[AArch64][SME] Support split ZPR and PPR area allocationusers/MacDue/split_pprs

For a while we have supported the `-aarch64-stack-hazard-size=<size>`
option, which adds "hazard padding" between GPRs and FPR/ZPRs. However,
there is currently a hole in this mitigation as PPR and FPR/ZPR accesses
to the same area also cause streaming memory hazards (this is noted by
`-pass-remarks-analysis=sme -aarch64-stack-hazard-remark-size=<val>`),
and the current stack layout places PPRs and ZPRs within the same area.

Which looks like:

------------------------------------  Higher address
| callee-saved gpr registers        |
|---------------------------------- |
| lr,fp  (a.k.a. "frame record")    |
|-----------------------------------| <- fp(=x29)
|   <hazard padding>                |
|-----------------------------------|
| callee-saved fp/simd/SVE regs     |
|-----------------------------------|
|        SVE stack objects          |
|-----------------------------------|
| local variables of fixed size     |
|   <FPR>                           |
|   <hazard padding>                |
|   <GPR>                           |
------------------------------------| <- sp
                                    | Lower address

With this patch the stack (and hazard padding) is rearranged so that
hazard padding is placed between the PPRs and ZPRs rather than within
the (fixed size) callee-save region. Which looks something like this:

------------------------------------  Higher address
| callee-saved gpr registers        |
|---------------------------------- |
| lr,fp  (a.k.a. "frame record")    |
|-----------------------------------| <- fp(=x29)
|        callee-saved PPRs          |
|        PPR stack objects          | (These are SVE predicates)
|-----------------------------------|
|   <hazard padding>                |
|-----------------------------------|
|       callee-saved ZPR regs       | (These are SVE vectors)
|        ZPR stack objects          | Note: FPRs are promoted to ZPRs
|-----------------------------------|
| local variables of fixed size     |
|   <FPR>                           |
|   <hazard padding>                |
|   <GPR>                           |
------------------------------------| <- sp
                                    | Lower address

This layout is only enabled if:

 * SplitSVEObjects are enabled (`-aarch64-split-sve-objects`)
   - (This may be enabled by default in a later patch)
 * Streaming memory hazards are present
   - (`-aarch64-stack-hazard-size=<val>` != 0)
 * PPRs and FPRs/ZPRs are on the stack
 * There's no stack realignment or variable-sized objects
   - This is left as a TODO for now

Additionally, any FPR callee-saves that are present will be promoted to
ZPRs. This is to prevent stack hazards between FPRs and GRPs in the
fixed size callee-save area (which would otherwise require more hazard
padding, or moving the FPR callee-saves).

This layout should resolve the hole in the hazard padding mitigation,
and is not intended change codegen for non-SME code.

Change-Id: I2e1906577c2ac79c40bc69e7c15e3ef09857445f

1 files changed, 544 insertions, 332 deletions

diff --git a/llvm/test/CodeGen/AArch64/stack-hazard.ll b/llvm/test/CodeGen/AArch64/stack-hazard.ll
index 5f52280..333a8be 100644
--- a/llvm/test/CodeGen/AArch64/stack-hazard.ll
+++ b/llvm/test/CodeGen/AArch64/stack-hazard.ll
@@ -1,7 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
 ; RUN: llc < %s -mtriple=aarch64 -mattr=+sve2 -aarch64-stack-hazard-size=0 | FileCheck %s --check-prefixes=CHECK,CHECK0
 ; RUN: llc < %s -mtriple=aarch64 -mattr=+sve2 -aarch64-stack-hazard-size=64 | FileCheck %s --check-prefixes=CHECK,CHECK64
-; RUN: llc < %s -mtriple=aarch64 -mattr=+sve2 -aarch64-stack-hazard-size=1024 | FileCheck %s --check-prefixes=CHECK,CHECK1024
+; RUN: llc < %s -mtriple=aarch64 -mattr=+sve2 -aarch64-stack-hazard-size=1024 | FileCheck %s --check-prefixes=CHECK,CHECK1024,CHECK1024-NOSPLITSVE
+; RUN: llc < %s -mtriple=aarch64 -mattr=+sve2 -aarch64-split-sve-objects -aarch64-stack-hazard-size=1024 | FileCheck %s --check-prefixes=CHECK,CHECK1024,CHECK1024-SPLITSVE
 
 define i32 @basic(i32 noundef %num) {
 ; CHECK-LABEL: basic:
@@ -1503,72 +1504,24 @@ define [2 x <vscale x 4 x i1>] @sve_signature_pred_2xv4i1([2 x <vscale x 4 x i1>
 }
 
