[llvm-branch-commits] [llvm] [AArch64] Disable SVE paired ld1/st1 for callee-saves. (PR #107406)

Sander de Smalen via llvm-branch-commits llvm-branch-commits at lists.llvm.org
Thu Sep 5 07:20:59 PDT 2024


https://github.com/sdesmalen-arm created https://github.com/llvm/llvm-project/pull/107406

The functionality to make use of SVE's load/store pair instructions for the callee-saves is broken because the offsets used in the instructions are incorrect.

This is addressed by #105518 but given the complexity of this code and the subtleties around calculating the right offsets, we favour disabling the behaviour altogether for LLVM 19.

This fix is critical for any programs being compiled with `+sme2`.

>From 7dd550be0af7ae1ffb806af80c4fd2bc3bc79fd7 Mon Sep 17 00:00:00 2001
From: Sander de Smalen <sander.desmalen at arm.com>
Date: Thu, 5 Sep 2024 15:06:19 +0100
Subject: [PATCH] [AArch64] Disable SVE paired ld1/st1 for callee-saves.

The functionality to make use of SVE's load/store pair instructions for
the callee-saves is broken because the offsets used in the instructions
are incorrect.

This is addressed by #105518 but given the complexity of this code
and the subtleties around calculating the right offsets, we favour
disabling the behaviour altogether for LLVM 19.

This fix is critical for any programs being compiled with `+sme2`.
---
 .../Target/AArch64/AArch64FrameLowering.cpp   |   33 -
 llvm/test/CodeGen/AArch64/sme-vg-to-stack.ll  |  104 +-
 .../CodeGen/AArch64/sme2-intrinsics-ld1.ll    | 1488 +++++++++++------
 .../CodeGen/AArch64/sme2-intrinsics-ldnt1.ll  | 1488 +++++++++++------
 .../AArch64/sve-callee-save-restore-pairs.ll  |  140 +-
 5 files changed, 2036 insertions(+), 1217 deletions(-)

diff --git a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
index ba46ededc63a83..87e057a468afd6 100644
--- a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -2931,16 +2931,6 @@ struct RegPairInfo {
 
 } // end anonymous namespace
 
-unsigned findFreePredicateReg(BitVector &SavedRegs) {
-  for (unsigned PReg = AArch64::P8; PReg <= AArch64::P15; ++PReg) {
-    if (SavedRegs.test(PReg)) {
-      unsigned PNReg = PReg - AArch64::P0 + AArch64::PN0;
-      return PNReg;
-    }
-  }
-  return AArch64::NoRegister;
-}
-
 static void computeCalleeSaveRegisterPairs(
     MachineFunction &MF, ArrayRef<CalleeSavedInfo> CSI,
     const TargetRegisterInfo *TRI, SmallVectorImpl<RegPairInfo> &RegPairs,
@@ -3645,7 +3635,6 @@ void AArch64FrameLowering::determineCalleeSaves(MachineFunction &MF,
 
   unsigned ExtraCSSpill = 0;
   bool HasUnpairedGPR64 = false;
-  bool HasPairZReg = false;
   // Figure out which callee-saved registers to save/restore.
   for (unsigned i = 0; CSRegs[i]; ++i) {
     const unsigned Reg = CSRegs[i];
@@ -3699,28 +3688,6 @@ void AArch64FrameLowering::determineCalleeSaves(MachineFunction &MF,
           !RegInfo->isReservedReg(MF, PairedReg))
         ExtraCSSpill = PairedReg;
     }
-    // Check if there is a pair of ZRegs, so it can select PReg for spill/fill
-    HasPairZReg |= (AArch64::ZPRRegClass.contains(Reg, CSRegs[i ^ 1]) &&
-                    SavedRegs.test(CSRegs[i ^ 1]));
-  }
-
-  if (HasPairZReg && (Subtarget.hasSVE2p1() || Subtarget.hasSME2())) {
-    AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
-    // Find a suitable predicate register for the multi-vector spill/fill
-    // instructions.
-    unsigned PnReg = findFreePredicateReg(SavedRegs);
-    if (PnReg != AArch64::NoRegister)
-      AFI->setPredicateRegForFillSpill(PnReg);
-    // If no free callee-save has been found assign one.
-    if (!AFI->getPredicateRegForFillSpill() &&
-        MF.getFunction().getCallingConv() ==
-            CallingConv::AArch64_SVE_VectorCall) {
-      SavedRegs.set(AArch64::P8);
-      AFI->setPredicateRegForFillSpill(AArch64::PN8);
-    }
-
-    assert(!RegInfo->isReservedReg(MF, AFI->getPredicateRegForFillSpill()) &&
-           "Predicate cannot be a reserved register");
   }
 
