy LDR_PXI $sp, 5
-# CHECK: $p5 = frame-destroy LDR_PXI $sp, 14
-# CHECK-NEXT: $p4 = frame-destroy LDR_PXI $sp, 15
+# CHECK: $z8 = frame-destroy LDR_ZXI $sp, 17
+# CHECK-NEXT: $z9 = frame-destroy LDR_ZXI $sp, 16
+# CHECK: $z22 = frame-destroy LDR_ZXI $sp, 3
# CHECK-NEXT: $z23 = frame-destroy LDR_ZXI $sp, 2
-# CHECK-NEXT: $z22 = frame-destroy LDR_ZXI $sp, 3
-# CHECK: $z9 = frame-destroy LDR_ZXI $sp, 16
-# CHECK-NEXT: $z8 = frame-destroy LDR_ZXI $sp, 17
+# CHECK-NEXT: $p4 = frame-destroy LDR_PXI $sp, 15
+# CHECK-NEXT: $p5 = frame-destroy LDR_PXI $sp, 14
+# CHECK: $p14 = frame-destroy LDR_PXI $sp, 5
+# CHECK-NEXT: $p15 = frame-destroy LDR_PXI $sp, 4
# CHECK-NEXT: frame-destroy CFI_INSTRUCTION restore $z8
# CHECK-NEXT: frame-destroy CFI_INSTRUCTION restore $z9
# CHECK-NEXT: frame-destroy CFI_INSTRUCTION restore $z10
@@ -1198,10 +1198,10 @@ body: |
# CHECK: $sp = frame-destroy ADDVL_XXI $sp, 7
# CHECK-NEXT: frame-destroy CFI_INSTRUCTION escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0x2e, 0x00, 0x1e, 0x22
-# CHECK-NEXT: $p15 = frame-destroy LDR_PXI $sp, 6
-# CHECK-NEXT: $p4 = frame-destroy LDR_PXI $sp, 7
-# CHECK-NEXT: $z23 = frame-destroy LDR_ZXI $sp, 1
# CHECK-NEXT: $z8 = frame-destroy LDR_ZXI $sp, 2
+# CHECK-NEXT: $z23 = frame-destroy LDR_ZXI $sp, 1
+# CHECK-NEXT: $p4 = frame-destroy LDR_PXI $sp, 7
+# CHECK-NEXT: $p15 = frame-destroy LDR_PXI $sp, 6
# CHECK-NEXT: $sp = frame-destroy ADDVL_XXI $sp, 3
# CHECK-NEXT: frame-destroy CFI_INSTRUCTION def_cfa $wsp, 16
# CHECK-NEXT: frame-destroy CFI_INSTRUCTION restore $z8
diff --git a/llvm/test/CodeGen/AArch64/sme-streaming-compatible-interface.ll b/llvm/test/CodeGen/AArch64/sme-streaming-compatible-interface.ll
index 5d0c9127d3ebb2..23acc57159907b 100644
--- a/llvm/test/CodeGen/AArch64/sme-streaming-compatible-interface.ll
+++ b/llvm/test/CodeGen/AArch64/sme-streaming-compatible-interface.ll
@@ -219,34 +219,34 @@ define <vscale x 2 x double> @streaming_compatible_with_scalable_vectors(<vscale
; CHECK-NEXT: ldr z1, [sp] // 16-byte Folded Reload
; CHECK-NEXT: fadd z0.d, z1.d, z0.d
; CHECK-NEXT: addvl sp, sp, #2
-; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #18
; CHECK-NEXT: ldp x30, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x29, [sp], #32 // 8-byte Folded Reload
@@ -311,34 +311,34 @@ define <vscale x 2 x i1> @streaming_compatible_with_predicate_vectors(<vscale x
; CHECK-NEXT: ldr p1, [sp, #6, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: and p0.b, p1/z, p1.b, p0.b
; CHECK-NEXT: addvl sp, sp, #1
-; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #18
; CHECK-NEXT: ldp x30, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldr x29, [sp], #32 // 8-byte Folded Reload
diff --git a/llvm/test/CodeGen/AArch64/sme-streaming-interface.ll b/llvm/test/CodeGen/AArch64/sme-streaming-interface.ll
index dd7d6470ad7b08..efb904b9bb333e 100644
--- a/llvm/test/CodeGen/AArch64/sme-streaming-interface.ll
+++ b/llvm/test/CodeGen/AArch64/sme-streaming-interface.ll
@@ -187,34 +187,34 @@ define <vscale x 4 x i32> @smstart_clobber_sve(<vscale x 4 x i32> %x) nounwind {
; CHECK-NEXT: smstop sm
; CHECK-NEXT: ldr z0, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #1
-; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #18
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -267,34 +267,34 @@ define <vscale x 4 x i32> @smstart_clobber_sve_duplicate(<vscale x 4 x i32> %x)
; CHECK-NEXT: smstop sm
; CHECK-NEXT: ldr z0, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #1
-; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #18
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
diff --git a/llvm/test/CodeGen/AArch64/sme2-intrinsics-ld1.ll b/llvm/test/CodeGen/AArch64/sme2-intrinsics-ld1.ll
index 6c94546c9525aa..5110a6360ebcff 100644
--- a/llvm/test/CodeGen/AArch64/sme2-intrinsics-ld1.ll
+++ b/llvm/test/CodeGen/AArch64/sme2-intrinsics-ld1.ll
@@ -69,17 +69,17 @@ define <vscale x 32 x i8> @ld1_x2_i8_z0_z8(<vscale x 16 x i8> %unused, <vscale x
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -109,16 +109,16 @@ define <vscale x 32 x i8> @ld1_x2_i8_z0_z8(<vscale x 16 x i8> %unused, <vscale x
; CONTIGUOUS-NEXT: ldr z0, [sp]
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -198,17 +198,17 @@ define <vscale x 32 x i8> @ld1_x2_i8_z0_z8_scalar(<vscale x 16 x i8> %unused, <v
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -238,16 +238,16 @@ define <vscale x 32 x i8> @ld1_x2_i8_z0_z8_scalar(<vscale x 16 x i8> %unused, <v
; CONTIGUOUS-NEXT: ldr z0, [sp]
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -328,17 +328,17 @@ define <vscale x 16 x i16> @ld1_x2_i16_z0_z8(<vscale x 8 x i16> %unused, <vscale
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -368,16 +368,16 @@ define <vscale x 16 x i16> @ld1_x2_i16_z0_z8(<vscale x 8 x i16> %unused, <vscale
; CONTIGUOUS-NEXT: ldr z0, [sp]
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -457,17 +457,17 @@ define <vscale x 16 x i16> @ld1_x2_i16_z0_z8_scalar(<vscale x 8 x i16> %unused,
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -497,16 +497,16 @@ define <vscale x 16 x i16> @ld1_x2_i16_z0_z8_scalar(<vscale x 8 x i16> %unused,
; CONTIGUOUS-NEXT: ldr z0, [sp]
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -587,17 +587,17 @@ define <vscale x 8 x i32> @ld1_x2_i32_z0_z8(<vscale x 4 x i32> %unused, <vscale
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -627,16 +627,16 @@ define <vscale x 8 x i32> @ld1_x2_i32_z0_z8(<vscale x 4 x i32> %unused, <vscale
; CONTIGUOUS-NEXT: ldr z0, [sp]
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -716,17 +716,17 @@ define <vscale x 8 x i32> @ld1_x2_i32_z0_z8_scalar(<vscale x 4 x i32> %unused, <
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -756,16 +756,16 @@ define <vscale x 8 x i32> @ld1_x2_i32_z0_z8_scalar(<vscale x 4 x i32> %unused, <
; CONTIGUOUS-NEXT: ldr z0, [sp]
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -846,17 +846,17 @@ define <vscale x 4 x i64> @ld1_x2_i64_z0_z8(<vscale x 2 x i64> %unused, <vscale
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -886,16 +886,16 @@ define <vscale x 4 x i64> @ld1_x2_i64_z0_z8(<vscale x 2 x i64> %unused, <vscale
; CONTIGUOUS-NEXT: ldr z0, [sp]
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -975,17 +975,17 @@ define <vscale x 4 x i64> @ld1_x2_i64_z0_z8_scalar(<vscale x 2 x i64> %unused, <
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -1015,16 +1015,16 @@ define <vscale x 4 x i64> @ld1_x2_i64_z0_z8_scalar(<vscale x 2 x i64> %unused, <
; CONTIGUOUS-NEXT: ldr z0, [sp]
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1107,18 +1107,18 @@ define <vscale x 64 x i8> @ld1_x4_i8_z0_z4_z8_z12(<vscale x 16 x i8> %unused, <v
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1153,16 +1153,16 @@ define <vscale x 64 x i8> @ld1_x4_i8_z0_z4_z8_z12(<vscale x 16 x i8> %unused, <v
; CONTIGUOUS-NEXT: ldr z2, [sp, #2, mul vl]
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1248,18 +1248,18 @@ define <vscale x 64 x i8> @ld1_x4_i8_z0_z4_z8_z12_scalar(<vscale x 16 x i8> %unu
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1294,16 +1294,16 @@ define <vscale x 64 x i8> @ld1_x4_i8_z0_z4_z8_z12_scalar(<vscale x 16 x i8> %unu
; CONTIGUOUS-NEXT: ldr z2, [sp, #2, mul vl]
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1390,18 +1390,18 @@ define <vscale x 32 x i16> @ld1_x4_i16_z0_z4_z8_z12(<vscale x 8 x i16> %unused,
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1436,16 +1436,16 @@ define <vscale x 32 x i16> @ld1_x4_i16_z0_z4_z8_z12(<vscale x 8 x i16> %unused,
; CONTIGUOUS-NEXT: ldr z2, [sp, #2, mul vl]
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1532,18 +1532,18 @@ define <vscale x 32 x i16> @ld1_x4_i16_z0_z4_z8_z12_scalar(<vscale x 8 x i16> %u
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1578,16 +1578,16 @@ define <vscale x 32 x i16> @ld1_x4_i16_z0_z4_z8_z12_scalar(<vscale x 8 x i16> %u
; CONTIGUOUS-NEXT: ldr z2, [sp, #2, mul vl]
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1674,18 +1674,18 @@ define <vscale x 16 x i32> @ld1_x4_i32_z0_z4_z8_z12(<vscale x 4 x i32> %unused,
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1720,16 +1720,16 @@ define <vscale x 16 x i32> @ld1_x4_i32_z0_z4_z8_z12(<vscale x 4 x i32> %unused,
; CONTIGUOUS-NEXT: ldr z2, [sp, #2, mul vl]
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1816,18 +1816,18 @@ define <vscale x 16 x i32> @ld1_x4_i32_z0_z4_z8_z12_scalar(<vscale x 4 x i32> %u
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1862,16 +1862,16 @@ define <vscale x 16 x i32> @ld1_x4_i32_z0_z4_z8_z12_scalar(<vscale x 4 x i32> %u
; CONTIGUOUS-NEXT: ldr z2, [sp, #2, mul vl]
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1958,18 +1958,18 @@ define <vscale x 8 x i64> @ld1_x4_i64_z0_z4_z8_z12(<vscale x 2 x i64> %unused, <
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -2004,16 +2004,16 @@ define <vscale x 8 x i64> @ld1_x4_i64_z0_z4_z8_z12(<vscale x 2 x i64> %unused, <
; CONTIGUOUS-NEXT: ldr z2, [sp, #2, mul vl]
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -2100,18 +2100,18 @@ define <vscale x 8 x i64> @ld1_x4_i64_z0_z4_z8_z12_scalar(<vscale x 2 x i64> %un
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -2146,16 +2146,16 @@ define <vscale x 8 x i64> @ld1_x4_i64_z0_z4_z8_z12_scalar(<vscale x 2 x i64> %un
; CONTIGUOUS-NEXT: ldr z2, [sp, #2, mul vl]
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
diff --git a/llvm/test/CodeGen/AArch64/sme2-intrinsics-ldnt1.ll b/llvm/test/CodeGen/AArch64/sme2-intrinsics-ldnt1.ll
index 1df619a40ef3fa..4db6b3db7bd0b8 100644
--- a/llvm/test/CodeGen/AArch64/sme2-intrinsics-ldnt1.ll
+++ b/llvm/test/CodeGen/AArch64/sme2-intrinsics-ldnt1.ll
@@ -22,17 +22,17 @@ define <vscale x 32 x i8> @ldnt1_x2_i8_z0_z8(<vscale x 16 x i8> %unused, <vscale
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -62,16 +62,16 @@ define <vscale x 32 x i8> @ldnt1_x2_i8_z0_z8(<vscale x 16 x i8> %unused, <vscale
; CONTIGUOUS-NEXT: ldr z0, [sp]
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -104,17 +104,17 @@ define <vscale x 32 x i8> @ldnt1_x2_i8_z0_z8_scalar(<vscale x 16 x i8> %unused,
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -144,16 +144,16 @@ define <vscale x 32 x i8> @ldnt1_x2_i8_z0_z8_scalar(<vscale x 16 x i8> %unused,
; CONTIGUOUS-NEXT: ldr z0, [sp]
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -187,17 +187,17 @@ define <vscale x 16 x i16> @ldnt1_x2_i16_z0_z8(<vscale x 8 x i16> %unused, <vsca
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -227,16 +227,16 @@ define <vscale x 16 x i16> @ldnt1_x2_i16_z0_z8(<vscale x 8 x i16> %unused, <vsca
; CONTIGUOUS-NEXT: ldr z0, [sp]
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -269,17 +269,17 @@ define <vscale x 16 x i16> @ldnt1_x2_i16_z0_z8_scalar(<vscale x 8 x i16> %unused
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -309,16 +309,16 @@ define <vscale x 16 x i16> @ldnt1_x2_i16_z0_z8_scalar(<vscale x 8 x i16> %unused
; CONTIGUOUS-NEXT: ldr z0, [sp]
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -352,17 +352,17 @@ define <vscale x 8 x i32> @ldnt1_x2_i32_z0_z8(<vscale x 4 x i32> %unused, <vscal
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -392,16 +392,16 @@ define <vscale x 8 x i32> @ldnt1_x2_i32_z0_z8(<vscale x 4 x i32> %unused, <vscal
; CONTIGUOUS-NEXT: ldr z0, [sp]
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -434,17 +434,17 @@ define <vscale x 8 x i32> @ldnt1_x2_i32_z0_z8_scalar(<vscale x 4 x i32> %unused,
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -474,16 +474,16 @@ define <vscale x 8 x i32> @ldnt1_x2_i32_z0_z8_scalar(<vscale x 4 x i32> %unused,
; CONTIGUOUS-NEXT: ldr z0, [sp]
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -517,17 +517,17 @@ define <vscale x 4 x i64> @ldnt1_x2_i64_z0_z8(<vscale x 2 x i64> %unused, <vscal
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -557,16 +557,16 @@ define <vscale x 4 x i64> @ldnt1_x2_i64_z0_z8(<vscale x 2 x i64> %unused, <vscal
; CONTIGUOUS-NEXT: ldr z0, [sp]
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -599,17 +599,17 @@ define <vscale x 4 x i64> @ldnt1_x2_i64_z0_z8_scalar(<vscale x 2 x i64> %unused,
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z8.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; STRIDED-NEXT: ret
@@ -639,16 +639,16 @@ define <vscale x 4 x i64> @ldnt1_x2_i64_z0_z8_scalar(<vscale x 2 x i64> %unused,
; CONTIGUOUS-NEXT: ldr z0, [sp]
; CONTIGUOUS-NEXT: ldr z1, [sp, #1, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #2
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #16
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -682,18 +682,18 @@ define <vscale x 64 x i8> @ldnt1_x4_i8_z0_z4_z8_z12(<vscale x 16 x i8> %unused,
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -728,16 +728,16 @@ define <vscale x 64 x i8> @ldnt1_x4_i8_z0_z4_z8_z12(<vscale x 16 x i8> %unused,
; CONTIGUOUS-NEXT: ldr z2, [sp, #2, mul vl]
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -774,18 +774,18 @@ define <vscale x 64 x i8> @ldnt1_x4_i8_z0_z4_z8_z12_scalar(<vscale x 16 x i8> %u
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -820,16 +820,16 @@ define <vscale x 64 x i8> @ldnt1_x4_i8_z0_z4_z8_z12_scalar(<vscale x 16 x i8> %u
; CONTIGUOUS-NEXT: ldr z2, [sp, #2, mul vl]
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -867,18 +867,18 @@ define <vscale x 32 x i16> @ldnt1_x4_i16_z0_z4_z8_z12(<vscale x 8 x i16> %unused
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -913,16 +913,16 @@ define <vscale x 32 x i16> @ldnt1_x4_i16_z0_z4_z8_z12(<vscale x 8 x i16> %unused
; CONTIGUOUS-NEXT: ldr z2, [sp, #2, mul vl]
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -959,18 +959,18 @@ define <vscale x 32 x i16> @ldnt1_x4_i16_z0_z4_z8_z12_scalar(<vscale x 8 x i16>
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1005,16 +1005,16 @@ define <vscale x 32 x i16> @ldnt1_x4_i16_z0_z4_z8_z12_scalar(<vscale x 8 x i16>
; CONTIGUOUS-NEXT: ldr z2, [sp, #2, mul vl]
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1052,18 +1052,18 @@ define <vscale x 16 x i32> @ldnt1_x4_i32_z0_z4_z8_z12(<vscale x 4 x i32> %unused
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1098,16 +1098,16 @@ define <vscale x 16 x i32> @ldnt1_x4_i32_z0_z4_z8_z12(<vscale x 4 x i32> %unused
; CONTIGUOUS-NEXT: ldr z2, [sp, #2, mul vl]
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1144,18 +1144,18 @@ define <vscale x 16 x i32> @ldnt1_x4_i32_z0_z4_z8_z12_scalar(<vscale x 4 x i32>
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1190,16 +1190,16 @@ define <vscale x 16 x i32> @ldnt1_x4_i32_z0_z4_z8_z12_scalar(<vscale x 4 x i32>
; CONTIGUOUS-NEXT: ldr z2, [sp, #2, mul vl]
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1237,18 +1237,18 @@ define <vscale x 8 x i64> @ldnt1_x4_i64_z0_z4_z8_z12(<vscale x 2 x i64> %unused,
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1283,16 +1283,16 @@ define <vscale x 8 x i64> @ldnt1_x4_i64_z0_z4_z8_z12(<vscale x 2 x i64> %unused,
; CONTIGUOUS-NEXT: ldr z2, [sp, #2, mul vl]
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
@@ -1329,18 +1329,18 @@ define <vscale x 8 x i64> @ldnt1_x4_i64_z0_z4_z8_z12_scalar(<vscale x 2 x i64> %
; STRIDED-NEXT: //APP
; STRIDED-NEXT: nop
; STRIDED-NEXT: //NO_APP
-; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: ptrue pn8.b
-; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: mov z2.d, z8.d
; STRIDED-NEXT: mov z3.d, z12.d
-; STRIDED-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
-; STRIDED-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
; STRIDED-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #30, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #22, mul vl] // 32-byte Folded Reload
+; STRIDED-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; STRIDED-NEXT: mov z1.d, z4.d
; STRIDED-NEXT: addvl sp, sp, #17
; STRIDED-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1375,16 +1375,16 @@ define <vscale x 8 x i64> @ldnt1_x4_i64_z0_z4_z8_z12_scalar(<vscale x 2 x i64> %
; CONTIGUOUS-NEXT: ldr z2, [sp, #2, mul vl]
; CONTIGUOUS-NEXT: ldr z3, [sp, #3, mul vl]
; CONTIGUOUS-NEXT: addvl sp, sp, #4
-; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ptrue pn8.b
-; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
-; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
; CONTIGUOUS-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #18, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #14, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #10, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #6, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
