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
33 lines
1.5 KiB
LLVM
33 lines
1.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-unknown -mcpu=core-avx2 | FileCheck %s
|
|
|
|
%v8_uniform_FVector3 = type { float, float, float }
|
|
|
|
declare <8 x float> @llvm.x86.avx.hadd.ps.256(<8 x float>, <8 x float>)
|
|
|
|
define void @foo(ptr %Out, ptr %In, <8 x i32> %__mask) {
|
|
; CHECK-LABEL: foo:
|
|
; CHECK: # %bb.0: # %allocas
|
|
; CHECK-NEXT: vmovups (%rsi), %xmm0
|
|
; CHECK-NEXT: vhaddps 32(%rsi), %xmm0, %xmm0
|
|
; CHECK-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,0,1,1]
|
|
; CHECK-NEXT: vhaddps %ymm0, %ymm0, %ymm0
|
|
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; CHECK-NEXT: vaddss %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vmovss %xmm0, (%rdi)
|
|
; CHECK-NEXT: vzeroupper
|
|
; CHECK-NEXT: retq
|
|
allocas:
|
|
%ptr_masked_load74 = load <8 x float>, ptr %In, align 4
|
|
%ptr8096 = getelementptr float, ptr %In, i64 8
|
|
%ptr80_masked_load82 = load <8 x float>, ptr %ptr8096, align 4
|
|
%ret_7.i.i = shufflevector <8 x float> %ptr_masked_load74, <8 x float> %ptr80_masked_load82, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
|
|
%v1.i.i100 = tail call <8 x float> @llvm.x86.avx.hadd.ps.256(<8 x float> %ret_7.i.i, <8 x float> %ret_7.i.i)
|
|
%v2.i.i101 = tail call <8 x float> @llvm.x86.avx.hadd.ps.256(<8 x float> %v1.i.i100, <8 x float> %v1.i.i100)
|
|
%scalar1.i.i102 = extractelement <8 x float> %v2.i.i101, i32 0
|
|
%scalar2.i.i103 = extractelement <8 x float> %v2.i.i101, i32 4
|
|
%sum.i.i104 = fadd float %scalar1.i.i102, %scalar2.i.i103
|
|
store float %sum.i.i104, ptr %Out, align 4
|
|
ret void
|
|
}
|