[llvm] [AArch64][SME] Enable `aarch64-split-sve-objects` with hazard padding (PR #161714)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Oct 2 11:17:45 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-aarch64
Author: Benjamin Maxwell (MacDue)
<details>
<summary>Changes</summary>
This enables `aarch64-split-sve-objects` by default. Note: This option only has an effect when used in conjunction with hazard padding (`aarch64-stack-hazard-size` != 0).
See https://github.com/llvm/llvm-project/pull/142392 for more details.
---
Patch is 27.00 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/161714.diff
3 Files Affected:
- (modified) llvm/lib/Target/AArch64/AArch64FrameLowering.cpp (+1-1)
- (modified) llvm/test/CodeGen/AArch64/ssve-stack-hazard-remarks.ll (+2-4)
- (modified) llvm/test/CodeGen/AArch64/stack-hazard.ll (+138-134)
``````````diff
diff --git a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
index 8d6eb91d74375..4357264d2232d 100644
--- a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -282,7 +282,7 @@ static cl::opt<bool> OrderFrameObjects("aarch64-order-frame-objects",
static cl::opt<bool>
SplitSVEObjects("aarch64-split-sve-objects",
cl::desc("Split allocation of ZPR & PPR objects"),
- cl::init(false), cl::Hidden);
+ cl::init(true), cl::Hidden);
cl::opt<bool> EnableHomogeneousPrologEpilog(
"homogeneous-prolog-epilog", cl::Hidden,
diff --git a/llvm/test/CodeGen/AArch64/ssve-stack-hazard-remarks.ll b/llvm/test/CodeGen/AArch64/ssve-stack-hazard-remarks.ll
index 1de8d0a080b70..cd144eede20b6 100644
--- a/llvm/test/CodeGen/AArch64/ssve-stack-hazard-remarks.ll
+++ b/llvm/test/CodeGen/AArch64/ssve-stack-hazard-remarks.ll
@@ -68,13 +68,12 @@ entry:
}
; SVE calling conventions
-; Predicate register spills end up in FP region, currently. This can be
-; mitigated with the -aarch64-enable-zpr-predicate-spills option.
+; Padding is placed predicate and fpr/zpr register spills, so only emit remarks when hazard padding is off.
+; Note: The -aarch64-enable-zpr-predicate-spills option is deprecated (and will be removed soon).
define i32 @svecc_call(<4 x i16> %P0, ptr %P1, i32 %P2, <vscale x 16 x i8> %P3, i16 %P4) #2 {
; CHECK: remark: <unknown>:0:0: stack hazard in 'svecc_call': PPR stack object at [SP-64-258 * vscale] is too close to FPR stack object at [SP-64-256 * vscale]
; CHECK: remark: <unknown>:0:0: stack hazard in 'svecc_call': FPR stack object at [SP-64-16 * vscale] is too close to GPR stack object at [SP-64]
-; CHECK-PADDING: remark: <unknown>:0:0: stack hazard in 'svecc_call': PPR stack object at [SP-1088-258 * vscale] is too close to FPR stack object at [SP-1088-256 * vscale]
; CHECK-PADDING-NOT: remark: <unknown>:0:0: stack hazard in 'svecc_call':
; CHECK-ZPR-PRED-SPILLS-NOT: <unknown>:0:0: stack hazard in 'svecc_call': PPR stack object at {{.*}} is too close to FPR stack object
; CHECK-ZPR-PRED-SPILLS: <unknown>:0:0: stack hazard in 'svecc_call': FPR stack object at [SP-64-16 * vscale] is too close to GPR stack object at [SP-64]
@@ -89,7 +88,6 @@ entry:
define i32 @svecc_alloca_call(<4 x i16> %P0, ptr %P1, i32 %P2, <vscale x 16 x i8> %P3, i16 %P4) #2 {
; CHECK: remark: <unknown>:0:0: stack hazard in 'svecc_alloca_call': PPR stack object at [SP-64-258 * vscale] is too close to FPR stack object at [SP-64-256 * vscale]
; CHECK: remark: <unknown>:0:0: stack hazard in 'svecc_alloca_call': FPR stack object at [SP-64-16 * vscale] is too close to GPR stack object at [SP-64]