   if (MF.getFunction().getCallingConv() == CallingConv::Win64 &&
diff --git a/llvm/test/CodeGen/AArch64/sme-vg-to-stack.ll b/llvm/test/CodeGen/AArch64/sme-vg-to-stack.ll
index 6264ce0cf4ae6d..fa8f92cb0a2c99 100644
--- a/llvm/test/CodeGen/AArch64/sme-vg-to-stack.ll
+++ b/llvm/test/CodeGen/AArch64/sme-vg-to-stack.ll
@@ -329,27 +329,34 @@ define void @vg_unwind_with_sve_args(<vscale x 2 x i64> %x) #0 {
 ; CHECK-NEXT:    .cfi_offset w29, -32
 ; CHECK-NEXT:    addvl sp, sp, #-18
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x20, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 32 + 144 * VG
-; CHECK-NEXT:    str p8, [sp, #11, mul vl] // 2-byte Folded Spill
-; CHECK-NEXT:    ptrue pn8.b
 ; CHECK-NEXT:    str p15, [sp, #4, mul vl] // 2-byte Folded Spill
-; CHECK-NEXT:    st1b { z22.b, z23.b }, pn8, [sp, #4, mul vl] // 32-byte Folded Spill
-; CHECK-NEXT:    st1b { z20.b, z21.b }, pn8, [sp, #8, mul vl] // 32-byte Folded Spill
 ; CHECK-NEXT:    str p14, [sp, #5, mul vl] // 2-byte Folded Spill
-; CHECK-NEXT:    st1b { z18.b, z19.b }, pn8, [sp, #12, mul vl] // 32-byte Folded Spill
-; CHECK-NEXT:    st1b { z16.b, z17.b }, pn8, [sp, #16, mul vl] // 32-byte Folded Spill
 ; CHECK-NEXT:    str p13, [sp, #6, mul vl] // 2-byte Folded Spill
-; CHECK-NEXT:    st1b { z14.b, z15.b }, pn8, [sp, #20, mul vl] // 32-byte Folded Spill
-; CHECK-NEXT:    st1b { z12.b, z13.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
 ; CHECK-NEXT:    str p12, [sp, #7, mul vl] // 2-byte Folded Spill
-; CHECK-NEXT:    st1b { z10.b, z11.b }, pn8, [sp, #28, mul vl] // 32-byte Folded Spill
 ; CHECK-NEXT:    str p11, [sp, #8, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    str p10, [sp, #9, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    str p9, [sp, #10, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    str p8, [sp, #11, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    str p7, [sp, #12, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    str p6, [sp, #13, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    str p5, [sp, #14, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    str p4, [sp, #15, mul vl] // 2-byte Folded Spill
-; CHECK-NEXT:    st1b { z8.b, z9.b }, pn8, [sp, #32, mul vl] // 32-byte Folded Spill
+; CHECK-NEXT:    str z23, [sp, #2, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    str z22, [sp, #3, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    str z21, [sp, #4, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    str z20, [sp, #5, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    str z19, [sp, #6, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    str z18, [sp, #7, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    str z17, [sp, #8, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    str z16, [sp, #9, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    str z15, [sp, #10, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    str z14, [sp, #11, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    str z13, [sp, #12, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    str z12, [sp, #13, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    str z11, [sp, #14, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    str z10, [sp, #15, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    str z9, [sp, #16, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    str z8, [sp, #17, mul vl] // 16-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x10, 0x48, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 32 - 8 * VG
 ; CHECK-NEXT:    .cfi_escape 0x10, 0x49, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 32 - 16 * VG
 ; CHECK-NEXT:    .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 32 - 24 * VG
@@ -371,16 +378,23 @@ define void @vg_unwind_with_sve_args(<vscale x 2 x i64> %x) #0 {
 ; CHECK-NEXT:    .cfi_restore vg
 ; CHECK-NEXT:    addvl sp, sp, #1
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x20, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 32 + 144 * VG
-; CHECK-NEXT:    ptrue pn8.b
+; 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 p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; CHECK-NEXT:    ld1b { z22.b, z23.b }, pn8/z, [sp, #4, mul vl] // 32-byte Folded Reload
-; CHECK-NEXT:    ld1b { z20.b, z21.b }, pn8/z, [sp, #8, mul vl] // 32-byte Folded Reload
-; CHECK-NEXT:    ld1b { z18.b, z19.b }, pn8/z, [sp, #12, mul vl] // 32-byte Folded Reload
-; CHECK-NEXT:    ld1b { z16.b, z17.b }, pn8/z, [sp, #16, mul vl] // 32-byte Folded Reload
-; CHECK-NEXT:    ld1b { z14.b, z15.b }, pn8/z, [sp, #20, mul vl] // 32-byte Folded Reload
-; CHECK-NEXT:    ld1b { z12.b, z13.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
-; CHECK-NEXT:    ld1b { z10.b, z11.b }, pn8/z, [sp, #28, mul vl] // 32-byte Folded Reload
-; CHECK-NEXT:    ld1b { z8.b, z9.b }, pn8/z, [sp, #32, mul vl] // 32-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
@@ -424,27 +438,34 @@ define void @vg_unwind_with_sve_args(<vscale x 2 x i64> %x) #0 {
 ; FP-CHECK-NEXT:    .cfi_offset w30, -40
 ; FP-CHECK-NEXT:    .cfi_offset w29, -48
 ; FP-CHECK-NEXT:    addvl sp, sp, #-18
-; FP-CHECK-NEXT:    str p8, [sp, #11, mul vl] // 2-byte Folded Spill
-; FP-CHECK-NEXT:    ptrue pn8.b
 ; FP-CHECK-NEXT:    str p15, [sp, #4, mul vl] // 2-byte Folded Spill
-; FP-CHECK-NEXT:    st1b { z22.b, z23.b }, pn8, [sp, #4, mul vl] // 32-byte Folded Spill
-; FP-CHECK-NEXT:    st1b { z20.b, z21.b }, pn8, [sp, #8, mul vl] // 32-byte Folded Spill
 ; FP-CHECK-NEXT:    str p14, [sp, #5, mul vl] // 2-byte Folded Spill
-; FP-CHECK-NEXT:    st1b { z18.b, z19.b }, pn8, [sp, #12, mul vl] // 32-byte Folded Spill
-; FP-CHECK-NEXT:    st1b { z16.b, z17.b }, pn8, [sp, #16, mul vl] // 32-byte Folded Spill
 ; FP-CHECK-NEXT:    str p13, [sp, #6, mul vl] // 2-byte Folded Spill
-; FP-CHECK-NEXT:    st1b { z14.b, z15.b }, pn8, [sp, #20, mul vl] // 32-byte Folded Spill
-; FP-CHECK-NEXT:    st1b { z12.b, z13.b }, pn8, [sp, #24, mul vl] // 32-byte Folded Spill
 ; FP-CHECK-NEXT:    str p12, [sp, #7, mul vl] // 2-byte Folded Spill
-; FP-CHECK-NEXT:    st1b { z10.b, z11.b }, pn8, [sp, #28, mul vl] // 32-byte Folded Spill
 ; FP-CHECK-NEXT:    str p11, [sp, #8, mul vl] // 2-byte Folded Spill
 ; FP-CHECK-NEXT:    str p10, [sp, #9, mul vl] // 2-byte Folded Spill
 ; FP-CHECK-NEXT:    str p9, [sp, #10, mul vl] // 2-byte Folded Spill
+; FP-CHECK-NEXT:    str p8, [sp, #11, mul vl] // 2-byte Folded Spill
 ; FP-CHECK-NEXT:    str p7, [sp, #12, mul vl] // 2-byte Folded Spill
 ; FP-CHECK-NEXT:    str p6, [sp, #13, mul vl] // 2-byte Folded Spill
 ; FP-CHECK-NEXT:    str p5, [sp, #14, mul vl] // 2-byte Folded Spill
 ; FP-CHECK-NEXT:    str p4, [sp, #15, mul vl] // 2-byte Folded Spill
-; FP-CHECK-NEXT:    st1b { z8.b, z9.b }, pn8, [sp, #32, mul vl] // 32-byte Folded Spill
+; FP-CHECK-NEXT:    str z23, [sp, #2, mul vl] // 16-byte Folded Spill
+; FP-CHECK-NEXT:    str z22, [sp, #3, mul vl] // 16-byte Folded Spill
+; FP-CHECK-NEXT:    str z21, [sp, #4, mul vl] // 16-byte Folded Spill
+; FP-CHECK-NEXT:    str z20, [sp, #5, mul vl] // 16-byte Folded Spill
+; FP-CHECK-NEXT:    str z19, [sp, #6, mul vl] // 16-byte Folded Spill
+; FP-CHECK-NEXT:    str z18, [sp, #7, mul vl] // 16-byte Folded Spill
+; FP-CHECK-NEXT:    str z17, [sp, #8, mul vl] // 16-byte Folded Spill
+; FP-CHECK-NEXT:    str z16, [sp, #9, mul vl] // 16-byte Folded Spill
+; FP-CHECK-NEXT:    str z15, [sp, #10, mul vl] // 16-byte Folded Spill
+; FP-CHECK-NEXT:    str z14, [sp, #11, mul vl] // 16-byte Folded Spill