 define [2 x <vscale x 4 x i1>] @sve_signature_pred_2xv4i1_caller([2 x <vscale x 4 x i1>] %arg1, [2 x <vscale x 4 x i1>] %arg2) nounwind "aarch64_pstate_sm_compatible" {
-; CHECK0-LABEL: sve_signature_pred_2xv4i1_caller:
-; CHECK0:       // %bb.0:
-; CHECK0-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
-; CHECK0-NEXT:    addvl sp, sp, #-1
-; CHECK0-NEXT:    str p5, [sp, #6, mul vl] // 2-byte Folded Spill
-; CHECK0-NEXT:    mov p5.b, p0.b
-; CHECK0-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
-; CHECK0-NEXT:    mov p4.b, p1.b
-; CHECK0-NEXT:    mov p0.b, p2.b
-; CHECK0-NEXT:    mov p1.b, p3.b
-; CHECK0-NEXT:    mov p2.b, p5.b
-; CHECK0-NEXT:    mov p3.b, p4.b
-; CHECK0-NEXT:    bl sve_signature_pred_2xv4i1
-; CHECK0-NEXT:    ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
-; CHECK0-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
-; CHECK0-NEXT:    addvl sp, sp, #1
-; CHECK0-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
-; CHECK0-NEXT:    ret
-;
-; CHECK64-LABEL: sve_signature_pred_2xv4i1_caller:
-; CHECK64:       // %bb.0:
-; CHECK64-NEXT:    sub sp, sp, #80
-; CHECK64-NEXT:    stp x29, x30, [sp, #64] // 16-byte Folded Spill
-; CHECK64-NEXT:    addvl sp, sp, #-1
-; CHECK64-NEXT:    str p5, [sp, #6, mul vl] // 2-byte Folded Spill
-; CHECK64-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
-; CHECK64-NEXT:    sub sp, sp, #64
-; CHECK64-NEXT:    mov p4.b, p1.b
-; CHECK64-NEXT:    mov p5.b, p0.b
-; CHECK64-NEXT:    mov p0.b, p2.b
-; CHECK64-NEXT:    mov p1.b, p3.b
-; CHECK64-NEXT:    mov p2.b, p5.b
-; CHECK64-NEXT:    mov p3.b, p4.b
-; CHECK64-NEXT:    bl sve_signature_pred_2xv4i1
-; CHECK64-NEXT:    add sp, sp, #64
-; CHECK64-NEXT:    ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
-; CHECK64-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
-; CHECK64-NEXT:    addvl sp, sp, #1
-; CHECK64-NEXT:    ldp x29, x30, [sp, #64] // 16-byte Folded Reload
-; CHECK64-NEXT:    add sp, sp, #80
-; CHECK64-NEXT:    ret
-;
-; CHECK1024-LABEL: sve_signature_pred_2xv4i1_caller:
-; CHECK1024:       // %bb.0:
-; CHECK1024-NEXT:    sub sp, sp, #1040
-; CHECK1024-NEXT:    str x29, [sp, #1024] // 8-byte Folded Spill
-; CHECK1024-NEXT:    str x30, [sp, #1032] // 8-byte Folded Spill
-; CHECK1024-NEXT:    addvl sp, sp, #-1
-; CHECK1024-NEXT:    str p5, [sp, #6, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    sub sp, sp, #1024
-; CHECK1024-NEXT:    mov p4.b, p1.b
-; CHECK1024-NEXT:    mov p5.b, p0.b
-; CHECK1024-NEXT:    mov p0.b, p2.b
-; CHECK1024-NEXT:    mov p1.b, p3.b
-; CHECK1024-NEXT:    mov p2.b, p5.b
-; CHECK1024-NEXT:    mov p3.b, p4.b
-; CHECK1024-NEXT:    bl sve_signature_pred_2xv4i1
-; CHECK1024-NEXT:    add sp, sp, #1024
-; CHECK1024-NEXT:    ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    addvl sp, sp, #1
-; CHECK1024-NEXT:    ldr x30, [sp, #1032] // 8-byte Folded Reload
-; CHECK1024-NEXT:    ldr x29, [sp, #1024] // 8-byte Folded Reload
-; CHECK1024-NEXT:    add sp, sp, #1040
-; CHECK1024-NEXT:    ret
+; CHECK-LABEL: sve_signature_pred_2xv4i1_caller:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
+; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p5, [sp, #6, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    mov p5.b, p0.b
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    mov p4.b, p1.b
+; CHECK-NEXT:    mov p0.b, p2.b
+; CHECK-NEXT:    mov p1.b, p3.b
+; CHECK-NEXT:    mov p2.b, p5.b
+; CHECK-NEXT:    mov p3.b, p4.b
+; CHECK-NEXT:    bl sve_signature_pred_2xv4i1
+; CHECK-NEXT:    ldr p5, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK-NEXT:    addvl sp, sp, #1
+; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; CHECK-NEXT:    ret
   %res = call [2 x <vscale x 4 x i1>] @sve_signature_pred_2xv4i1([2 x <vscale x 4 x i1>] %arg2, [2 x <vscale x 4 x i1>] %arg1)
   ret [2 x <vscale x 4 x i1>] %res
 }
@@ -2113,139 +2066,269 @@ define i32 @svecc_call(<4 x i16> %P0, ptr %P1, i32 %P2, <vscale x 16 x i8> %P3,
 ; CHECK64-NEXT:    .cfi_restore w29
 ; CHECK64-NEXT:    ret
 ;
-; CHECK1024-LABEL: svecc_call:
-; CHECK1024:       // %bb.0: // %entry
-; CHECK1024-NEXT:    sub sp, sp, #1088
-; CHECK1024-NEXT:    .cfi_def_cfa_offset 1088
-; CHECK1024-NEXT:    cntd x9
-; CHECK1024-NEXT:    str x29, [sp, #1024] // 8-byte Folded Spill
-; CHECK1024-NEXT:    str x30, [sp, #1032] // 8-byte Folded Spill
-; CHECK1024-NEXT:    str x9, [sp, #1040] // 8-byte Folded Spill
-; CHECK1024-NEXT:    str x28, [sp, #1048] // 8-byte Folded Spill
-; CHECK1024-NEXT:    str x27, [sp, #1056] // 8-byte Folded Spill
-; CHECK1024-NEXT:    str x26, [sp, #1064] // 8-byte Folded Spill
-; CHECK1024-NEXT:    str x19, [sp, #1072] // 8-byte Folded Spill
-; CHECK1024-NEXT:    add x29, sp, #1024
-; CHECK1024-NEXT:    .cfi_def_cfa w29, 64
-; CHECK1024-NEXT:    .cfi_offset w19, -16
-; CHECK1024-NEXT:    .cfi_offset w26, -24
-; CHECK1024-NEXT:    .cfi_offset w27, -32
-; CHECK1024-NEXT:    .cfi_offset w28, -40
-; CHECK1024-NEXT:    .cfi_offset vg, -48
-; CHECK1024-NEXT:    .cfi_offset w30, -56
-; CHECK1024-NEXT:    .cfi_offset w29, -64
-; CHECK1024-NEXT:    addvl sp, sp, #-18
-; CHECK1024-NEXT:    str p15, [sp, #4, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p14, [sp, #5, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p13, [sp, #6, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p12, [sp, #7, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p11, [sp, #8, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p10, [sp, #9, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p9, [sp, #10, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p8, [sp, #11, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p7, [sp, #12, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p6, [sp, #13, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p5, [sp, #14, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p4, [sp, #15, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str z23, [sp, #2, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z22, [sp, #3, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z21, [sp, #4, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z20, [sp, #5, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z19, [sp, #6, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z18, [sp, #7, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z17, [sp, #8, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z16, [sp, #9, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z15, [sp, #10, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z14, [sp, #11, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z13, [sp, #12, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z12, [sp, #13, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z11, [sp, #14, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z10, [sp, #15, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z9, [sp, #16, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z8, [sp, #17, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    .cfi_escape 0x10, 0x48, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x78, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d8 @ cfa - 8 * IncomingVG - 1088
