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
41 lines
2.2 KiB
LLVM
41 lines
2.2 KiB
LLVM
; RUN: llc -mcpu=cortex-a8 < %s | FileCheck %s
|
|
|
|
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64"
|
|
target triple = "armv7-eabi"
|
|
|
|
%foo = type { <4 x float> }
|
|
|
|
define arm_aapcs_vfpcc void @bar(ptr noalias sret(%foo) %agg.result, <4 x float> %quat.0) nounwind {
|
|
entry:
|
|
%quat_addr = alloca %foo, align 16 ; <ptr> [#uses=2]
|
|
%0 = getelementptr inbounds %foo, ptr %quat_addr, i32 0, i32 0 ; <ptr> [#uses=1]
|
|
store <4 x float> %quat.0, ptr %0
|
|
%1 = call arm_aapcs_vfpcc <4 x float> @quux(ptr %quat_addr) nounwind ; <<4 x float>> [#uses=3]
|
|
%2 = fmul <4 x float> %1, %1 ; <<4 x float>> [#uses=2]
|
|
%3 = shufflevector <4 x float> %2, <4 x float> undef, <2 x i32> <i32 0, i32 1> ; <<2 x float>> [#uses=1]
|
|
%4 = shufflevector <4 x float> %2, <4 x float> undef, <2 x i32> <i32 2, i32 3> ; <<2 x float>> [#uses=1]
|
|
;CHECK-NOT: vmov
|
|
;CHECK: vpadd
|
|
%5 = call <2 x float> @llvm.arm.neon.vpadd.v2f32(<2 x float> %3, <2 x float> %4) nounwind ; <<2 x float>> [#uses=2]
|
|
%6 = call <2 x float> @llvm.arm.neon.vpadd.v2f32(<2 x float> %5, <2 x float> %5) nounwind ; <<2 x float>> [#uses=2]
|
|
%7 = shufflevector <2 x float> %6, <2 x float> %6, <4 x i32> <i32 0, i32 1, i32 2, i32 3> ; <<4 x float>> [#uses=2]
|
|
;CHECK: vorr
|
|
%8 = call <4 x float> @llvm.arm.neon.vrsqrte.v4f32(<4 x float> %7) nounwind ; <<4 x float>> [#uses=3]
|
|
%9 = fmul <4 x float> %8, %8 ; <<4 x float>> [#uses=1]
|
|
%10 = call <4 x float> @llvm.arm.neon.vrsqrts.v4f32(<4 x float> %9, <4 x float> %7) nounwind ; <<4 x float>> [#uses=1]
|
|
%11 = fmul <4 x float> %10, %8 ; <<4 x float>> [#uses=1]
|
|
%12 = fmul <4 x float> %11, %1 ; <<4 x float>> [#uses=1]
|
|
%13 = call arm_aapcs_vfpcc ptr @baz(ptr %agg.result, <4 x float> %12) nounwind ; <ptr> [#uses=0]
|
|
ret void
|
|
}
|
|
|
|
declare arm_aapcs_vfpcc ptr @baz(ptr, <4 x float>) nounwind
|
|
|
|
declare arm_aapcs_vfpcc <4 x float> @quux(ptr nocapture) nounwind readonly
|
|
|
|
declare <2 x float> @llvm.arm.neon.vpadd.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
|
|
|
declare <4 x float> @llvm.arm.neon.vrsqrte.v4f32(<4 x float>) nounwind readnone
|
|
|
|
declare <4 x float> @llvm.arm.neon.vrsqrts.v4f32(<4 x float>, <4 x float>) nounwind readnone
|