derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
398 lines
14 KiB
LLVM
398 lines
14 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=aarch64 -aarch64-streaming-hazard-size=0 -mattr=+sve -mattr=+sme < %s | FileCheck %s
|
|
|
|
declare void @private_za_callee()
|
|
declare void @shared_za_callee() "aarch64_inout_za"
|
|
declare void @preserves_za_callee() "aarch64_preserves_za"
|
|
|
|
declare float @llvm.cos.f32(float)
|
|
|
|
; Test lazy-save mechanism for a single callee.
|
|
define void @test_lazy_save_1_callee() nounwind "aarch64_inout_za" {
|
|
; CHECK-LABEL: test_lazy_save_1_callee:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
|
|
; CHECK-NEXT: str x19, [sp, #16] // 8-byte Spill
|
|
; CHECK-NEXT: mov x29, sp
|
|
; CHECK-NEXT: sub sp, sp, #16
|
|
; CHECK-NEXT: rdsvl x8, #1
|
|
; CHECK-NEXT: mov x9, sp
|
|
; CHECK-NEXT: msub x9, x8, x8, x9
|
|
; CHECK-NEXT: mov sp, x9
|
|
; CHECK-NEXT: sub x10, x29, #16
|
|
; CHECK-NEXT: stp x9, x8, [x29, #-16]
|
|
; CHECK-NEXT: msr TPIDR2_EL0, x10
|
|
; CHECK-NEXT: bl private_za_callee
|
|
; CHECK-NEXT: smstart za
|
|
; CHECK-NEXT: mrs x8, TPIDR2_EL0
|
|
; CHECK-NEXT: sub x0, x29, #16
|
|
; CHECK-NEXT: cbnz x8, .LBB0_2
|
|
; CHECK-NEXT: // %bb.1:
|
|
; CHECK-NEXT: bl __arm_tpidr2_restore
|
|
; CHECK-NEXT: .LBB0_2:
|
|
; CHECK-NEXT: msr TPIDR2_EL0, xzr
|
|
; CHECK-NEXT: mov sp, x29
|
|
; CHECK-NEXT: ldr x19, [sp, #16] // 8-byte Reload
|
|
; CHECK-NEXT: ldp x29, x30, [sp], #32 // 16-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
call void @private_za_callee()
|
|
ret void
|
|
}
|
|
|
|
; Test lazy-save mechanism for multiple callees.
|
|
define void @test_lazy_save_2_callees() nounwind "aarch64_inout_za" {
|
|
;
|
|
; CHECK-LABEL: test_lazy_save_2_callees:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
|
|
; CHECK-NEXT: str x19, [sp, #16] // 8-byte Spill
|
|
; CHECK-NEXT: mov x29, sp
|
|
; CHECK-NEXT: sub sp, sp, #16
|
|
; CHECK-NEXT: rdsvl x8, #1
|
|
; CHECK-NEXT: mov x9, sp
|
|
; CHECK-NEXT: msub x9, x8, x8, x9
|
|
; CHECK-NEXT: mov sp, x9
|
|
; CHECK-NEXT: sub x10, x29, #16
|
|
; CHECK-NEXT: stp x9, x8, [x29, #-16]
|
|
; CHECK-NEXT: msr TPIDR2_EL0, x10
|
|
; CHECK-NEXT: bl private_za_callee
|
|
; CHECK-NEXT: bl private_za_callee
|
|
; CHECK-NEXT: smstart za
|
|
; CHECK-NEXT: mrs x8, TPIDR2_EL0
|
|
; CHECK-NEXT: sub x0, x29, #16
|
|
; CHECK-NEXT: cbnz x8, .LBB1_2
|
|
; CHECK-NEXT: // %bb.1:
|
|
; CHECK-NEXT: bl __arm_tpidr2_restore
|
|
; CHECK-NEXT: .LBB1_2:
|
|
; CHECK-NEXT: msr TPIDR2_EL0, xzr
|
|
; CHECK-NEXT: mov sp, x29
|
|
; CHECK-NEXT: ldr x19, [sp, #16] // 8-byte Reload
|
|
; CHECK-NEXT: ldp x29, x30, [sp], #32 // 16-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
call void @private_za_callee()
|
|
call void @private_za_callee()
|
|
ret void
|
|
}
|
|
|
|
; Test a call of an intrinsic that gets expanded to a library call.
