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
126 lines
5.2 KiB
LLVM
126 lines
5.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse3 | FileCheck %s --check-prefix=SSE3
|
|
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=SSE41
|
|
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX-32
|
|
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX-32
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX-64
|
|
|
|
define <3 x i16> @zext_i8(<3 x i8>) {
|
|
; SSE3-LABEL: zext_i8:
|
|
; SSE3: # %bb.0:
|
|
; SSE3-NEXT: movzbl {{[0-9]+}}(%esp), %edx
|
|
; SSE3-NEXT: movzbl {{[0-9]+}}(%esp), %eax
|
|
; SSE3-NEXT: movzbl {{[0-9]+}}(%esp), %ecx
|
|
; SSE3-NEXT: # kill: def $ax killed $ax killed $eax
|
|
; SSE3-NEXT: # kill: def $dx killed $dx killed $edx
|
|
; SSE3-NEXT: # kill: def $cx killed $cx killed $ecx
|
|
; SSE3-NEXT: retl
|
|
;
|
|
; SSE41-LABEL: zext_i8:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: movzbl {{[0-9]+}}(%esp), %edx
|
|
; SSE41-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSE41-NEXT: pinsrb $1, %edx, %xmm0
|
|
; SSE41-NEXT: movzbl {{[0-9]+}}(%esp), %ecx
|
|
; SSE41-NEXT: pmovzxbw {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
|
|
; SSE41-NEXT: movd %xmm0, %eax
|
|
; SSE41-NEXT: # kill: def $ax killed $ax killed $eax
|
|
; SSE41-NEXT: # kill: def $dx killed $dx killed $edx
|
|
; SSE41-NEXT: # kill: def $cx killed $cx killed $ecx
|
|
; SSE41-NEXT: retl
|
|
;
|
|
; AVX-32-LABEL: zext_i8:
|
|
; AVX-32: # %bb.0:
|
|
; AVX-32-NEXT: movzbl {{[0-9]+}}(%esp), %edx
|
|
; AVX-32-NEXT: vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; AVX-32-NEXT: vpinsrb $1, %edx, %xmm0, %xmm0
|
|
; AVX-32-NEXT: movzbl {{[0-9]+}}(%esp), %ecx
|
|
; AVX-32-NEXT: vpmovzxbw {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
|
|
; AVX-32-NEXT: vmovd %xmm0, %eax
|
|
; AVX-32-NEXT: # kill: def $ax killed $ax killed $eax
|
|
; AVX-32-NEXT: # kill: def $dx killed $dx killed $edx
|
|
; AVX-32-NEXT: # kill: def $cx killed $cx killed $ecx
|
|
; AVX-32-NEXT: retl
|
|
;
|
|
; AVX-64-LABEL: zext_i8:
|
|
; AVX-64: # %bb.0:
|
|
; AVX-64-NEXT: vmovd %edi, %xmm0
|
|
; AVX-64-NEXT: vpinsrb $1, %esi, %xmm0, %xmm0
|
|
; AVX-64-NEXT: movzbl %dl, %ecx
|
|
; AVX-64-NEXT: movzbl %sil, %edx
|
|
; AVX-64-NEXT: vpmovzxbw {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
|
|
; AVX-64-NEXT: vmovd %xmm0, %eax
|
|
; AVX-64-NEXT: # kill: def $ax killed $ax killed $eax
|
|
; AVX-64-NEXT: # kill: def $dx killed $dx killed $edx
|
|
; AVX-64-NEXT: # kill: def $cx killed $cx killed $ecx
|
|
; AVX-64-NEXT: retq
|
|
%2 = zext <3 x i8> %0 to <3 x i16>