-; CHECK1024-NEXT:    .cfi_escape 0x10, 0x49, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x70, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d9 @ cfa - 16 * IncomingVG - 1088
-; CHECK1024-NEXT:    .cfi_escape 0x10, 0x4a, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x68, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d10 @ cfa - 24 * IncomingVG - 1088
-; CHECK1024-NEXT:    .cfi_escape 0x10, 0x4b, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x60, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d11 @ cfa - 32 * IncomingVG - 1088
-; CHECK1024-NEXT:    .cfi_escape 0x10, 0x4c, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x58, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d12 @ cfa - 40 * IncomingVG - 1088
-; CHECK1024-NEXT:    .cfi_escape 0x10, 0x4d, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x50, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d13 @ cfa - 48 * IncomingVG - 1088
-; CHECK1024-NEXT:    .cfi_escape 0x10, 0x4e, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x48, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d14 @ cfa - 56 * IncomingVG - 1088
-; CHECK1024-NEXT:    .cfi_escape 0x10, 0x4f, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x40, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d15 @ cfa - 64 * IncomingVG - 1088
-; CHECK1024-NEXT:    sub sp, sp, #1024
-; CHECK1024-NEXT:    mov x8, x0
-; CHECK1024-NEXT:    bl __arm_sme_state
-; CHECK1024-NEXT:    mov x19, x0
-; CHECK1024-NEXT:    //APP
-; CHECK1024-NEXT:    //NO_APP
-; CHECK1024-NEXT:    tbz w19, #0, .LBB28_2
-; CHECK1024-NEXT:  // %bb.1: // %entry
-; CHECK1024-NEXT:    smstop sm
-; CHECK1024-NEXT:  .LBB28_2: // %entry
-; CHECK1024-NEXT:    mov x0, x8
-; CHECK1024-NEXT:    mov w1, #45 // =0x2d
-; CHECK1024-NEXT:    mov w2, #37 // =0x25
-; CHECK1024-NEXT:    bl memset
-; CHECK1024-NEXT:    tbz w19, #0, .LBB28_4
-; CHECK1024-NEXT:  // %bb.3: // %entry
-; CHECK1024-NEXT:    smstart sm
-; CHECK1024-NEXT:  .LBB28_4: // %entry
-; CHECK1024-NEXT:    mov w0, #22647 // =0x5877
-; CHECK1024-NEXT:    movk w0, #59491, lsl #16
-; CHECK1024-NEXT:    add sp, sp, #1024
-; CHECK1024-NEXT:    ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    addvl sp, sp, #18
-; CHECK1024-NEXT:    .cfi_restore z8
-; CHECK1024-NEXT:    .cfi_restore z9
-; CHECK1024-NEXT:    .cfi_restore z10
-; CHECK1024-NEXT:    .cfi_restore z11
-; CHECK1024-NEXT:    .cfi_restore z12
-; CHECK1024-NEXT:    .cfi_restore z13
-; CHECK1024-NEXT:    .cfi_restore z14
-; CHECK1024-NEXT:    .cfi_restore z15
-; CHECK1024-NEXT:    .cfi_def_cfa wsp, 1088
-; CHECK1024-NEXT:    ldr x19, [sp, #1072] // 8-byte Folded Reload
-; CHECK1024-NEXT:    ldr x26, [sp, #1064] // 8-byte Folded Reload
-; CHECK1024-NEXT:    ldr x27, [sp, #1056] // 8-byte Folded Reload
-; CHECK1024-NEXT:    ldr x28, [sp, #1048] // 8-byte Folded Reload
-; CHECK1024-NEXT:    ldr x30, [sp, #1032] // 8-byte Folded Reload
-; CHECK1024-NEXT:    ldr x29, [sp, #1024] // 8-byte Folded Reload
-; CHECK1024-NEXT:    add sp, sp, #1088
-; CHECK1024-NEXT:    .cfi_def_cfa_offset 0
-; CHECK1024-NEXT:    .cfi_restore w19
-; CHECK1024-NEXT:    .cfi_restore w26
-; CHECK1024-NEXT:    .cfi_restore w27
-; CHECK1024-NEXT:    .cfi_restore w28
-; CHECK1024-NEXT:    .cfi_restore vg
-; CHECK1024-NEXT:    .cfi_restore w30
-; CHECK1024-NEXT:    .cfi_restore w29
-; CHECK1024-NEXT:    ret
+; CHECK1024-NOSPLITSVE-LABEL: svecc_call:
+; CHECK1024-NOSPLITSVE:       // %bb.0: // %entry
+; CHECK1024-NOSPLITSVE-NEXT:    sub sp, sp, #1088
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_def_cfa_offset 1088
+; CHECK1024-NOSPLITSVE-NEXT:    cntd x9
+; CHECK1024-NOSPLITSVE-NEXT:    str x29, [sp, #1024] // 8-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str x30, [sp, #1032] // 8-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str x9, [sp, #1040] // 8-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str x28, [sp, #1048] // 8-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str x27, [sp, #1056] // 8-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str x26, [sp, #1064] // 8-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str x19, [sp, #1072] // 8-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    add x29, sp, #1024
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_def_cfa w29, 64
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_offset w19, -16
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_offset w26, -24
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_offset w27, -32
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_offset w28, -40
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_offset vg, -48
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_offset w30, -56
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_offset w29, -64
+; CHECK1024-NOSPLITSVE-NEXT:    addvl sp, sp, #-18
+; CHECK1024-NOSPLITSVE-NEXT:    str p15, [sp, #4, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p14, [sp, #5, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p13, [sp, #6, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p12, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p11, [sp, #8, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p10, [sp, #9, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p9, [sp, #10, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p8, [sp, #11, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p7, [sp, #12, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p6, [sp, #13, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p5, [sp, #14, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p4, [sp, #15, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z23, [sp, #2, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z22, [sp, #3, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z21, [sp, #4, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z20, [sp, #5, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z19, [sp, #6, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z18, [sp, #7, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z17, [sp, #8, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z16, [sp, #9, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z15, [sp, #10, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z14, [sp, #11, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z13, [sp, #12, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z12, [sp, #13, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z11, [sp, #14, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z10, [sp, #15, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z9, [sp, #16, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z8, [sp, #17, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_escape 0x10, 0x48, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x78, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d8 @ cfa - 8 * IncomingVG - 1088