+; FP-CHECK-NEXT:    str z13, [sp, #12, mul vl] // 16-byte Folded Spill
+; FP-CHECK-NEXT:    str z12, [sp, #13, mul vl] // 16-byte Folded Spill
+; FP-CHECK-NEXT:    str z11, [sp, #14, mul vl] // 16-byte Folded Spill
+; FP-CHECK-NEXT:    str z10, [sp, #15, mul vl] // 16-byte Folded Spill
+; FP-CHECK-NEXT:    str z9, [sp, #16, mul vl] // 16-byte Folded Spill
+; FP-CHECK-NEXT:    str z8, [sp, #17, mul vl] // 16-byte Folded Spill
 ; FP-CHECK-NEXT:    .cfi_escape 0x10, 0x48, 0x0a, 0x11, 0x50, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 48 - 8 * VG
 ; FP-CHECK-NEXT:    .cfi_escape 0x10, 0x49, 0x0a, 0x11, 0x50, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 48 - 16 * VG
 ; FP-CHECK-NEXT:    .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x50, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 48 - 24 * VG
@@ -464,16 +485,23 @@ define void @vg_unwind_with_sve_args(<vscale x 2 x i64> %x) #0 {
 ; FP-CHECK-NEXT:    smstart sm
 ; FP-CHECK-NEXT:    .cfi_restore vg
 ; FP-CHECK-NEXT:    addvl sp, sp, #1
-; FP-CHECK-NEXT:    ptrue pn8.b
+; FP-CHECK-NEXT:    ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
+; FP-CHECK-NEXT:    ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; FP-CHECK-NEXT:    ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; FP-CHECK-NEXT:    ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; FP-CHECK-NEXT:    ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; FP-CHECK-NEXT:    ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; FP-CHECK-NEXT:    ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; FP-CHECK-NEXT:    ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; FP-CHECK-NEXT:    ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; FP-CHECK-NEXT:    ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; FP-CHECK-NEXT:    ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; FP-CHECK-NEXT:    ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; FP-CHECK-NEXT:    ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; FP-CHECK-NEXT:    ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; FP-CHECK-NEXT:    ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; FP-CHECK-NEXT:    ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
 ; FP-CHECK-NEXT:    ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; FP-CHECK-NEXT:    ld1b { z22.b, z23.b }, pn8/z, [sp, #4, mul vl] // 32-byte Folded Reload
-; FP-CHECK-NEXT:    ld1b { z20.b, z21.b }, pn8/z, [sp, #8, mul vl] // 32-byte Folded Reload
-; FP-CHECK-NEXT:    ld1b { z18.b, z19.b }, pn8/z, [sp, #12, mul vl] // 32-byte Folded Reload
-; FP-CHECK-NEXT:    ld1b { z16.b, z17.b }, pn8/z, [sp, #16, mul vl] // 32-byte Folded Reload
-; FP-CHECK-NEXT:    ld1b { z14.b, z15.b }, pn8/z, [sp, #20, mul vl] // 32-byte Folded Reload
-; FP-CHECK-NEXT:    ld1b { z12.b, z13.b }, pn8/z, [sp, #24, mul vl] // 32-byte Folded Reload
-; FP-CHECK-NEXT:    ld1b { z10.b, z11.b }, pn8/z, [sp, #28, mul vl] // 32-byte Folded Reload
-; FP-CHECK-NEXT:    ld1b { z8.b, z9.b }, pn8/z, [sp, #32, mul vl] // 32-byte Folded Reload
 ; FP-CHECK-NEXT:    ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
 ; FP-CHECK-NEXT:    ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
 ; FP-CHECK-NEXT:    ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
diff --git a/llvm/test/CodeGen/AArch64/sme2-intrinsics-ld1.ll b/llvm/test/CodeGen/AArch64/sme2-intrinsics-ld1.ll
index 29d3d68fc4c3de..013d8a0512b157 100644
--- a/llvm/test/CodeGen/AArch64/sme2-intrinsics-ld1.ll
+++ b/llvm/test/CodeGen/AArch64/sme2-intrinsics-ld1.ll
@@ -55,31 +55,45 @@ 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:    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:    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:    mov z1.d, z8.d
-; 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:    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:    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:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; STRIDED-NEXT:    ret
@@ -89,14 +103,20 @@ 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:    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 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:    str z9, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-2
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -109,15 +129,21 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -184,31 +210,45 @@ 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:    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:    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:    mov z1.d, z8.d
-; 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:    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:    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:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; STRIDED-NEXT:    ret
@@ -218,14 +258,20 @@ 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:    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 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:    str z9, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-2
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -238,15 +284,21 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -314,31 +366,45 @@ 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:    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:    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:    mov z1.d, z8.d
-; 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:    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:    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:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; STRIDED-NEXT:    ret
@@ -348,14 +414,20 @@ 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:    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 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:    str z9, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-2
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -368,15 +440,21 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -443,31 +521,45 @@ 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:    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:    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:    mov z1.d, z8.d
-; 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:    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:    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:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; STRIDED-NEXT:    ret
@@ -477,14 +569,20 @@ 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:    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 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:    str z9, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-2
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -497,15 +595,21 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -573,31 +677,45 @@ 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:    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:    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:    mov z1.d, z8.d
-; 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:    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:    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:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; STRIDED-NEXT:    ret
@@ -607,14 +725,20 @@ 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:    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 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:    str z9, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-2