|
|
ret <3 x i16> %2
|
|
}
|
|
|
|
define <3 x i16> @sext_i8(<3 x i8>) {
|
|
; SSE3-LABEL: sext_i8:
|
|
; SSE3: # %bb.0:
|
|
; SSE3-NEXT: movzbl {{[0-9]+}}(%esp), %eax
|
|
; SSE3-NEXT: movl {{[0-9]+}}(%esp), %ecx
|
|
; SSE3-NEXT: shll $24, %ecx
|
|
; SSE3-NEXT: shll $8, %eax
|
|
; SSE3-NEXT: orl %ecx, %eax
|
|
; SSE3-NEXT: movd %eax, %xmm0
|
|
; SSE3-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; SSE3-NEXT: shll $8, %eax
|
|
; SSE3-NEXT: pinsrw $2, %eax, %xmm0
|
|
; SSE3-NEXT: psraw $8, %xmm0
|
|
; SSE3-NEXT: movd %xmm0, %eax
|
|
; SSE3-NEXT: pextrw $1, %xmm0, %edx
|
|
; SSE3-NEXT: pextrw $2, %xmm0, %ecx
|
|
; SSE3-NEXT: # kill: def $ax killed $ax killed $eax
|
|
; SSE3-NEXT: # kill: def $dx killed $dx killed $edx
|
|
; SSE3-NEXT: # kill: def $cx killed $cx killed $ecx
|
|
; SSE3-NEXT: retl
|
|
;
|
|
; SSE41-LABEL: sext_i8:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSE41-NEXT: pinsrb $1, {{[0-9]+}}(%esp), %xmm0
|
|
; SSE41-NEXT: pinsrb $2, {{[0-9]+}}(%esp), %xmm0
|
|
; SSE41-NEXT: pmovsxbw %xmm0, %xmm0
|
|
; SSE41-NEXT: movd %xmm0, %eax
|
|
; SSE41-NEXT: pextrw $1, %xmm0, %edx
|
|
; SSE41-NEXT: pextrw $2, %xmm0, %ecx
|
|
; SSE41-NEXT: # kill: def $ax killed $ax killed $eax
|
|
; SSE41-NEXT: # kill: def $dx killed $dx killed $edx
|
|
; SSE41-NEXT: # kill: def $cx killed $cx killed $ecx
|
|
; SSE41-NEXT: retl
|
|
;
|
|
; AVX-32-LABEL: sext_i8:
|
|
; AVX-32: # %bb.0:
|
|
; AVX-32-NEXT: vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; AVX-32-NEXT: vpinsrb $1, {{[0-9]+}}(%esp), %xmm0, %xmm0
|
|
; AVX-32-NEXT: vpinsrb $2, {{[0-9]+}}(%esp), %xmm0, %xmm0
|
|
; AVX-32-NEXT: vpmovsxbw %xmm0, %xmm0
|
|
; AVX-32-NEXT: vmovd %xmm0, %eax
|
|
; AVX-32-NEXT: vpextrw $1, %xmm0, %edx
|
|
; AVX-32-NEXT: vpextrw $2, %xmm0, %ecx
|
|
; AVX-32-NEXT: # kill: def $ax killed $ax killed $eax
|
|
; AVX-32-NEXT: # kill: def $dx killed $dx killed $edx
|
|
; AVX-32-NEXT: # kill: def $cx killed $cx killed $ecx
|
|
; AVX-32-NEXT: retl
|
|
;
|
|
; AVX-64-LABEL: sext_i8:
|
|
; AVX-64: # %bb.0:
|
|
; AVX-64-NEXT: vmovd %edi, %xmm0
|
|
; AVX-64-NEXT: vpinsrb $1, %esi, %xmm0, %xmm0
|
|
; AVX-64-NEXT: vpinsrb $2, %edx, %xmm0, %xmm0
|
|
; AVX-64-NEXT: vpmovsxbw %xmm0, %xmm0
|
|
; AVX-64-NEXT: vmovd %xmm0, %eax
|
|
; AVX-64-NEXT: vpextrw $1, %xmm0, %edx
|
|
; AVX-64-NEXT: vpextrw $2, %xmm0, %ecx
|
|
; AVX-64-NEXT: # kill: def $ax killed $ax killed $eax
|
|
; AVX-64-NEXT: # kill: def $dx killed $dx killed $edx
|
|
; AVX-64-NEXT: # kill: def $cx killed $cx killed $ecx
|
|
; AVX-64-NEXT: retq
|
|
%2 = sext <3 x i8> %0 to <3 x i16>
|
|
ret <3 x i16> %2
|
|
}
|