+; CONTIGUOUS-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CONTIGUOUS-NEXT: addvl sp, sp, #15
; CONTIGUOUS-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CONTIGUOUS-NEXT: ret
diff --git a/llvm/test/CodeGen/AArch64/stack-probing-sve.ll b/llvm/test/CodeGen/AArch64/stack-probing-sve.ll
index 03a9220ebfddc6..9f76cbb8912b44 100644
--- a/llvm/test/CodeGen/AArch64/stack-probing-sve.ll
+++ b/llvm/test/CodeGen/AArch64/stack-probing-sve.ll
@@ -191,10 +191,10 @@ define void @sve_4v_csr(<vscale x 4 x float> %a) #0 {
; CHECK-NEXT: .cfi_escape 0x10, 0x4b, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x60, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d11 @ cfa - 16 - 32 * VG
; CHECK-NEXT: //APP
; CHECK-NEXT: //NO_APP
-; CHECK-NEXT: ldr z11, [sp] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #4
; CHECK-NEXT: .cfi_def_cfa wsp, 16
; CHECK-NEXT: .cfi_restore z8
@@ -245,22 +245,22 @@ define void @sve_16v_csr(<vscale x 4 x float> %a) #0 {
; CHECK-NEXT: .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 16 - 64 * VG
; CHECK-NEXT: //APP
; CHECK-NEXT: //NO_APP
-; CHECK-NEXT: ldr z23, [sp] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z22, [sp, #1, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z21, [sp, #2, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z20, [sp, #3, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z19, [sp, #4, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z18, [sp, #5, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z17, [sp, #6, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z16, [sp, #7, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z15, [sp, #8, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z14, [sp, #9, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z13, [sp, #10, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z12, [sp, #11, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z12, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z13, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z14, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z15, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z16, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z17, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z18, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z19, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z20, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z21, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z22, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z23, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #16
; CHECK-NEXT: .cfi_def_cfa wsp, 16
; CHECK-NEXT: .cfi_restore z8
@@ -317,10 +317,10 @@ define void @sve_4p_csr(<vscale x 4 x float> %a) #0 {
; CHECK-NEXT: str p8, [sp, #7, mul vl] // 2-byte Folded Spill
; CHECK-NEXT: //APP
; CHECK-NEXT: //NO_APP
-; CHECK-NEXT: ldr p11, [sp, #4, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p10, [sp, #5, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p9, [sp, #6, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p9, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p10, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p11, [sp, #4, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #1
; CHECK-NEXT: .cfi_def_cfa wsp, 16
; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -380,23 +380,23 @@ define void @sve_16v_1p_csr(<vscale x 4 x float> %a) #0 {
; CHECK-NEXT: .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 16 - 64 * VG
; CHECK-NEXT: //APP
; CHECK-NEXT: //NO_APP
-; CHECK-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #16, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z12, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z13, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z14, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z15, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z16, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z17, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z18, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z19, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z20, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z21, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z22, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z23, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #17
; CHECK-NEXT: .cfi_def_cfa wsp, 16
; CHECK-NEXT: .cfi_restore z8
@@ -697,10 +697,10 @@ define void @sve_unprobed_area(<vscale x 4 x float> %a, i32 %n) #0 {
; CHECK-NEXT: //NO_APP
; CHECK-NEXT: addvl sp, sp, #4
; CHECK-NEXT: .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 32 * VG
-; CHECK-NEXT: ldr p9, [sp, #7, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr p9, [sp, #7, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #4
; CHECK-NEXT: .cfi_def_cfa wsp, 16
; CHECK-NEXT: .cfi_restore z8
diff --git a/llvm/test/CodeGen/AArch64/sve-alloca.ll b/llvm/test/CodeGen/AArch64/sve-alloca.ll
index 209c6198fe575e..d2087f0de07440 100644
--- a/llvm/test/CodeGen/AArch64/sve-alloca.ll
+++ b/llvm/test/CodeGen/AArch64/sve-alloca.ll
@@ -66,34 +66,34 @@ define void @foo(<vscale x 4 x i64> %dst, i1 %cond) {
; CHECK-NEXT: st1d { z0.d }, p0, [x0]
; CHECK-NEXT: bl bar
; CHECK-NEXT: addvl sp, x29, #-18
-; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: mov sp, x29
; CHECK-NEXT: ldp x28, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldp x29, x30, [sp], #32 // 16-byte Folded Reload
diff --git a/llvm/test/CodeGen/AArch64/sve-breakdown-scalable-vectortype.ll b/llvm/test/CodeGen/AArch64/sve-breakdown-scalable-vectortype.ll
index 5b69b68552a4d7..f2247ac11608e9 100644
--- a/llvm/test/CodeGen/AArch64/sve-breakdown-scalable-vectortype.ll
+++ b/llvm/test/CodeGen/AArch64/sve-breakdown-scalable-vectortype.ll
@@ -25,8 +25,8 @@ define <vscale x 32 x i8> @wide_32i8(i1 %b, <vscale x 16 x i8> %legal, <vscale x
; CHECK-NEXT: .LBB0_2: // %common.ret
; CHECK-NEXT: mov z0.d, z9.d
; CHECK-NEXT: mov z1.d, z8.d
-; CHECK-NEXT: ldr z9, [sp] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #2
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -53,8 +53,8 @@ define <vscale x 16 x i16> @wide_16i16(i1 %b, <vscale x 16 x i8> %legal, <vscale
; CHECK-NEXT: .LBB1_2: // %common.ret
; CHECK-NEXT: mov z0.d, z9.d
; CHECK-NEXT: mov z1.d, z8.d
-; CHECK-NEXT: ldr z9, [sp] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #2
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -81,8 +81,8 @@ define <vscale x 8 x i32> @wide_8i32(i1 %b, <vscale x 16 x i8> %legal, <vscale x
; CHECK-NEXT: .LBB2_2: // %common.ret
; CHECK-NEXT: mov z0.d, z9.d
; CHECK-NEXT: mov z1.d, z8.d
-; CHECK-NEXT: ldr z9, [sp] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #2
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -109,8 +109,8 @@ define <vscale x 4 x i64> @wide_4i64(i1 %b, <vscale x 16 x i8> %legal, <vscale x
; CHECK-NEXT: .LBB3_2: // %common.ret
; CHECK-NEXT: mov z0.d, z9.d
; CHECK-NEXT: mov z1.d, z8.d
-; CHECK-NEXT: ldr z9, [sp] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #2
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -137,8 +137,8 @@ define <vscale x 16 x half> @wide_16f16(i1 %b, <vscale x 16 x i8> %legal, <vscal
; CHECK-NEXT: .LBB4_2: // %common.ret
; CHECK-NEXT: mov z0.d, z9.d
; CHECK-NEXT: mov z1.d, z8.d
-; CHECK-NEXT: ldr z9, [sp] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #2
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -165,8 +165,8 @@ define <vscale x 8 x float> @wide_8f32(i1 %b, <vscale x 16 x i8> %legal, <vscale
; CHECK-NEXT: .LBB5_2: // %common.ret
; CHECK-NEXT: mov z0.d, z9.d
; CHECK-NEXT: mov z1.d, z8.d
-; CHECK-NEXT: ldr z9, [sp] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #2
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -193,8 +193,8 @@ define <vscale x 4 x double> @wide_4f64(i1 %b, <vscale x 16 x i8> %legal, <vscal
; CHECK-NEXT: .LBB6_2: // %common.ret
; CHECK-NEXT: mov z0.d, z9.d
; CHECK-NEXT: mov z1.d, z8.d
-; CHECK-NEXT: ldr z9, [sp] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #2
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -227,10 +227,10 @@ define <vscale x 48 x i8> @wide_48i8(i1 %b, <vscale x 16 x i8> %legal, <vscale x
; CHECK-NEXT: .LBB7_2: // %common.ret
; CHECK-NEXT: mov z0.d, z10.d
; CHECK-NEXT: mov z1.d, z9.d
-; CHECK-NEXT: ldr z10, [sp] // 16-byte Folded Reload
-; CHECK-NEXT: mov z2.d, z8.d
; CHECK-NEXT: ldr z9, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: mov z2.d, z8.d
; CHECK-NEXT: ldr z8, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #3
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -259,10 +259,10 @@ define <vscale x 24 x i16> @wide_24i16(i1 %b, <vscale x 16 x i8> %legal, <vscale
; CHECK-NEXT: .LBB8_2: // %common.ret
; CHECK-NEXT: mov z0.d, z10.d
; CHECK-NEXT: mov z1.d, z9.d
-; CHECK-NEXT: ldr z10, [sp] // 16-byte Folded Reload
-; CHECK-NEXT: mov z2.d, z8.d
; CHECK-NEXT: ldr z9, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: mov z2.d, z8.d
; CHECK-NEXT: ldr z8, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #3
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -291,10 +291,10 @@ define <vscale x 12 x i32> @wide_12i32(i1 %b, <vscale x 16 x i8> %legal, <vscale
; CHECK-NEXT: .LBB9_2: // %common.ret
; CHECK-NEXT: mov z0.d, z10.d
; CHECK-NEXT: mov z1.d, z9.d
-; CHECK-NEXT: ldr z10, [sp] // 16-byte Folded Reload
-; CHECK-NEXT: mov z2.d, z8.d
; CHECK-NEXT: ldr z9, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: mov z2.d, z8.d
; CHECK-NEXT: ldr z8, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #3
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -323,10 +323,10 @@ define <vscale x 6 x i64> @wide_6i64(i1 %b, <vscale x 16 x i8> %legal, <vscale x
; CHECK-NEXT: .LBB10_2: // %common.ret
; CHECK-NEXT: mov z0.d, z10.d
; CHECK-NEXT: mov z1.d, z9.d
-; CHECK-NEXT: ldr z10, [sp] // 16-byte Folded Reload
-; CHECK-NEXT: mov z2.d, z8.d
; CHECK-NEXT: ldr z9, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: mov z2.d, z8.d
; CHECK-NEXT: ldr z8, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #3
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -355,10 +355,10 @@ define <vscale x 24 x half> @wide_24f16(i1 %b, <vscale x 16 x i8> %legal, <vscal
; CHECK-NEXT: .LBB11_2: // %common.ret
; CHECK-NEXT: mov z0.d, z10.d
; CHECK-NEXT: mov z1.d, z9.d
-; CHECK-NEXT: ldr z10, [sp] // 16-byte Folded Reload
-; CHECK-NEXT: mov z2.d, z8.d
; CHECK-NEXT: ldr z9, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: mov z2.d, z8.d
; CHECK-NEXT: ldr z8, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #3
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -387,10 +387,10 @@ define <vscale x 12 x float> @wide_12f32(i1 %b, <vscale x 16 x i8> %legal, <vsca
; CHECK-NEXT: .LBB12_2: // %common.ret
; CHECK-NEXT: mov z0.d, z10.d
; CHECK-NEXT: mov z1.d, z9.d
-; CHECK-NEXT: ldr z10, [sp] // 16-byte Folded Reload
-; CHECK-NEXT: mov z2.d, z8.d
; CHECK-NEXT: ldr z9, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: mov z2.d, z8.d
; CHECK-NEXT: ldr z8, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #3
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -419,10 +419,10 @@ define <vscale x 6 x double> @wide_6f64(i1 %b, <vscale x 16 x i8> %legal, <vscal
; CHECK-NEXT: .LBB13_2: // %common.ret
; CHECK-NEXT: mov z0.d, z10.d
; CHECK-NEXT: mov z1.d, z9.d
-; CHECK-NEXT: ldr z10, [sp] // 16-byte Folded Reload
-; CHECK-NEXT: mov z2.d, z8.d
; CHECK-NEXT: ldr z9, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: mov z2.d, z8.d
; CHECK-NEXT: ldr z8, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #3
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -457,12 +457,12 @@ define <vscale x 64 x i8> @wide_64i8(i1 %b, <vscale x 16 x i8> %legal, <vscale x
; CHECK-NEXT: .LBB14_2: // %common.ret
; CHECK-NEXT: mov z0.d, z11.d
; CHECK-NEXT: mov z1.d, z10.d
-; CHECK-NEXT: ldr z11, [sp] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: mov z2.d, z9.d
; CHECK-NEXT: mov z3.d, z8.d
-; CHECK-NEXT: ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #4
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -493,12 +493,12 @@ define <vscale x 32 x i16> @wide_32i16(i1 %b, <vscale x 16 x i8> %legal, <vscale
; CHECK-NEXT: .LBB15_2: // %common.ret
; CHECK-NEXT: mov z0.d, z11.d
; CHECK-NEXT: mov z1.d, z10.d
-; CHECK-NEXT: ldr z11, [sp] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: mov z2.d, z9.d
; CHECK-NEXT: mov z3.d, z8.d
-; CHECK-NEXT: ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #4
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -529,12 +529,12 @@ define <vscale x 16 x i32> @wide_16i32(i1 %b, <vscale x 16 x i8> %legal, <vscale
; CHECK-NEXT: .LBB16_2: // %common.ret
; CHECK-NEXT: mov z0.d, z11.d
; CHECK-NEXT: mov z1.d, z10.d
-; CHECK-NEXT: ldr z11, [sp] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: mov z2.d, z9.d
; CHECK-NEXT: mov z3.d, z8.d
-; CHECK-NEXT: ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #4
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -565,12 +565,12 @@ define <vscale x 8 x i64> @wide_8i64(i1 %b, <vscale x 16 x i8> %legal, <vscale x
; CHECK-NEXT: .LBB17_2: // %common.ret
; CHECK-NEXT: mov z0.d, z11.d
; CHECK-NEXT: mov z1.d, z10.d
-; CHECK-NEXT: ldr z11, [sp] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: mov z2.d, z9.d
; CHECK-NEXT: mov z3.d, z8.d
-; CHECK-NEXT: ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #4
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -601,12 +601,12 @@ define <vscale x 32 x half> @wide_32f16(i1 %b, <vscale x 16 x i8> %legal, <vscal
; CHECK-NEXT: .LBB18_2: // %common.ret
; CHECK-NEXT: mov z0.d, z11.d
; CHECK-NEXT: mov z1.d, z10.d
-; CHECK-NEXT: ldr z11, [sp] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: mov z2.d, z9.d
; CHECK-NEXT: mov z3.d, z8.d
-; CHECK-NEXT: ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #4
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -637,12 +637,12 @@ define <vscale x 16 x float> @wide_16f32(i1 %b, <vscale x 16 x i8> %legal, <vsca
; CHECK-NEXT: .LBB19_2: // %common.ret
; CHECK-NEXT: mov z0.d, z11.d
; CHECK-NEXT: mov z1.d, z10.d
-; CHECK-NEXT: ldr z11, [sp] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: mov z2.d, z9.d
; CHECK-NEXT: mov z3.d, z8.d
-; CHECK-NEXT: ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #4
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -673,12 +673,12 @@ define <vscale x 8 x double> @wide_8f64(i1 %b, <vscale x 16 x i8> %legal, <vscal
; CHECK-NEXT: .LBB20_2: // %common.ret
; CHECK-NEXT: mov z0.d, z11.d
; CHECK-NEXT: mov z1.d, z10.d
-; CHECK-NEXT: ldr z11, [sp] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: mov z2.d, z9.d
; CHECK-NEXT: mov z3.d, z8.d
-; CHECK-NEXT: ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #4
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
diff --git a/llvm/test/CodeGen/AArch64/sve-callee-save-restore-pairs.ll b/llvm/test/CodeGen/AArch64/sve-callee-save-restore-pairs.ll
new file mode 100644
index 00000000000000..76aeda125fe40e
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/sve-callee-save-restore-pairs.ll
@@ -0,0 +1,295 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sme -verify-machineinstrs < %s | FileCheck %s --check-prefixes=NOPAIR
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=NOPAIR
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sme2 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=PAIR
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2p1 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=PAIR
+
+
+declare void @my_func()
+
+define void @fbyte(<vscale x 16 x i8> %v) {
+; NOPAIR-LABEL: fbyte:
+; NOPAIR: // %bb.0:
+; NOPAIR-NEXT: stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
+; NOPAIR-NEXT: addvl sp, sp, #-18
