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
37 lines
2.4 KiB
LLVM
37 lines
2.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -mattr=+avx512f,+avx512vl | FileCheck %s
|
|
|
|
declare <16 x i32> @llvm.experimental.vector.compress.v16i32(<16 x i32>, <16 x i1>, <16 x i32>)
|
|
|
|
define <16 x i32> @test_compress_freeze_elimination(<16 x i32> %a0, <16 x i32> %a1, <16 x i8> %a3) {
|
|
; CHECK-LABEL: test_compress_freeze_elimination:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vpcmpgtd %zmm1, %zmm0, %k1
|
|
; CHECK-NEXT: vpmovzxbd {{.*#+}} zmm1 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
|
|
; CHECK-NEXT: vpbroadcastd {{.*#+}} zmm0 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
|
|
; CHECK-NEXT: vpcompressd %zmm1, %zmm0 {%k1}
|
|
; CHECK-NEXT: retq
|
|
%cmp = icmp sgt <16 x i32> %a0, %a1
|
|
%ext = zext <16 x i8> %a3 to <16 x i32>
|
|
%cpr = call <16 x i32> @llvm.experimental.vector.compress.v16i32(<16 x i32> %ext, <16 x i1> %cmp, <16 x i32> splat(i32 15))
|
|
%fr = freeze <16 x i32> %cpr
|
|
%and = and <16 x i32> %fr, splat(i32 255)
|
|
ret <16 x i32> %and
|
|
}
|
|
|
|
define <16 x i32> @test_compress_freeze(<16 x i32> %a0, <16 x i32> %a1, <16 x i8> %a3) {
|
|
; CHECK-LABEL: test_compress_freeze:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vpcmpgtd %zmm1, %zmm0, %k1
|
|
; CHECK-NEXT: vpmovzxbd {{.*#+}} zmm0 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
|
|
; CHECK-NEXT: vpcompressd %zmm0, %zmm0 {%k1}
|
|
; CHECK-NEXT: vpandd {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to16}, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%cmp = icmp sgt <16 x i32> %a0, %a1
|
|
%ext = zext <16 x i8> %a3 to <16 x i32>
|
|
%cpr = call <16 x i32> @llvm.experimental.vector.compress.v16i32(<16 x i32> %ext, <16 x i1> %cmp, <16 x i32> poison)
|
|
%fr = freeze <16 x i32> %cpr
|
|
%and = and <16 x i32> %fr, splat(i32 255)
|
|
ret <16 x i32> %and
|
|
}
|