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_escape 0x10, 0x49, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x70, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d9 @ cfa - 16 * IncomingVG - 1088
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_escape 0x10, 0x4a, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x68, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d10 @ cfa - 24 * IncomingVG - 1088
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_escape 0x10, 0x4b, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x60, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d11 @ cfa - 32 * IncomingVG - 1088
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_escape 0x10, 0x4c, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x58, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d12 @ cfa - 40 * IncomingVG - 1088
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_escape 0x10, 0x4d, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x50, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d13 @ cfa - 48 * IncomingVG - 1088
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_escape 0x10, 0x4e, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x48, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d14 @ cfa - 56 * IncomingVG - 1088
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_escape 0x10, 0x4f, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x40, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d15 @ cfa - 64 * IncomingVG - 1088
+; CHECK1024-NOSPLITSVE-NEXT:    sub sp, sp, #1024
+; CHECK1024-NOSPLITSVE-NEXT:    mov x8, x0
+; CHECK1024-NOSPLITSVE-NEXT:    bl __arm_sme_state
+; CHECK1024-NOSPLITSVE-NEXT:    mov x19, x0
+; CHECK1024-NOSPLITSVE-NEXT:    //APP
+; CHECK1024-NOSPLITSVE-NEXT:    //NO_APP
+; CHECK1024-NOSPLITSVE-NEXT:    tbz w19, #0, .LBB28_2
+; CHECK1024-NOSPLITSVE-NEXT:  // %bb.1: // %entry
+; CHECK1024-NOSPLITSVE-NEXT:    smstop sm
+; CHECK1024-NOSPLITSVE-NEXT:  .LBB28_2: // %entry
+; CHECK1024-NOSPLITSVE-NEXT:    mov x0, x8
+; CHECK1024-NOSPLITSVE-NEXT:    mov w1, #45 // =0x2d
+; CHECK1024-NOSPLITSVE-NEXT:    mov w2, #37 // =0x25
+; CHECK1024-NOSPLITSVE-NEXT:    bl memset
+; CHECK1024-NOSPLITSVE-NEXT:    tbz w19, #0, .LBB28_4
+; CHECK1024-NOSPLITSVE-NEXT:  // %bb.3: // %entry
+; CHECK1024-NOSPLITSVE-NEXT:    smstart sm
+; CHECK1024-NOSPLITSVE-NEXT:  .LBB28_4: // %entry
+; CHECK1024-NOSPLITSVE-NEXT:    mov w0, #22647 // =0x5877
+; CHECK1024-NOSPLITSVE-NEXT:    movk w0, #59491, lsl #16
+; CHECK1024-NOSPLITSVE-NEXT:    add sp, sp, #1024
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    addvl sp, sp, #18
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore z8
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore z9
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore z10
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore z11
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore z12
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore z13
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore z14
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore z15
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_def_cfa wsp, 1088
+; CHECK1024-NOSPLITSVE-NEXT:    ldr x19, [sp, #1072] // 8-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr x26, [sp, #1064] // 8-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr x27, [sp, #1056] // 8-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr x28, [sp, #1048] // 8-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr x30, [sp, #1032] // 8-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr x29, [sp, #1024] // 8-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    add sp, sp, #1088
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_def_cfa_offset 0
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore w19
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore w26
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore w27
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore w28
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore vg
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore w30
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore w29
+; CHECK1024-NOSPLITSVE-NEXT:    ret
+;
+; CHECK1024-SPLITSVE-LABEL: svecc_call:
+; CHECK1024-SPLITSVE:       // %bb.0: // %entry
+; CHECK1024-SPLITSVE-NEXT:    stp x29, x30, [sp, #-64]! // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    .cfi_def_cfa_offset 64
+; CHECK1024-SPLITSVE-NEXT:    cntd x9
+; CHECK1024-SPLITSVE-NEXT:    stp x28, x27, [sp, #32] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str x9, [sp, #16] // 8-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    stp x26, x19, [sp, #48] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    mov x29, sp
+; CHECK1024-SPLITSVE-NEXT:    .cfi_def_cfa w29, 64
+; CHECK1024-SPLITSVE-NEXT:    .cfi_offset w19, -8
+; CHECK1024-SPLITSVE-NEXT:    .cfi_offset w26, -16
+; CHECK1024-SPLITSVE-NEXT:    .cfi_offset w27, -24
+; CHECK1024-SPLITSVE-NEXT:    .cfi_offset w28, -32
+; CHECK1024-SPLITSVE-NEXT:    .cfi_offset vg, -48
+; CHECK1024-SPLITSVE-NEXT:    .cfi_offset w30, -56
+; CHECK1024-SPLITSVE-NEXT:    .cfi_offset w29, -64
+; CHECK1024-SPLITSVE-NEXT:    addvl sp, sp, #-2
+; CHECK1024-SPLITSVE-NEXT:    str p15, [sp, #4, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p14, [sp, #5, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p13, [sp, #6, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p12, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p11, [sp, #8, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p10, [sp, #9, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p9, [sp, #10, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p8, [sp, #11, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p7, [sp, #12, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p6, [sp, #13, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p5, [sp, #14, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p4, [sp, #15, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    sub sp, sp, #1024
+; CHECK1024-SPLITSVE-NEXT:    addvl sp, sp, #-16
+; CHECK1024-SPLITSVE-NEXT:    str z23, [sp] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z22, [sp, #1, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z21, [sp, #2, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z20, [sp, #3, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z19, [sp, #4, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z18, [sp, #5, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z17, [sp, #6, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z16, [sp, #7, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z15, [sp, #8, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z14, [sp, #9, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z13, [sp, #10, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z12, [sp, #11, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z11, [sp, #12, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z9, [sp, #14, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z8, [sp, #15, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    .cfi_escape 0x10, 0x48, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x68, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d8 @ cfa - 24 * IncomingVG - 1088