+; NOPAIR-NEXT: str p15, [sp, #4, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p14, [sp, #5, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p13, [sp, #6, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p12, [sp, #7, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p11, [sp, #8, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p10, [sp, #9, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p9, [sp, #10, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p8, [sp, #11, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p7, [sp, #12, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p6, [sp, #13, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p5, [sp, #14, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p4, [sp, #15, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str z23, [sp, #2, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z22, [sp, #3, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z21, [sp, #4, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z20, [sp, #5, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z19, [sp, #6, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z18, [sp, #7, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z17, [sp, #8, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z16, [sp, #9, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z15, [sp, #10, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z14, [sp, #11, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z13, [sp, #12, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z12, [sp, #13, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z11, [sp, #14, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z10, [sp, #15, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z9, [sp, #16, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z8, [sp, #17, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 144 * VG
+; NOPAIR-NEXT: .cfi_offset w30, -8
+; NOPAIR-NEXT: .cfi_offset w29, -16
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x48, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 16 - 8 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x49, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 16 - 16 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 16 - 24 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4b, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x60, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d11 @ cfa - 16 - 32 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4c, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x58, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d12 @ cfa - 16 - 40 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4d, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x50, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d13 @ cfa - 16 - 48 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 16 - 56 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 16 - 64 * VG
+; NOPAIR-NEXT: bl my_func
+; NOPAIR-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: addvl sp, sp, #18
+; NOPAIR-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; NOPAIR-NEXT: ret
+;
+; PAIR-LABEL: fbyte:
+; PAIR: // %bb.0:
+; PAIR-NEXT: stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
+; PAIR-NEXT: addvl sp, sp, #-18
+; PAIR-NEXT: str p8, [sp, #11, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: ptrue pn8.b
+; PAIR-NEXT: str p15, [sp, #4, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #4, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #8, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: str p14, [sp, #5, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #12, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #16, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: str p13, [sp, #6, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #20, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: str p12, [sp, #7, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #28, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: str p11, [sp, #8, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p10, [sp, #9, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p9, [sp, #10, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p7, [sp, #12, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p6, [sp, #13, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p5, [sp, #14, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p4, [sp, #15, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #32, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 144 * VG
+; PAIR-NEXT: .cfi_offset w30, -8
+; PAIR-NEXT: .cfi_offset w29, -16
+; PAIR-NEXT: .cfi_escape 0x10, 0x48, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 16 - 8 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x49, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 16 - 16 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 16 - 24 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4b, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x60, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d11 @ cfa - 16 - 32 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4c, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x58, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d12 @ cfa - 16 - 40 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4d, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x50, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d13 @ cfa - 16 - 48 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 16 - 56 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 16 - 64 * VG
+; PAIR-NEXT: bl my_func
+; PAIR-NEXT: ptrue pn8.b
+; PAIR-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #32, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #28, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #20, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #16, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #12, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #8, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #4, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: addvl sp, sp, #18
+; PAIR-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; PAIR-NEXT: ret
+ call void @my_func()
+ ret void
+}
+
+define void @fhalf(<vscale x 8 x half> %v) {
+; NOPAIR-LABEL: fhalf:
+; NOPAIR: // %bb.0:
+; NOPAIR-NEXT: stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
+; NOPAIR-NEXT: addvl sp, sp, #-18
+; NOPAIR-NEXT: str p15, [sp, #4, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p14, [sp, #5, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p13, [sp, #6, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p12, [sp, #7, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p11, [sp, #8, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p10, [sp, #9, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p9, [sp, #10, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p8, [sp, #11, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p7, [sp, #12, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p6, [sp, #13, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p5, [sp, #14, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str p4, [sp, #15, mul vl] // 2-byte Folded Spill
+; NOPAIR-NEXT: str z23, [sp, #2, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z22, [sp, #3, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z21, [sp, #4, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z20, [sp, #5, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z19, [sp, #6, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z18, [sp, #7, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z17, [sp, #8, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z16, [sp, #9, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z15, [sp, #10, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z14, [sp, #11, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z13, [sp, #12, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z12, [sp, #13, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z11, [sp, #14, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z10, [sp, #15, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z9, [sp, #16, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: str z8, [sp, #17, mul vl] // 16-byte Folded Spill
+; NOPAIR-NEXT: .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 144 * VG
+; NOPAIR-NEXT: .cfi_offset w30, -8
+; NOPAIR-NEXT: .cfi_offset w29, -16
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x48, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 16 - 8 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x49, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 16 - 16 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 16 - 24 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4b, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x60, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d11 @ cfa - 16 - 32 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4c, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x58, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d12 @ cfa - 16 - 40 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4d, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x50, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d13 @ cfa - 16 - 48 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 16 - 56 * VG
+; NOPAIR-NEXT: .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 16 - 64 * VG
+; NOPAIR-NEXT: bl my_func
+; NOPAIR-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: addvl sp, sp, #18
+; NOPAIR-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; NOPAIR-NEXT: ret
+;
+; PAIR-LABEL: fhalf:
+; PAIR: // %bb.0:
+; PAIR-NEXT: stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
+; PAIR-NEXT: addvl sp, sp, #-18
+; PAIR-NEXT: str p8, [sp, #11, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: ptrue pn8.b
+; PAIR-NEXT: str p15, [sp, #4, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z22.b, z23.b }, pn8, [sp, #4, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: st1b { z20.b, z21.b }, pn8, [sp, #8, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: str p14, [sp, #5, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z18.b, z19.b }, pn8, [sp, #12, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: st1b { z16.b, z17.b }, pn8, [sp, #16, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: str p13, [sp, #6, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z14.b, z15.b }, pn8, [sp, #20, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: st1b { z12.b, z13.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: str p12, [sp, #7, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z10.b, z11.b }, pn8, [sp, #28, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: str p11, [sp, #8, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p10, [sp, #9, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p9, [sp, #10, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p7, [sp, #12, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p6, [sp, #13, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p5, [sp, #14, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: str p4, [sp, #15, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT: st1b { z8.b, z9.b }, pn8, [sp, #32, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT: .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 144 * VG
+; PAIR-NEXT: .cfi_offset w30, -8
+; PAIR-NEXT: .cfi_offset w29, -16
+; PAIR-NEXT: .cfi_escape 0x10, 0x48, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 16 - 8 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x49, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 16 - 16 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 16 - 24 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4b, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x60, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d11 @ cfa - 16 - 32 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4c, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x58, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d12 @ cfa - 16 - 40 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4d, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x50, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d13 @ cfa - 16 - 48 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 16 - 56 * VG
+; PAIR-NEXT: .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 16 - 64 * VG
+; PAIR-NEXT: bl my_func
+; PAIR-NEXT: ptrue pn8.b
+; PAIR-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #32, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #28, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #20, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #16, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #12, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #8, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #4, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: addvl sp, sp, #18
+; PAIR-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; PAIR-NEXT: ret
+ call void @my_func()
+ ret void
+}
+
+
+
diff --git a/llvm/test/CodeGen/AArch64/sve-calling-convention-mixed.ll b/llvm/test/CodeGen/AArch64/sve-calling-convention-mixed.ll
index 783878fe738068..4e3b88bccae521 100644
--- a/llvm/test/CodeGen/AArch64/sve-calling-convention-mixed.ll
+++ b/llvm/test/CodeGen/AArch64/sve-calling-convention-mixed.ll
@@ -567,34 +567,34 @@ define <vscale x 4 x float> @sve_caller_non_sve_callee_high_range(<vscale x 4 x
; CHECK-NEXT: bl non_sve_callee_high_range
; CHECK-NEXT: ldr z0, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #3
-; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #18
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -659,34 +659,34 @@ define <vscale x 4 x float> @sve_ret_caller_non_sve_callee_high_range() {
; CHECK-NEXT: fmov s7, #7.00000000
; CHECK-NEXT: bl non_sve_callee_high_range
; CHECK-NEXT: addvl sp, sp, #2
-; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #18
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
diff --git a/llvm/test/CodeGen/AArch64/sve-fptosi-sat.ll b/llvm/test/CodeGen/AArch64/sve-fptosi-sat.ll
index 43113df07c079f..50d38e1777951b 100644
--- a/llvm/test/CodeGen/AArch64/sve-fptosi-sat.ll
+++ b/llvm/test/CodeGen/AArch64/sve-fptosi-sat.ll
@@ -360,11 +360,11 @@ define <vscale x 8 x i32> @test_signed_v8f64_v8i32(<vscale x 8 x double> %f) {
; CHECK-NEXT: fcmuo p0.d, p0/z, z2.d, z2.d
; CHECK-NEXT: sel z0.d, p5, z26.d, z6.d
; CHECK-NEXT: sel z1.d, p6, z26.d, z5.d
-; CHECK-NEXT: ldr p6, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: sel z2.d, p7, z26.d, z7.d
-; CHECK-NEXT: ldr p7, [sp, #4, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p6, [sp, #5, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: sel z3.d, p1, z26.d, z4.d
-; CHECK-NEXT: ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p7, [sp, #4, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: mov z0.d, p2/m, #0 // =0x0
; CHECK-NEXT: mov z1.d, p3/m, #0 // =0x0
; CHECK-NEXT: mov z2.d, p4/m, #0 // =0x0
@@ -469,11 +469,11 @@ define <vscale x 8 x i16> @test_signed_v8f64_v8i16(<vscale x 8 x double> %f) {
; CHECK-NEXT: fcmuo p0.d, p0/z, z0.d, z0.d
; CHECK-NEXT: sel z2.d, p5, z25.d, z5.d
; CHECK-NEXT: sel z0.d, p6, z25.d, z6.d
-; CHECK-NEXT: ldr p6, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: sel z1.d, p7, z25.d, z7.d
-; CHECK-NEXT: ldr p7, [sp, #4, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p6, [sp, #5, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: sel z3.d, p1, z25.d, z24.d
-; CHECK-NEXT: ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p7, [sp, #4, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: mov z2.d, p2/m, #0 // =0x0
; CHECK-NEXT: mov z0.d, p3/m, #0 // =0x0
; CHECK-NEXT: mov z1.d, p4/m, #0 // =0x0
diff --git a/llvm/test/CodeGen/AArch64/sve-fptoui-sat.ll b/llvm/test/CodeGen/AArch64/sve-fptoui-sat.ll
index c9e06fd9f3414e..51ea661840dfa4 100644
--- a/llvm/test/CodeGen/AArch64/sve-fptoui-sat.ll
+++ b/llvm/test/CodeGen/AArch64/sve-fptoui-sat.ll
@@ -268,11 +268,11 @@ define <vscale x 8 x i32> @test_signed_v8f64_v8i32(<vscale x 8 x double> %f) {
; CHECK-NEXT: mov z7.d, p3/m, #0 // =0x0
; CHECK-NEXT: mov z24.d, p4/m, #0 // =0x0
; CHECK-NEXT: sel z1.d, p5, z0.d, z5.d
-; CHECK-NEXT: ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: sel z2.d, p6, z0.d, z6.d
-; CHECK-NEXT: ldr p6, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: sel z3.d, p1, z0.d, z7.d
-; CHECK-NEXT: ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p6, [sp, #5, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: sel z4.d, p0, z0.d, z24.d
; CHECK-NEXT: uzp1 z0.s, z2.s, z1.s
; CHECK-NEXT: uzp1 z1.s, z4.s, z3.s
@@ -351,11 +351,11 @@ define <vscale x 8 x i16> @test_signed_v8f64_v8i16(<vscale x 8 x double> %f) {
; CHECK-NEXT: mov z7.d, p3/m, #0 // =0x0
; CHECK-NEXT: mov z24.d, p4/m, #0 // =0x0
; CHECK-NEXT: sel z0.d, p5, z2.d, z5.d
-; CHECK-NEXT: ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: sel z1.d, p6, z2.d, z6.d
-; CHECK-NEXT: ldr p6, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: sel z3.d, p1, z2.d, z7.d
