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
50 lines
2.0 KiB
LLVM
50 lines
2.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefixes=SSE
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX
|
|
|
|
declare <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32>, <4 x i32>)
|
|
|
|
define <8 x i16> @combine_packss_v4i32_signsplat(<4 x i32> %a0, <4 x i32> %a1) {
|
|
; SSE-LABEL: combine_packss_v4i32_signsplat:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: pcmpgtd %xmm1, %xmm0
|
|
; SSE-NEXT: pcmpeqd %xmm1, %xmm1
|
|
; SSE-NEXT: packssdw %xmm1, %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: combine_packss_v4i32_signsplat:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vpcmpgtd %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
|
|
; AVX-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
%cmp = icmp sgt <4 x i32> %a0, %a1
|
|
%ext = sext <4 x i1> %cmp to <4 x i32>
|
|
%pack = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %ext, <4 x i32> splat (i32 -1))
|
|
%signsplat = ashr <8 x i16> %pack, splat (i16 15)
|
|
ret <8 x i16> %signsplat
|
|
}
|
|
|
|
define <8 x i16> @combine_packss_v4i32_freeze_signsplat(<4 x i32> %a0, <4 x i32> %a1) {
|
|
; SSE-LABEL: combine_packss_v4i32_freeze_signsplat:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: pcmpgtd %xmm1, %xmm0
|
|
; SSE-NEXT: pcmpeqd %xmm1, %xmm1
|
|
; SSE-NEXT: packssdw %xmm1, %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: combine_packss_v4i32_freeze_signsplat:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vpcmpgtd %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
|
|
; AVX-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
%cmp = icmp sgt <4 x i32> %a0, %a1
|
|
%ext = sext <4 x i1> %cmp to <4 x i32>
|
|
%pack = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %ext, <4 x i32> splat (i32 -1))
|
|
%freeze = freeze <8 x i16> %pack
|
|
%signsplat = ashr <8 x i16> %freeze, splat (i16 15)
|
|
ret <8 x i16> %signsplat
|
|
}
|