-; CHECK-PADDING: remark: <unknown>:0:0: stack hazard in 'svecc_alloca_call': PPR stack object at [SP-1088-258 * vscale] is too close to FPR stack object at [SP-1088-256 * vscale]
; CHECK-PADDING-NOT: remark: <unknown>:0:0: stack hazard in 'svecc_alloca_call':
; CHECK-ZPR-PRED-SPILLS-NOT: <unknown>:0:0: stack hazard in 'svecc_call': PPR stack object at {{.*}} is too close to FPR stack object
; CHECK-ZPR-PRED-SPILLS: <unknown>:0:0: stack hazard in 'svecc_alloca_call': FPR stack object at [SP-64-16 * vscale] is too close to GPR stack object at [SP-64]
diff --git a/llvm/test/CodeGen/AArch64/stack-hazard.ll b/llvm/test/CodeGen/AArch64/stack-hazard.ll
index 333a8be27f687..bdee359487ce6 100644
--- a/llvm/test/CodeGen/AArch64/stack-hazard.ll
+++ b/llvm/test/CodeGen/AArch64/stack-hazard.ll
@@ -1,8 +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,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
+; RUN: llc < %s -mtriple=aarch64 -mattr=+sve2 -aarch64-split-sve-objects=false -aarch64-stack-hazard-size=1024 | FileCheck %s --check-prefixes=CHECK,CHECK1024,CHECK1024-NOSPLITSVE
+; RUN: llc < %s -mtriple=aarch64 -mattr=+sve2 -aarch64-stack-hazard-size=1024 | FileCheck %s --check-prefixes=CHECK,CHECK1024,CHECK1024-SPLITSVE
define i32 @basic(i32 noundef %num) {
; CHECK-LABEL: basic:
@@ -1940,23 +1940,22 @@ define i32 @svecc_call(<4 x i16> %P0, ptr %P1, i32 %P2, <vscale x 16 x i8> %P3,
;
; CHECK64-LABEL: svecc_call:
; CHECK64: // %bb.0: // %entry
-; CHECK64-NEXT: sub sp, sp, #128
-; CHECK64-NEXT: .cfi_def_cfa_offset 128
+; CHECK64-NEXT: stp x29, x30, [sp, #-64]! // 16-byte Folded Spill
+; CHECK64-NEXT: .cfi_def_cfa_offset 64
; CHECK64-NEXT: cntd x9
-; CHECK64-NEXT: stp x29, x30, [sp, #64] // 16-byte Folded Spill
-; CHECK64-NEXT: stp x9, x28, [sp, #80] // 16-byte Folded Spill
-; CHECK64-NEXT: stp x27, x26, [sp, #96] // 16-byte Folded Spill
-; CHECK64-NEXT: str x19, [sp, #112] // 8-byte Folded Spill
-; CHECK64-NEXT: add x29, sp, #64
+; CHECK64-NEXT: stp x28, x27, [sp, #32] // 16-byte Folded Spill
+; CHECK64-NEXT: str x9, [sp, #16] // 8-byte Folded Spill
+; CHECK64-NEXT: stp x26, x19, [sp, #48] // 16-byte Folded Spill
+; CHECK64-NEXT: mov x29, sp
; CHECK64-NEXT: .cfi_def_cfa w29, 64
-; CHECK64-NEXT: .cfi_offset w19, -16
-; CHECK64-NEXT: .cfi_offset w26, -24
-; CHECK64-NEXT: .cfi_offset w27, -32
-; CHECK64-NEXT: .cfi_offset w28, -40
+; CHECK64-NEXT: .cfi_offset w19, -8
+; CHECK64-NEXT: .cfi_offset w26, -16
+; CHECK64-NEXT: .cfi_offset w27, -24
+; CHECK64-NEXT: .cfi_offset w28, -32
; CHECK64-NEXT: .cfi_offset vg, -48
; CHECK64-NEXT: .cfi_offset w30, -56
; CHECK64-NEXT: .cfi_offset w29, -64
-; CHECK64-NEXT: addvl sp, sp, #-18
+; CHECK64-NEXT: addvl sp, sp, #-2
; CHECK64-NEXT: str p15, [sp, #4, mul vl] // 2-byte Folded Spill
; CHECK64-NEXT: str p14, [sp, #5, mul vl] // 2-byte Folded Spill
; CHECK64-NEXT: str p13, [sp, #6, mul vl] // 2-byte Folded Spill
@@ -1969,30 +1968,32 @@ define i32 @svecc_call(<4 x i16> %P0, ptr %P1, i32 %P2, <vscale x 16 x i8> %P3,
; CHECK64-NEXT: str p6, [sp, #13, mul vl] // 2-byte Folded Spill
; CHECK64-NEXT: str p5, [sp, #14, mul vl] // 2-byte Folded Spill
; CHECK64-NEXT: str p4, [sp, #15, mul vl] // 2-byte Folded Spill
