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
67 lines
2.3 KiB
LLVM
67 lines
2.3 KiB
LLVM
; RUN: llc -verify-machineinstrs -mcpu=pwr8 -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck %s
|
|
|
|
; This code causes an assertion failure if dereferenceable flag is not properly set in the load generated for memcpy
|
|
|
|
; CHECK-LABEL: @func
|
|
; CHECK: lxvd2x [[VREG:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK-NOT: lxvd2x
|
|
; CHECK: stxvd2x [[VREG:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: stxvd2x [[VREG:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: blr
|
|
|
|
define void @func(i1 %flag) {
|
|
entry:
|
|
%pairs = alloca [4 x <2 x i64>], align 8
|
|
%pair1 = getelementptr inbounds [4 x <2 x i64>], ptr %pairs, i64 0, i64 1
|
|
%pair2 = getelementptr inbounds [4 x <2 x i64>], ptr %pairs, i64 0, i64 2
|
|
br i1 %flag, label %end, label %dummy
|
|
|
|
end:
|
|
; copy third element into first element by memcpy
|
|
call void @llvm.memcpy.p0.p0.i64(ptr align 8 nonnull %pairs, ptr align 8 %pair2, i64 16, i1 false)
|
|
; copy third element into second element by LD/ST
|
|
%vec2 = load <2 x i64>, ptr %pair2, align 8
|
|
store <2 x i64> %vec2, ptr %pair1, align 8
|
|
ret void
|
|
|
|
dummy:
|
|
; to make use of %pair2 in another BB
|
|
call void @llvm.memcpy.p0.p0.i64(ptr %pair2, ptr %pair2, i64 0, i1 false)
|
|
br label %end
|
|
}
|
|
|
|
|
|
; CHECK-LABEL: @func2
|
|
; CHECK: lxvd2x [[VREG:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK-NOT: lxvd2x
|
|
; CHECK: stxvd2x [[VREG:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: stxvd2x [[VREG:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: blr
|
|
|
|
define void @func2(i1 %flag) {
|
|
entry:
|
|
%pairs = alloca [4 x <2 x i64>], align 8
|
|
%pair1 = getelementptr inbounds [4 x <2 x i64>], ptr %pairs, i64 0, i64 1
|
|
%pair2 = getelementptr inbounds [4 x <2 x i64>], ptr %pairs, i64 0, i64 2
|
|
br i1 %flag, label %end, label %dummy
|
|
|
|
end:
|
|
; copy third element into first element by memcpy
|
|
call void @llvm.memmove.p0.p0.i64(ptr align 8 nonnull %pairs, ptr align 8 %pair2, i64 16, i1 false)
|
|
; copy third element into second element by LD/ST
|
|
%vec2 = load <2 x i64>, ptr %pair2, align 8
|
|
store <2 x i64> %vec2, ptr %pair1, align 8
|
|
ret void
|
|
|
|
dummy:
|
|
; to make use of %pair2 in another BB
|
|
call void @llvm.memcpy.p0.p0.i64(ptr %pair2, ptr %pair2, i64 0, i1 false)
|
|
br label %end
|
|
}
|
|
|
|
; Function Attrs: argmemonly nounwind
|
|
declare void @llvm.memcpy.p0.p0.i64(ptr nocapture writeonly, ptr nocapture readonly, i64, i1) #1
|
|
declare void @llvm.memmove.p0.p0.i64(ptr nocapture writeonly, ptr nocapture readonly, i64, i1) #1
|
|
|
|
attributes #1 = { argmemonly nounwind }
|