|
|
define float @test_lazy_save_expanded_intrinsic(float %a) nounwind "aarch64_inout_za" {
|
|
; CHECK-LABEL: test_lazy_save_expanded_intrinsic:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
|
|
; CHECK-NEXT: str x19, [sp, #16] // 8-byte Spill
|
|
; CHECK-NEXT: mov x29, sp
|
|
; CHECK-NEXT: sub sp, sp, #16
|
|
; CHECK-NEXT: rdsvl x8, #1
|
|
; CHECK-NEXT: mov x9, sp
|
|
; CHECK-NEXT: msub x9, x8, x8, x9
|
|
; CHECK-NEXT: mov sp, x9
|
|
; CHECK-NEXT: sub x10, x29, #16
|
|
; CHECK-NEXT: stp x9, x8, [x29, #-16]
|
|
; CHECK-NEXT: msr TPIDR2_EL0, x10
|
|
; CHECK-NEXT: bl cosf
|
|
; CHECK-NEXT: smstart za
|
|
; CHECK-NEXT: mrs x8, TPIDR2_EL0
|
|
; CHECK-NEXT: sub x0, x29, #16
|
|
; CHECK-NEXT: cbnz x8, .LBB2_2
|
|
; CHECK-NEXT: // %bb.1:
|
|
; CHECK-NEXT: bl __arm_tpidr2_restore
|
|
; CHECK-NEXT: .LBB2_2:
|
|
; CHECK-NEXT: msr TPIDR2_EL0, xzr
|
|
; CHECK-NEXT: mov sp, x29
|
|
; CHECK-NEXT: ldr x19, [sp, #16] // 8-byte Reload
|
|
; CHECK-NEXT: ldp x29, x30, [sp], #32 // 16-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
%res = call float @llvm.cos.f32(float %a)
|
|
ret float %res
|
|
}
|
|
|
|
; Test a combination of streaming-compatible -> normal call with lazy-save.
|
|
define void @test_lazy_save_and_conditional_smstart() nounwind "aarch64_inout_za" "aarch64_pstate_sm_compatible" {
|
|
;
|
|
; CHECK-LABEL: test_lazy_save_and_conditional_smstart:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: stp d15, d14, [sp, #-96]! // 16-byte Folded Spill
|
|
; CHECK-NEXT: stp d13, d12, [sp, #16] // 16-byte Folded Spill
|
|
; CHECK-NEXT: stp d11, d10, [sp, #32] // 16-byte Folded Spill
|
|
; CHECK-NEXT: stp d9, d8, [sp, #48] // 16-byte Folded Spill
|
|
; CHECK-NEXT: stp x29, x30, [sp, #64] // 16-byte Folded Spill
|
|
; CHECK-NEXT: add x29, sp, #64
|
|
; CHECK-NEXT: stp x20, x19, [sp, #80] // 16-byte Folded Spill
|
|
; CHECK-NEXT: sub sp, sp, #16
|
|
; CHECK-NEXT: rdsvl x8, #1
|
|
; CHECK-NEXT: mov x9, sp
|
|
; CHECK-NEXT: msub x9, x8, x8, x9
|
|
; CHECK-NEXT: mov sp, x9
|
|
; CHECK-NEXT: stp x9, x8, [x29, #-80]
|
|
; CHECK-NEXT: mrs x20, SVCR
|
|
; CHECK-NEXT: sub x8, x29, #80
|
|
; CHECK-NEXT: msr TPIDR2_EL0, x8
|
|
; CHECK-NEXT: tbz w20, #0, .LBB3_2
|
|
; CHECK-NEXT: // %bb.1:
|
|
; CHECK-NEXT: smstop sm
|
|
; CHECK-NEXT: .LBB3_2:
|
|
; CHECK-NEXT: bl private_za_callee
|
|
; CHECK-NEXT: tbz w20, #0, .LBB3_4
|
|
; CHECK-NEXT: // %bb.3:
|
|
; CHECK-NEXT: smstart sm
|
|
; CHECK-NEXT: .LBB3_4:
|
|
; CHECK-NEXT: smstart za
|
|
; CHECK-NEXT: mrs x8, TPIDR2_EL0
|
|
; CHECK-NEXT: sub x0, x29, #80
|
|
; CHECK-NEXT: cbnz x8, .LBB3_6
|
|
; CHECK-NEXT: // %bb.5:
|
|
; CHECK-NEXT: bl __arm_tpidr2_restore
|
|
; CHECK-NEXT: .LBB3_6:
|
|
; CHECK-NEXT: msr TPIDR2_EL0, xzr
|
|
; CHECK-NEXT: sub sp, x29, #64
|
|
; CHECK-NEXT: ldp x20, x19, [sp, #80] // 16-byte Folded Reload
|
|
; CHECK-NEXT: ldp x29, x30, [sp, #64] // 16-byte Folded Reload
|
|
; CHECK-NEXT: ldp d9, d8, [sp, #48] // 16-byte Folded Reload
|
|
; CHECK-NEXT: ldp d11, d10, [sp, #32] // 16-byte Folded Reload
|
|
; CHECK-NEXT: ldp d13, d12, [sp, #16] // 16-byte Folded Reload
|
|
; CHECK-NEXT: ldp d15, d14, [sp], #96 // 16-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
call void @private_za_callee()
|
|
ret void
|
|
}
|
|
|
|
; Note: For the final @private_za_callee() we setup a lazy save then don't
|
|
; restore from it (since ZA is off on return). We could improve this case
|
|
; by turning ZA off before the final private ZA call.
|
|
define void @test_lazy_save_mixed_shared_and_private_callees() "aarch64_new_za"
|
|
;
|
|
; CHECK-LABEL: test_lazy_save_mixed_shared_and_private_callees:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
|
|
; CHECK-NEXT: str x19, [sp, #16] // 8-byte Spill
|
|
; CHECK-NEXT: mov x29, sp
|
|
; CHECK-NEXT: sub sp, sp, #16
|
|
; CHECK-NEXT: .cfi_def_cfa w29, 32
|
|
; CHECK-NEXT: .cfi_offset w19, -16
|
|
; CHECK-NEXT: .cfi_offset w30, -24
|
|
; CHECK-NEXT: .cfi_offset w29, -32
|
|
; CHECK-NEXT: rdsvl x8, #1
|
|
; CHECK-NEXT: mov x9, sp
|
|
; CHECK-NEXT: msub x9, x8, x8, x9
|
|
; CHECK-NEXT: mov sp, x9
|
|
; CHECK-NEXT: stp x9, x8, [x29, #-16]
|
|
; CHECK-NEXT: mrs x8, TPIDR2_EL0
|
|
; CHECK-NEXT: cbz x8, .LBB4_2
|
|
; CHECK-NEXT: // %bb.1:
|
|
; CHECK-NEXT: bl __arm_tpidr2_save
|
|
; CHECK-NEXT: msr TPIDR2_EL0, xzr
|
|
; CHECK-NEXT: zero {za}
|
|
; CHECK-NEXT: .LBB4_2:
|
|
; CHECK-NEXT: smstart za
|
|
; CHECK-NEXT: sub x8, x29, #16
|
|
; CHECK-NEXT: msr TPIDR2_EL0, x8
|
|
; CHECK-NEXT: bl private_za_callee
|
|
; CHECK-NEXT: smstart za
|
|
; CHECK-NEXT: mrs x8, TPIDR2_EL0
|
|
; CHECK-NEXT: sub x0, x29, #16
|
|
; CHECK-NEXT: cbnz x8, .LBB4_4
|
|
; CHECK-NEXT: // %bb.3:
|
|
; CHECK-NEXT: bl __arm_tpidr2_restore
|
|
; CHECK-NEXT: .LBB4_4:
|
|
; CHECK-NEXT: msr TPIDR2_EL0, xzr
|
|