+; CHECK1024-SPLITSVE-NEXT:    .cfi_escape 0x10, 0x49, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x60, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d9 @ cfa - 32 * IncomingVG - 1088
+; CHECK1024-SPLITSVE-NEXT:    .cfi_escape 0x10, 0x4a, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x58, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d10 @ cfa - 40 * IncomingVG - 1088
+; CHECK1024-SPLITSVE-NEXT:    .cfi_escape 0x10, 0x4b, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x50, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d11 @ cfa - 48 * IncomingVG - 1088
+; CHECK1024-SPLITSVE-NEXT:    .cfi_escape 0x10, 0x4c, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x48, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d12 @ cfa - 56 * IncomingVG - 1088
+; CHECK1024-SPLITSVE-NEXT:    .cfi_escape 0x10, 0x4d, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x40, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d13 @ cfa - 64 * IncomingVG - 1088
+; CHECK1024-SPLITSVE-NEXT:    .cfi_escape 0x10, 0x4e, 0x0e, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0xb8, 0x7f, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d14 @ cfa - 72 * IncomingVG - 1088
+; CHECK1024-SPLITSVE-NEXT:    .cfi_escape 0x10, 0x4f, 0x0e, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0xb0, 0x7f, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d15 @ cfa - 80 * IncomingVG - 1088
+; CHECK1024-SPLITSVE-NEXT:    sub sp, sp, #1024
+; CHECK1024-SPLITSVE-NEXT:    mov x8, x0
+; CHECK1024-SPLITSVE-NEXT:    bl __arm_sme_state
+; CHECK1024-SPLITSVE-NEXT:    mov x19, x0
+; CHECK1024-SPLITSVE-NEXT:    //APP
+; CHECK1024-SPLITSVE-NEXT:    //NO_APP
+; CHECK1024-SPLITSVE-NEXT:    tbz w19, #0, .LBB28_2
+; CHECK1024-SPLITSVE-NEXT:  // %bb.1: // %entry
+; CHECK1024-SPLITSVE-NEXT:    smstop sm
+; CHECK1024-SPLITSVE-NEXT:  .LBB28_2: // %entry
+; CHECK1024-SPLITSVE-NEXT:    mov x0, x8
+; CHECK1024-SPLITSVE-NEXT:    mov w1, #45 // =0x2d
+; CHECK1024-SPLITSVE-NEXT:    mov w2, #37 // =0x25
+; CHECK1024-SPLITSVE-NEXT:    bl memset
+; CHECK1024-SPLITSVE-NEXT:    tbz w19, #0, .LBB28_4
+; CHECK1024-SPLITSVE-NEXT:  // %bb.3: // %entry
+; CHECK1024-SPLITSVE-NEXT:    smstart sm
+; CHECK1024-SPLITSVE-NEXT:  .LBB28_4: // %entry
+; CHECK1024-SPLITSVE-NEXT:    mov w0, #22647 // =0x5877
+; CHECK1024-SPLITSVE-NEXT:    movk w0, #59491, lsl #16
+; CHECK1024-SPLITSVE-NEXT:    add sp, sp, #1024
+; CHECK1024-SPLITSVE-NEXT:    ldr z23, [sp] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z22, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z21, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z20, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z19, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z18, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z17, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z16, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z15, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z14, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z13, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z12, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z8, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    add sp, sp, #1024
+; CHECK1024-SPLITSVE-NEXT:    addvl sp, sp, #16
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore z8
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore z9
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore z10
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore z11
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore z12
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore z13
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore z14
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore z15
+; CHECK1024-SPLITSVE-NEXT:    ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    addvl sp, sp, #2
+; CHECK1024-SPLITSVE-NEXT:    .cfi_def_cfa wsp, 64
+; CHECK1024-SPLITSVE-NEXT:    ldp x26, x19, [sp, #48] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldp x28, x27, [sp, #32] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldp x29, x30, [sp], #64 // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    .cfi_def_cfa_offset 0
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore w19
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore w26
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore w27
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore w28
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore vg
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore w30
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore w29
+; CHECK1024-SPLITSVE-NEXT:    ret
 entry:
   tail call void asm sideeffect "", "~{x0},~{x28},~{x27},~{x3}"() #2
   %call = call ptr @memset(ptr noundef nonnull %P1, i32 noundef 45, i32 noundef 37)
@@ -2505,138 +2588,267 @@ define i32 @svecc_alloca_call(<4 x i16> %P0, ptr %P1, i32 %P2, <vscale x 16 x i8
 ; CHECK64-NEXT:    .cfi_restore w29
 ; CHECK64-NEXT:    ret
 ;
-; CHECK1024-LABEL: svecc_alloca_call:
-; CHECK1024:       // %bb.0: // %entry
-; CHECK1024-NEXT:    sub sp, sp, #1088
-; CHECK1024-NEXT:    .cfi_def_cfa_offset 1088
-; CHECK1024-NEXT:    cntd x9
-; CHECK1024-NEXT:    str x29, [sp, #1024] // 8-byte Folded Spill
-; CHECK1024-NEXT:    str x30, [sp, #1032] // 8-byte Folded Spill
-; CHECK1024-NEXT:    str x9, [sp, #1040] // 8-byte Folded Spill
-; CHECK1024-NEXT:    str x28, [sp, #1048] // 8-byte Folded Spill
-; CHECK1024-NEXT:    str x27, [sp, #1056] // 8-byte Folded Spill
-; CHECK1024-NEXT:    str x26, [sp, #1064] // 8-byte Folded Spill
-; CHECK1024-NEXT:    str x19, [sp, #1072] // 8-byte Folded Spill
-; CHECK1024-NEXT:    add x29, sp, #1024
-; CHECK1024-NEXT:    .cfi_def_cfa w29, 64
-; CHECK1024-NEXT:    .cfi_offset w19, -16
-; CHECK1024-NEXT:    .cfi_offset w26, -24
-; CHECK1024-NEXT:    .cfi_offset w27, -32
-; CHECK1024-NEXT:    .cfi_offset w28, -40
-; CHECK1024-NEXT:    .cfi_offset vg, -48
-; CHECK1024-NEXT:    .cfi_offset w30, -56
-; CHECK1024-NEXT:    .cfi_offset w29, -64
-; CHECK1024-NEXT:    addvl sp, sp, #-18