-; CHECK64-NEXT: str z23, [sp, #2, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z22, [sp, #3, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z21, [sp, #4, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z20, [sp, #5, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z19, [sp, #6, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z18, [sp, #7, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z17, [sp, #8, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z16, [sp, #9, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z15, [sp, #10, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z14, [sp, #11, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z13, [sp, #12, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z12, [sp, #13, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z11, [sp, #14, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z10, [sp, #15, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z9, [sp, #16, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z8, [sp, #17, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: .cfi_escape 0x10, 0x48, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x78, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d8 @ cfa - 8 * IncomingVG - 128
-; CHECK64-NEXT: .cfi_escape 0x10, 0x49, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x70, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d9 @ cfa - 16 * IncomingVG - 128
-; CHECK64-NEXT: .cfi_escape 0x10, 0x4a, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x68, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d10 @ cfa - 24 * IncomingVG - 128
-; CHECK64-NEXT: .cfi_escape 0x10, 0x4b, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x60, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d11 @ cfa - 32 * IncomingVG - 128
-; CHECK64-NEXT: .cfi_escape 0x10, 0x4c, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x58, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d12 @ cfa - 40 * IncomingVG - 128
-; CHECK64-NEXT: .cfi_escape 0x10, 0x4d, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x50, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d13 @ cfa - 48 * IncomingVG - 128
-; CHECK64-NEXT: .cfi_escape 0x10, 0x4e, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x48, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d14 @ cfa - 56 * IncomingVG - 128
-; CHECK64-NEXT: .cfi_escape 0x10, 0x4f, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x40, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d15 @ cfa - 64 * IncomingVG - 128
+; CHECK64-NEXT: sub sp, sp, #64
+; CHECK64-NEXT: addvl sp, sp, #-16
+; CHECK64-NEXT: str z23, [sp] // 16-byte Folded Spill
+; CHECK64-NEXT: str z22, [sp, #1, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z21, [sp, #2, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z20, [sp, #3, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z19, [sp, #4, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z18, [sp, #5, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z17, [sp, #6, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z16, [sp, #7, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z15, [sp, #8, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z14, [sp, #9, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z13, [sp, #10, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z12, [sp, #11, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z11, [sp, #12, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z10, [sp, #13, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z9, [sp, #14, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: str z8, [sp, #15, mul vl] // 16-byte Folded Spill
