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
84 lines
4.0 KiB
LLVM
84 lines
4.0 KiB
LLVM
; RUN: opt < %s -S | FileCheck %s
|
|
; RUN: verify-uselistorder < %s
|
|
; CHECK-NOT: {@llvm\\.palign}
|
|
|
|
define <4 x i32> @align1(<4 x i32> %a, <4 x i32> %b) nounwind readnone ssp {
|
|
entry:
|
|
%0 = bitcast <4 x i32> %b to <2 x i64> ; <<2 x i64>> [#uses=1]
|
|
%1 = bitcast <4 x i32> %a to <2 x i64> ; <<2 x i64>> [#uses=1]
|
|
%2 = tail call <2 x i64> @llvm.x86.ssse3.palign.r.128(<2 x i64> %1, <2 x i64> %0, i8 15) ; <<2 x i64>> [#uses=1]
|
|
%3 = bitcast <2 x i64> %2 to <4 x i32> ; <<4 x i32>> [#uses=1]
|
|
ret <4 x i32> %3
|
|
}
|
|
|
|
define double @align8(<2 x i32> %a, <2 x i32> %b) nounwind readnone ssp {
|
|
entry:
|
|
%0 = bitcast <2 x i32> %b to <1 x i64> ; <<1 x i64>> [#uses=1]
|
|
%1 = bitcast <2 x i32> %a to <1 x i64> ; <<1 x i64>> [#uses=1]
|
|
%2 = tail call <1 x i64> @llvm.x86.ssse3.palign.r(<1 x i64> %1, <1 x i64> %0, i8 7) ; <<1 x i64>> [#uses=1]
|
|
%3 = extractelement <1 x i64> %2, i32 0 ; <i64> [#uses=1]
|
|
%retval12 = bitcast i64 %3 to double ; <double> [#uses=1]
|
|
ret double %retval12
|
|
}
|
|
|
|
declare <1 x i64> @llvm.x86.ssse3.palign.r(<1 x i64>, <1 x i64>, i8) nounwind readnone
|
|
|
|
define double @align7(<2 x i32> %a, <2 x i32> %b) nounwind readnone ssp {
|
|
entry:
|
|
%0 = bitcast <2 x i32> %b to <1 x i64> ; <<1 x i64>> [#uses=1]
|
|
%1 = bitcast <2 x i32> %a to <1 x i64> ; <<1 x i64>> [#uses=1]
|
|
%2 = tail call <1 x i64> @llvm.x86.ssse3.palign.r(<1 x i64> %1, <1 x i64> %0, i8 16) ; <<1 x i64>> [#uses=1]
|
|
%3 = extractelement <1 x i64> %2, i32 0 ; <i64> [#uses=1]
|
|
%retval12 = bitcast i64 %3 to double ; <double> [#uses=1]
|
|
ret double %retval12
|
|
}
|
|
|
|
define double @align6(<2 x i32> %a, <2 x i32> %b) nounwind readnone ssp {
|
|
entry:
|
|
%0 = bitcast <2 x i32> %b to <1 x i64> ; <<1 x i64>> [#uses=1]
|
|
%1 = bitcast <2 x i32> %a to <1 x i64> ; <<1 x i64>> [#uses=1]
|
|
%2 = tail call <1 x i64> @llvm.x86.ssse3.palign.r(<1 x i64> %1, <1 x i64> %0, i8 9) ; <<1 x i64>> [#uses=1]
|
|
%3 = extractelement <1 x i64> %2, i32 0 ; <i64> [#uses=1]
|
|
%retval12 = bitcast i64 %3 to double ; <double> [#uses=1]
|
|
ret double %retval12
|
|
}
|
|
|
|
define double @align5(<2 x i32> %a, <2 x i32> %b) nounwind readnone ssp {
|
|
entry:
|
|
%0 = bitcast <2 x i32> %b to <1 x i64> ; <<1 x i64>> [#uses=1]
|
|
%1 = bitcast <2 x i32> %a to <1 x i64> ; <<1 x i64>> [#uses=1]
|
|
%2 = tail call <1 x i64> @llvm.x86.ssse3.palign.r(<1 x i64> %1, <1 x i64> %0, i8 8) ; <<1 x i64>> [#uses=1]
|
|
%3 = extractelement <1 x i64> %2, i32 0 ; <i64> [#uses=1]
|
|
%retval12 = bitcast i64 %3 to double ; <double> [#uses=1]
|
|
ret double %retval12
|
|
}
|
|
|
|
define <4 x i32> @align4(<4 x i32> %a, <4 x i32> %b) nounwind readnone ssp {
|
|
entry:
|
|
%0 = bitcast <4 x i32> %b to <2 x i64> ; <<2 x i64>> [#uses=1]
|
|
%1 = bitcast <4 x i32> %a to <2 x i64> ; <<2 x i64>> [#uses=1]
|
|
%2 = tail call <2 x i64> @llvm.x86.ssse3.palign.r.128(<2 x i64> %1, <2 x i64> %0, i8 32) ; <<2 x i64>> [#uses=1]
|
|
%3 = bitcast <2 x i64> %2 to <4 x i32> ; <<4 x i32>> [#uses=1]
|
|
ret <4 x i32> %3
|
|
}
|
|
|
|
declare <2 x i64> @llvm.x86.ssse3.palign.r.128(<2 x i64>, <2 x i64>, i8) nounwind readnone
|
|
|
|
define <4 x i32> @align3(<4 x i32> %a, <4 x i32> %b) nounwind readnone ssp {
|
|
entry:
|
|
%0 = bitcast <4 x i32> %b to <2 x i64> ; <<2 x i64>> [#uses=1]
|
|
%1 = bitcast <4 x i32> %a to <2 x i64> ; <<2 x i64>> [#uses=1]
|
|
%2 = tail call <2 x i64> @llvm.x86.ssse3.palign.r.128(<2 x i64> %1, <2 x i64> %0, i8 17) ; <<2 x i64>> [#uses=1]
|
|
%3 = bitcast <2 x i64> %2 to <4 x i32> ; <<4 x i32>> [#uses=1]
|
|
ret <4 x i32> %3
|
|
}
|
|
|
|
define <4 x i32> @align2(<4 x i32> %a, <4 x i32> %b) nounwind readnone ssp {
|
|
entry:
|
|
%0 = bitcast <4 x i32> %b to <2 x i64> ; <<2 x i64>> [#uses=1]
|
|
%1 = bitcast <4 x i32> %a to <2 x i64> ; <<2 x i64>> [#uses=1]
|
|
%2 = tail call <2 x i64> @llvm.x86.ssse3.palign.r.128(<2 x i64> %1, <2 x i64> %0, i8 16) ; <<2 x i64>> [#uses=1]
|
|
%3 = bitcast <2 x i64> %2 to <4 x i32> ; <<4 x i32>> [#uses=1]
|
|
ret <4 x i32> %3
|
|
}
|