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
52 lines
2.2 KiB
LLVM
52 lines
2.2 KiB
LLVM
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+mmx,+fma,+f16c,+avx512f -stop-after finalize-isel -o - %s | FileCheck %s
|
|
; This test ensures that the MXCSR is implicitly used by MMX FP instructions.
|
|
|
|
define <1 x i64> @mxcsr_mmx(<4 x float> %a0) {
|
|
; CHECK: MMX_CVTPS2PIrr %{{[0-9]}}, implicit $mxcsr
|
|
; CHECK: MMX_CVTPI2PSrr %{{[0-9]}}, killed %{{[0-9]}}, implicit $mxcsr
|
|
; CHECK: MMX_CVTTPS2PIrr killed %{{[0-9]}}, implicit $mxcsr
|
|
; CHECK: MMX_CVTPI2PDrr killed %{{[0-9]$}}
|
|
; CHECK: MMX_CVTPD2PIrr killed %{{[0-9]}}, implicit $mxcsr
|
|
%1 = call <1 x i64> @llvm.x86.sse.cvtps2pi(<4 x float> %a0)
|
|
%2 = call <4 x float> @llvm.x86.sse.cvtpi2ps(<4 x float> %a0, <1 x i64> %1)
|
|
%3 = call <1 x i64> @llvm.x86.sse.cvttps2pi(<4 x float> %2)
|
|
%4 = call <2 x double> @llvm.x86.sse.cvtpi2pd(<1 x i64> %3)
|
|
%5 = call <1 x i64> @llvm.x86.sse.cvtpd2pi(<2 x double> %4)
|
|
ret <1 x i64> %5
|
|
}
|
|
|
|
define half @mxcsr_f16c(float %a) {
|
|
; CHECK: VCVTPS2PH{{.*}}mxcsr
|
|
%res = fptrunc float %a to half
|
|
ret half %res
|
|
}
|
|
|
|
define <4 x float> @mxcsr_fma_ss(<4 x float> %a, <4 x float> %b) {
|
|
; CHECK: VFMADD{{.*}}mxcsr
|
|
%res = call <4 x float> @llvm.x86.fma.vfmadd.ss(<4 x float> %b, <4 x float> %a, <4 x float>
|
|
%a)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @mxcsr_fma_ps(<4 x float> %a, <4 x float> %b) {
|
|
; CHECK: VFMADD{{.*}}mxcsr
|
|
%res = call <4 x float> @llvm.x86.fma.vfmadd.ps(<4 x float> %b, <4 x float> %a, <4 x float>
|
|
%a)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <8 x double> @mxcsr_fma_sae(<8 x double> %a, <8 x double> %b, <8 x double> %c) {
|
|
; CHECK: VFMADD{{.*}}mxcsr
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a, <8 x double> %b, <8 x double> %c, i8 -1, i32 10)
|
|
ret <8 x double> %res
|
|
}
|
|
|
|
declare <1 x i64> @llvm.x86.sse.cvtps2pi(<4 x float>)
|
|
declare<4 x float> @llvm.x86.sse.cvtpi2ps(<4 x float>, <1 x i64>)
|
|
declare <1 x i64> @llvm.x86.sse.cvttps2pi(<4 x float>)
|
|
declare <2 x double> @llvm.x86.sse.cvtpi2pd(<1 x i64>)
|
|
declare <1 x i64> @llvm.x86.sse.cvtpd2pi(<2 x double>)
|
|
declare <4 x float> @llvm.x86.fma.vfmadd.ss(<4 x float>, <4 x float>, <4 x float>)
|
|
declare <4 x float> @llvm.x86.fma.vfmadd.ps(<4 x float>, <4 x float>, <4 x float>)
|
|
declare <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double>, <8 x double>, <8 x double>, i8, i32)
|