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
166 lines
6.6 KiB
LLVM
166 lines
6.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=haswell | FileCheck %s -check-prefix=NOAA
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=haswell -combiner-global-alias-analysis=1 | FileCheck %s -check-prefix=AA
|
|
|
|
declare void @llvm.lifetime.start.p0(i64, ptr nocapture)
|
|
declare void @llvm.memcpy.p0.p0.i64(ptr nocapture writeonly, ptr nocapture readonly, i64, i1)
|
|
declare void @llvm.lifetime.end.p0(i64, ptr nocapture)
|
|
|
|
%struct.S = type { [16 x i8] }
|
|
|
|
define dso_local void @_Z4SwapP1SS0_(ptr nocapture %a, ptr nocapture %b) local_unnamed_addr {
|
|
; NOAA-LABEL: _Z4SwapP1SS0_:
|
|
; NOAA: # %bb.0: # %entry
|
|
; NOAA-NEXT: vmovups (%rdi), %xmm0
|
|
; NOAA-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; NOAA-NEXT: vmovups (%rsi), %xmm0
|
|
; NOAA-NEXT: vmovups %xmm0, (%rdi)
|
|
; NOAA-NEXT: vmovaps -{{[0-9]+}}(%rsp), %xmm0
|
|
; NOAA-NEXT: vmovups %xmm0, (%rsi)
|
|
; NOAA-NEXT: retq
|
|
;
|
|
; AA-LABEL: _Z4SwapP1SS0_:
|
|
; AA: # %bb.0: # %entry
|
|
; AA-NEXT: vmovups (%rdi), %xmm0
|
|
; AA-NEXT: vmovups (%rsi), %xmm1
|
|
; AA-NEXT: vmovups %xmm1, (%rdi)
|
|
; AA-NEXT: vmovups %xmm0, (%rsi)
|
|
; AA-NEXT: retq
|
|
entry:
|
|
%tmp.sroa.0 = alloca [16 x i8], align 1
|
|
call void @llvm.lifetime.start.p0(i64 16, ptr nonnull %tmp.sroa.0)
|
|
call void @llvm.memcpy.p0.p0.i64(ptr nonnull align 1 %tmp.sroa.0, ptr align 1 %a, i64 16, i1 false)
|
|
tail call void @llvm.memcpy.p0.p0.i64(ptr align 1 %a, ptr align 1 %b, i64 16, i1 false), !tbaa.struct !2
|
|
call void @llvm.memcpy.p0.p0.i64(ptr align 1 %b, ptr nonnull align 1 %tmp.sroa.0, i64 16, i1 false)
|
|
call void @llvm.lifetime.end.p0(i64 16, ptr nonnull %tmp.sroa.0)
|
|
ret void
|
|
}
|
|
|
|
define dso_local void @onealloc_noreadback(ptr nocapture %a, ptr nocapture %b) local_unnamed_addr {
|
|
; NOAA-LABEL: onealloc_noreadback:
|
|
; NOAA: # %bb.0: # %entry
|
|
; NOAA-NEXT: retq
|
|
;
|
|
; AA-LABEL: onealloc_noreadback:
|
|
; AA: # %bb.0: # %entry
|
|
; AA-NEXT: retq
|
|
entry:
|
|
%alloc = alloca [16 x i8], i8 2, align 1
|
|
%part2 = getelementptr inbounds [16 x i8], ptr %alloc, i64 1, i64 0
|
|
call void @llvm.lifetime.start.p0(i64 32, ptr nonnull %alloc)
|
|
call void @llvm.memcpy.p0.p0.i64(ptr nonnull align 1 %alloc, ptr align 1 %a, i64 16, i1 false)
|
|
tail call void @llvm.memcpy.p0.p0.i64(ptr nonnull align 1 %part2, ptr align 1 %b, i64 16, i1 false)
|
|
call void @llvm.lifetime.end.p0(i64 32, ptr nonnull %alloc)
|
|
ret void
|
|
}
|
|
|
|
|
|
define dso_local void @twoallocs_trivial(ptr nocapture %a, ptr nocapture %b) local_unnamed_addr {
|
|
; NOAA-LABEL: twoallocs_trivial:
|
|
; NOAA: # %bb.0: # %entry
|
|
; NOAA-NEXT: retq
|
|
;
|
|
; AA-LABEL: twoallocs_trivial:
|
|
; AA: # %bb.0: # %entry
|
|
; AA-NEXT: retq
|
|
entry:
|
|
%alloc1 = alloca [16 x i8], align 1
|
|
%alloc2 = alloca [16 x i8], align 1
|
|
call void @llvm.lifetime.start.p0(i64 16, ptr nonnull %alloc1)
|
|
call void @llvm.lifetime.start.p0(i64 16, ptr nonnull %alloc2)
|
|
call void @llvm.memcpy.p0.p0.i64(ptr nonnull align 1 %alloc1, ptr align 1 %a, i64 16, i1 false)
|
|
call void @llvm.memcpy.p0.p0.i64(ptr nonnull align 1 %alloc2, ptr align 1 %b, i64 16, i1 false)
|
|
call void @llvm.lifetime.end.p0(i64 16, ptr nonnull %alloc1)
|
|
call void @llvm.lifetime.end.p0(i64 16, ptr nonnull %alloc2)
|
|
ret void
|
|
}
|
|
|
|
define dso_local void @twoallocs(ptr nocapture %a, ptr nocapture %b) local_unnamed_addr {
|
|
; NOAA-LABEL: twoallocs:
|
|
; NOAA: # %bb.0: # %entry
|
|