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -627,15 +751,21 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -702,31 +832,45 @@ 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:    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:    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:    mov z1.d, z8.d
-; 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:    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:    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:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; STRIDED-NEXT:    ret
@@ -736,14 +880,20 @@ 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:    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 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:    str z9, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-2
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -756,15 +906,21 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -832,31 +988,45 @@ 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:    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:    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:    mov z1.d, z8.d
-; 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:    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:    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:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; STRIDED-NEXT:    ret
@@ -866,14 +1036,20 @@ 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:    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 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:    str z9, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-2
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -886,15 +1062,21 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -961,31 +1143,45 @@ 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:    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:    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:    mov z1.d, z8.d
-; 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:    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:    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:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; STRIDED-NEXT:    ret
@@ -995,14 +1191,20 @@ 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:    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 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:    str z9, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-2
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -1015,15 +1217,21 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -1093,32 +1301,46 @@ 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:    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:    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 { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; 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:    mov z2.d, z8.d
 ; STRIDED-NEXT:    mov z3.d, z12.d
-; STRIDED-NEXT:    ld1b { z12.b, z13.b }, pn8/z, [sp, #22, 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:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
+; 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:    mov z1.d, z4.d
 ; STRIDED-NEXT:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1129,14 +1351,19 @@ 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:    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 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:    st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-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:    str z9, [sp, #14, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-4
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -1153,15 +1380,20 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -1234,32 +1466,46 @@ 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:    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:    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 { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; 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:    mov z2.d, z8.d
 ; STRIDED-NEXT:    mov z3.d, z12.d
-; STRIDED-NEXT:    ld1b { z12.b, z13.b }, pn8/z, [sp, #22, 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:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
+; 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:    mov z1.d, z4.d
 ; STRIDED-NEXT:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1270,14 +1516,19 @@ 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:    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 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:    st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-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:    str z9, [sp, #14, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-4
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -1294,15 +1545,20 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -1376,32 +1632,46 @@ 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:    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:    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 { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; 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:    mov z2.d, z8.d
 ; STRIDED-NEXT:    mov z3.d, z12.d
-; STRIDED-NEXT:    ld1b { z12.b, z13.b }, pn8/z, [sp, #22, 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:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
+; 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:    mov z1.d, z4.d
 ; STRIDED-NEXT:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1412,14 +1682,19 @@ 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:    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 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:    st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-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:    str z9, [sp, #14, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-4
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -1436,15 +1711,20 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -1518,32 +1798,46 @@ 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:    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:    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 { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; 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:    mov z2.d, z8.d
 ; STRIDED-NEXT:    mov z3.d, z12.d
-; STRIDED-NEXT:    ld1b { z12.b, z13.b }, pn8/z, [sp, #22, 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:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
+; 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:    mov z1.d, z4.d
 ; STRIDED-NEXT:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1554,14 +1848,19 @@ 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:    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 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:    st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-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:    str z9, [sp, #14, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-4
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -1578,15 +1877,20 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -1660,32 +1964,46 @@ 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:    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:    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 { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; 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:    mov z2.d, z8.d
