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
1.8 KiB
LLVM
37 lines
1.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -mattr=avx512vl,avx512bw,avx512dq | FileCheck %s
|
|
|
|
define void @EntryModule(ptr %buffer_table) {
|
|
; CHECK-LABEL: EntryModule:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: movq (%rdi), %rax
|
|
; CHECK-NEXT: movq 24(%rdi), %rcx
|
|
; CHECK-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; CHECK-NEXT: vcmpneqps (%rax), %xmm0, %xmm0
|
|
; CHECK-NEXT: vpsrld $31, %xmm0, %xmm1
|
|
; CHECK-NEXT: vpshufd {{.*#+}} xmm2 = xmm1[1,1,1,1]
|
|
; CHECK-NEXT: vpshufd {{.*#+}} xmm3 = xmm1[2,3,2,3]
|
|
; CHECK-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,3,3,3]
|
|
; CHECK-NEXT: vpaddd %xmm1, %xmm3, %xmm1
|
|
; CHECK-NEXT: vpsubd %xmm0, %xmm2, %xmm0
|
|
; CHECK-NEXT: vpaddd %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vmovd %xmm0, (%rcx)
|
|
; CHECK-NEXT: retq
|
|
entry:
|
|
%i1 = load ptr, ptr %buffer_table, align 8
|
|
%i6 = load <8 x float>, ptr %i1, align 16
|
|
%i7 = fcmp une <8 x float> %i6, zeroinitializer
|
|
%i8 = zext <8 x i1> %i7 to <8 x i32>
|
|
%i18 = getelementptr inbounds ptr, ptr %buffer_table, i64 3
|
|
%i19 = load ptr, ptr %i18, align 8
|
|
%shift = shufflevector <8 x i32> %i8, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%i20 = add nuw nsw <8 x i32> %shift, %i8
|
|
%shift13 = shufflevector <8 x i32> %i8, <8 x i32> undef, <8 x i32> <i32 2, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%i21 = add nuw nsw <8 x i32> %i20, %shift13
|
|
%shift14 = shufflevector <8 x i32> %i8, <8 x i32> undef, <8 x i32> <i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%i22 = add nuw nsw <8 x i32> %i21, %shift14
|
|
%i23 = extractelement <8 x i32> %i22, i32 0
|
|
store i32 %i23, ptr %i19, align 8
|
|
ret void
|
|
}
|