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
85 lines
2.6 KiB
LLVM
85 lines
2.6 KiB
LLVM
; RUN: llc -mtriple=thumbv7-netbsd-eabi -o - %s | FileCheck %s
|
|
declare void @bar()
|
|
|
|
; ARM's frame lowering attempts to tack another callee-saved register onto the
|
|
; list when it detects a potential misaligned VFP store. However, if there are
|
|
; none available it used to just vpush anyway and misreport the location of the
|
|
; registers in unwind info. Since there are benefits to aligned stores, it's
|
|
; better to correct the code than the .cfi_offset directive.
|
|
|
|
define void @test_dpr_align(i8 %l, i8 %r) {
|
|
; CHECK-LABEL: test_dpr_align:
|
|
; CHECK: push.w {r4, r5, r6, r7, r8, r9, r10, r11, lr}
|
|
; CHECK: .cfi_def_cfa_offset 36
|
|
; CHECK: sub sp, #4
|
|
; CHECK: .cfi_def_cfa_offset 40
|
|
; CHECK: vpush {d8}
|
|
; CHECK: .cfi_offset d8, -48
|
|
; CHECK-NOT: sub sp
|
|
; [...]
|
|
; CHECK: bl bar
|
|
; CHECK-NOT: add sp
|
|
; CHECK: vpop {d8}
|
|
; CHECK: add sp, #4
|
|
; CHECK: pop.w {r4, r5, r6, r7, r8, r9, r10, r11, pc}
|
|
call void asm sideeffect "", "~{r4},~{r5},~{r6},~{r7},~{r8},~{r9},~{r10},~{r11},~{d8}"()
|
|
call void @bar()
|
|
ret void
|
|
}
|
|
|
|
; The prologue (but not the epilogue) can be made more space efficient by
|
|
; chucking an argument register into the list. Not worth it in general though,
|
|
; "sub sp, #4" is likely faster.
|
|
define void @test_dpr_align_tiny(i8 %l, i8 %r) minsize {
|
|
; CHECK-LABEL: test_dpr_align_tiny:
|
|
; CHECK: push.w {r3, r4, r5, r6, r7, r8, r9, r10, r11, lr}
|
|
; CHECK-NOT: sub sp
|
|
; CHECK: vpush {d8}
|
|
; CHECK: .cfi_offset d8, -48
|
|
; CHECK-NOT: sub sp
|
|
; [...]
|
|
; CHECK: bl bar
|
|
; CHECK-NOT: add sp
|
|
; CHECK: vpop {d8}
|
|
; CHECK: add sp, #4
|
|
; CHECK: pop.w {r4, r5, r6, r7, r8, r9, r10, r11, pc}
|
|
call void asm sideeffect "", "~{r4},~{r5},~{r6},~{r7},~{r8},~{r9},~{r10},~{r11},~{d8}"()
|
|
call void @bar()
|
|
ret void
|
|
}
|
|
|
|
|
|
; However, we shouldn't do a 2-step align/adjust if there are no DPRs to be
|
|
; saved.
|
|
define void @test_nodpr_noalign(i8 %l, i8 %r) {
|
|
; CHECK-LABEL: test_nodpr_noalign:
|
|
; CHECK: push.w {r4, r5, r6, r7, r8, r9, r10, r11, lr}
|
|
; CHECK-NOT: sub sp
|
|
; CHECK: sub sp, #12
|
|
; CHECK-NOT: sub sp
|
|
; [...]
|
|
; CHECK: bl bar
|
|
; CHECK-NOT: add sp
|
|
; CHECK: add sp, #12
|
|
; CHECK-NOT: add sp
|
|
; CHECK: pop.w {r4, r5, r6, r7, r8, r9, r10, r11, pc}
|
|
alloca i64
|
|
call void asm sideeffect "", "~{r4},~{r5},~{r6},~{r7},~{r8},~{r9},~{r10},~{r11}"()
|
|
call void @bar()
|
|
ret void
|
|
}
|
|
|
|
define void @test_frame_pointer_offset() minsize "frame-pointer"="all" {
|
|
; CHECK-LABEL: test_frame_pointer_offset:
|
|
; CHECK: push {r4, r5, r6, r7, lr}
|
|
; CHECK: .cfi_def_cfa_offset 20
|
|
; CHECK: add r7, sp, #12
|
|
; CHECK: .cfi_def_cfa r7, 8
|
|
; CHECK-NOT: .cfi_def_cfa_offset
|
|
; CHECK: push.w {r7, r8, r9, r10, r11}
|
|
; CHECK-NOT: .cfi_def_cfa_offset
|
|
call void asm sideeffect "", "~{r4},~{r5},~{r6},~{r7},~{r8},~{r9},~{r10},~{r11},~{d8}"()
|
|
call void @bar()
|
|
ret void
|
|
}
|