 ; STRIDED-NEXT:    mov z3.d, z12.d
-; STRIDED-NEXT:    ld1b { z12.b, z13.b }, pn8/z, [sp, #22, 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:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
+; 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:    mov z1.d, z4.d
 ; STRIDED-NEXT:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1696,14 +2014,19 @@ 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:    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 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:    st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-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:    str z9, [sp, #14, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-4
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -1720,15 +2043,20 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -1802,32 +2130,46 @@ 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:    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:    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 { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; 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:    mov z2.d, z8.d
 ; STRIDED-NEXT:    mov z3.d, z12.d
-; STRIDED-NEXT:    ld1b { z12.b, z13.b }, pn8/z, [sp, #22, 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:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
+; 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:    mov z1.d, z4.d
 ; STRIDED-NEXT:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1838,14 +2180,19 @@ 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:    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 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:    st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-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:    str z9, [sp, #14, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-4
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -1862,15 +2209,20 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -1944,32 +2296,46 @@ 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:    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:    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 { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; 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:    mov z2.d, z8.d
 ; STRIDED-NEXT:    mov z3.d, z12.d
-; STRIDED-NEXT:    ld1b { z12.b, z13.b }, pn8/z, [sp, #22, 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:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
+; 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:    mov z1.d, z4.d
 ; STRIDED-NEXT:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1980,14 +2346,19 @@ 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:    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 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:    st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-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:    str z9, [sp, #14, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-4
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -2004,15 +2375,20 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -2086,32 +2462,46 @@ 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:    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:    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 { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; 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:    mov z2.d, z8.d
 ; STRIDED-NEXT:    mov z3.d, z12.d
-; STRIDED-NEXT:    ld1b { z12.b, z13.b }, pn8/z, [sp, #22, 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:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
+; 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:    mov z1.d, z4.d
 ; STRIDED-NEXT:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -2122,14 +2512,19 @@ 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:    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 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:    st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-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:    str z9, [sp, #14, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-4
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -2146,15 +2541,20 @@ 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:    ptrue pn8.b
+; 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:    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:    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
diff --git a/llvm/test/CodeGen/AArch64/sme2-intrinsics-ldnt1.ll b/llvm/test/CodeGen/AArch64/sme2-intrinsics-ldnt1.ll
index 3d3748e1011228..eff1260c947dd3 100644
--- a/llvm/test/CodeGen/AArch64/sme2-intrinsics-ldnt1.ll
+++ b/llvm/test/CodeGen/AArch64/sme2-intrinsics-ldnt1.ll
@@ -8,31 +8,45 @@ 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:    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:    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:    mov z1.d, z8.d
-; 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:    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:    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:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; STRIDED-NEXT:    ret
@@ -42,14 +56,20 @@ 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:    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 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:    str z9, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-2
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -62,15 +82,21 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -90,31 +116,45 @@ 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:    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:    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:    mov z1.d, z8.d
-; 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:    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:    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:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; STRIDED-NEXT:    ret
@@ -124,14 +164,20 @@ 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:    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 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:    str z9, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-2
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -144,15 +190,21 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -173,31 +225,45 @@ 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:    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:    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:    mov z1.d, z8.d
-; 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:    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:    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:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; STRIDED-NEXT:    ret
@@ -207,14 +273,20 @@ 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:    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 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:    str z9, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-2
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -227,15 +299,21 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -255,31 +333,45 @@ 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:    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:    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:    mov z1.d, z8.d
