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
89 lines
2.4 KiB
ArmAsm
Executable File
89 lines
2.4 KiB
ArmAsm
Executable File
# This reproduces a bug with shrink wrapping when trying to move
|
|
# push-pops in a function where we are not allowed to modify the
|
|
# stack layout for alignment reasons. In this bug, we failed to
|
|
# propagate alignment requirement upwards in the call graph for
|
|
# some functions when there is a cycle in the call graph.
|
|
|
|
# REQUIRES: system-linux
|
|
|
|
# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown \
|
|
# RUN: %s -o %t.o
|
|
# RUN: link_fdata %s %t.o %t.fdata
|
|
# Delete our BB symbols so BOLT doesn't mark them as entry points
|
|
# RUN: llvm-strip --strip-unneeded %t.o
|
|
# RUN: %clang %cflags -no-pie %t.o -o %t.exe -Wl,-q
|
|
|
|
# RUN: llvm-bolt %t.exe --relocs=1 --frame-opt=all --print-finalized \
|
|
# RUN: --lite=0 --print-only=main --data %t.fdata -o %t.out | FileCheck %s
|
|
|
|
# RUN: %t.out
|
|
|
|
# CHECK: BOLT-INFO: Shrink wrapping moved 1 spills inserting load/stores and 0 spills inserting push/pops
|
|
|
|
.text
|
|
.globl bar
|
|
.type bar, %function
|
|
.p2align 4
|
|
bar:
|
|
# FDATA: 0 [unknown] 0 1 bar 0 0 510
|
|
pushq %rbp
|
|
movq %rsp, %rbp
|
|
pushq %rbx # We save rbx here, but there is an
|
|
# opportunity to move it to .BB2
|
|
subq $0x18, %rsp
|
|
cmpl $0x2, %edi
|
|
.J1:
|
|
jb .BBend
|
|
# FDATA: 1 bar #.J1# 1 bar #.BB2# 0 10
|
|
# FDATA: 1 bar #.J1# 1 bar #.BBend# 0 500
|
|
.BB2:
|
|
movq $2, %rbx # Use rbx in a cold block
|
|
xorq %rax, %rax
|
|
movb mystring, %al
|
|
addq %rbx, %rax
|
|
movb %al, mystring
|
|
leaq mystring, %rdi
|
|
#callq puts
|
|
|
|
.BBend:
|
|
addq $0x18, %rsp
|
|
pop %rbx # Restore
|
|
xorq %rax, %rax
|
|
cmpq $0x0, %rax
|
|
jne .BBnever
|
|
jmp .BBbarend
|
|
.BBnever:
|
|
# This is a path that is never executed, but we add a call to main here
|
|
# to force a cycle in the call graph and to require us to have an aligned
|
|
# stack
|
|
callq main
|
|
.BBbarend:
|
|
leaveq
|
|
retq
|
|
.size bar, .-bar
|
|
|
|
# Frame alignedness information needs to be transmitted from foo to main to bar
|
|
.globl main
|
|
.type main, %function
|
|
.p2align 4
|
|
main:
|
|
# Call a function that requires an aligned stack
|
|
callq foo
|
|
# Call a function that can be shrink-wrapped
|
|
callq bar
|
|
retq
|
|
.size main, .-main
|
|
|
|
# Frame alignedness information needs to be transmitted from foo to main to bar
|
|
.globl foo
|
|
.type foo, %function
|
|
.p2align 4
|
|
foo:
|
|
# Use an instruction that requires an aligned stack
|
|
movdqa -0x10(%rsp), %xmm0
|
|
retq
|
|
.size foo, .-foo
|
|
|
|
.data
|
|
mystring: .asciz "0 is rbx mod 10 contents in decimal\n"
|