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
79 lines
2.7 KiB
LLVM
79 lines
2.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=i686-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=X86
|
|
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=X64
|
|
|
|
define <2 x i64> @shl1(<4 x i32> %r, <4 x i32> %a) nounwind readnone ssp {
|
|
; X86-LABEL: shl1:
|
|
; X86: # %bb.0: # %entry
|
|
; X86-NEXT: pslld $23, %xmm1
|
|
; X86-NEXT: paddd {{\.?LCPI[0-9]+_[0-9]+}}, %xmm1
|
|
; X86-NEXT: cvttps2dq %xmm1, %xmm1
|
|
; X86-NEXT: pmulld %xmm1, %xmm0
|
|
; X86-NEXT: retl
|
|
;
|
|
; X64-LABEL: shl1:
|
|
; X64: # %bb.0: # %entry
|
|
; X64-NEXT: pslld $23, %xmm1
|
|
; X64-NEXT: paddd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
|
|
; X64-NEXT: cvttps2dq %xmm1, %xmm1
|
|
; X64-NEXT: pmulld %xmm1, %xmm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%shl = shl <4 x i32> %r, %a ; <<4 x i32>> [#uses=1]
|
|
%tmp2 = bitcast <4 x i32> %shl to <2 x i64> ; <<2 x i64>> [#uses=1]
|
|
ret <2 x i64> %tmp2
|
|
}
|
|
|
|
define <2 x i64> @shl2(<16 x i8> %r, <16 x i8> %a) nounwind readnone ssp {
|
|
; X86-LABEL: shl2:
|
|
; X86: # %bb.0: # %entry
|
|
; X86-NEXT: movdqa %xmm1, %xmm2
|
|
; X86-NEXT: movdqa %xmm0, %xmm1
|
|
; X86-NEXT: psllw $5, %xmm2
|
|
; X86-NEXT: movdqa %xmm0, %xmm3
|
|
; X86-NEXT: psllw $4, %xmm3
|
|
; X86-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}, %xmm3
|
|
; X86-NEXT: movdqa %xmm2, %xmm0
|
|
; X86-NEXT: pblendvb %xmm0, %xmm3, %xmm1
|
|
; X86-NEXT: movdqa %xmm1, %xmm3
|
|
; X86-NEXT: paddb %xmm1, %xmm3
|
|
; X86-NEXT: paddb %xmm3, %xmm3
|
|
; X86-NEXT: paddb %xmm2, %xmm2
|
|
; X86-NEXT: movdqa %xmm2, %xmm0
|
|
; X86-NEXT: pblendvb %xmm0, %xmm3, %xmm1
|
|
; X86-NEXT: movdqa %xmm1, %xmm3
|
|
; X86-NEXT: paddb %xmm1, %xmm3
|
|
; X86-NEXT: paddb %xmm2, %xmm2
|
|
; X86-NEXT: movdqa %xmm2, %xmm0
|
|
; X86-NEXT: pblendvb %xmm0, %xmm3, %xmm1
|
|
; X86-NEXT: movdqa %xmm1, %xmm0
|
|
; X86-NEXT: retl
|
|
;
|
|
; X64-LABEL: shl2:
|
|
; X64: # %bb.0: # %entry
|
|
; X64-NEXT: movdqa %xmm0, %xmm2
|
|
; X64-NEXT: psllw $5, %xmm1
|
|
; X64-NEXT: movdqa %xmm0, %xmm3
|
|
; X64-NEXT: psllw $4, %xmm3
|
|
; X64-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm3
|
|
; X64-NEXT: movdqa %xmm1, %xmm0
|
|
; X64-NEXT: pblendvb %xmm0, %xmm3, %xmm2
|
|
; X64-NEXT: movdqa %xmm2, %xmm3
|
|
; X64-NEXT: paddb %xmm2, %xmm3
|
|
; X64-NEXT: paddb %xmm3, %xmm3
|
|
; X64-NEXT: paddb %xmm1, %xmm1
|
|
; X64-NEXT: movdqa %xmm1, %xmm0
|
|
; X64-NEXT: pblendvb %xmm0, %xmm3, %xmm2
|
|
; X64-NEXT: movdqa %xmm2, %xmm3
|
|
; X64-NEXT: paddb %xmm2, %xmm3
|
|
; X64-NEXT: paddb %xmm1, %xmm1
|
|
; X64-NEXT: movdqa %xmm1, %xmm0
|
|
; X64-NEXT: pblendvb %xmm0, %xmm3, %xmm2
|
|
; X64-NEXT: movdqa %xmm2, %xmm0
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%shl = shl <16 x i8> %r, %a ; <<16 x i8>> [#uses=1]
|
|
%tmp2 = bitcast <16 x i8> %shl to <2 x i64> ; <<2 x i64>> [#uses=1]
|
|
ret <2 x i64> %tmp2
|
|
}
|