-; CHECK-NEXT: ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p6, [sp, #5, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: sel z2.d, p0, z2.d, z24.d
; CHECK-NEXT: uzp1 z0.s, z1.s, z0.s
; CHECK-NEXT: uzp1 z1.s, z2.s, z3.s
diff --git a/llvm/test/CodeGen/AArch64/sve-pred-arith.ll b/llvm/test/CodeGen/AArch64/sve-pred-arith.ll
index 4d46ac5ecbaa95..536d03cce31825 100644
--- a/llvm/test/CodeGen/AArch64/sve-pred-arith.ll
+++ b/llvm/test/CodeGen/AArch64/sve-pred-arith.ll
@@ -66,13 +66,13 @@ define aarch64_sve_vector_pcs <vscale x 64 x i1> @add_nxv64i1(<vscale x 64 x i1>
; CHECK-NEXT: ldr p8, [x3]
; CHECK-NEXT: eor p0.b, p4/z, p0.b, p5.b
; CHECK-NEXT: eor p1.b, p4/z, p1.b, p6.b
-; CHECK-NEXT: ldr p6, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: eor p2.b, p4/z, p2.b, p7.b
-; CHECK-NEXT: ldr p7, [sp, #4, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p6, [sp, #5, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: eor p3.b, p4/z, p3.b, p8.b
-; CHECK-NEXT: ldr p8, [sp, #3, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p7, [sp, #4, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p8, [sp, #3, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #1
; CHECK-NEXT: .cfi_def_cfa wsp, 16
; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -150,13 +150,13 @@ define aarch64_sve_vector_pcs <vscale x 64 x i1> @sub_nxv64i1(<vscale x 64 x i1>
; CHECK-NEXT: ldr p8, [x3]
; CHECK-NEXT: eor p0.b, p4/z, p0.b, p5.b
; CHECK-NEXT: eor p1.b, p4/z, p1.b, p6.b
-; CHECK-NEXT: ldr p6, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: eor p2.b, p4/z, p2.b, p7.b
-; CHECK-NEXT: ldr p7, [sp, #4, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p6, [sp, #5, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: eor p3.b, p4/z, p3.b, p8.b
-; CHECK-NEXT: ldr p8, [sp, #3, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p7, [sp, #4, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p8, [sp, #3, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #1
; CHECK-NEXT: .cfi_def_cfa wsp, 16
; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
diff --git a/llvm/test/CodeGen/AArch64/sve-tailcall.ll b/llvm/test/CodeGen/AArch64/sve-tailcall.ll
index f32c80d392b633..9857931eff3d66 100644
--- a/llvm/test/CodeGen/AArch64/sve-tailcall.ll
+++ b/llvm/test/CodeGen/AArch64/sve-tailcall.ll
@@ -13,8 +13,8 @@ define <vscale x 4 x i32> @sve_caller_sve_callee() nounwind {
; CHECK-NEXT: str z9, [sp, #1, mul vl] // 16-byte Folded Spill
; CHECK-NEXT: //APP
; CHECK-NEXT: //NO_APP
-; CHECK-NEXT: ldr z10, [sp] // 16-byte Folded Reload
; CHECK-NEXT: ldr z9, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #2
; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: b sve_callee
@@ -32,8 +32,8 @@ define <vscale x 4 x i32> @sve_caller_sve_callee_fastcc() nounwind {
; CHECK-NEXT: str z9, [sp, #1, mul vl] // 16-byte Folded Spill
; CHECK-NEXT: //APP
; CHECK-NEXT: //NO_APP
-; CHECK-NEXT: ldr z10, [sp] // 16-byte Folded Reload
; CHECK-NEXT: ldr z9, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #2
; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: b sve_callee
@@ -83,34 +83,34 @@ define i32 @sve_caller_non_sve_callee(<vscale x 4 x i32> %arg) nounwind {
; CHECK-NEXT: //APP
; CHECK-NEXT: //NO_APP
; CHECK-NEXT: bl non_sve_callee
-; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #18
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
@@ -158,34 +158,34 @@ define i32 @sve_caller_non_sve_callee_fastcc(<vscale x 4 x i32> %arg) nounwind {
; CHECK-NEXT: //APP
; CHECK-NEXT: //NO_APP
; CHECK-NEXT: bl non_sve_callee
-; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #18
; CHECK-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT: ret
diff --git a/llvm/test/CodeGen/AArch64/sve-trunc.ll b/llvm/test/CodeGen/AArch64/sve-trunc.ll
index dfa4a6148b86e9..214e79ed033555 100644
--- a/llvm/test/CodeGen/AArch64/sve-trunc.ll
+++ b/llvm/test/CodeGen/AArch64/sve-trunc.ll
@@ -136,9 +136,9 @@ define <vscale x 16 x i1> @trunc_i64toi1_split3(<vscale x 16 x i64> %in) {
; CHECK-NEXT: cmpne p0.d, p0/z, z0.d, #0
; CHECK-NEXT: uzp1 p3.s, p4.s, p3.s
; CHECK-NEXT: uzp1 p4.s, p6.s, p5.s
-; CHECK-NEXT: ldr p6, [sp, #5, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: uzp1 p0.s, p0.s, p2.s
; CHECK-NEXT: ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: uzp1 p0.s, p0.s, p2.s
+; CHECK-NEXT: ldr p6, [sp, #5, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: uzp1 p1.h, p3.h, p1.h
; CHECK-NEXT: uzp1 p0.h, p0.h, p4.h
; CHECK-NEXT: ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
diff --git a/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-ldst-pair.ll b/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-ldst-pair.ll
index c7f38861102c00..76aeda125fe40e 100644
--- a/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-ldst-pair.ll
+++ b/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-ldst-pair.ll
@@ -52,34 +52,34 @@ define void @fbyte(<vscale x 16 x i8> %v) {
; NOPAIR-NEXT: .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 16 - 56 * VG
; NOPAIR-NEXT: .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 16 - 64 * VG
; NOPAIR-NEXT: bl my_func
-; NOPAIR-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
; NOPAIR-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
; NOPAIR-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; NOPAIR-NEXT: addvl sp, sp, #18
; NOPAIR-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; NOPAIR-NEXT: ret
@@ -121,27 +121,27 @@ define void @fbyte(<vscale x 16 x i8> %v) {
; PAIR-NEXT: .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 16 - 56 * VG
; PAIR-NEXT: .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 16 - 64 * VG
; PAIR-NEXT: bl my_func
-; PAIR-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
; PAIR-NEXT: ptrue pn8.b
-; PAIR-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #4, mul vl] // 32-byte Folded Reload
-; PAIR-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #8, mul vl] // 32-byte Folded Reload
-; PAIR-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #12, mul vl] // 32-byte Folded Reload
-; PAIR-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #16, mul vl] // 32-byte Folded Reload
-; PAIR-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #20, mul vl] // 32-byte Folded Reload
-; PAIR-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
-; PAIR-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #28, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
; PAIR-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #32, mul vl] // 32-byte Folded Reload
-; PAIR-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #28, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #20, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #16, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #12, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #8, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #4, mul vl] // 32-byte Folded Reload
; PAIR-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; PAIR-NEXT: addvl sp, sp, #18
; PAIR-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; PAIR-NEXT: ret
@@ -194,34 +194,34 @@ define void @fhalf(<vscale x 8 x half> %v) {
; NOPAIR-NEXT: .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 16 - 56 * VG
; NOPAIR-NEXT: .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 16 - 64 * VG
; NOPAIR-NEXT: bl my_func
-; NOPAIR-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
; NOPAIR-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
-; NOPAIR-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
-; NOPAIR-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; NOPAIR-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
; NOPAIR-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; NOPAIR-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; NOPAIR-NEXT: addvl sp, sp, #18
; NOPAIR-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; NOPAIR-NEXT: ret
@@ -263,27 +263,27 @@ define void @fhalf(<vscale x 8 x half> %v) {
; PAIR-NEXT: .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 16 - 56 * VG
; PAIR-NEXT: .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 16 - 64 * VG
; PAIR-NEXT: bl my_func
-; PAIR-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
; PAIR-NEXT: ptrue pn8.b
-; PAIR-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #4, mul vl] // 32-byte Folded Reload
-; PAIR-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #8, mul vl] // 32-byte Folded Reload
-; PAIR-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #12, mul vl] // 32-byte Folded Reload
-; PAIR-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #16, mul vl] // 32-byte Folded Reload
-; PAIR-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #20, mul vl] // 32-byte Folded Reload
-; PAIR-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
-; PAIR-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #28, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
; PAIR-NEXT: ld1b { z8.b, z9.b }, pn8/z, [sp, #32, mul vl] // 32-byte Folded Reload
-; PAIR-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ld1b { z10.b, z11.b }, pn8/z, [sp, #28, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z12.b, z13.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z14.b, z15.b }, pn8/z, [sp, #20, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z16.b, z17.b }, pn8/z, [sp, #16, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z18.b, z19.b }, pn8/z, [sp, #12, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z20.b, z21.b }, pn8/z, [sp, #8, mul vl] // 32-byte Folded Reload
+; PAIR-NEXT: ld1b { z22.b, z23.b }, pn8/z, [sp, #4, mul vl] // 32-byte Folded Reload
; PAIR-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; PAIR-NEXT: addvl sp, sp, #18
; PAIR-NEXT: ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; PAIR-NEXT: ret
diff --git a/llvm/test/CodeGen/AArch64/unwind-preserved.ll b/llvm/test/CodeGen/AArch64/unwind-preserved.ll
index f3c4d217e6fcaa..415865b5293b76 100644
--- a/llvm/test/CodeGen/AArch64/unwind-preserved.ll
+++ b/llvm/test/CodeGen/AArch64/unwind-preserved.ll
@@ -63,34 +63,34 @@ define <vscale x 4 x i32> @invoke_callee_may_throw_sve(<vscale x 4 x i32> %v) uw
; CHECK-NEXT: ldr z0, [sp, #1, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #2
; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 144 * VG
-; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #18
; CHECK-NEXT: .cfi_def_cfa wsp, 16
; CHECK-NEXT: .cfi_restore z8
@@ -112,34 +112,34 @@ define <vscale x 4 x i32> @invoke_callee_may_throw_sve(<vscale x 4 x i32> %v) uw
; CHECK-NEXT: ldr z0, [sp] // 16-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #2
; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 144 * VG
-; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
-; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
; CHECK-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: addvl sp, sp, #18
; CHECK-NEXT: .cfi_def_cfa wsp, 16
; CHECK-NEXT: .cfi_restore z8
@@ -215,34 +215,34 @@ define <vscale x 4 x i32> @invoke_callee_may_throw_sve(<vscale x 4 x i32> %v) uw
; GISEL-NEXT: ldr z0, [sp, #1, mul vl] // 16-byte Folded Reload
; GISEL-NEXT: addvl sp, sp, #2
; GISEL-NEXT: .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 144 * VG
-; GISEL-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
; GISEL-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; GISEL-NEXT: addvl sp, sp, #18
; GISEL-NEXT: .cfi_def_cfa wsp, 16
; GISEL-NEXT: .cfi_restore z8
@@ -264,34 +264,34 @@ define <vscale x 4 x i32> @invoke_callee_may_throw_sve(<vscale x 4 x i32> %v) uw
; GISEL-NEXT: ldr z0, [sp] // 16-byte Folded Reload
; GISEL-NEXT: addvl sp, sp, #2
; GISEL-NEXT: .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 144 * VG
-; GISEL-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
-; GISEL-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
-; GISEL-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
; GISEL-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
+; GISEL-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; GISEL-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; GISEL-NEXT: addvl sp, sp, #18
; GISEL-NEXT: .cfi_def_cfa wsp, 16
; GISEL-NEXT: .cfi_restore z8
diff --git a/mir.mir b/mir.mir
new file mode 100644
index 00000000000000..6e7a3dcf907660
--- /dev/null
+++ b/mir.mir
@@ -0,0 +1,1874 @@
+--- |
+ ; ModuleID = '/home/carcon01/2024/llvm-project/llvm/test/CodeGen/AArch64/framelayout-sve.mir'
+ source_filename = "/home/carcon01/2024/llvm-project/llvm/test/CodeGen/AArch64/framelayout-sve.mir"
+ target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
+ target triple = "aarch64-none-linux-gnu"
+
+ ; Function Attrs: uwtable
+ define void @test_allocate_sve() #0 {
+ entry:
+ unreachable
+ }
+
+ ; Function Attrs: uwtable
+ define void @test_allocate_sve_gpr_callee_saves() #0 {
+ entry:
+ unreachable
+ }
+
+ ; Function Attrs: uwtable
+ define void @test_allocate_sve_gpr_realigned() #0 {
+ entry:
+ unreachable
+ }
+
+ ; Function Attrs: uwtable
+ define void @test_address_sve() #0 {
+ entry:
+ unreachable
+ }
+
+ ; Function Attrs: uwtable
+ define void @test_address_sve_fp() #0 {
+ entry:
+ unreachable
+ }
+
+ ; Function Attrs: uwtable
+ define void @test_stack_arg_sve() #0 {
+ entry:
+ unreachable
+ }
+
+ ; Function Attrs: uwtable
+ define void @test_address_sve_out_of_range() #0 {
+ entry:
+ unreachable
+ }
+
+ ; Function Attrs: uwtable
+ define void @test_address_gpr_vla() #0 {
+ entry:
+ unreachable
+ }
+
+ ; Function Attrs: uwtable
+ define aarch64_sve_vector_pcs void @save_restore_pregs_sve() #0 {
+ entry:
+ unreachable
+ }
+
+ ; Function Attrs: uwtable
+ define aarch64_sve_vector_pcs void @save_restore_zregs_sve() #0 {
+ entry:
+ unreachable
+ }
+
+ ; Function Attrs: uwtable
+ define aarch64_sve_vector_pcs void @save_restore_sve() #0 {
+ entry:
+ unreachable
+ }
+
+ ; Function Attrs: uwtable
+ define aarch64_sve_vector_pcs void @save_restore_sve_realign() #0 {
+ entry:
+ unreachable
+ }
+
+ ; Function Attrs: uwtable
+ define aarch64_sve_vector_pcs void @frame_layout() #0 {
+ entry:
+ unreachable
+ }
+
+ ; Function Attrs: uwtable
+ define void @fp_relative_index_with_float_save() #0 {
+ entry:
+ unreachable
+ }
+
+ ; Function Attrs: uwtable
+ define void @fp_relative_that_is_not_a_multiple_of_VLx16() #0 {
+ entry:
+ unreachable
+ }
+
+ attributes #0 = { uwtable "target-features"="+sve" }
+
+...
+---
+name: test_allocate_sve
+alignment: 1
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: false
+hasWinCFI: false
+callsEHReturn: false
+callsUnwindInit: false
+hasEHCatchret: false
+hasEHScopes: false
+hasEHFunclets: false
+isOutlined: false
+debugInstrRef: false
+failsVerification: false
+tracksDebugUserValues: false
+registers: []
+liveins: []
+frameInfo:
+ isFrameAddressTaken: false
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 32
+ offsetAdjustment: 0
+ maxAlignment: 16
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ functionContext: ''
+ maxCallFrameSize: 0
+ cvBytesOfCalleeSavedRegisters: 0
+ hasOpaqueSPAdjustment: false
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ hasTailCall: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack: []
+stack:
+ - { id: 0, name: '', type: default, offset: -18, size: 18, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 1, name: '', type: default, offset: -32, size: 16, alignment: 8,
+ stack-id: default, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 2, name: '', type: spill-slot, offset: -16, size: 8, alignment: 16,
+ stack-id: default, callee-saved-register: '$fp', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+entry_values: []
+callSites: []
+debugValueSubstitutions: []
+constants: []
+machineFunctionInfo:
+ hasRedZone: false
+body: |
+ bb.0.entry:
+ early-clobber $sp = frame-setup STRXpre killed $fp, $sp, -16 :: (store (s64) into %stack.2)
+ frame-setup CFI_INSTRUCTION def_cfa_offset 16
+ frame-setup CFI_INSTRUCTION offset $w29, -16
+ $sp = frame-setup SUBXri $sp, 16, 0
+ frame-setup CFI_INSTRUCTION def_cfa_offset 32
+ $sp = frame-setup ADDVL_XXI $sp, -2
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x20, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-destroy ADDVL_XXI $sp, 2
+ frame-destroy CFI_INSTRUCTION def_cfa $wsp, 32
+ $sp = frame-destroy ADDXri $sp, 16, 0
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 16
+ early-clobber $sp, $fp = frame-destroy LDRXpost $sp, 16 :: (load (s64) from %stack.2)
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 0
+ frame-destroy CFI_INSTRUCTION restore $w29
+ RET_ReallyLR
+
+...