; CHECK-NEXT: bl shared_za_callee
|
|
; CHECK-NEXT: bl preserves_za_callee
|
|
; CHECK-NEXT: sub x8, x29, #16
|
|
; CHECK-NEXT: msr TPIDR2_EL0, x8
|
|
; CHECK-NEXT: bl private_za_callee
|
|
; CHECK-NEXT: msr TPIDR2_EL0, xzr
|
|
; CHECK-NEXT: smstop za
|
|
; CHECK-NEXT: mov sp, x29
|
|
; CHECK-NEXT: ldr x19, [sp, #16] // 8-byte Reload
|
|
; CHECK-NEXT: ldp x29, x30, [sp], #32 // 16-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
{
|
|
call void @private_za_callee()
|
|
call void @shared_za_callee()
|
|
call void @preserves_za_callee()
|
|
call void @private_za_callee()
|
|
ret void
|
|
}
|
|
|
|
define void @test_many_back2back_private_za_calls() "aarch64_inout_za" {
|
|
;
|
|
; CHECK-LABEL: test_many_back2back_private_za_calls:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
|
|
; CHECK-NEXT: str x19, [sp, #16] // 8-byte Spill
|
|
; CHECK-NEXT: mov x29, sp
|
|
; CHECK-NEXT: sub sp, sp, #16
|
|
; CHECK-NEXT: .cfi_def_cfa w29, 32
|
|
; CHECK-NEXT: .cfi_offset w19, -16
|
|
; CHECK-NEXT: .cfi_offset w30, -24
|
|
; CHECK-NEXT: .cfi_offset w29, -32
|
|
; CHECK-NEXT: rdsvl x8, #1
|
|
; CHECK-NEXT: mov x9, sp
|
|
; CHECK-NEXT: msub x9, x8, x8, x9
|
|
; CHECK-NEXT: mov sp, x9
|
|
; CHECK-NEXT: stp x9, x8, [x29, #-16]
|
|
; CHECK-NEXT: bl shared_za_callee
|
|
; CHECK-NEXT: sub x8, x29, #16
|
|
; CHECK-NEXT: msr TPIDR2_EL0, x8
|
|
; CHECK-NEXT: bl private_za_callee
|
|
; CHECK-NEXT: bl private_za_callee
|
|
; CHECK-NEXT: bl private_za_callee
|
|
; CHECK-NEXT: bl private_za_callee
|
|
; CHECK-NEXT: bl private_za_callee
|
|
; CHECK-NEXT: bl private_za_callee
|
|
; CHECK-NEXT: smstart za
|
|
; CHECK-NEXT: mrs x8, TPIDR2_EL0
|
|
; CHECK-NEXT: sub x0, x29, #16
|
|
; CHECK-NEXT: cbnz x8, .LBB5_2
|
|
; CHECK-NEXT: // %bb.1:
|
|
; CHECK-NEXT: bl __arm_tpidr2_restore
|
|
; CHECK-NEXT: .LBB5_2:
|
|
; CHECK-NEXT: msr TPIDR2_EL0, xzr
|
|
; CHECK-NEXT: bl shared_za_callee
|
|
; CHECK-NEXT: mov sp, x29
|
|
; CHECK-NEXT: ldr x19, [sp, #16] // 8-byte Reload
|
|
; CHECK-NEXT: ldp x29, x30, [sp], #32 // 16-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
call void @shared_za_callee()
|
|
call void @private_za_callee()
|
|
call void @private_za_callee()
|
|
call void @private_za_callee()
|
|
call void @private_za_callee()
|
|
call void @private_za_callee()
|
|
call void @private_za_callee()
|
|
call void @shared_za_callee()
|
|
ret void
|
|
}
|
|
|
|
