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
47 lines
2.2 KiB
LLVM
47 lines
2.2 KiB
LLVM
; RUN: opt -passes=always-inline -S < %s | FileCheck %s
|
|
|
|
|
|
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-grtev4-linux-gnu"
|
|
|
|
; After AlwaysInline the callee's attributes should be merged into caller's attibutes.
|
|
|
|
; CHECK: define dso_local <2 x i64> @foo(ptr byval(<8 x i64>) align 64 %0)
|
|
; CHECK: attributes #0 = { mustprogress uwtable "disable-tail-calls"="false" "frame-pointer"="none" "less-precise-fpmad"="false" "min-legal-vector-width"="512"
|
|
|
|
; Function Attrs: uwtable mustprogress
|
|
define dso_local <2 x i64> @foo(ptr byval(<8 x i64>) align 64 %0) #0 {
|
|
entry:
|
|
%kBias.addr = alloca <8 x i64>, align 64
|
|
%indirect-arg-temp = alloca <8 x i64>, align 64
|
|
%kBias = load <8 x i64>, ptr %0, align 64, !tbaa !2
|
|
store <8 x i64> %kBias, ptr %kBias.addr, align 64, !tbaa !2
|
|
%1 = load <8 x i64>, ptr %kBias.addr, align 64, !tbaa !2
|
|
store <8 x i64> %1, ptr %indirect-arg-temp, align 64, !tbaa !2
|
|
%call = call <2 x i64> @bar(ptr byval(<8 x i64>) align 64 %indirect-arg-temp)
|
|
ret <2 x i64> %call
|
|
}
|
|
|
|
; Function Attrs: alwaysinline nounwind uwtable mustprogress
|
|
define internal <2 x i64> @bar(ptr byval(<8 x i64>) align 64 %0) #1 {
|
|
entry:
|
|
%__A.addr = alloca <8 x i64>, align 64
|
|
%__A = load <8 x i64>, ptr %0, align 64, !tbaa !2
|
|
store <8 x i64> %__A, ptr %__A.addr, align 64, !tbaa !2
|
|
%1 = load <8 x i64>, ptr %__A.addr, align 64, !tbaa !2
|
|
%2 = bitcast <8 x i64> %1 to <16 x i32>
|
|
%3 = call <16 x i8> @llvm.x86.avx512.mask.pmovs.db.512(<16 x i32> %2, <16 x i8> zeroinitializer, i16 -1)
|
|
%4 = bitcast <16 x i8> %3 to <2 x i64>
|
|
ret <2 x i64> %4
|
|
}
|
|
|
|
; Function Attrs: nounwind readnone
|
|
declare <16 x i8> @llvm.x86.avx512.mask.pmovs.db.512(<16 x i32>, <16 x i8>, i16)
|
|
|
|
attributes #0 = { uwtable mustprogress "disable-tail-calls"="false" "frame-pointer"="none" "less-precise-fpmad"="false" "min-legal-vector-width"="128" "prefer-vector-width"="128" }
|
|
attributes #1 = { alwaysinline nounwind uwtable mustprogress "disable-tail-calls"="false" "frame-pointer"="none" "less-precise-fpmad"="false" "min-legal-vector-width"="512" "prefer-vector-width"="128" }
|
|
|
|
!2 = !{!3, !3, i64 0}
|
|
!3 = !{!"omnipotent char", !4, i64 0}
|
|
!4 = !{!"Simple C++ TBAA"}
|