+; CHECK64-NEXT: .cfi_escape 0x10, 0x48, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x68, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d8 @ cfa - 24 * IncomingVG - 128
+; CHECK64-NEXT: .cfi_escape 0x10, 0x49, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x60, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d9 @ cfa - 32 * IncomingVG - 128
+; CHECK64-NEXT: .cfi_escape 0x10, 0x4a, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x58, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d10 @ cfa - 40 * IncomingVG - 128
+; CHECK64-NEXT: .cfi_escape 0x10, 0x4b, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x50, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d11 @ cfa - 48 * IncomingVG - 128
+; CHECK64-NEXT: .cfi_escape 0x10, 0x4c, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x48, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d12 @ cfa - 56 * IncomingVG - 128
+; CHECK64-NEXT: .cfi_escape 0x10, 0x4d, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x40, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d13 @ cfa - 64 * IncomingVG - 128
+; CHECK64-NEXT: .cfi_escape 0x10, 0x4e, 0x0e, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0xb8, 0x7f, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d14 @ cfa - 72 * IncomingVG - 128
+; CHECK64-NEXT: .cfi_escape 0x10, 0x4f, 0x0e, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0xb0, 0x7f, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d15 @ cfa - 80 * IncomingVG - 128
; CHECK64-NEXT: sub sp, sp, #64
; CHECK64-NEXT: mov x8, x0
; CHECK64-NEXT: bl __arm_sme_state
@@ -2014,22 +2015,32 @@ define i32 @svecc_call(<4 x i16> %P0, ptr %P1, i32 %P2, <vscale x 16 x i8> %P3,
; CHECK64-NEXT: mov w0, #22647 // =0x5877
; CHECK64-NEXT: movk w0, #59491, lsl #16
; CHECK64-NEXT: add sp, sp, #64
-; CHECK64-NEXT: ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
-; CHECK64-NEXT: ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
-; CHECK64-NEXT: ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
-; CHECK64-NEXT: ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
-; CHECK64-NEXT: ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
-; CHECK64-NEXT: ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
-; CHECK64-NEXT: ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
-; CHECK64-NEXT: ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
-; CHECK64-NEXT: ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
-; CHECK64-NEXT: ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
-; CHECK64-NEXT: ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
-; CHECK64-NEXT: ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
-; CHECK64-NEXT: ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
-; CHECK64-NEXT: ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
-; CHECK64-NEXT: ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
-; CHECK64-NEXT: ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
+; CHECK64-NEXT: ldr z23, [sp] // 16-byte Folded Reload
+; CHECK64-NEXT: ldr z22, [sp, #1, mul vl] // 16-byte Folded Reload
+; CHECK64-NEXT: ldr z21, [sp, #2, mul vl] // 16-byte Folded Reload
+; CHECK64-NEXT: ldr z20, [sp, #3, mul vl] // 16-byte Folded Reload
+; CHECK64-NEXT: ldr z19, [sp, #4, mul vl] // 16-byte Folded Reload
+; CHECK64-NEXT: ldr z18, [sp, #5, mul vl] // 16-byte Folded Reload
+; CHECK64-NEXT: ldr z17, [sp, #6, mul vl] // 16-byte Folded Reload