-; CHECK1024-NEXT:    str p15, [sp, #4, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p14, [sp, #5, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p13, [sp, #6, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p12, [sp, #7, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p11, [sp, #8, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p10, [sp, #9, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p9, [sp, #10, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p8, [sp, #11, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p7, [sp, #12, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p6, [sp, #13, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p5, [sp, #14, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str p4, [sp, #15, mul vl] // 2-byte Folded Spill
-; CHECK1024-NEXT:    str z23, [sp, #2, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z22, [sp, #3, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z21, [sp, #4, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z20, [sp, #5, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z19, [sp, #6, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z18, [sp, #7, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z17, [sp, #8, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z16, [sp, #9, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z15, [sp, #10, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z14, [sp, #11, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z13, [sp, #12, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z12, [sp, #13, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z11, [sp, #14, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z10, [sp, #15, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z9, [sp, #16, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    str z8, [sp, #17, mul vl] // 16-byte Folded Spill
-; CHECK1024-NEXT:    .cfi_escape 0x10, 0x48, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x78, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d8 @ cfa - 8 * IncomingVG - 1088
-; CHECK1024-NEXT:    .cfi_escape 0x10, 0x49, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x70, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d9 @ cfa - 16 * IncomingVG - 1088
-; CHECK1024-NEXT:    .cfi_escape 0x10, 0x4a, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x68, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d10 @ cfa - 24 * IncomingVG - 1088
-; CHECK1024-NEXT:    .cfi_escape 0x10, 0x4b, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x60, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d11 @ cfa - 32 * IncomingVG - 1088
-; CHECK1024-NEXT:    .cfi_escape 0x10, 0x4c, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x58, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d12 @ cfa - 40 * IncomingVG - 1088
-; CHECK1024-NEXT:    .cfi_escape 0x10, 0x4d, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x50, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d13 @ cfa - 48 * IncomingVG - 1088
-; CHECK1024-NEXT:    .cfi_escape 0x10, 0x4e, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x48, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d14 @ cfa - 56 * IncomingVG - 1088
-; CHECK1024-NEXT:    .cfi_escape 0x10, 0x4f, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x40, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d15 @ cfa - 64 * IncomingVG - 1088
-; CHECK1024-NEXT:    sub sp, sp, #1072
-; CHECK1024-NEXT:    bl __arm_sme_state
-; CHECK1024-NEXT:    mov x19, x0
-; CHECK1024-NEXT:    //APP
-; CHECK1024-NEXT:    //NO_APP
-; CHECK1024-NEXT:    tbz w19, #0, .LBB29_2
-; CHECK1024-NEXT:  // %bb.1: // %entry
-; CHECK1024-NEXT:    smstop sm
-; CHECK1024-NEXT:  .LBB29_2: // %entry
-; CHECK1024-NEXT:    mov x0, sp
-; CHECK1024-NEXT:    mov w1, #45 // =0x2d
-; CHECK1024-NEXT:    mov w2, #37 // =0x25
-; CHECK1024-NEXT:    bl memset
-; CHECK1024-NEXT:    tbz w19, #0, .LBB29_4
-; CHECK1024-NEXT:  // %bb.3: // %entry
-; CHECK1024-NEXT:    smstart sm
-; CHECK1024-NEXT:  .LBB29_4: // %entry
-; CHECK1024-NEXT:    mov w0, #22647 // =0x5877
-; CHECK1024-NEXT:    movk w0, #59491, lsl #16
-; CHECK1024-NEXT:    add sp, sp, #1072
-; CHECK1024-NEXT:    ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
-; CHECK1024-NEXT:    ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
-; CHECK1024-NEXT:    addvl sp, sp, #18
-; CHECK1024-NEXT:    .cfi_restore z8
-; CHECK1024-NEXT:    .cfi_restore z9
-; CHECK1024-NEXT:    .cfi_restore z10
-; CHECK1024-NEXT:    .cfi_restore z11
-; CHECK1024-NEXT:    .cfi_restore z12
-; CHECK1024-NEXT:    .cfi_restore z13
-; CHECK1024-NEXT:    .cfi_restore z14
-; CHECK1024-NEXT:    .cfi_restore z15
-; CHECK1024-NEXT:    .cfi_def_cfa wsp, 1088
-; CHECK1024-NEXT:    ldr x19, [sp, #1072] // 8-byte Folded Reload
-; CHECK1024-NEXT:    ldr x26, [sp, #1064] // 8-byte Folded Reload
-; CHECK1024-NEXT:    ldr x27, [sp, #1056] // 8-byte Folded Reload
-; CHECK1024-NEXT:    ldr x28, [sp, #1048] // 8-byte Folded Reload
-; CHECK1024-NEXT:    ldr x30, [sp, #1032] // 8-byte Folded Reload
-; CHECK1024-NEXT:    ldr x29, [sp, #1024] // 8-byte Folded Reload
-; CHECK1024-NEXT:    add sp, sp, #1088
-; CHECK1024-NEXT:    .cfi_def_cfa_offset 0
-; CHECK1024-NEXT:    .cfi_restore w19
-; CHECK1024-NEXT:    .cfi_restore w26
-; CHECK1024-NEXT:    .cfi_restore w27
-; CHECK1024-NEXT:    .cfi_restore w28
-; CHECK1024-NEXT:    .cfi_restore vg
-; CHECK1024-NEXT:    .cfi_restore w30
-; CHECK1024-NEXT:    .cfi_restore w29
-; CHECK1024-NEXT:    ret
+; CHECK1024-NOSPLITSVE-LABEL: svecc_alloca_call:
+; CHECK1024-NOSPLITSVE:       // %bb.0: // %entry
+; CHECK1024-NOSPLITSVE-NEXT:    sub sp, sp, #1088
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_def_cfa_offset 1088
+; CHECK1024-NOSPLITSVE-NEXT:    cntd x9
+; CHECK1024-NOSPLITSVE-NEXT:    str x29, [sp, #1024] // 8-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str x30, [sp, #1032] // 8-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str x9, [sp, #1040] // 8-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str x28, [sp, #1048] // 8-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str x27, [sp, #1056] // 8-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str x26, [sp, #1064] // 8-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str x19, [sp, #1072] // 8-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    add x29, sp, #1024
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_def_cfa w29, 64
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_offset w19, -16
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_offset w26, -24
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_offset w27, -32
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_offset w28, -40
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_offset vg, -48
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_offset w30, -56
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_offset w29, -64
+; CHECK1024-NOSPLITSVE-NEXT:    addvl sp, sp, #-18
