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
67 lines
2.3 KiB
LLVM
67 lines
2.3 KiB
LLVM
;RUN: llc < %s -mtriple=r600 -mcpu=redwood | FileCheck %s
|
|
|
|
; CHECK-LABEL: {{^}}main:
|
|
; CHECK: ADD *
|
|
|
|
define amdgpu_vs void @main(<4 x float> inreg %reg0, <4 x float> inreg %reg1, <4 x float> inreg %reg2) {
|
|
main_body:
|
|
%0 = extractelement <4 x float> %reg1, i32 0
|
|
%1 = extractelement <4 x float> %reg1, i32 1
|
|
%2 = extractelement <4 x float> %reg1, i32 2
|
|
%3 = extractelement <4 x float> %reg1, i32 3
|
|
%4 = extractelement <4 x float> %reg2, i32 0
|
|
%5 = fadd float %0, 2.0
|
|
%6 = fadd float %1, 3.0
|
|
%7 = fadd float %2, 4.0
|
|
%8 = fadd float %3, 5.0
|
|
%9 = bitcast float %4 to i32
|
|
%10 = mul i32 %9, 6
|
|
%11 = bitcast i32 %10 to float
|
|
%12 = insertelement <4 x float> poison, float %5, i32 0
|
|
%13 = insertelement <4 x float> %12, float %6, i32 1
|
|
%14 = insertelement <4 x float> %13, float %7, i32 2
|
|
%15 = insertelement <4 x float> %14, float %8, i32 3
|
|
%16 = insertelement <4 x float> %15, float %11, i32 3
|
|
|
|
%17 = call float @llvm.r600.dot4(<4 x float> %15,<4 x float> %16)
|
|
%18 = insertelement <4 x float> poison, float %17, i32 0
|
|
call void @llvm.r600.store.swizzle(<4 x float> %18, i32 0, i32 2)
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}main2:
|
|
; CHECK-NOT: ADD *
|
|
|
|
define amdgpu_vs void @main2(<4 x float> inreg %reg0, <4 x float> inreg %reg1, <4 x float> inreg %reg2) {
|
|
main_body:
|
|
%0 = extractelement <4 x float> %reg1, i32 0
|
|
%1 = extractelement <4 x float> %reg1, i32 1
|
|
%2 = extractelement <4 x float> %reg1, i32 2
|
|
%3 = extractelement <4 x float> %reg1, i32 3
|
|
%4 = extractelement <4 x float> %reg2, i32 0
|
|
%5 = fadd float %0, 2.0
|
|
%6 = fadd float %1, 3.0
|
|
%7 = fadd float %2, 4.0
|
|
%8 = fadd float %3, 2.0
|
|
%9 = bitcast float %4 to i32
|
|
%10 = mul i32 %9, 6
|
|
%11 = bitcast i32 %10 to float
|
|
%12 = insertelement <4 x float> poison, float %5, i32 0
|
|
%13 = insertelement <4 x float> %12, float %6, i32 1
|
|
%14 = insertelement <4 x float> %13, float %7, i32 2
|
|
%15 = insertelement <4 x float> %14, float %8, i32 3
|
|
%16 = insertelement <4 x float> %15, float %11, i32 3
|
|
|
|
%17 = call float @llvm.r600.dot4(<4 x float> %15,<4 x float> %16)
|
|
%18 = insertelement <4 x float> poison, float %17, i32 0
|
|
call void @llvm.r600.store.swizzle(<4 x float> %18, i32 0, i32 2)
|
|
ret void
|
|
}
|
|
|
|
; Function Attrs: readnone
|
|
declare float @llvm.r600.dot4(<4 x float>, <4 x float>) #1
|
|
|
|
declare void @llvm.r600.store.swizzle(<4 x float>, i32, i32)
|
|
|
|
attributes #1 = { readnone }
|