+---
+name: test_allocate_sve_gpr_callee_saves
+alignment: 1
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: false
+hasWinCFI: false
+callsEHReturn: false
+callsUnwindInit: false
+hasEHCatchret: false
+hasEHScopes: false
+hasEHFunclets: false
+isOutlined: false
+debugInstrRef: false
+failsVerification: false
+tracksDebugUserValues: false
+registers: []
+liveins: []
+frameInfo:
+ isFrameAddressTaken: false
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 48
+ offsetAdjustment: 0
+ maxAlignment: 16
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ functionContext: ''
+ maxCallFrameSize: 0
+ cvBytesOfCalleeSavedRegisters: 0
+ hasOpaqueSPAdjustment: false
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ hasTailCall: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack: []
+stack:
+ - { id: 0, name: '', type: default, offset: -18, size: 18, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 1, name: '', type: default, offset: -48, size: 16, alignment: 8,
+ stack-id: default, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 2, name: '', type: spill-slot, offset: -8, size: 8, alignment: 8,
+ stack-id: default, callee-saved-register: '$x20', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 3, name: '', type: spill-slot, offset: -16, size: 8, alignment: 8,
+ stack-id: default, callee-saved-register: '$x21', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 4, name: '', type: spill-slot, offset: -32, size: 8, alignment: 16,
+ stack-id: default, callee-saved-register: '$fp', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+entry_values: []
+callSites: []
+debugValueSubstitutions: []
+constants: []
+machineFunctionInfo:
+ hasRedZone: false
+body: |
+ bb.0.entry:
+ liveins: $x20, $x21
+
+ early-clobber $sp = frame-setup STRXpre killed $fp, $sp, -32 :: (store (s64) into %stack.4)
+ frame-setup CFI_INSTRUCTION def_cfa_offset 32
+ frame-setup STPXi killed $x21, killed $x20, $sp, 2 :: (store (s64) into %stack.3), (store (s64) into %stack.2)
+ frame-setup CFI_INSTRUCTION offset $w20, -8
+ frame-setup CFI_INSTRUCTION offset $w21, -16
+ frame-setup CFI_INSTRUCTION offset $w29, -32
+ $sp = frame-setup SUBXri $sp, 16, 0
+ frame-setup CFI_INSTRUCTION def_cfa_offset 48
+ $sp = frame-setup ADDVL_XXI $sp, -2
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x30, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $x20 = IMPLICIT_DEF
+ $x21 = IMPLICIT_DEF
+ $sp = frame-destroy ADDVL_XXI $sp, 2
+ frame-destroy CFI_INSTRUCTION def_cfa $wsp, 48
+ $sp = frame-destroy ADDXri $sp, 16, 0
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 32
+ $x21, $x20 = frame-destroy LDPXi $sp, 2 :: (load (s64) from %stack.3), (load (s64) from %stack.2)
+ early-clobber $sp, $fp = frame-destroy LDRXpost $sp, 32 :: (load (s64) from %stack.4)
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 0
+ frame-destroy CFI_INSTRUCTION restore $w20
+ frame-destroy CFI_INSTRUCTION restore $w21
+ frame-destroy CFI_INSTRUCTION restore $w29
+ RET_ReallyLR
+
+...
+---
+name: test_allocate_sve_gpr_realigned
+alignment: 1
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: false
+hasWinCFI: false
+callsEHReturn: false
+callsUnwindInit: false
+hasEHCatchret: false
+hasEHScopes: false
+hasEHFunclets: false
+isOutlined: false
+debugInstrRef: false
+failsVerification: false
+tracksDebugUserValues: false
+registers: []
+liveins: []
+frameInfo:
+ isFrameAddressTaken: false
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 32
+ offsetAdjustment: 0
+ maxAlignment: 32
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ functionContext: ''
+ maxCallFrameSize: 0
+ cvBytesOfCalleeSavedRegisters: 0
+ hasOpaqueSPAdjustment: false
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ hasTailCall: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack: []
+stack:
+ - { id: 0, name: '', type: default, offset: -18, size: 18, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 1, name: '', type: default, offset: -32, size: 16, alignment: 32,
+ stack-id: default, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 2, name: '', type: spill-slot, offset: -8, size: 8, alignment: 8,
+ stack-id: default, callee-saved-register: '$lr', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 3, name: '', type: spill-slot, offset: -16, size: 8, alignment: 8,
+ stack-id: default, callee-saved-register: '$fp', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+entry_values: []
+callSites: []
+debugValueSubstitutions: []
+constants: []
+machineFunctionInfo:
+ hasRedZone: false
+body: |
+ bb.0.entry:
+ liveins: $lr
+
+ early-clobber $sp = frame-setup STPXpre killed $fp, killed $lr, $sp, -2 :: (store (s64) into %stack.3), (store (s64) into %stack.2)
+ frame-setup CFI_INSTRUCTION def_cfa_offset 16
+ $fp = frame-setup ADDXri $sp, 0, 0
+ frame-setup CFI_INSTRUCTION def_cfa $w29, 16
+ frame-setup CFI_INSTRUCTION offset $w30, -8
+ frame-setup CFI_INSTRUCTION offset $w29, -16
+ $x9 = frame-setup SUBXri $sp, 16, 0
+ $x9 = frame-setup ADDVL_XXI $x9, -2
+ $sp = frame-setup ANDXri killed $x9, 7930
+ $sp = frame-destroy ADDXri $fp, 0, 0
+ frame-destroy CFI_INSTRUCTION def_cfa $wsp, 16
+ early-clobber $sp, $fp, $lr = frame-destroy LDPXpost $sp, 2 :: (load (s64) from %stack.3), (load (s64) from %stack.2)
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 0
+ frame-destroy CFI_INSTRUCTION restore $w30
+ frame-destroy CFI_INSTRUCTION restore $w29
+ RET_ReallyLR
+
+...
+---
+name: test_address_sve
+alignment: 1
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: false
+hasWinCFI: false
+callsEHReturn: false
+callsUnwindInit: false
+hasEHCatchret: false
+hasEHScopes: false
+hasEHFunclets: false
+isOutlined: false
+debugInstrRef: false
+failsVerification: false
+tracksDebugUserValues: false
+registers: []
+liveins: []
+frameInfo:
+ isFrameAddressTaken: false
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 32
+ offsetAdjustment: 0
+ maxAlignment: 16
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ functionContext: ''
+ maxCallFrameSize: 0
+ cvBytesOfCalleeSavedRegisters: 0
+ hasOpaqueSPAdjustment: false
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ hasTailCall: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack: []
+stack:
+ - { id: 0, name: '', type: default, offset: -16, size: 16, alignment: 8,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 1, name: '', type: default, offset: -32, size: 16, alignment: 8,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 2, name: '', type: default, offset: -34, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 3, name: '', type: default, offset: -32, size: 16, alignment: 8,
+ stack-id: default, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 4, name: '', type: spill-slot, offset: -16, size: 8, alignment: 16,
+ stack-id: default, callee-saved-register: '$fp', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+entry_values: []
+callSites: []
+debugValueSubstitutions: []
+constants: []
+machineFunctionInfo:
+ hasRedZone: false
+body: |
+ bb.0.entry:
+ liveins: $z0, $z1, $p0
+
+ early-clobber $sp = frame-setup STRXpre killed $fp, $sp, -16 :: (store (s64) into %stack.4)
+ frame-setup CFI_INSTRUCTION def_cfa_offset 16
+ frame-setup CFI_INSTRUCTION offset $w29, -16
+ $sp = frame-setup SUBXri $sp, 16, 0
+ frame-setup CFI_INSTRUCTION def_cfa_offset 32
+ $sp = frame-setup ADDVL_XXI $sp, -3
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x20, 0x22, 0x11, 0x18, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $x8 = ADDXri $sp, 16, 0
+ STR_ZXI $z0, killed $x8, 2
+ $x8 = ADDXri $sp, 16, 0
+ STR_ZXI $z1, killed $x8, 1
+ $x8 = ADDXri $sp, 16, 0
+ STR_PXI $p0, killed $x8, 7
+ $sp = frame-destroy ADDVL_XXI $sp, 3
+ frame-destroy CFI_INSTRUCTION def_cfa $wsp, 32
+ $sp = frame-destroy ADDXri $sp, 16, 0
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 16
+ early-clobber $sp, $fp = frame-destroy LDRXpost $sp, 16 :: (load (s64) from %stack.4)
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 0
+ frame-destroy CFI_INSTRUCTION restore $w29
+ RET_ReallyLR
+
+...
+---
+name: test_address_sve_fp
+alignment: 1
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: false
+hasWinCFI: false
+callsEHReturn: false
+callsUnwindInit: false
+hasEHCatchret: false
+hasEHScopes: false
+hasEHFunclets: false
+isOutlined: false
+debugInstrRef: false
+failsVerification: false
+tracksDebugUserValues: false
+registers: []
+liveins: []
+frameInfo:
+ isFrameAddressTaken: true
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 32
+ offsetAdjustment: 0
+ maxAlignment: 16
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ functionContext: ''
+ maxCallFrameSize: 0
+ cvBytesOfCalleeSavedRegisters: 0
+ hasOpaqueSPAdjustment: false
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ hasTailCall: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack: []
+stack:
+ - { id: 0, name: '', type: default, offset: -16, size: 16, alignment: 8,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 1, name: '', type: default, offset: -32, size: 16, alignment: 8,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 2, name: '', type: default, offset: -34, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 3, name: '', type: default, offset: -32, size: 16, alignment: 8,
+ stack-id: default, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 4, name: '', type: spill-slot, offset: -8, size: 8, alignment: 8,
+ stack-id: default, callee-saved-register: '$lr', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 5, name: '', type: spill-slot, offset: -16, size: 8, alignment: 8,
+ stack-id: default, callee-saved-register: '$fp', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+entry_values: []
+callSites: []
+debugValueSubstitutions: []
+constants: []
+machineFunctionInfo:
+ hasRedZone: false
+body: |
+ bb.0.entry:
+ liveins: $z0, $z1, $p0, $lr
+
+ early-clobber $sp = frame-setup STPXpre killed $fp, killed $lr, $sp, -2 :: (store (s64) into %stack.5), (store (s64) into %stack.4)
+ frame-setup CFI_INSTRUCTION def_cfa_offset 16
+ $fp = frame-setup ADDXri $sp, 0, 0
+ frame-setup CFI_INSTRUCTION def_cfa $w29, 16
+ frame-setup CFI_INSTRUCTION offset $w30, -8
+ frame-setup CFI_INSTRUCTION offset $w29, -16
+ $sp = frame-setup SUBXri $sp, 16, 0
+ $sp = frame-setup ADDVL_XXI $sp, -3
+ STR_ZXI $z0, $fp, -1
+ STR_ZXI $z1, $fp, -2
+ STR_PXI $p0, $fp, -17
+ $sp = frame-destroy ADDVL_XXI $sp, 3
+ $sp = frame-destroy ADDXri $sp, 16, 0
+ frame-destroy CFI_INSTRUCTION def_cfa $wsp, 16
+ early-clobber $sp, $fp, $lr = frame-destroy LDPXpost $sp, 2 :: (load (s64) from %stack.5), (load (s64) from %stack.4)
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 0
+ frame-destroy CFI_INSTRUCTION restore $w30
+ frame-destroy CFI_INSTRUCTION restore $w29
+ RET_ReallyLR
+
+...
+---
+name: test_stack_arg_sve
+alignment: 1
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: false
+hasWinCFI: false
+callsEHReturn: false
+callsUnwindInit: false
+hasEHCatchret: false
+hasEHScopes: false
+hasEHFunclets: false
+isOutlined: false
+debugInstrRef: false
+failsVerification: false
+tracksDebugUserValues: false
+registers: []
+liveins: []
+frameInfo:
+ isFrameAddressTaken: false
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 32
+ offsetAdjustment: 0
+ maxAlignment: 16
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ functionContext: ''
+ maxCallFrameSize: 0
+ cvBytesOfCalleeSavedRegisters: 0
+ hasOpaqueSPAdjustment: false
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ hasTailCall: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack:
+ - { id: 0, type: default, offset: 0, size: 16, alignment: 16, stack-id: default,
+ isImmutable: false, isAliased: false, callee-saved-register: '',
+ callee-saved-restored: true, debug-info-variable: '', debug-info-expression: '',
+ debug-info-location: '' }
+stack:
+ - { id: 0, name: '', type: default, offset: -16, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 1, name: '', type: default, offset: -32, size: 16, alignment: 16,
+ stack-id: default, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 2, name: '', type: spill-slot, offset: -16, size: 8, alignment: 16,
+ stack-id: default, callee-saved-register: '$fp', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+entry_values: []
+callSites: []
+debugValueSubstitutions: []
+constants: []
+machineFunctionInfo:
+ hasRedZone: false
+body: |
+ bb.0.entry:
+ liveins: $x0
+
+ early-clobber $sp = frame-setup STRXpre killed $fp, $sp, -16 :: (store (s64) into %stack.2)
+ frame-setup CFI_INSTRUCTION def_cfa_offset 16
+ frame-setup CFI_INSTRUCTION offset $w29, -16
+ $sp = frame-setup SUBXri $sp, 16, 0
+ frame-setup CFI_INSTRUCTION def_cfa_offset 32
+ $sp = frame-setup ADDVL_XXI $sp, -1
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x20, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $x8 = ADDVL_XXI $sp, 1
+ $x0 = LDRXui killed $x8, 4
+ $sp = frame-destroy ADDVL_XXI $sp, 1
+ frame-destroy CFI_INSTRUCTION def_cfa $wsp, 32
+ $sp = frame-destroy ADDXri $sp, 16, 0
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 16
+ early-clobber $sp, $fp = frame-destroy LDRXpost $sp, 16 :: (load (s64) from %stack.2)
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 0
+ frame-destroy CFI_INSTRUCTION restore $w29
+ RET_ReallyLR
+
+...