+; CHECK1024-NOSPLITSVE-NEXT:    str p15, [sp, #4, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p14, [sp, #5, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p13, [sp, #6, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p12, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p11, [sp, #8, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p10, [sp, #9, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p9, [sp, #10, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p8, [sp, #11, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p7, [sp, #12, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p6, [sp, #13, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p5, [sp, #14, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str p4, [sp, #15, mul vl] // 2-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z23, [sp, #2, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z22, [sp, #3, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z21, [sp, #4, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z20, [sp, #5, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z19, [sp, #6, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z18, [sp, #7, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z17, [sp, #8, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z16, [sp, #9, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z15, [sp, #10, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z14, [sp, #11, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z13, [sp, #12, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z12, [sp, #13, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z11, [sp, #14, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z10, [sp, #15, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z9, [sp, #16, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    str z8, [sp, #17, mul vl] // 16-byte Folded Spill
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_escape 0x10, 0x48, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x78, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d8 @ cfa - 8 * IncomingVG - 1088
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_escape 0x10, 0x49, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x70, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d9 @ cfa - 16 * IncomingVG - 1088
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_escape 0x10, 0x4a, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x68, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d10 @ cfa - 24 * IncomingVG - 1088
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_escape 0x10, 0x4b, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x60, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d11 @ cfa - 32 * IncomingVG - 1088
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_escape 0x10, 0x4c, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x58, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d12 @ cfa - 40 * IncomingVG - 1088
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_escape 0x10, 0x4d, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x50, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d13 @ cfa - 48 * IncomingVG - 1088
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_escape 0x10, 0x4e, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x48, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d14 @ cfa - 56 * IncomingVG - 1088
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_escape 0x10, 0x4f, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x40, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d15 @ cfa - 64 * IncomingVG - 1088
+; CHECK1024-NOSPLITSVE-NEXT:    sub sp, sp, #1072
+; CHECK1024-NOSPLITSVE-NEXT:    bl __arm_sme_state
+; CHECK1024-NOSPLITSVE-NEXT:    mov x19, x0
+; CHECK1024-NOSPLITSVE-NEXT:    //APP
+; CHECK1024-NOSPLITSVE-NEXT:    //NO_APP
+; CHECK1024-NOSPLITSVE-NEXT:    tbz w19, #0, .LBB29_2
+; CHECK1024-NOSPLITSVE-NEXT:  // %bb.1: // %entry
+; CHECK1024-NOSPLITSVE-NEXT:    smstop sm
+; CHECK1024-NOSPLITSVE-NEXT:  .LBB29_2: // %entry
+; CHECK1024-NOSPLITSVE-NEXT:    mov x0, sp
+; CHECK1024-NOSPLITSVE-NEXT:    mov w1, #45 // =0x2d
+; CHECK1024-NOSPLITSVE-NEXT:    mov w2, #37 // =0x25
+; CHECK1024-NOSPLITSVE-NEXT:    bl memset
+; CHECK1024-NOSPLITSVE-NEXT:    tbz w19, #0, .LBB29_4
+; CHECK1024-NOSPLITSVE-NEXT:  // %bb.3: // %entry
+; CHECK1024-NOSPLITSVE-NEXT:    smstart sm
+; CHECK1024-NOSPLITSVE-NEXT:  .LBB29_4: // %entry
+; CHECK1024-NOSPLITSVE-NEXT:    mov w0, #22647 // =0x5877
+; CHECK1024-NOSPLITSVE-NEXT:    movk w0, #59491, lsl #16
+; CHECK1024-NOSPLITSVE-NEXT:    add sp, sp, #1072
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    addvl sp, sp, #18
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore z8
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore z9
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore z10
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore z11
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore z12
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore z13
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore z14
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore z15
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_def_cfa wsp, 1088
+; CHECK1024-NOSPLITSVE-NEXT:    ldr x19, [sp, #1072] // 8-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr x26, [sp, #1064] // 8-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr x27, [sp, #1056] // 8-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr x28, [sp, #1048] // 8-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr x30, [sp, #1032] // 8-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    ldr x29, [sp, #1024] // 8-byte Folded Reload
+; CHECK1024-NOSPLITSVE-NEXT:    add sp, sp, #1088
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_def_cfa_offset 0
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore w19
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore w26
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore w27
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore w28
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore vg
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore w30
+; CHECK1024-NOSPLITSVE-NEXT:    .cfi_restore w29
+; CHECK1024-NOSPLITSVE-NEXT:    ret
+;
+; CHECK1024-SPLITSVE-LABEL: svecc_alloca_call:
+; CHECK1024-SPLITSVE:       // %bb.0: // %entry
+; CHECK1024-SPLITSVE-NEXT:    stp x29, x30, [sp, #-64]! // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    .cfi_def_cfa_offset 64
+; CHECK1024-SPLITSVE-NEXT:    cntd x9
+; CHECK1024-SPLITSVE-NEXT:    stp x28, x27, [sp, #32] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str x9, [sp, #16] // 8-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    stp x26, x19, [sp, #48] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    mov x29, sp
+; CHECK1024-SPLITSVE-NEXT:    .cfi_def_cfa w29, 64
+; CHECK1024-SPLITSVE-NEXT:    .cfi_offset w19, -8
+; CHECK1024-SPLITSVE-NEXT:    .cfi_offset w26, -16
+; CHECK1024-SPLITSVE-NEXT:    .cfi_offset w27, -24
+; CHECK1024-SPLITSVE-NEXT:    .cfi_offset w28, -32
+; CHECK1024-SPLITSVE-NEXT:    .cfi_offset vg, -48