define void @test_shared_private_shared() nounwind "aarch64_inout_za" {
|
|
; CHECK-LABEL: test_shared_private_shared:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
|
|
; CHECK-NEXT: str x19, [sp, #16] // 8-byte Spill
|
|
; CHECK-NEXT: mov x29, sp
|
|
; CHECK-NEXT: sub sp, sp, #16
|
|
; CHECK-NEXT: rdsvl x8, #1
|
|
; CHECK-NEXT: mov x9, sp
|
|
; CHECK-NEXT: msub x9, x8, x8, x9
|
|
; CHECK-NEXT: mov sp, x9
|
|
; CHECK-NEXT: stp x9, x8, [x29, #-16]
|
|
; CHECK-NEXT: bl shared_za_callee
|
|
; CHECK-NEXT: sub x8, x29, #16
|
|
; CHECK-NEXT: msr TPIDR2_EL0, x8
|
|
; CHECK-NEXT: bl private_za_callee
|
|
; CHECK-NEXT: smstart za
|
|
; CHECK-NEXT: mrs x8, TPIDR2_EL0
|
|
; CHECK-NEXT: sub x0, x29, #16
|
|
; CHECK-NEXT: cbnz x8, .LBB6_2
|
|
; CHECK-NEXT: // %bb.1:
|
|
; CHECK-NEXT: bl __arm_tpidr2_restore
|
|
; CHECK-NEXT: .LBB6_2:
|
|
; CHECK-NEXT: msr TPIDR2_EL0, xzr
|
|
; CHECK-NEXT: bl shared_za_callee
|
|
; CHECK-NEXT: mov sp, x29
|
|
; CHECK-NEXT: ldr x19, [sp, #16] // 8-byte Reload
|
|
; CHECK-NEXT: ldp x29, x30, [sp], #32 // 16-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
call void @shared_za_callee()
|
|
call void @private_za_callee()
|
|
call void @shared_za_callee()
|
|
ret void
|
|
}
|
|
|
|
define void @test_only_shared_za() nounwind "aarch64_inout_za" {
|
|
; CHECK-LABEL: test_only_shared_za:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
|
|
; CHECK-NEXT: bl shared_za_callee
|
|
; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
call void @shared_za_callee()
|
|
ret void
|
|
}
|
|
|
|
declare i64 @shared_za_callee_i64(i64) "aarch64_inout_za"
|
|
declare i64 @private_za_callee_i64(i64)
|
|
|
|
define i64 @test_shared_private_shared_i64(i64 %x) nounwind "aarch64_inout_za" {
|
|
; CHECK-LABEL: test_shared_private_shared_i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
|
|
; CHECK-NEXT: str x19, [sp, #16] // 8-byte Spill
|
|
; CHECK-NEXT: mov x29, sp
|
|
; CHECK-NEXT: sub sp, sp, #16
|
|
; CHECK-NEXT: rdsvl x8, #1
|
|
; CHECK-NEXT: mov x9, sp
|
|
; CHECK-NEXT: msub x9, x8, x8, x9
|
|
; CHECK-NEXT: mov sp, x9
|
|
; CHECK-NEXT: stp x9, x8, [x29, #-16]
|
|
; CHECK-NEXT: bl shared_za_callee_i64
|
|
; CHECK-NEXT: sub x8, x29, #16
|
|
; CHECK-NEXT: msr TPIDR2_EL0, x8
|
|
; CHECK-NEXT: bl private_za_callee_i64
|
|
; CHECK-NEXT: mov x1, x0
|
|
; CHECK-NEXT: smstart za
|
|
; CHECK-NEXT: mrs x8, TPIDR2_EL0
|
|
; CHECK-NEXT: sub x0, x29, #16