-; 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:    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:    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:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; STRIDED-NEXT:    ret
@@ -289,14 +381,20 @@ 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:    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 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:    str z9, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-2
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -309,15 +407,21 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -338,31 +442,45 @@ 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:    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:    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:    mov z1.d, z8.d
-; 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:    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:    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:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; STRIDED-NEXT:    ret
@@ -372,14 +490,20 @@ 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:    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 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:    str z9, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-2
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -392,15 +516,21 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -420,31 +550,45 @@ 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:    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:    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:    mov z1.d, z8.d
-; 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:    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:    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:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; STRIDED-NEXT:    ret
@@ -454,14 +598,20 @@ 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:    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 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:    str z9, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-2
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -474,15 +624,21 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -503,31 +659,45 @@ 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:    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:    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:    mov z1.d, z8.d
-; 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:    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:    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:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; STRIDED-NEXT:    ret
@@ -537,14 +707,20 @@ 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:    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 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:    str z9, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-2
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -557,15 +733,21 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -585,31 +767,45 @@ 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:    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:    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:    mov z1.d, z8.d
-; 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:    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:    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:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; STRIDED-NEXT:    ret
@@ -619,14 +815,20 @@ 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:    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 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:    str z9, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-2
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -639,15 +841,21 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -668,32 +876,46 @@ 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:    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:    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 { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; 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:    mov z2.d, z8.d
 ; STRIDED-NEXT:    mov z3.d, z12.d
-; STRIDED-NEXT:    ld1b { z12.b, z13.b }, pn8/z, [sp, #22, 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:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
+; 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:    mov z1.d, z4.d
 ; STRIDED-NEXT:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -704,14 +926,19 @@ 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:    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 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:    st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-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:    str z9, [sp, #14, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-4
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -728,15 +955,20 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -760,32 +992,46 @@ 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:    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:    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 { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; 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:    mov z2.d, z8.d
 ; STRIDED-NEXT:    mov z3.d, z12.d
-; STRIDED-NEXT:    ld1b { z12.b, z13.b }, pn8/z, [sp, #22, 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:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
+; 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:    mov z1.d, z4.d
 ; STRIDED-NEXT:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -796,14 +1042,19 @@ 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:    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 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:    st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-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:    str z9, [sp, #14, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-4
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -820,15 +1071,20 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -853,32 +1109,46 @@ 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:    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:    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 { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; 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:    mov z2.d, z8.d
 ; STRIDED-NEXT:    mov z3.d, z12.d
-; STRIDED-NEXT:    ld1b { z12.b, z13.b }, pn8/z, [sp, #22, 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:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
+; 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:    mov z1.d, z4.d
 ; STRIDED-NEXT:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -889,14 +1159,19 @@ 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:    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 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:    st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-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:    str z9, [sp, #14, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-4
