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
150 lines
5.1 KiB
LLVM
150 lines
5.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+sse2 < %s | FileCheck %s --check-prefix=SSE2
|
|
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+avx < %s | FileCheck %s --check-prefix=AVX
|
|
|
|
define <8 x i16> @test1(<8 x i16> %A, <8 x i16> %B) {
|
|
; SSE2-LABEL: test1:
|
|
; SSE2: # %bb.0: # %entry
|
|
; SSE2-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1]
|
|
; SSE2-NEXT: psrldq {{.*#+}} xmm1 = xmm1[14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
|
|
; SSE2-NEXT: psllw %xmm1, %xmm0
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; AVX-LABEL: test1:
|
|
; AVX: # %bb.0: # %entry
|
|
; AVX-NEXT: vpmovzxwq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
|
|
; AVX-NEXT: vpsllw %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
entry:
|
|
%vecinit14 = shufflevector <8 x i16> %B, <8 x i16> undef, <8 x i32> zeroinitializer
|
|
%shl = shl <8 x i16> %A, %vecinit14
|
|
ret <8 x i16> %shl
|
|
}
|
|
|
|
define <4 x i32> @test2(<4 x i32> %A, <4 x i32> %B) {
|
|
; SSE2-LABEL: test2:
|
|
; SSE2: # %bb.0: # %entry
|
|
; SSE2-NEXT: xorps %xmm2, %xmm2
|
|
; SSE2-NEXT: movss {{.*#+}} xmm2 = xmm1[0],xmm2[1,2,3]
|
|
; SSE2-NEXT: pslld %xmm2, %xmm0
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; AVX-LABEL: test2:
|
|
; AVX: # %bb.0: # %entry
|
|
; AVX-NEXT: vpmovzxdq {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero
|
|
; AVX-NEXT: vpslld %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
entry:
|
|
%vecinit6 = shufflevector <4 x i32> %B, <4 x i32> undef, <4 x i32> zeroinitializer
|
|
%shl = shl <4 x i32> %A, %vecinit6
|
|
ret <4 x i32> %shl
|
|
}
|
|
|
|
define <2 x i64> @test3(<2 x i64> %A, <2 x i64> %B) {
|
|
; SSE2-LABEL: test3:
|
|
; SSE2: # %bb.0: # %entry
|
|
; SSE2-NEXT: psllq %xmm1, %xmm0
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; AVX-LABEL: test3:
|
|
; AVX: # %bb.0: # %entry
|
|
; AVX-NEXT: vpsllq %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
entry:
|
|
%vecinit2 = shufflevector <2 x i64> %B, <2 x i64> undef, <2 x i32> zeroinitializer
|
|
%shl = shl <2 x i64> %A, %vecinit2
|
|
ret <2 x i64> %shl
|
|
}
|
|
|
|
define <8 x i16> @test4(<8 x i16> %A, <8 x i16> %B) {
|
|
; SSE2-LABEL: test4:
|
|
; SSE2: # %bb.0: # %entry
|
|
; SSE2-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1]
|
|
; SSE2-NEXT: psrldq {{.*#+}} xmm1 = xmm1[14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
|
|
; SSE2-NEXT: psrlw %xmm1, %xmm0
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; AVX-LABEL: test4:
|
|
; AVX: # %bb.0: # %entry
|
|
; AVX-NEXT: vpmovzxwq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
|
|
; AVX-NEXT: vpsrlw %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
entry:
|
|
%vecinit14 = shufflevector <8 x i16> %B, <8 x i16> undef, <8 x i32> zeroinitializer
|
|
%shr = lshr <8 x i16> %A, %vecinit14
|
|
ret <8 x i16> %shr
|
|
}
|
|
|
|
define <4 x i32> @test5(<4 x i32> %A, <4 x i32> %B) {
|
|
; SSE2-LABEL: test5:
|
|
; SSE2: # %bb.0: # %entry
|
|
; SSE2-NEXT: xorps %xmm2, %xmm2
|
|
; SSE2-NEXT: movss {{.*#+}} xmm2 = xmm1[0],xmm2[1,2,3]
|
|
; SSE2-NEXT: psrld %xmm2, %xmm0
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; AVX-LABEL: test5:
|
|
; AVX: # %bb.0: # %entry
|
|
; AVX-NEXT: vpmovzxdq {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero
|
|
; AVX-NEXT: vpsrld %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
entry:
|
|
%vecinit6 = shufflevector <4 x i32> %B, <4 x i32> undef, <4 x i32> zeroinitializer
|
|
%shr = lshr <4 x i32> %A, %vecinit6
|
|
ret <4 x i32> %shr
|
|
}
|
|
|
|
define <2 x i64> @test6(<2 x i64> %A, <2 x i64> %B) {
|
|
; SSE2-LABEL: test6:
|
|
; SSE2: # %bb.0: # %entry
|
|
; SSE2-NEXT: psrlq %xmm1, %xmm0
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; AVX-LABEL: test6:
|
|
; AVX: # %bb.0: # %entry
|
|
; AVX-NEXT: vpsrlq %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
entry:
|
|
%vecinit2 = shufflevector <2 x i64> %B, <2 x i64> undef, <2 x i32> zeroinitializer
|
|
%shr = lshr <2 x i64> %A, %vecinit2
|
|
ret <2 x i64> %shr
|
|
}
|
|
|
|
define <8 x i16> @test7(<8 x i16> %A, <8 x i16> %B) {
|
|
; SSE2-LABEL: test7:
|
|
; SSE2: # %bb.0: # %entry
|
|
; SSE2-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1]
|
|
; SSE2-NEXT: psrldq {{.*#+}} xmm1 = xmm1[14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
|
|
; SSE2-NEXT: psraw %xmm1, %xmm0
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; AVX-LABEL: test7:
|
|
; AVX: # %bb.0: # %entry
|
|
; AVX-NEXT: vpmovzxwq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
|
|
; AVX-NEXT: vpsraw %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
entry:
|
|
%vecinit14 = shufflevector <8 x i16> %B, <8 x i16> undef, <8 x i32> zeroinitializer
|
|
%shr = ashr <8 x i16> %A, %vecinit14
|
|
ret <8 x i16> %shr
|
|
}
|
|
|
|
define <4 x i32> @test8(<4 x i32> %A, <4 x i32> %B) {
|
|
; SSE2-LABEL: test8:
|
|
; SSE2: # %bb.0: # %entry
|
|
; SSE2-NEXT: xorps %xmm2, %xmm2
|
|
; SSE2-NEXT: movss {{.*#+}} xmm2 = xmm1[0],xmm2[1,2,3]
|
|
; SSE2-NEXT: psrad %xmm2, %xmm0
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; AVX-LABEL: test8:
|
|
; AVX: # %bb.0: # %entry
|
|
; AVX-NEXT: vpmovzxdq {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero
|
|
; AVX-NEXT: vpsrad %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
entry:
|
|
%vecinit6 = shufflevector <4 x i32> %B, <4 x i32> undef, <4 x i32> zeroinitializer
|
|
%shr = ashr <4 x i32> %A, %vecinit6
|
|
ret <4 x i32> %shr
|
|
}
|