+---
+name: test_address_sve_out_of_range
+alignment: 1
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: false
+hasWinCFI: false
+callsEHReturn: false
+callsUnwindInit: false
+hasEHCatchret: false
+hasEHScopes: false
+hasEHFunclets: false
+isOutlined: false
+debugInstrRef: false
+failsVerification: false
+tracksDebugUserValues: false
+registers: []
+liveins: []
+frameInfo:
+ isFrameAddressTaken: false
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 16
+ offsetAdjustment: 0
+ maxAlignment: 16
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ functionContext: ''
+ maxCallFrameSize: 0
+ cvBytesOfCalleeSavedRegisters: 0
+ hasOpaqueSPAdjustment: false
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ hasTailCall: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack: []
+stack:
+ - { id: 0, name: '', type: default, offset: -16, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 1, name: '', type: default, offset: -3600, size: 3584, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 2, name: '', type: default, offset: -4112, size: 512, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 3, name: '', type: spill-slot, offset: -16, size: 8, alignment: 16,
+ stack-id: default, callee-saved-register: '$fp', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+entry_values: []
+callSites: []
+debugValueSubstitutions: []
+constants: []
+machineFunctionInfo:
+ hasRedZone: false
+body: |
+ bb.0.entry:
+ liveins: $z0, $p0
+
+ early-clobber $sp = frame-setup STRXpre killed $fp, $sp, -16 :: (store (s64) into %stack.3)
+ frame-setup CFI_INSTRUCTION def_cfa_offset 16
+ frame-setup CFI_INSTRUCTION offset $w29, -16
+ $sp = frame-setup ADDVL_XXI $sp, -32
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x80, 0x02, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-setup ADDVL_XXI $sp, -32
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x80, 0x04, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-setup ADDVL_XXI $sp, -32
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x80, 0x06, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-setup ADDVL_XXI $sp, -32
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x80, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-setup ADDVL_XXI $sp, -32
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x80, 0x0a, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-setup ADDVL_XXI $sp, -32
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x80, 0x0c, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-setup ADDVL_XXI $sp, -32
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x80, 0x0e, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-setup ADDVL_XXI $sp, -32
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x80, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-setup ADDVL_XXI $sp, -1
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x88, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $x8 = ADDVL_XXI $sp, 1
+ STR_ZXI $z0, killed $x8, 255
+ $x8 = ADDPL_XXI $sp, 1
+ STR_PXI $p0, killed $x8, 255
+ $sp = frame-destroy ADDVL_XXI $sp, 31
+ frame-destroy CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x90, 0x0e, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-destroy ADDVL_XXI $sp, 31
+ frame-destroy CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x98, 0x0c, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-destroy ADDVL_XXI $sp, 31
+ frame-destroy CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0xa0, 0x0a, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-destroy ADDVL_XXI $sp, 31
+ frame-destroy CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0xa8, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-destroy ADDVL_XXI $sp, 31
+ frame-destroy CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0xb0, 0x06, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-destroy ADDVL_XXI $sp, 31
+ frame-destroy CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0xb8, 0x04, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-destroy ADDVL_XXI $sp, 31
+ frame-destroy CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0xc0, 0x02, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-destroy ADDVL_XXI $sp, 31
+ frame-destroy CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0xc8, 0x00, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-destroy ADDVL_XXI $sp, 9
+ frame-destroy CFI_INSTRUCTION def_cfa $wsp, 16
+ early-clobber $sp, $fp = frame-destroy LDRXpost $sp, 16 :: (load (s64) from %stack.3)
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 0
+ frame-destroy CFI_INSTRUCTION restore $w29
+ RET_ReallyLR
+
+...
+---
+name: test_address_gpr_vla
+alignment: 1
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: false
+hasWinCFI: false
+callsEHReturn: false
+callsUnwindInit: false
+hasEHCatchret: false
+hasEHScopes: false
+hasEHFunclets: false
+isOutlined: false
+debugInstrRef: false
+failsVerification: false
+tracksDebugUserValues: false
+registers: []
+liveins: []
+frameInfo:
+ isFrameAddressTaken: false
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 48
+ offsetAdjustment: 0
+ maxAlignment: 16
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ functionContext: ''
+ maxCallFrameSize: 0
+ cvBytesOfCalleeSavedRegisters: 0
+ hasOpaqueSPAdjustment: false
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ hasTailCall: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack: []
+stack:
+ - { id: 0, name: '', type: default, offset: -16, size: 16, alignment: 8,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 1, name: '', type: default, offset: -48, size: 16, alignment: 8,
+ stack-id: default, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 2, name: '', type: variable-sized, offset: -48, alignment: 1,
+ stack-id: default, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 3, name: '', type: spill-slot, offset: -16, size: 8, alignment: 16,
+ stack-id: default, callee-saved-register: '$x19', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 4, name: '', type: spill-slot, offset: -24, size: 8, alignment: 8,
+ stack-id: default, callee-saved-register: '$lr', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 5, name: '', type: spill-slot, offset: -32, size: 8, alignment: 8,
+ stack-id: default, callee-saved-register: '$fp', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+entry_values: []
+callSites: []
+debugValueSubstitutions: []
+constants: []
+machineFunctionInfo:
+ hasRedZone: false
+body: |
+ bb.0.entry:
+ liveins: $xzr, $lr
+
+ early-clobber $sp = frame-setup STPXpre killed $fp, killed $lr, $sp, -4 :: (store (s64) into %stack.5), (store (s64) into %stack.4)
+ frame-setup CFI_INSTRUCTION def_cfa_offset 32
+ frame-setup STRXui killed $x19, $sp, 2 :: (store (s64) into %stack.3)
+ $fp = frame-setup ADDXri $sp, 0, 0
+ frame-setup CFI_INSTRUCTION def_cfa $w29, 32
+ frame-setup CFI_INSTRUCTION offset $w19, -16
+ frame-setup CFI_INSTRUCTION offset $w30, -24
+ frame-setup CFI_INSTRUCTION offset $w29, -32
+ $sp = frame-setup SUBXri $sp, 16, 0
+ $sp = frame-setup ADDVL_XXI $sp, -1
+ $x19 = ADDXri $sp, 0, 0
+ STRXui $xzr, $x19, 0
+ $sp = frame-destroy ADDXri $fp, 0, 0
+ frame-destroy CFI_INSTRUCTION def_cfa $wsp, 32
+ $x19 = frame-destroy LDRXui $sp, 2 :: (load (s64) from %stack.3)
+ early-clobber $sp, $fp, $lr = frame-destroy LDPXpost $sp, 4 :: (load (s64) from %stack.5), (load (s64) from %stack.4)
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 0
+ frame-destroy CFI_INSTRUCTION restore $w19
+ frame-destroy CFI_INSTRUCTION restore $w30
+ frame-destroy CFI_INSTRUCTION restore $w29
+ RET_ReallyLR
+
+...
+---
+name: save_restore_pregs_sve
+alignment: 1
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: false
+hasWinCFI: false
+callsEHReturn: false
+callsUnwindInit: false
+hasEHCatchret: false
+hasEHScopes: false
+hasEHFunclets: false
+isOutlined: false
+debugInstrRef: false
+failsVerification: false
+tracksDebugUserValues: false
+registers: []
+liveins: []
+frameInfo:
+ isFrameAddressTaken: false
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 48
+ offsetAdjustment: 0
+ maxAlignment: 16
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ functionContext: ''
+ maxCallFrameSize: 0
+ cvBytesOfCalleeSavedRegisters: 0
+ hasOpaqueSPAdjustment: false
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ hasTailCall: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack: []
+stack:
+ - { id: 0, name: '', type: default, offset: -48, size: 32, alignment: 16,
+ stack-id: default, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 1, name: '', type: spill-slot, offset: -2, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p4', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 2, name: '', type: spill-slot, offset: -4, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p5', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 3, name: '', type: spill-slot, offset: -6, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p6', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 4, name: '', type: spill-slot, offset: -16, size: 8, alignment: 16,
+ stack-id: default, callee-saved-register: '$fp', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+entry_values: []
+callSites: []
+debugValueSubstitutions: []
+constants: []
+machineFunctionInfo:
+ hasRedZone: false
+body: |
+ bb.0.entry:
+ liveins: $p6, $p5, $p4
+
+ early-clobber $sp = frame-setup STRXpre killed $fp, $sp, -16 :: (store (s64) into %stack.4)
+ frame-setup CFI_INSTRUCTION def_cfa_offset 16
+ frame-setup CFI_INSTRUCTION offset $w29, -16
+ $sp = frame-setup ADDVL_XXI $sp, -1
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup STR_PXI killed $p6, $sp, 5 :: (store (s16) into %stack.3)
+ frame-setup STR_PXI killed $p5, $sp, 6 :: (store (s16) into %stack.2)
+ frame-setup STR_PXI killed $p4, $sp, 7 :: (store (s16) into %stack.1)
+ $sp = frame-setup SUBXri $sp, 32, 0
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x30, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $p4 = IMPLICIT_DEF
+ $p5 = IMPLICIT_DEF
+ $p6 = IMPLICIT_DEF
+ $sp = frame-destroy ADDXri $sp, 32, 0
+ frame-destroy CFI_INSTRUCTION escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $p4 = frame-destroy LDR_PXI $sp, 7 :: (load (s16) from %stack.1)
+ $p5 = frame-destroy LDR_PXI $sp, 6 :: (load (s16) from %stack.2)
+ $p6 = frame-destroy LDR_PXI $sp, 5 :: (load (s16) from %stack.3)
+ $sp = frame-destroy ADDVL_XXI $sp, 1
+ frame-destroy CFI_INSTRUCTION def_cfa $wsp, 16
+ early-clobber $sp, $fp = frame-destroy LDRXpost $sp, 16 :: (load (s64) from %stack.4)
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 0
+ frame-destroy CFI_INSTRUCTION restore $w29
+ RET_ReallyLR
+
+...
+---
+name: save_restore_zregs_sve
+alignment: 1
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: false
+hasWinCFI: false
+callsEHReturn: false
+callsUnwindInit: false
+hasEHCatchret: false
+hasEHScopes: false
+hasEHFunclets: false
+isOutlined: false
+debugInstrRef: false
+failsVerification: false
+tracksDebugUserValues: false
+registers: []
+liveins: []
+frameInfo:
+ isFrameAddressTaken: false
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 48
+ offsetAdjustment: 0
+ maxAlignment: 16
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ functionContext: ''
+ maxCallFrameSize: 0
+ cvBytesOfCalleeSavedRegisters: 0
+ hasOpaqueSPAdjustment: false
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ hasTailCall: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack: []
+stack:
+ - { id: 0, name: '', type: default, offset: -48, size: 32, alignment: 16,
+ stack-id: default, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 1, name: '', type: spill-slot, offset: -16, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z8', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 2, name: '', type: spill-slot, offset: -32, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z9', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 3, name: '', type: spill-slot, offset: -48, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z10', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 4, name: '', type: spill-slot, offset: -16, size: 8, alignment: 16,
+ stack-id: default, callee-saved-register: '$fp', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+entry_values: []
+callSites: []
+debugValueSubstitutions: []
+constants: []
+machineFunctionInfo:
+ hasRedZone: false
+body: |
+ bb.0.entry:
+ liveins: $z10, $z9, $z8
+
+ early-clobber $sp = frame-setup STRXpre killed $fp, $sp, -16 :: (store (s64) into %stack.4)
+ frame-setup CFI_INSTRUCTION def_cfa_offset 16
+ frame-setup CFI_INSTRUCTION offset $w29, -16
+ $sp = frame-setup ADDVL_XXI $sp, -3
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup STR_ZXI killed $z10, $sp, 0 :: (store (s128) into %stack.3)
+ frame-setup STR_ZXI killed $z9, $sp, 1 :: (store (s128) into %stack.2)
+ frame-setup STR_ZXI killed $z8, $sp, 2 :: (store (s128) into %stack.1)
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x48, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x49, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x4a, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-setup SUBXri $sp, 32, 0
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x30, 0x22, 0x11, 0x18, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $z8 = IMPLICIT_DEF
+ $z9 = IMPLICIT_DEF
+ $z10 = IMPLICIT_DEF
+ $sp = frame-destroy ADDXri $sp, 32, 0
+ frame-destroy CFI_INSTRUCTION escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $z8 = frame-destroy LDR_ZXI $sp, 2 :: (load (s128) from %stack.1)
+ $z9 = frame-destroy LDR_ZXI $sp, 1 :: (load (s128) from %stack.2)
+ $z10 = frame-destroy LDR_ZXI $sp, 0 :: (load (s128) from %stack.3)
+ $sp = frame-destroy ADDVL_XXI $sp, 3
+ frame-destroy CFI_INSTRUCTION def_cfa $wsp, 16
+ frame-destroy CFI_INSTRUCTION restore $z8
+ frame-destroy CFI_INSTRUCTION restore $z9
+ frame-destroy CFI_INSTRUCTION restore $z10
+ early-clobber $sp, $fp = frame-destroy LDRXpost $sp, 16 :: (load (s64) from %stack.4)
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 0
+ frame-destroy CFI_INSTRUCTION restore $w29
+ RET_ReallyLR
+
+...