+; CHECK1024-SPLITSVE-NEXT:    .cfi_offset w30, -56
+; CHECK1024-SPLITSVE-NEXT:    .cfi_offset w29, -64
+; CHECK1024-SPLITSVE-NEXT:    addvl sp, sp, #-2
+; CHECK1024-SPLITSVE-NEXT:    str p15, [sp, #4, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p14, [sp, #5, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p13, [sp, #6, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p12, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p11, [sp, #8, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p10, [sp, #9, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p9, [sp, #10, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p8, [sp, #11, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p7, [sp, #12, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p6, [sp, #13, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p5, [sp, #14, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str p4, [sp, #15, mul vl] // 2-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    sub sp, sp, #1024
+; CHECK1024-SPLITSVE-NEXT:    addvl sp, sp, #-16
+; CHECK1024-SPLITSVE-NEXT:    str z23, [sp] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z22, [sp, #1, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z21, [sp, #2, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z20, [sp, #3, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z19, [sp, #4, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z18, [sp, #5, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z17, [sp, #6, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z16, [sp, #7, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z15, [sp, #8, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z14, [sp, #9, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z13, [sp, #10, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z12, [sp, #11, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z11, [sp, #12, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z9, [sp, #14, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    str z8, [sp, #15, mul vl] // 16-byte Folded Spill
+; CHECK1024-SPLITSVE-NEXT:    .cfi_escape 0x10, 0x48, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x68, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d8 @ cfa - 24 * IncomingVG - 1088
+; CHECK1024-SPLITSVE-NEXT:    .cfi_escape 0x10, 0x49, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x60, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d9 @ cfa - 32 * IncomingVG - 1088
+; CHECK1024-SPLITSVE-NEXT:    .cfi_escape 0x10, 0x4a, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x58, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d10 @ cfa - 40 * IncomingVG - 1088
+; CHECK1024-SPLITSVE-NEXT:    .cfi_escape 0x10, 0x4b, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x50, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d11 @ cfa - 48 * IncomingVG - 1088
+; CHECK1024-SPLITSVE-NEXT:    .cfi_escape 0x10, 0x4c, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x48, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d12 @ cfa - 56 * IncomingVG - 1088
+; CHECK1024-SPLITSVE-NEXT:    .cfi_escape 0x10, 0x4d, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x40, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d13 @ cfa - 64 * IncomingVG - 1088
+; CHECK1024-SPLITSVE-NEXT:    .cfi_escape 0x10, 0x4e, 0x0e, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0xb8, 0x7f, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d14 @ cfa - 72 * IncomingVG - 1088
+; CHECK1024-SPLITSVE-NEXT:    .cfi_escape 0x10, 0x4f, 0x0e, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0xb0, 0x7f, 0x1e, 0x22, 0x11, 0xc0, 0x77, 0x22 // $d15 @ cfa - 80 * IncomingVG - 1088
+; CHECK1024-SPLITSVE-NEXT:    sub sp, sp, #1072
+; CHECK1024-SPLITSVE-NEXT:    bl __arm_sme_state
+; CHECK1024-SPLITSVE-NEXT:    mov x19, x0
+; CHECK1024-SPLITSVE-NEXT:    //APP
+; CHECK1024-SPLITSVE-NEXT:    //NO_APP
+; CHECK1024-SPLITSVE-NEXT:    tbz w19, #0, .LBB29_2
+; CHECK1024-SPLITSVE-NEXT:  // %bb.1: // %entry
+; CHECK1024-SPLITSVE-NEXT:    smstop sm
+; CHECK1024-SPLITSVE-NEXT:  .LBB29_2: // %entry
+; CHECK1024-SPLITSVE-NEXT:    mov x0, sp
+; CHECK1024-SPLITSVE-NEXT:    mov w1, #45 // =0x2d
+; CHECK1024-SPLITSVE-NEXT:    mov w2, #37 // =0x25
+; CHECK1024-SPLITSVE-NEXT:    bl memset
+; CHECK1024-SPLITSVE-NEXT:    tbz w19, #0, .LBB29_4
+; CHECK1024-SPLITSVE-NEXT:  // %bb.3: // %entry
+; CHECK1024-SPLITSVE-NEXT:    smstart sm
+; CHECK1024-SPLITSVE-NEXT:  .LBB29_4: // %entry
+; CHECK1024-SPLITSVE-NEXT:    mov w0, #22647 // =0x5877
+; CHECK1024-SPLITSVE-NEXT:    movk w0, #59491, lsl #16
+; CHECK1024-SPLITSVE-NEXT:    add sp, sp, #1072
+; CHECK1024-SPLITSVE-NEXT:    ldr z23, [sp] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z22, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z21, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z20, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z19, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z18, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z17, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z16, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z15, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z14, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z13, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z12, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr z8, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    add sp, sp, #1024
+; CHECK1024-SPLITSVE-NEXT:    addvl sp, sp, #16
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore z8
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore z9
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore z10
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore z11
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore z12
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore z13
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore z14
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore z15
+; CHECK1024-SPLITSVE-NEXT:    ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    addvl sp, sp, #2
+; CHECK1024-SPLITSVE-NEXT:    .cfi_def_cfa wsp, 64
+; CHECK1024-SPLITSVE-NEXT:    ldp x26, x19, [sp, #48] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldp x28, x27, [sp, #32] // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    ldp x29, x30, [sp], #64 // 16-byte Folded Reload
+; CHECK1024-SPLITSVE-NEXT:    .cfi_def_cfa_offset 0
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore w19
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore w26
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore w27
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore w28
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore vg
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore w30
+; CHECK1024-SPLITSVE-NEXT:    .cfi_restore w29
+; CHECK1024-SPLITSVE-NEXT:    ret
 
 entry:
   tail call void asm sideeffect "", "~{x0},~{x28},~{x27},~{x3}"() #2