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -913,15 +1188,20 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -945,32 +1225,46 @@ 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:    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:    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 { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; 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:    mov z2.d, z8.d
 ; STRIDED-NEXT:    mov z3.d, z12.d
-; STRIDED-NEXT:    ld1b { z12.b, z13.b }, pn8/z, [sp, #22, 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:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
+; 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:    mov z1.d, z4.d
 ; STRIDED-NEXT:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -981,14 +1275,19 @@ 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:    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 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:    st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-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:    str z9, [sp, #14, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-4
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -1005,15 +1304,20 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -1038,32 +1342,46 @@ 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:    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:    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 { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; 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:    mov z2.d, z8.d
 ; STRIDED-NEXT:    mov z3.d, z12.d
-; STRIDED-NEXT:    ld1b { z12.b, z13.b }, pn8/z, [sp, #22, 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:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
+; 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:    mov z1.d, z4.d
 ; STRIDED-NEXT:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1074,14 +1392,19 @@ 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:    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 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:    st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-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:    str z9, [sp, #14, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-4
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -1098,15 +1421,20 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -1130,32 +1458,46 @@ 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:    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:    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 { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; 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:    mov z2.d, z8.d
 ; STRIDED-NEXT:    mov z3.d, z12.d
-; STRIDED-NEXT:    ld1b { z12.b, z13.b }, pn8/z, [sp, #22, 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:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
+; 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:    mov z1.d, z4.d
 ; STRIDED-NEXT:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1166,14 +1508,19 @@ 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:    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 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:    st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-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:    str z9, [sp, #14, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-4
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -1190,15 +1537,20 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -1223,32 +1575,46 @@ 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:    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:    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 { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; 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:    mov z2.d, z8.d
 ; STRIDED-NEXT:    mov z3.d, z12.d
-; STRIDED-NEXT:    ld1b { z12.b, z13.b }, pn8/z, [sp, #22, 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:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
+; 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:    mov z1.d, z4.d
 ; STRIDED-NEXT:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1259,14 +1625,19 @@ 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:    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 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:    st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-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:    str z9, [sp, #14, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-4
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -1283,15 +1654,20 @@ 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:    ptrue pn8.b
+; 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:    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:    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
@@ -1315,32 +1691,46 @@ 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:    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:    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 { z10.b, z11.b }, pn8/z, [sp, #26, mul vl] // 32-byte Folded Reload
+; 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:    mov z2.d, z8.d
 ; STRIDED-NEXT:    mov z3.d, z12.d
-; STRIDED-NEXT:    ld1b { z12.b, z13.b }, pn8/z, [sp, #22, 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:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
+; 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:    mov z1.d, z4.d
 ; STRIDED-NEXT:    addvl sp, sp, #17
 ; STRIDED-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -1351,14 +1741,19 @@ 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:    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 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:    st1b { z10.b, z11.b }, pn8, [sp, #24, mul vl] // 32-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:    str z9, [sp, #14, mul vl] // 16-byte Folded Spill
 ; CONTIGUOUS-NEXT:    addvl sp, sp, #-4
 ; CONTIGUOUS-NEXT:    mov p8.b, p0.b
@@ -1375,15 +1770,20 @@ 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:    ptrue pn8.b
+; 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:    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:    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
diff --git a/llvm/test/CodeGen/AArch64/sve-callee-save-restore-pairs.ll b/llvm/test/CodeGen/AArch64/sve-callee-save-restore-pairs.ll
index 470c0dd45782c9..c0d5d9dfdbb0d7 100644
--- a/llvm/test/CodeGen/AArch64/sve-callee-save-restore-pairs.ll
+++ b/llvm/test/CodeGen/AArch64/sve-callee-save-restore-pairs.ll
@@ -88,27 +88,34 @@ define void @fbyte(<vscale x 16 x i8> %v) {
 ; 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 p8, [sp, #11, 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:    str z23, [sp, #2, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z22, [sp, #3, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z21, [sp, #4, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z20, [sp, #5, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z19, [sp, #6, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z18, [sp, #7, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z17, [sp, #8, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z16, [sp, #9, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z15, [sp, #10, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z14, [sp, #11, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z13, [sp, #12, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z12, [sp, #13, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z11, [sp, #14, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z10, [sp, #15, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z9, [sp, #16, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z8, [sp, #17, mul vl] // 16-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