; NOAA-NEXT: vmovups (%rdi), %xmm0
|
|
; NOAA-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; NOAA-NEXT: vmovups %xmm0, (%rsi)
|
|
; NOAA-NEXT: retq
|
|
;
|
|
; AA-LABEL: twoallocs:
|
|
; AA: # %bb.0: # %entry
|
|
; AA-NEXT: vmovups (%rdi), %xmm0
|
|
; AA-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; AA-NEXT: vmovups %xmm0, (%rsi)
|
|
; AA-NEXT: retq
|
|
entry:
|
|
%alloc1 = alloca [16 x i8], align 1
|
|
%alloc2 = alloca [16 x i8], align 1
|
|
call void @llvm.lifetime.start.p0(i64 16, ptr nonnull %alloc1)
|
|
call void @llvm.lifetime.start.p0(i64 16, ptr nonnull %alloc2)
|
|
call void @llvm.memcpy.p0.p0.i64(ptr nonnull align 1 %alloc2, ptr align 1 %a, i64 16, i1 false)
|
|
call void @llvm.lifetime.end.p0(i64 16, ptr nonnull %alloc1)
|
|
tail call void @llvm.memcpy.p0.p0.i64(ptr nonnull align 1 %b, ptr align 1 %alloc2, i64 16, i1 false)
|
|
call void @llvm.lifetime.end.p0(i64 16, ptr nonnull %alloc2)
|
|
ret void
|
|
}
|
|
|
|
define dso_local void @onealloc_readback_1(ptr nocapture %a, ptr nocapture %b) local_unnamed_addr {
|
|
; NOAA-LABEL: onealloc_readback_1:
|
|
; NOAA: # %bb.0: # %entry
|
|
; NOAA-NEXT: vmovups (%rdi), %xmm0
|
|
; NOAA-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; NOAA-NEXT: vmovups (%rsi), %xmm0
|
|
; NOAA-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; NOAA-NEXT: vmovups %xmm0, (%rdi)
|
|
; NOAA-NEXT: retq
|
|
;
|
|
; AA-LABEL: onealloc_readback_1:
|
|
; AA: # %bb.0: # %entry
|
|
; AA-NEXT: vmovups (%rsi), %xmm0
|
|
; AA-NEXT: vmovups %xmm0, (%rdi)
|
|
; AA-NEXT: retq
|
|
entry:
|
|
%alloc = alloca [16 x i8], i8 2, align 1
|
|
%part1 = getelementptr inbounds [16 x i8], ptr %alloc, i64 1, i64 0
|
|
call void @llvm.lifetime.start.p0(i64 32, ptr nonnull %alloc)
|
|
call void @llvm.memcpy.p0.p0.i64(ptr nonnull align 1 %part1, ptr align 1 %a, i64 16, i1 false)
|
|
call void @llvm.memcpy.p0.p0.i64(ptr nonnull align 1 %alloc, ptr align 1 %b, i64 16, i1 false)
|
|
tail call void @llvm.memcpy.p0.p0.i64(ptr nonnull align 1 %a, ptr align 1 %alloc, i64 16, i1 false)
|
|
call void @llvm.lifetime.end.p0(i64 32, ptr nonnull %alloc)
|
|
ret void
|
|
}
|
|
|
|
define dso_local void @onealloc_readback_2(ptr nocapture %a, ptr nocapture %b) local_unnamed_addr {
|
|
; NOAA-LABEL: onealloc_readback_2:
|
|
; NOAA: # %bb.0: # %entry
|
|
; NOAA-NEXT: vmovups (%rdi), %xmm0
|
|
; NOAA-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; NOAA-NEXT: vmovups (%rsi), %xmm0
|
|
; NOAA-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; NOAA-NEXT: vmovups %xmm0, (%rdi)
|
|
; NOAA-NEXT: retq
|
|
;
|
|
; AA-LABEL: onealloc_readback_2:
|
|
; AA: # %bb.0: # %entry
|
|
; AA-NEXT: vmovups (%rsi), %xmm0
|
|
; AA-NEXT: vmovups %xmm0, (%rdi)
|
|
; AA-NEXT: retq
|
|
entry:
|
|
%alloc = alloca [16 x i8], i8 2, align 1
|
|
%part2 = getelementptr inbounds [16 x i8], ptr %alloc, i64 1, i64 0
|
|
call void @llvm.lifetime.start.p0(i64 32, ptr nonnull %alloc)
|
|
call void @llvm.memcpy.p0.p0.i64(ptr nonnull align 1 %alloc, ptr align 1 %a, i64 16, i1 false)
|
|
call void @llvm.memcpy.p0.p0.i64(ptr nonnull align 1 %part2, ptr align 1 %b, i64 16, i1 false)
|
|
tail call void @llvm.memcpy.p0.p0.i64(ptr nonnull align 1 %a, ptr align 1 %part2, i64 16, i1 false)
|
|
call void @llvm.lifetime.end.p0(i64 32, ptr nonnull %alloc)
|
|
ret void
|
|
}
|
|
|
|
|
|
!llvm.module.flags = !{!0}
|
|
!llvm.ident = !{!1}
|
|
|
|
!0 = !{i32 1, !"wchar_size", i32 4}
|
|
!1 = !{!"clang version 9.0.0 (trunk 352631) (llvm/trunk 352632)"}
|
|
!2 = !{i64 0, i64 16, !3}
|
|
!3 = !{!4, !4, i64 0}
|
|
!4 = !{!"omnipotent char", !5, i64 0}
|
|
!5 = !{!"Simple C++ TBAA"}
|