+---
+name: save_restore_sve
+alignment: 1
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: false
+hasWinCFI: false
+callsEHReturn: false
+callsUnwindInit: false
+hasEHCatchret: false
+hasEHScopes: false
+hasEHFunclets: false
+isOutlined: false
+debugInstrRef: false
+failsVerification: false
+tracksDebugUserValues: false
+registers: []
+liveins: []
+frameInfo:
+ isFrameAddressTaken: false
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 64
+ offsetAdjustment: 0
+ maxAlignment: 16
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ functionContext: ''
+ maxCallFrameSize: 0
+ cvBytesOfCalleeSavedRegisters: 0
+ hasOpaqueSPAdjustment: false
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ hasTailCall: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack: []
+stack:
+ - { id: 0, name: '', type: default, offset: -304, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 1, name: '', type: default, offset: -64, size: 32, alignment: 16,
+ stack-id: default, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 2, name: '', type: spill-slot, offset: -16, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z8', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 3, name: '', type: spill-slot, offset: -32, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z9', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 4, name: '', type: spill-slot, offset: -48, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z10', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 5, name: '', type: spill-slot, offset: -64, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z11', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 6, name: '', type: spill-slot, offset: -80, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z12', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 7, name: '', type: spill-slot, offset: -96, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z13', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 8, name: '', type: spill-slot, offset: -112, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z14', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 9, name: '', type: spill-slot, offset: -128, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z15', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 10, name: '', type: spill-slot, offset: -144, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z16', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 11, name: '', type: spill-slot, offset: -160, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z17', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 12, name: '', type: spill-slot, offset: -176, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z18', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 13, name: '', type: spill-slot, offset: -192, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z19', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 14, name: '', type: spill-slot, offset: -208, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z20', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 15, name: '', type: spill-slot, offset: -224, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z21', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 16, name: '', type: spill-slot, offset: -240, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z22', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 17, name: '', type: spill-slot, offset: -256, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z23', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 18, name: '', type: spill-slot, offset: -258, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p4', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 19, name: '', type: spill-slot, offset: -260, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p5', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 20, name: '', type: spill-slot, offset: -262, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p6', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 21, name: '', type: spill-slot, offset: -264, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p7', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 22, name: '', type: spill-slot, offset: -266, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p8', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 23, name: '', type: spill-slot, offset: -268, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p9', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 24, name: '', type: spill-slot, offset: -270, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p10', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 25, name: '', type: spill-slot, offset: -272, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p11', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 26, name: '', type: spill-slot, offset: -274, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p12', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 27, name: '', type: spill-slot, offset: -276, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p13', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 28, name: '', type: spill-slot, offset: -278, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p14', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 29, name: '', type: spill-slot, offset: -280, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p15', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 30, name: '', type: spill-slot, offset: -8, size: 8, alignment: 8,
+ stack-id: default, callee-saved-register: '$x19', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 31, name: '', type: spill-slot, offset: -16, size: 8, alignment: 8,
+ stack-id: default, callee-saved-register: '$x20', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 32, name: '', type: spill-slot, offset: -24, size: 8, alignment: 8,
+ stack-id: default, callee-saved-register: '$x21', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 33, name: '', type: spill-slot, offset: -32, size: 8, alignment: 8,
+ stack-id: default, callee-saved-register: '$fp', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+entry_values: []
+callSites: []
+debugValueSubstitutions: []
+constants: []
+machineFunctionInfo:
+ hasRedZone: false
+body: |
+ bb.0.entry:
+ liveins: $x21, $x19, $x20, $p15, $p14, $p13, $p12, $p11, $p10, $p9, $p8, $p7, $p6, $p5, $p4, $z23, $z22, $z21, $z20, $z19, $z18, $z17, $z16, $z15, $z14, $z13, $z12, $z11, $z10, $z9, $z8
+
+ early-clobber $sp = frame-setup STPXpre killed $fp, killed $x21, $sp, -4 :: (store (s64) into %stack.33), (store (s64) into %stack.32)
+ frame-setup CFI_INSTRUCTION def_cfa_offset 32
+ frame-setup STPXi killed $x20, killed $x19, $sp, 2 :: (store (s64) into %stack.31), (store (s64) into %stack.30)
+ frame-setup CFI_INSTRUCTION offset $w19, -8
+ frame-setup CFI_INSTRUCTION offset $w20, -16
+ frame-setup CFI_INSTRUCTION offset $w21, -24
+ frame-setup CFI_INSTRUCTION offset $w29, -32
+ $sp = frame-setup ADDVL_XXI $sp, -18
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x20, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup STR_PXI killed $p15, $sp, 4 :: (store (s16) into %stack.29)
+ frame-setup STR_PXI killed $p14, $sp, 5 :: (store (s16) into %stack.28)
+ frame-setup STR_PXI killed $p13, $sp, 6 :: (store (s16) into %stack.27)
+ frame-setup STR_PXI killed $p12, $sp, 7 :: (store (s16) into %stack.26)
+ frame-setup STR_PXI killed $p11, $sp, 8 :: (store (s16) into %stack.25)
+ frame-setup STR_PXI killed $p10, $sp, 9 :: (store (s16) into %stack.24)
+ frame-setup STR_PXI killed $p9, $sp, 10 :: (store (s16) into %stack.23)
+ frame-setup STR_PXI killed $p8, $sp, 11 :: (store (s16) into %stack.22)
+ frame-setup STR_PXI killed $p7, $sp, 12 :: (store (s16) into %stack.21)
+ frame-setup STR_PXI killed $p6, $sp, 13 :: (store (s16) into %stack.20)
+ frame-setup STR_PXI killed $p5, $sp, 14 :: (store (s16) into %stack.19)
+ frame-setup STR_PXI killed $p4, $sp, 15 :: (store (s16) into %stack.18)
+ frame-setup STR_ZXI killed $z23, $sp, 2 :: (store (s128) into %stack.17)
+ frame-setup STR_ZXI killed $z22, $sp, 3 :: (store (s128) into %stack.16)
+ frame-setup STR_ZXI killed $z21, $sp, 4 :: (store (s128) into %stack.15)
+ frame-setup STR_ZXI killed $z20, $sp, 5 :: (store (s128) into %stack.14)
+ frame-setup STR_ZXI killed $z19, $sp, 6 :: (store (s128) into %stack.13)
+ frame-setup STR_ZXI killed $z18, $sp, 7 :: (store (s128) into %stack.12)
+ frame-setup STR_ZXI killed $z17, $sp, 8 :: (store (s128) into %stack.11)
+ frame-setup STR_ZXI killed $z16, $sp, 9 :: (store (s128) into %stack.10)
+ frame-setup STR_ZXI killed $z15, $sp, 10 :: (store (s128) into %stack.9)
+ frame-setup STR_ZXI killed $z14, $sp, 11 :: (store (s128) into %stack.8)
+ frame-setup STR_ZXI killed $z13, $sp, 12 :: (store (s128) into %stack.7)
+ frame-setup STR_ZXI killed $z12, $sp, 13 :: (store (s128) into %stack.6)
+ frame-setup STR_ZXI killed $z11, $sp, 14 :: (store (s128) into %stack.5)
+ frame-setup STR_ZXI killed $z10, $sp, 15 :: (store (s128) into %stack.4)
+ frame-setup STR_ZXI killed $z9, $sp, 16 :: (store (s128) into %stack.3)
+ frame-setup STR_ZXI killed $z8, $sp, 17 :: (store (s128) into %stack.2)
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x48, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x49, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x4a, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x4b, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x60, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x4c, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x58, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x4d, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x50, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x4e, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x4f, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-setup SUBXri $sp, 32, 0
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0e, 0x8f, 0x00, 0x11, 0xc0, 0x00, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-setup ADDVL_XXI $sp, -1
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0e, 0x8f, 0x00, 0x11, 0xc0, 0x00, 0x22, 0x11, 0x98, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $z8_z9_z10_z11 = IMPLICIT_DEF
+ $z12_z13_z14_z15 = IMPLICIT_DEF
+ $z16_z17_z18_z19 = IMPLICIT_DEF
+ $z20_z21_z22_z23 = IMPLICIT_DEF
+ $z24_z25_z26_z27 = IMPLICIT_DEF
+ $z28_z29_z30_z31 = IMPLICIT_DEF
+ $p4 = IMPLICIT_DEF
+ $p5 = IMPLICIT_DEF
+ $p6 = IMPLICIT_DEF
+ $p7 = IMPLICIT_DEF
+ $p8 = IMPLICIT_DEF
+ $p9 = IMPLICIT_DEF
+ $p10 = IMPLICIT_DEF
+ $p11 = IMPLICIT_DEF
+ $p12 = IMPLICIT_DEF
+ $p13 = IMPLICIT_DEF
+ $p14 = IMPLICIT_DEF
+ $p15 = IMPLICIT_DEF
+ $x19 = IMPLICIT_DEF
+ $x20 = IMPLICIT_DEF
+ $x21 = IMPLICIT_DEF
+ $sp = frame-destroy ADDXri $sp, 32, 0
+ frame-destroy CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x20, 0x22, 0x11, 0x98, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-destroy ADDVL_XXI $sp, 1
+ frame-destroy CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x20, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $z8 = frame-destroy LDR_ZXI $sp, 17 :: (load (s128) from %stack.2)
+ $z9 = frame-destroy LDR_ZXI $sp, 16 :: (load (s128) from %stack.3)
+ $z10 = frame-destroy LDR_ZXI $sp, 15 :: (load (s128) from %stack.4)
+ $z11 = frame-destroy LDR_ZXI $sp, 14 :: (load (s128) from %stack.5)
+ $z12 = frame-destroy LDR_ZXI $sp, 13 :: (load (s128) from %stack.6)
+ $z13 = frame-destroy LDR_ZXI $sp, 12 :: (load (s128) from %stack.7)
+ $z14 = frame-destroy LDR_ZXI $sp, 11 :: (load (s128) from %stack.8)
+ $z15 = frame-destroy LDR_ZXI $sp, 10 :: (load (s128) from %stack.9)
+ $z16 = frame-destroy LDR_ZXI $sp, 9 :: (load (s128) from %stack.10)
+ $z17 = frame-destroy LDR_ZXI $sp, 8 :: (load (s128) from %stack.11)
+ $z18 = frame-destroy LDR_ZXI $sp, 7 :: (load (s128) from %stack.12)
+ $z19 = frame-destroy LDR_ZXI $sp, 6 :: (load (s128) from %stack.13)
+ $z20 = frame-destroy LDR_ZXI $sp, 5 :: (load (s128) from %stack.14)
+ $z21 = frame-destroy LDR_ZXI $sp, 4 :: (load (s128) from %stack.15)
+ $z22 = frame-destroy LDR_ZXI $sp, 3 :: (load (s128) from %stack.16)
+ $z23 = frame-destroy LDR_ZXI $sp, 2 :: (load (s128) from %stack.17)
+ $p4 = frame-destroy LDR_PXI $sp, 15 :: (load (s16) from %stack.18)
+ $p5 = frame-destroy LDR_PXI $sp, 14 :: (load (s16) from %stack.19)
+ $p6 = frame-destroy LDR_PXI $sp, 13 :: (load (s16) from %stack.20)
+ $p7 = frame-destroy LDR_PXI $sp, 12 :: (load (s16) from %stack.21)
+ $p8 = frame-destroy LDR_PXI $sp, 11 :: (load (s16) from %stack.22)
+ $p9 = frame-destroy LDR_PXI $sp, 10 :: (load (s16) from %stack.23)
+ $p10 = frame-destroy LDR_PXI $sp, 9 :: (load (s16) from %stack.24)
+ $p11 = frame-destroy LDR_PXI $sp, 8 :: (load (s16) from %stack.25)
+ $p12 = frame-destroy LDR_PXI $sp, 7 :: (load (s16) from %stack.26)
+ $p13 = frame-destroy LDR_PXI $sp, 6 :: (load (s16) from %stack.27)
+ $p14 = frame-destroy LDR_PXI $sp, 5 :: (load (s16) from %stack.28)
+ $p15 = frame-destroy LDR_PXI $sp, 4 :: (load (s16) from %stack.29)
+ $sp = frame-destroy ADDVL_XXI $sp, 18
+ frame-destroy CFI_INSTRUCTION def_cfa $wsp, 32
+ frame-destroy CFI_INSTRUCTION restore $z8
+ frame-destroy CFI_INSTRUCTION restore $z9
+ frame-destroy CFI_INSTRUCTION restore $z10
+ frame-destroy CFI_INSTRUCTION restore $z11
+ frame-destroy CFI_INSTRUCTION restore $z12
+ frame-destroy CFI_INSTRUCTION restore $z13
+ frame-destroy CFI_INSTRUCTION restore $z14
+ frame-destroy CFI_INSTRUCTION restore $z15
+ $x20, $x19 = frame-destroy LDPXi $sp, 2 :: (load (s64) from %stack.31), (load (s64) from %stack.30)
+ early-clobber $sp, $fp, $x21 = frame-destroy LDPXpost $sp, 4 :: (load (s64) from %stack.33), (load (s64) from %stack.32)
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 0
+ frame-destroy CFI_INSTRUCTION restore $w19
+ frame-destroy CFI_INSTRUCTION restore $w20
+ frame-destroy CFI_INSTRUCTION restore $w21
+ frame-destroy CFI_INSTRUCTION restore $w29
+ RET_ReallyLR
+
+...
+---
+name: save_restore_sve_realign
+alignment: 1
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: false
+hasWinCFI: false
+callsEHReturn: false
+callsUnwindInit: false
+hasEHCatchret: false
+hasEHScopes: false
+hasEHFunclets: false
+isOutlined: false
+debugInstrRef: false
+failsVerification: false
+tracksDebugUserValues: false
+registers: []
+liveins: []
+frameInfo:
+ isFrameAddressTaken: false
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 32
+ offsetAdjustment: 0
+ maxAlignment: 32
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ functionContext: ''
+ maxCallFrameSize: 0
+ cvBytesOfCalleeSavedRegisters: 0
+ hasOpaqueSPAdjustment: false
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ hasTailCall: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack: []
+stack:
+ - { id: 0, name: '', type: default, offset: -304, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 1, name: '', type: default, offset: -32, size: 16, alignment: 32,
+ stack-id: default, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 2, name: '', type: spill-slot, offset: -16, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z8', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 3, name: '', type: spill-slot, offset: -32, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z9', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 4, name: '', type: spill-slot, offset: -48, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z10', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 5, name: '', type: spill-slot, offset: -64, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z11', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 6, name: '', type: spill-slot, offset: -80, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z12', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 7, name: '', type: spill-slot, offset: -96, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z13', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 8, name: '', type: spill-slot, offset: -112, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z14', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 9, name: '', type: spill-slot, offset: -128, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z15', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 10, name: '', type: spill-slot, offset: -144, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z16', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 11, name: '', type: spill-slot, offset: -160, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z17', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 12, name: '', type: spill-slot, offset: -176, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z18', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 13, name: '', type: spill-slot, offset: -192, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z19', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 14, name: '', type: spill-slot, offset: -208, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z20', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 15, name: '', type: spill-slot, offset: -224, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z21', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 16, name: '', type: spill-slot, offset: -240, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z22', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 17, name: '', type: spill-slot, offset: -256, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z23', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 18, name: '', type: spill-slot, offset: -258, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p4', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 19, name: '', type: spill-slot, offset: -260, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p5', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 20, name: '', type: spill-slot, offset: -262, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p6', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 21, name: '', type: spill-slot, offset: -264, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p7', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 22, name: '', type: spill-slot, offset: -266, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p8', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 23, name: '', type: spill-slot, offset: -268, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p9', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 24, name: '', type: spill-slot, offset: -270, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p10', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 25, name: '', type: spill-slot, offset: -272, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p11', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 26, name: '', type: spill-slot, offset: -274, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p12', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 27, name: '', type: spill-slot, offset: -276, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p13', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 28, name: '', type: spill-slot, offset: -278, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p14', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 29, name: '', type: spill-slot, offset: -280, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p15', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 30, name: '', type: spill-slot, offset: -8, size: 8, alignment: 8,