@@ -121,16 +128,23 @@ 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:    ptrue pn8.b
+; PAIR-NEXT:    ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
 ; PAIR-NEXT:    ldr p15, [sp, #4, 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:    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:    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:    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 p14, [sp, #5, mul vl] // 2-byte Folded Reload
 ; PAIR-NEXT:    ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
 ; PAIR-NEXT:    ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
@@ -230,27 +244,34 @@ define void @fhalf(<vscale x 8 x half> %v) {
 ; 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 p8, [sp, #11, 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:    str z23, [sp, #2, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z22, [sp, #3, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z21, [sp, #4, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z20, [sp, #5, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z19, [sp, #6, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z18, [sp, #7, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z17, [sp, #8, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z16, [sp, #9, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z15, [sp, #10, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z14, [sp, #11, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z13, [sp, #12, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z12, [sp, #13, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z11, [sp, #14, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z10, [sp, #15, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z9, [sp, #16, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z8, [sp, #17, mul vl] // 16-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
@@ -263,16 +284,23 @@ 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:    ptrue pn8.b
+; PAIR-NEXT:    ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
 ; PAIR-NEXT:    ldr p15, [sp, #4, 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:    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:    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:    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 p14, [sp, #5, mul vl] // 2-byte Folded Reload
 ; PAIR-NEXT:    ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
 ; PAIR-NEXT:    ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
@@ -323,12 +351,11 @@ define aarch64_sve_vector_pcs void @test_clobbers_z_p_regs() {
 ; PAIR:       // %bb.0:
 ; PAIR-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
 ; PAIR-NEXT:    addvl sp, sp, #-4
-; PAIR-NEXT:    str p8, [sp, #5, mul vl] // 2-byte Folded Spill
-; PAIR-NEXT:    ptrue pn8.b
 ; PAIR-NEXT:    str p5, [sp, #6, mul vl] // 2-byte Folded Spill
 ; PAIR-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; PAIR-NEXT:    str z10, [sp, #1, mul vl] // 16-byte Folded Spill
-; PAIR-NEXT:    st1b { z8.b, z9.b }, pn8, [sp, #4, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT:    str z9, [sp, #2, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z8, [sp, #3, mul vl] // 16-byte Folded Spill
 ; PAIR-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 32 * VG
 ; 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
@@ -336,10 +363,9 @@ define aarch64_sve_vector_pcs void @test_clobbers_z_p_regs() {
 ; PAIR-NEXT:    .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 16 - 24 * VG
 ; PAIR-NEXT:    //APP
 ; PAIR-NEXT:    //NO_APP
-; PAIR-NEXT:    ptrue pn8.b
 ; PAIR-NEXT:    ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
-; PAIR-NEXT:    ld1b { z8.b, z9.b }, pn8/z, [sp, #4, mul vl] // 32-byte Folded Reload
-; PAIR-NEXT:    ldr p8, [sp, #5, mul vl] // 2-byte Folded Reload
+; PAIR-NEXT:    ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z8, [sp, #3, mul vl] // 16-byte Folded Reload
 ; PAIR-NEXT:    ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
 ; PAIR-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
 ; PAIR-NEXT:    addvl sp, sp, #4
@@ -381,11 +407,11 @@ define aarch64_sve_vector_pcs  void @test_clobbers_z_p_regs2() {
 ; PAIR:       // %bb.0:
 ; PAIR-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
 ; PAIR-NEXT:    addvl sp, sp, #-4
-; PAIR-NEXT:    str p9, [sp, #7, mul vl] // 2-byte Folded Spill
-; PAIR-NEXT:    ptrue pn9.b
 ; PAIR-NEXT:    str p10, [sp, #6, mul vl] // 2-byte Folded Spill
+; PAIR-NEXT:    str p9, [sp, #7, mul vl] // 2-byte Folded Spill
 ; PAIR-NEXT:    str z10, [sp, #1, mul vl] // 16-byte Folded Spill
-; PAIR-NEXT:    st1b { z8.b, z9.b }, pn9, [sp, #4, mul vl] // 32-byte Folded Spill
+; PAIR-NEXT:    str z9, [sp, #2, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    str z8, [sp, #3, mul vl] // 16-byte Folded Spill
 ; PAIR-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 32 * VG
 ; 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
@@ -393,10 +419,10 @@ define aarch64_sve_vector_pcs  void @test_clobbers_z_p_regs2() {
 ; PAIR-NEXT:    .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 16 - 24 * VG
 ; PAIR-NEXT:    //APP
 ; PAIR-NEXT:    //NO_APP
-; PAIR-NEXT:    ptrue pn9.b
 ; PAIR-NEXT:    ldr z10, [sp, #1, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z9, [sp, #2, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z8, [sp, #3, mul vl] // 16-byte Folded Reload
 ; PAIR-NEXT:    ldr p10, [sp, #6, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT:    ld1b { z8.b, z9.b }, pn9/z, [sp, #4, mul vl] // 32-byte Folded Reload
 ; PAIR-NEXT:    ldr p9, [sp, #7, mul vl] // 2-byte Folded Reload
 ; PAIR-NEXT:    addvl sp, sp, #4
 ; PAIR-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
@@ -429,20 +455,18 @@ define aarch64_sve_vector_pcs  void @test_clobbers_z_regs() {
 ; PAIR-LABEL: test_clobbers_z_regs:
 ; PAIR:       // %bb.0:
 ; PAIR-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; PAIR-NEXT:    addvl sp, sp, #-3
-; PAIR-NEXT:    str p8, [sp, #7, mul vl] // 2-byte Folded Spill
-; PAIR-NEXT:    ptrue pn8.b
-; PAIR-NEXT:    st1b { z8.b, z9.b }, pn8, [sp, #2, mul vl] // 32-byte Folded Spill
-; PAIR-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 24 * VG
+; PAIR-NEXT:    addvl sp, sp, #-2
+; PAIR-NEXT:    str z9, [sp] // 16-byte Folded Spill
+; PAIR-NEXT:    str z8, [sp, #1, mul vl] // 16-byte Folded Spill
+; PAIR-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG
 ; 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:    //APP
 ; PAIR-NEXT:    //NO_APP
-; PAIR-NEXT:    ptrue pn8.b
-; PAIR-NEXT:    ld1b { z8.b, z9.b }, pn8/z, [sp, #2, mul vl] // 32-byte Folded Reload
-; PAIR-NEXT:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
-; PAIR-NEXT:    addvl sp, sp, #3
+; PAIR-NEXT:    ldr z9, [sp] // 16-byte Folded Reload
+; PAIR-NEXT:    ldr z8, [sp, #1, mul vl] // 16-byte Folded Reload
+; PAIR-NEXT:    addvl sp, sp, #2
 ; PAIR-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; PAIR-NEXT:    ret
   call void asm sideeffect "", "~{z8},~{z9}"()



More information about the llvm-branch-commits mailing list