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
69 lines
2.3 KiB
LLVM
69 lines
2.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=X86
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=X64
|
|
|
|
define <8 x i32> @perm_cl_int_8x32(<8 x i32> %A) nounwind readnone {
|
|
; X86-LABEL: perm_cl_int_8x32:
|
|
; X86: # %bb.0: # %entry
|
|
; X86-NEXT: vmovaps {{.*#+}} ymm1 = [0,7,2,1,2,7,6,0]
|
|
; X86-NEXT: vpermps %ymm0, %ymm1, %ymm0
|
|
; X86-NEXT: retl
|
|
;
|
|
; X64-LABEL: perm_cl_int_8x32:
|
|
; X64: # %bb.0: # %entry
|
|
; X64-NEXT: vmovaps {{.*#+}} ymm1 = [0,7,2,1,2,7,6,0]
|
|
; X64-NEXT: vpermps %ymm0, %ymm1, %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%B = shufflevector <8 x i32> %A, <8 x i32> undef, <8 x i32> <i32 0, i32 7, i32 2, i32 1, i32 2, i32 7, i32 6, i32 0>
|
|
ret <8 x i32> %B
|
|
}
|
|
|
|
|
|
define <8 x float> @perm_cl_fp_8x32(<8 x float> %A) nounwind readnone {
|
|
; X86-LABEL: perm_cl_fp_8x32:
|
|
; X86: # %bb.0: # %entry
|
|
; X86-NEXT: vmovaps {{.*#+}} ymm1 = [u,7,2,u,4,u,1,6]
|
|
; X86-NEXT: vpermps %ymm0, %ymm1, %ymm0
|
|
; X86-NEXT: retl
|
|
;
|
|
; X64-LABEL: perm_cl_fp_8x32:
|
|
; X64: # %bb.0: # %entry
|
|
; X64-NEXT: vmovaps {{.*#+}} ymm1 = [u,7,2,u,4,u,1,6]
|
|
; X64-NEXT: vpermps %ymm0, %ymm1, %ymm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%B = shufflevector <8 x float> %A, <8 x float> undef, <8 x i32> <i32 undef, i32 7, i32 2, i32 undef, i32 4, i32 undef, i32 1, i32 6>
|
|
ret <8 x float> %B
|
|
}
|
|
|
|
define <4 x i64> @perm_cl_int_4x64(<4 x i64> %A) nounwind readnone {
|
|
; X86-LABEL: perm_cl_int_4x64:
|
|
; X86: # %bb.0: # %entry
|
|
; X86-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,3,2,1]
|
|
; X86-NEXT: retl
|
|
;
|
|
; X64-LABEL: perm_cl_int_4x64:
|
|
; X64: # %bb.0: # %entry
|
|
; X64-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,3,2,1]
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%B = shufflevector <4 x i64> %A, <4 x i64> undef, <4 x i32> <i32 0, i32 3, i32 2, i32 1>
|
|
ret <4 x i64> %B
|
|
}
|
|
|
|
define <4 x double> @perm_cl_fp_4x64(<4 x double> %A) nounwind readnone {
|
|
; X86-LABEL: perm_cl_fp_4x64:
|
|
; X86: # %bb.0: # %entry
|
|
; X86-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,3,2,1]
|
|
; X86-NEXT: retl
|
|
;
|
|
; X64-LABEL: perm_cl_fp_4x64:
|
|
; X64: # %bb.0: # %entry
|
|
; X64-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,3,2,1]
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%B = shufflevector <4 x double> %A, <4 x double> undef, <4 x i32> <i32 0, i32 3, i32 2, i32 1>
|
|
ret <4 x double> %B
|
|
}
|