+; CHECK64-NEXT: ldr z16, [sp, #7, mul vl] // 16-byte Folded Reload
+; CHECK64-NEXT: ldr z15, [sp, #8, mul vl] // 16-byte Folded Reload
+; CHECK64-NEXT: ldr z14, [sp, #9, mul vl] // 16-byte Folded Reload
+; CHECK64-NEXT: ldr z13, [sp, #10, mul vl] // 16-byte Folded Reload
+; CHECK64-NEXT: ldr z12, [sp, #11, mul vl] // 16-byte Folded Reload
+; CHECK64-NEXT: ldr z11, [sp, #12, mul vl] // 16-byte Folded Reload
+; CHECK64-NEXT: ldr z10, [sp, #13, mul vl] // 16-byte Folded Reload
+; CHECK64-NEXT: ldr z9, [sp, #14, mul vl] // 16-byte Folded Reload
+; CHECK64-NEXT: ldr z8, [sp, #15, mul vl] // 16-byte Folded Reload
+; CHECK64-NEXT: add sp, sp, #64
+; CHECK64-NEXT: addvl sp, sp, #16
+; CHECK64-NEXT: .cfi_restore z8
+; CHECK64-NEXT: .cfi_restore z9
+; CHECK64-NEXT: .cfi_restore z10
+; CHECK64-NEXT: .cfi_restore z11
+; CHECK64-NEXT: .cfi_restore z12
+; CHECK64-NEXT: .cfi_restore z13
+; CHECK64-NEXT: .cfi_restore z14
+; CHECK64-NEXT: .cfi_restore z15
; CHECK64-NEXT: ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; CHECK64-NEXT: ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
; CHECK64-NEXT: ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
@@ -2042,20 +2053,11 @@ define i32 @svecc_call(<4 x i16> %P0, ptr %P1, i32 %P2, <vscale x 16 x i8> %P3,
; CHECK64-NEXT: ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
; CHECK64-NEXT: ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
; CHECK64-NEXT: ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
-; CHECK64-NEXT: addvl sp, sp, #18
-; CHECK64-NEXT: .cfi_restore z8
-; CHECK64-NEXT: .cfi_restore z9
-; CHECK64-NEXT: .cfi_restore z10
-; CHECK64-NEXT: .cfi_restore z11
-; CHECK64-NEXT: .cfi_restore z12
-; CHECK64-NEXT: .cfi_restore z13
-; CHECK64-NEXT: .cfi_restore z14
-; CHECK64-NEXT: .cfi_restore z15
-; CHECK64-NEXT: .cfi_def_cfa wsp, 128
-; CHECK64-NEXT: ldp x26, x19, [sp, #104] // 16-byte Folded Reload
-; CHECK64-NEXT: ldp x28, x27, [sp, #88] // 16-byte Folded Reload
-; CHECK64-NEXT: ldp x29, x30, [sp, #64] // 16-byte Folded Reload
-; CHECK64-NEXT: add sp, sp, #128
+; CHECK64-NEXT: addvl sp, sp, #2
+; CHECK64-NEXT: .cfi_def_cfa wsp, 64
+; CHECK64-NEXT: ldp x26, x19, [sp, #48] // 16-byte Folded Reload
+; CHECK64-NEXT: ldp x28, x27, [sp, #32] // 16-byte Folded Reload
+; CHECK64-NEXT: ldp x29, x30, [sp], #64 // 16-byte Folded Reload
; CHECK64-NEXT: .cfi_def_cfa_offset 0
; CHECK64-NEXT: .cfi_restore w19
; CHECK64-NEXT: .cfi_restore w26
@@ -2463,23 +2465,22 @@ define i32 @svecc_alloca_call(<4 x i16> %P0, ptr %P1, i32 %P2, <vscale x 16 x i8
;
; CHECK64-LABEL: svecc_alloca_call:
; CHECK64: // %bb.0: // %entry
-; CHECK64-NEXT: sub sp, sp, #128
-; CHECK64-NEXT: .cfi_def_cfa_offset 128
+; CHECK64-NEXT: stp x29, x30, [sp, #-64]! // 16-byte Folded Spill
+; CHECK64-NEXT: .cfi_def_cfa_offset 64
; CHECK64-NEXT: cntd x9
-; CHECK64-NEXT: stp x29, x30, [sp, #64] // 16-byte Folded Spill
-; CHECK64-NEXT: stp x9, x28, [sp, #80] // 16-byte Folded Spill
-; CHECK64-NEXT: stp x27, x26, [sp, #96] // 16-byte Folded Spill
-; CHECK64-NEXT: str x19, [sp, #112] // 8-byte Folded Spill
-; CHECK64-NEXT: add x29, sp, #64
+; CHECK64-NEXT: stp x28, x27, [sp, #32] // 16-byte Folded Spill
+; CHECK64-NEXT: str x9, [sp, #16] // 8-byte Folded Spill
+; CHECK64-NEXT: stp x26, x19, [sp, #48] // 16-byte Folded Spill
+; CHECK64-NEXT: mov x29, sp
; CHECK64-NEXT: .cfi_def_cfa w29, 64
-; CHECK64-NEXT: .cfi_offset w19, -16
