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
3.3 KiB
LLVM
50 lines
3.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -mtriple=x86_64-- -mcpu=x86-64 -O3 -S < %s | FileCheck %s --check-prefixes=SSE2
|
|
; RUN: opt -mtriple=x86_64-- -mcpu=x86-64-v2 -O3 -S < %s | FileCheck %s --check-prefixes=SSE4
|
|
; RUN: opt -mtriple=x86_64-- -mcpu=btver2 -O3 -S < %s | FileCheck %s --check-prefixes=AVX
|
|
; RUN: opt -mtriple=x86_64-- -mcpu=x86-64-v3 -O3 -S < %s | FileCheck %s --check-prefixes=AVX
|
|
; RUN: opt -mtriple=x86_64-- -mcpu=x86-64 -passes="default<O3>" -S < %s | FileCheck %s --check-prefixes=SSE2
|
|
; RUN: opt -mtriple=x86_64-- -mcpu=x86-64-v2 -passes="default<O3>" -S < %s | FileCheck %s --check-prefixes=SSE4
|
|
; RUN: opt -mtriple=x86_64-- -mcpu=btver2 -passes="default<O3>" -S < %s | FileCheck %s --check-prefixes=AVX
|
|
; RUN: opt -mtriple=x86_64-- -mcpu=x86-64-v3 -passes="default<O3>" -S < %s | FileCheck %s --check-prefixes=AVX
|
|
|
|
define <4 x double> @PR94546(<4 x double> %a, <4 x double> %b) {
|
|
; SSE2-LABEL: @PR94546(
|
|
; SSE2-NEXT: [[TMP1:%.*]] = shufflevector <4 x double> [[A:%.*]], <4 x double> [[B:%.*]], <2 x i32> <i32 0, i32 6>
|
|
; SSE2-NEXT: [[TMP2:%.*]] = shufflevector <4 x double> [[A]], <4 x double> [[B]], <2 x i32> <i32 1, i32 7>
|
|
; SSE2-NEXT: [[TMP3:%.*]] = fadd <2 x double> [[TMP1]], [[TMP2]]
|
|
; SSE2-NEXT: [[TMP4:%.*]] = shufflevector <2 x double> [[TMP3]], <2 x double> poison, <4 x i32> <i32 0, i32 poison, i32 poison, i32 1>
|
|
; SSE2-NEXT: ret <4 x double> [[TMP4]]
|
|
;
|
|
; SSE4-LABEL: @PR94546(
|
|
; SSE4-NEXT: [[TMP1:%.*]] = shufflevector <4 x double> [[A:%.*]], <4 x double> [[B:%.*]], <4 x i32> <i32 0, i32 poison, i32 poison, i32 6>
|
|
; SSE4-NEXT: [[TMP2:%.*]] = shufflevector <4 x double> [[A]], <4 x double> [[B]], <4 x i32> <i32 1, i32 poison, i32 poison, i32 7>
|
|
; SSE4-NEXT: [[TMP3:%.*]] = fadd <4 x double> [[TMP1]], [[TMP2]]
|
|
; SSE4-NEXT: ret <4 x double> [[TMP3]]
|
|
;
|
|
; AVX-LABEL: @PR94546(
|
|
; AVX-NEXT: [[TMP1:%.*]] = shufflevector <4 x double> [[A:%.*]], <4 x double> [[B:%.*]], <4 x i32> <i32 0, i32 poison, i32 poison, i32 6>
|
|
; AVX-NEXT: [[TMP2:%.*]] = shufflevector <4 x double> [[A]], <4 x double> [[B]], <4 x i32> <i32 1, i32 poison, i32 poison, i32 7>
|
|
; AVX-NEXT: [[TMP3:%.*]] = fadd <4 x double> [[TMP1]], [[TMP2]]
|
|
; AVX-NEXT: ret <4 x double> [[TMP3]]
|
|
;
|
|
%vecext = extractelement <4 x double> %a, i32 0
|
|
%vecext1 = extractelement <4 x double> %a, i32 1
|
|
%add = fadd double %vecext, %vecext1
|
|
%vecinit = insertelement <4 x double> poison, double %add, i32 0
|
|
%vecext2 = extractelement <4 x double> %a, i32 2
|
|
%vecext3 = extractelement <4 x double> %a, i32 3
|
|
%add4 = fadd double %vecext2, %vecext3
|
|
%vecinit5 = insertelement <4 x double> %vecinit, double %add4, i32 1
|
|
%vecext6 = extractelement <4 x double> %b, i32 0
|
|
%vecext7 = extractelement <4 x double> %b, i32 1
|
|
%add8 = fadd double %vecext6, %vecext7
|
|
%vecinit9 = insertelement <4 x double> %vecinit5, double %add8, i32 2
|
|
%vecext10 = extractelement <4 x double> %b, i32 2
|
|
%vecext11 = extractelement <4 x double> %b, i32 3
|
|
%add12 = fadd double %vecext10, %vecext11
|
|
%vecinit13 = insertelement <4 x double> %vecinit9, double %add12, i32 3
|
|
%shuffle = shufflevector <4 x double> %vecinit13, <4 x double> %a, <4 x i32> <i32 0, i32 poison, i32 poison, i32 3>
|
|
ret <4 x double> %shuffle
|
|
}
|