|
|
; CHECK-NEXT: cbnz x8, .LBB8_2
|
|
; CHECK-NEXT: // %bb.1:
|
|
; CHECK-NEXT: bl __arm_tpidr2_restore
|
|
; CHECK-NEXT: .LBB8_2:
|
|
; CHECK-NEXT: mov x0, x1
|
|
; CHECK-NEXT: msr TPIDR2_EL0, xzr
|
|
; CHECK-NEXT: bl shared_za_callee_i64
|
|
; CHECK-NEXT: mov sp, x29
|
|
; CHECK-NEXT: ldr x19, [sp, #16] // 8-byte Reload
|
|
; CHECK-NEXT: ldp x29, x30, [sp], #32 // 16-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
%a = call i64 @shared_za_callee_i64(i64 %x)
|
|
%b = call i64 @private_za_callee_i64(i64 %a)
|
|
%c = call i64 @shared_za_callee_i64(i64 %b)
|
|
ret i64 %c
|
|
}
|
|
|
|
declare i64 @many_args_private_za_callee(
|
|
i64, i64, i64, i64, i64, i64, i64, i64, i64, i64)
|
|
|
|
; In this example some arguments are passed on the stack, which decrements the
|
|
; stack pointer before the call -- in this test the lazy save should be setup
|
|
; before the stack decrement.
|
|
define i64 @test_many_callee_arguments(
|
|
;
|
|
; CHECK-LABEL: test_many_callee_arguments:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
|
|
; CHECK-NEXT: str x19, [sp, #16] // 8-byte Spill
|
|
; CHECK-NEXT: mov x29, sp
|
|
; CHECK-NEXT: sub sp, sp, #16
|
|
; CHECK-NEXT: rdsvl x8, #1
|
|
; CHECK-NEXT: mov x9, sp
|
|
; CHECK-NEXT: msub x9, x8, x8, x9
|
|
; CHECK-NEXT: mov sp, x9
|
|
; CHECK-NEXT: ldp x10, x11, [x29, #32]
|
|
; CHECK-NEXT: sub x12, x29, #16
|
|
; CHECK-NEXT: stp x9, x8, [x29, #-16]
|
|
; CHECK-NEXT: msr TPIDR2_EL0, x12
|
|
; CHECK-NEXT: stp x10, x11, [sp, #-16]!
|
|
; CHECK-NEXT: bl many_args_private_za_callee
|
|
; CHECK-NEXT: add sp, sp, #16
|
|
; CHECK-NEXT: mov x1, x0
|
|
; CHECK-NEXT: smstart za
|
|
; CHECK-NEXT: mrs x8, TPIDR2_EL0
|
|
; CHECK-NEXT: sub x0, x29, #16
|
|
; CHECK-NEXT: cbnz x8, .LBB9_2
|
|
; CHECK-NEXT: // %bb.1:
|
|
; CHECK-NEXT: bl __arm_tpidr2_restore
|
|
; CHECK-NEXT: .LBB9_2:
|
|
; CHECK-NEXT: mov x0, x1
|
|
; CHECK-NEXT: msr TPIDR2_EL0, xzr
|
|
; CHECK-NEXT: mov sp, x29
|
|
; CHECK-NEXT: ldr x19, [sp, #16] // 8-byte Reload
|
|
; CHECK-NEXT: ldp x29, x30, [sp], #32 // 16-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
i64 %0, i64 %1, i64 %2, i64 %3, i64 %4, i64 %5, i64 %6, i64 %7, i64 %8, i64 %9
|
|
) nounwind "aarch64_inout_za" {
|
|
%ret = call i64 @many_args_private_za_callee(
|
|
i64 %0, i64 %1, i64 %2, i64 %3, i64 %4, i64 %5, i64 %6, i64 %7, i64 %8, i64 %9)
|
|
ret i64 %ret
|
|
}
|