-; CHECK64-NEXT: .cfi_offset w26, -24
-; CHECK64-NEXT: .cfi_offset w27, -32
-; CHECK64-NEXT: .cfi_offset w28, -40
+; CHECK64-NEXT: .cfi_offset w19, -8
+; CHECK64-NEXT: .cfi_offset w26, -16
+; CHECK64-NEXT: .cfi_offset w27, -24
+; CHECK64-NEXT: .cfi_offset w28, -32
; CHECK64-NEXT: .cfi_offset vg, -48
; CHECK64-NEXT: .cfi_offset w30, -56
; CHECK64-NEXT: .cfi_offset w29, -64
-; CHECK64-NEXT: addvl sp, sp, #-18
+; CHECK64-NEXT: addvl sp, sp, #-2
; CHECK64-NEXT: str p15, [sp, #4, mul vl] // 2-byte Folded Spill
; CHECK64-NEXT: str p14, [sp, #5, mul vl] // 2-byte Folded Spill
; CHECK64-NEXT: str p13, [sp, #6, mul vl] // 2-byte Folded Spill
@@ -2492,30 +2493,32 @@ define i32 @svecc_alloca_call(<4 x i16> %P0, ptr %P1, i32 %P2, <vscale x 16 x i8
; CHECK64-NEXT: str p6, [sp, #13, mul vl] // 2-byte Folded Spill
; CHECK64-NEXT: str p5, [sp, #14, mul vl] // 2-byte Folded Spill
; CHECK64-NEXT: str p4, [sp, #15, mul vl] // 2-byte Folded Spill
-; CHECK64-NEXT: str z23, [sp, #2, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z22, [sp, #3, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z21, [sp, #4, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z20, [sp, #5, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z19, [sp, #6, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z18, [sp, #7, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z17, [sp, #8, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z16, [sp, #9, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z15, [sp, #10, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z14, [sp, #11, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z13, [sp, #12, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z12, [sp, #13, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z11, [sp, #14, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z10, [sp, #15, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z9, [sp, #16, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: str z8, [sp, #17, mul vl] // 16-byte Folded Spill
-; CHECK64-NEXT: .cfi_escape 0x10, 0x48, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x78, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d8 @ cfa - 8 * IncomingVG - 128
-; CHECK64-NEXT: .cfi_escape 0x10, 0x49, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x70, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d9 @ cfa - 16 * IncomingVG - 128
-; CHECK64-NEXT: .cfi_escape 0x10, 0x4a, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x68, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d10 @ cfa - 24 * IncomingVG - 128
-; CHECK64-NEXT: .cfi_escape 0x10, 0x4b, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x60, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d11 @ cfa - 32 * IncomingVG - 128
-; CHECK64-NEXT: .cfi_escape 0x10, 0x4c, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x58, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d12 @ cfa - 40 * IncomingVG - 128
-; CHECK64-NEXT: .cfi_escape 0x10, 0x4d, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x50, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d13 @ cfa - 48 * IncomingVG - 128
-; CHECK64-NEXT: .cfi_escape 0x10, 0x4e, 0x0d, 0x12, 0x11, 0x50, 0x22, 0x06, 0x11, 0x48, 0x1e, 0x22, 0x11, 0x80, 0x7f, 0x22 // $d14 @ cfa - 56 * IncomingVG - 128
-; CHECK64-NEXT: .cfi_escape 0x1...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/161714
More information about the llvm-commits
mailing list