+ stack-id: default, callee-saved-register: '$lr', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 31, name: '', type: spill-slot, offset: -16, size: 8, alignment: 8,
+ stack-id: default, callee-saved-register: '$fp', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+entry_values: []
+callSites: []
+debugValueSubstitutions: []
+constants: []
+machineFunctionInfo:
+ hasRedZone: false
+body: |
+ bb.0.entry:
+ liveins: $lr, $p15, $p14, $p13, $p12, $p11, $p10, $p9, $p8, $p7, $p6, $p5, $p4, $z23, $z22, $z21, $z20, $z19, $z18, $z17, $z16, $z15, $z14, $z13, $z12, $z11, $z10, $z9, $z8
+
+ early-clobber $sp = frame-setup STPXpre killed $fp, killed $lr, $sp, -2 :: (store (s64) into %stack.31), (store (s64) into %stack.30)
+ frame-setup CFI_INSTRUCTION def_cfa_offset 16
+ $fp = frame-setup ADDXri $sp, 0, 0
+ frame-setup CFI_INSTRUCTION def_cfa $w29, 16
+ frame-setup CFI_INSTRUCTION offset $w30, -8
+ frame-setup CFI_INSTRUCTION offset $w29, -16
+ $sp = frame-setup ADDVL_XXI $sp, -18
+ frame-setup STR_PXI killed $p15, $sp, 4 :: (store (s16) into %stack.29)
+ frame-setup STR_PXI killed $p14, $sp, 5 :: (store (s16) into %stack.28)
+ frame-setup STR_PXI killed $p13, $sp, 6 :: (store (s16) into %stack.27)
+ frame-setup STR_PXI killed $p12, $sp, 7 :: (store (s16) into %stack.26)
+ frame-setup STR_PXI killed $p11, $sp, 8 :: (store (s16) into %stack.25)
+ frame-setup STR_PXI killed $p10, $sp, 9 :: (store (s16) into %stack.24)
+ frame-setup STR_PXI killed $p9, $sp, 10 :: (store (s16) into %stack.23)
+ frame-setup STR_PXI killed $p8, $sp, 11 :: (store (s16) into %stack.22)
+ frame-setup STR_PXI killed $p7, $sp, 12 :: (store (s16) into %stack.21)
+ frame-setup STR_PXI killed $p6, $sp, 13 :: (store (s16) into %stack.20)
+ frame-setup STR_PXI killed $p5, $sp, 14 :: (store (s16) into %stack.19)
+ frame-setup STR_PXI killed $p4, $sp, 15 :: (store (s16) into %stack.18)
+ frame-setup STR_ZXI killed $z23, $sp, 2 :: (store (s128) into %stack.17)
+ frame-setup STR_ZXI killed $z22, $sp, 3 :: (store (s128) into %stack.16)
+ frame-setup STR_ZXI killed $z21, $sp, 4 :: (store (s128) into %stack.15)
+ frame-setup STR_ZXI killed $z20, $sp, 5 :: (store (s128) into %stack.14)
+ frame-setup STR_ZXI killed $z19, $sp, 6 :: (store (s128) into %stack.13)
+ frame-setup STR_ZXI killed $z18, $sp, 7 :: (store (s128) into %stack.12)
+ frame-setup STR_ZXI killed $z17, $sp, 8 :: (store (s128) into %stack.11)
+ frame-setup STR_ZXI killed $z16, $sp, 9 :: (store (s128) into %stack.10)
+ frame-setup STR_ZXI killed $z15, $sp, 10 :: (store (s128) into %stack.9)
+ frame-setup STR_ZXI killed $z14, $sp, 11 :: (store (s128) into %stack.8)
+ frame-setup STR_ZXI killed $z13, $sp, 12 :: (store (s128) into %stack.7)
+ frame-setup STR_ZXI killed $z12, $sp, 13 :: (store (s128) into %stack.6)
+ frame-setup STR_ZXI killed $z11, $sp, 14 :: (store (s128) into %stack.5)
+ frame-setup STR_ZXI killed $z10, $sp, 15 :: (store (s128) into %stack.4)
+ frame-setup STR_ZXI killed $z9, $sp, 16 :: (store (s128) into %stack.3)
+ frame-setup STR_ZXI killed $z8, $sp, 17 :: (store (s128) into %stack.2)
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x48, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x49, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x4a, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x4b, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x60, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x4c, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x58, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x4d, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x50, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x4e, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $x9 = frame-setup SUBXri $sp, 16, 0
+ $x9 = frame-setup ADDVL_XXI $x9, -1
+ $sp = frame-setup ANDXri killed $x9, 7930
+ $z8_z9_z10_z11 = IMPLICIT_DEF
+ $z12_z13_z14_z15 = IMPLICIT_DEF
+ $z16_z17_z18_z19 = IMPLICIT_DEF
+ $z20_z21_z22_z23 = IMPLICIT_DEF
+ $z24_z25_z26_z27 = IMPLICIT_DEF
+ $z28_z29_z30_z31 = IMPLICIT_DEF
+ $p4 = IMPLICIT_DEF
+ $p5 = IMPLICIT_DEF
+ $p6 = IMPLICIT_DEF
+ $p7 = IMPLICIT_DEF
+ $p8 = IMPLICIT_DEF
+ $p9 = IMPLICIT_DEF
+ $p10 = IMPLICIT_DEF
+ $p11 = IMPLICIT_DEF
+ $p12 = IMPLICIT_DEF
+ $p13 = IMPLICIT_DEF
+ $p14 = IMPLICIT_DEF
+ $p15 = IMPLICIT_DEF
+ $sp = frame-destroy ADDVL_XXI $fp, -18
+ $z8 = frame-destroy LDR_ZXI $sp, 17 :: (load (s128) from %stack.2)
+ $z9 = frame-destroy LDR_ZXI $sp, 16 :: (load (s128) from %stack.3)
+ $z10 = frame-destroy LDR_ZXI $sp, 15 :: (load (s128) from %stack.4)
+ $z11 = frame-destroy LDR_ZXI $sp, 14 :: (load (s128) from %stack.5)
+ $z12 = frame-destroy LDR_ZXI $sp, 13 :: (load (s128) from %stack.6)
+ $z13 = frame-destroy LDR_ZXI $sp, 12 :: (load (s128) from %stack.7)
+ $z14 = frame-destroy LDR_ZXI $sp, 11 :: (load (s128) from %stack.8)
+ $z15 = frame-destroy LDR_ZXI $sp, 10 :: (load (s128) from %stack.9)
+ $z16 = frame-destroy LDR_ZXI $sp, 9 :: (load (s128) from %stack.10)
+ $z17 = frame-destroy LDR_ZXI $sp, 8 :: (load (s128) from %stack.11)
+ $z18 = frame-destroy LDR_ZXI $sp, 7 :: (load (s128) from %stack.12)
+ $z19 = frame-destroy LDR_ZXI $sp, 6 :: (load (s128) from %stack.13)
+ $z20 = frame-destroy LDR_ZXI $sp, 5 :: (load (s128) from %stack.14)
+ $z21 = frame-destroy LDR_ZXI $sp, 4 :: (load (s128) from %stack.15)
+ $z22 = frame-destroy LDR_ZXI $sp, 3 :: (load (s128) from %stack.16)
+ $z23 = frame-destroy LDR_ZXI $sp, 2 :: (load (s128) from %stack.17)
+ $p4 = frame-destroy LDR_PXI $sp, 15 :: (load (s16) from %stack.18)
+ $p5 = frame-destroy LDR_PXI $sp, 14 :: (load (s16) from %stack.19)
+ $p6 = frame-destroy LDR_PXI $sp, 13 :: (load (s16) from %stack.20)
+ $p7 = frame-destroy LDR_PXI $sp, 12 :: (load (s16) from %stack.21)
+ $p8 = frame-destroy LDR_PXI $sp, 11 :: (load (s16) from %stack.22)
+ $p9 = frame-destroy LDR_PXI $sp, 10 :: (load (s16) from %stack.23)
+ $p10 = frame-destroy LDR_PXI $sp, 9 :: (load (s16) from %stack.24)
+ $p11 = frame-destroy LDR_PXI $sp, 8 :: (load (s16) from %stack.25)
+ $p12 = frame-destroy LDR_PXI $sp, 7 :: (load (s16) from %stack.26)
+ $p13 = frame-destroy LDR_PXI $sp, 6 :: (load (s16) from %stack.27)
+ $p14 = frame-destroy LDR_PXI $sp, 5 :: (load (s16) from %stack.28)
+ $p15 = frame-destroy LDR_PXI $sp, 4 :: (load (s16) from %stack.29)
+ frame-destroy CFI_INSTRUCTION restore $z8
+ frame-destroy CFI_INSTRUCTION restore $z9
+ frame-destroy CFI_INSTRUCTION restore $z10
+ frame-destroy CFI_INSTRUCTION restore $z11
+ frame-destroy CFI_INSTRUCTION restore $z12
+ frame-destroy CFI_INSTRUCTION restore $z13
+ frame-destroy CFI_INSTRUCTION restore $z14
+ frame-destroy CFI_INSTRUCTION restore $z15
+ $sp = frame-destroy ADDXri $fp, 0, 0
+ frame-destroy CFI_INSTRUCTION def_cfa $wsp, 16
+ early-clobber $sp, $fp, $lr = frame-destroy LDPXpost $sp, 2 :: (load (s64) from %stack.31), (load (s64) from %stack.30)
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 0
+ frame-destroy CFI_INSTRUCTION restore $w30
+ frame-destroy CFI_INSTRUCTION restore $w29
+ RET_ReallyLR
+
+...
+---
+name: frame_layout
+alignment: 1
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: false
+hasWinCFI: false
+callsEHReturn: false
+callsUnwindInit: false
+hasEHCatchret: false
+hasEHScopes: false
+hasEHFunclets: false
+isOutlined: false
+debugInstrRef: false
+failsVerification: false
+tracksDebugUserValues: false
+registers: []
+liveins: []
+frameInfo:
+ isFrameAddressTaken: false
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 16
+ offsetAdjustment: 0
+ maxAlignment: 16
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ functionContext: ''
+ maxCallFrameSize: 0
+ cvBytesOfCalleeSavedRegisters: 0
+ hasOpaqueSPAdjustment: false
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ hasTailCall: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack: []
+stack:
+ - { id: 0, name: '', type: default, offset: -80, size: 32, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 1, name: '', type: default, offset: -84, size: 4, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 2, name: '', type: default, offset: -112, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 3, name: '', type: default, offset: -114, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 4, name: '', type: spill-slot, offset: -144, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 5, name: '', type: spill-slot, offset: -146, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 6, name: '', type: spill-slot, offset: -16, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z8', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 7, name: '', type: spill-slot, offset: -32, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '$z23', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 8, name: '', type: spill-slot, offset: -34, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p4', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 9, name: '', type: spill-slot, offset: -36, size: 2, alignment: 2,
+ stack-id: scalable-vector, callee-saved-register: '$p15', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 10, name: '', type: spill-slot, offset: -16, size: 8, alignment: 16,
+ stack-id: default, callee-saved-register: '$fp', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+entry_values: []
+callSites: []
+debugValueSubstitutions: []
+constants: []
+machineFunctionInfo:
+ hasRedZone: false
+body: |
+ bb.0.entry:
+ liveins: $p15, $p4, $z23, $z8
+
+ early-clobber $sp = frame-setup STRXpre killed $fp, $sp, -16 :: (store (s64) into %stack.10)
+ frame-setup CFI_INSTRUCTION def_cfa_offset 16
+ frame-setup CFI_INSTRUCTION offset $w29, -16
+ $sp = frame-setup ADDVL_XXI $sp, -3
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ frame-setup STR_PXI killed $p15, $sp, 6 :: (store (s16) into %stack.9)
+ frame-setup STR_PXI killed $p4, $sp, 7 :: (store (s16) into %stack.8)
+ frame-setup STR_ZXI killed $z23, $sp, 1 :: (store (s128) into %stack.7)
+ frame-setup STR_ZXI killed $z8, $sp, 2 :: (store (s128) into %stack.6)
+ frame-setup CFI_INSTRUCTION escape 0x10, 0x48, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $sp = frame-setup ADDVL_XXI $sp, -7
+ frame-setup CFI_INSTRUCTION escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0xd0, 0x00, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $z8 = IMPLICIT_DEF
+ $z23 = IMPLICIT_DEF
+ $p4 = IMPLICIT_DEF
+ $p15 = IMPLICIT_DEF
+ $sp = frame-destroy ADDVL_XXI $sp, 7
+ frame-destroy CFI_INSTRUCTION escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0x2e, 0x00, 0x1e, 0x22
+ $z8 = frame-destroy LDR_ZXI $sp, 2 :: (load (s128) from %stack.6)
+ $z23 = frame-destroy LDR_ZXI $sp, 1 :: (load (s128) from %stack.7)
+ $p4 = frame-destroy LDR_PXI $sp, 7 :: (load (s16) from %stack.8)
+ $p15 = frame-destroy LDR_PXI $sp, 6 :: (load (s16) from %stack.9)
+ $sp = frame-destroy ADDVL_XXI $sp, 3
+ frame-destroy CFI_INSTRUCTION def_cfa $wsp, 16
+ frame-destroy CFI_INSTRUCTION restore $z8
+ early-clobber $sp, $fp = frame-destroy LDRXpost $sp, 16 :: (load (s64) from %stack.10)
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 0
+ frame-destroy CFI_INSTRUCTION restore $w29
+ RET_ReallyLR
+
+...
+---
+name: fp_relative_index_with_float_save
+alignment: 1
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: false
+hasWinCFI: false
+callsEHReturn: false
+callsUnwindInit: false
+hasEHCatchret: false
+hasEHScopes: false
+hasEHFunclets: false
+isOutlined: false
+debugInstrRef: false
+failsVerification: false
+tracksDebugUserValues: false
+registers: []
+liveins: []
+frameInfo:
+ isFrameAddressTaken: true
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 64
+ offsetAdjustment: 0
+ maxAlignment: 32
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ functionContext: ''
+ maxCallFrameSize: 0
+ cvBytesOfCalleeSavedRegisters: 0
+ hasOpaqueSPAdjustment: false
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ hasTailCall: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack: []
+stack:
+ - { id: 0, name: '', type: default, offset: -16, size: 16, alignment: 16,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 1, name: '', type: default, offset: -64, size: 16, alignment: 32,
+ stack-id: default, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 2, name: '', type: spill-slot, offset: -8, size: 8, alignment: 8,
+ stack-id: default, callee-saved-register: '$lr', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 3, name: '', type: spill-slot, offset: -16, size: 8, alignment: 8,
+ stack-id: default, callee-saved-register: '$fp', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 4, name: '', type: spill-slot, offset: -32, size: 8, alignment: 16,
+ stack-id: default, callee-saved-register: '$d8', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+entry_values: []
+callSites: []
+debugValueSubstitutions: []
+constants: []
+machineFunctionInfo:
+ hasRedZone: false
+body: |
+ bb.0.entry:
+ liveins: $z0, $d8, $lr
+
+ early-clobber $sp = frame-setup STRDpre killed $d8, $sp, -32 :: (store (s64) into %stack.4)
+ frame-setup CFI_INSTRUCTION def_cfa_offset 32
+ frame-setup STPXi killed $fp, killed $lr, $sp, 2 :: (store (s64) into %stack.3), (store (s64) into %stack.2)
+ $fp = frame-setup ADDXri $sp, 16, 0
+ frame-setup CFI_INSTRUCTION def_cfa $w29, 16
+ frame-setup CFI_INSTRUCTION offset $w30, -8
+ frame-setup CFI_INSTRUCTION offset $w29, -16
+ frame-setup CFI_INSTRUCTION offset $b8, -32
+ $x9 = frame-setup SUBXri $sp, 32, 0
+ $x9 = frame-setup ADDVL_XXI $x9, -1
+ $sp = frame-setup ANDXri killed $x9, 7930
+ $d8 = IMPLICIT_DEF
+ $x8 = SUBXri $fp, 16, 0
+ STR_ZXI $z0, killed $x8, -1
+ $sp = frame-destroy SUBXri $fp, 16, 0
+ frame-destroy CFI_INSTRUCTION def_cfa $wsp, 32
+ $fp, $lr = frame-destroy LDPXi $sp, 2 :: (load (s64) from %stack.3), (load (s64) from %stack.2)
+ early-clobber $sp, $d8 = frame-destroy LDRDpost $sp, 32 :: (load (s64) from %stack.4)
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 0
+ frame-destroy CFI_INSTRUCTION restore $w30
+ frame-destroy CFI_INSTRUCTION restore $w29
+ frame-destroy CFI_INSTRUCTION restore $b8
+ RET_ReallyLR
+
+...
+---
+name: fp_relative_that_is_not_a_multiple_of_VLx16
+alignment: 1
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: false
+hasWinCFI: false
+callsEHReturn: false
+callsUnwindInit: false
+hasEHCatchret: false
+hasEHScopes: false
+hasEHFunclets: false
+isOutlined: false
+debugInstrRef: false
+failsVerification: false
+tracksDebugUserValues: false
+registers: []
+liveins: []
+frameInfo:
+ isFrameAddressTaken: false
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 32
+ offsetAdjustment: 0
+ maxAlignment: 16
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ functionContext: ''
+ maxCallFrameSize: 0
+ cvBytesOfCalleeSavedRegisters: 0
+ hasOpaqueSPAdjustment: false
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ hasTailCall: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack: []
+stack:
+ - { id: 0, name: '', type: default, offset: -156, size: 156, alignment: 1,
+ stack-id: scalable-vector, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 1, name: '', type: variable-sized, offset: -32, alignment: 1,
+ stack-id: default, callee-saved-register: '', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 2, name: '', type: spill-slot, offset: -16, size: 8, alignment: 16,
+ stack-id: default, callee-saved-register: '$x19', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 3, name: '', type: spill-slot, offset: -24, size: 8, alignment: 8,
+ stack-id: default, callee-saved-register: '$lr', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 4, name: '', type: spill-slot, offset: -32, size: 8, alignment: 8,
+ stack-id: default, callee-saved-register: '$fp', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+entry_values: []
+callSites: []
+debugValueSubstitutions: []
+constants: []
+machineFunctionInfo:
+ hasRedZone: false
+body: |
+ bb.0.entry:
+ liveins: $p0, $lr
+
+ early-clobber $sp = frame-setup STPXpre killed $fp, killed $lr, $sp, -4 :: (store (s64) into %stack.4), (store (s64) into %stack.3)
+ frame-setup CFI_INSTRUCTION def_cfa_offset 32
+ frame-setup STRXui killed $x19, $sp, 2 :: (store (s64) into %stack.2)
+ $fp = frame-setup ADDXri $sp, 0, 0
+ frame-setup CFI_INSTRUCTION def_cfa $w29, 32
+ frame-setup CFI_INSTRUCTION offset $w19, -16
+ frame-setup CFI_INSTRUCTION offset $w30, -24
+ frame-setup CFI_INSTRUCTION offset $w29, -32
+ $sp = frame-setup ADDVL_XXI $sp, -10
+ $x19 = ADDXri $sp, 0, 0
+ $x8 = ADDPL_XXI $fp, -14
+ renamable $z0 = LD1W_IMM killed renamable $p0, killed $x8, -8
+ $sp = frame-destroy ADDXri $fp, 0, 0
+ frame-destroy CFI_INSTRUCTION def_cfa $wsp, 32
+ $x19 = frame-destroy LDRXui $sp, 2 :: (load (s64) from %stack.2)
+ early-clobber $sp, $fp, $lr = frame-destroy LDPXpost $sp, 4 :: (load (s64) from %stack.4), (load (s64) from %stack.3)
+ frame-destroy CFI_INSTRUCTION def_cfa_offset 0
+ frame-destroy CFI_INSTRUCTION restore $w19
+ frame-destroy CFI_INSTRUCTION restore $w30
+ frame-destroy CFI_INSTRUCTION restore $w29
+ RET_ReallyLR
+
+...
More information about the llvm-commits
mailing list