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
102 lines
3.3 KiB
LLVM
102 lines
3.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
|
|
|
|
; FADD
|
|
|
|
define double @fadda_nxv8f64(double %init, <vscale x 8 x double> %a) {
|
|
; CHECK-LABEL: fadda_nxv8f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0
|
|
; CHECK-NEXT: fadda d0, p0, d0, z1.d
|
|
; CHECK-NEXT: fadda d0, p0, d0, z2.d
|
|
; CHECK-NEXT: fadda d0, p0, d0, z3.d
|
|
; CHECK-NEXT: fadda d0, p0, d0, z4.d
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $z0
|
|
; CHECK-NEXT: ret
|
|
%res = call double @llvm.vector.reduce.fadd.nxv8f64(double %init, <vscale x 8 x double> %a)
|
|
ret double %res
|
|
}
|
|
|
|
; FADDV
|
|
|
|
define float @faddv_nxv8f32(float %init, <vscale x 8 x float> %a) {
|
|
; CHECK-LABEL: faddv_nxv8f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fadd z1.s, z1.s, z2.s
|
|
; CHECK-NEXT: ptrue p0.s
|
|
; CHECK-NEXT: faddv s1, p0, z1.s
|
|
; CHECK-NEXT: fadd s0, s0, s1
|
|
; CHECK-NEXT: ret
|
|
%res = call fast float @llvm.vector.reduce.fadd.nxv8f32(float %init, <vscale x 8 x float> %a)
|
|
ret float %res
|
|
}
|
|
|
|
; FMAXNMV
|
|
|
|
define double @fmaxv_nxv8f64(<vscale x 8 x double> %a) {
|
|
; CHECK-LABEL: fmaxv_nxv8f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: fmaxnm z1.d, p0/m, z1.d, z3.d
|
|
; CHECK-NEXT: fmaxnm z0.d, p0/m, z0.d, z2.d
|
|
; CHECK-NEXT: fmaxnm z0.d, p0/m, z0.d, z1.d
|
|
; CHECK-NEXT: fmaxnmv d0, p0, z0.d
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $z0
|
|
; CHECK-NEXT: ret
|
|
%res = call double @llvm.vector.reduce.fmax.nxv8f64(<vscale x 8 x double> %a)
|
|
ret double %res
|
|
}
|
|
|
|
; FMINNMV
|
|
|
|
define half @fminv_nxv16f16(<vscale x 16 x half> %a) {
|
|
; CHECK-LABEL: fminv_nxv16f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.h
|
|
; CHECK-NEXT: fminnm z0.h, p0/m, z0.h, z1.h
|
|
; CHECK-NEXT: fminnmv h0, p0, z0.h
|
|
; CHECK-NEXT: // kill: def $h0 killed $h0 killed $z0
|
|
; CHECK-NEXT: ret
|
|
%res = call half @llvm.vector.reduce.fmin.nxv16f16(<vscale x 16 x half> %a)
|
|
ret half %res
|
|
}
|
|
|
|
; FMAXV
|
|
|
|
define double @fmaximumv_nxv8f64(<vscale x 8 x double> %a) {
|
|
; CHECK-LABEL: fmaximumv_nxv8f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: fmax z1.d, p0/m, z1.d, z3.d
|
|
; CHECK-NEXT: fmax z0.d, p0/m, z0.d, z2.d
|
|
; CHECK-NEXT: fmax z0.d, p0/m, z0.d, z1.d
|
|
; CHECK-NEXT: fmaxv d0, p0, z0.d
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $z0
|
|
; CHECK-NEXT: ret
|
|
%res = call double @llvm.vector.reduce.fmaximum.nxv8f64(<vscale x 8 x double> %a)
|
|
ret double %res
|
|
}
|
|
|
|
; FMINV
|
|
|
|
define half @fminimumv_nxv16f16(<vscale x 16 x half> %a) {
|
|
; CHECK-LABEL: fminimumv_nxv16f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.h
|
|
; CHECK-NEXT: fmin z0.h, p0/m, z0.h, z1.h
|
|
; CHECK-NEXT: fminv h0, p0, z0.h
|
|
; CHECK-NEXT: // kill: def $h0 killed $h0 killed $z0
|
|
; CHECK-NEXT: ret
|
|
%res = call half @llvm.vector.reduce.fminimum.nxv16f16(<vscale x 16 x half> %a)
|
|
ret half %res
|
|
}
|
|
|
|
declare double @llvm.vector.reduce.fadd.nxv8f64(double, <vscale x 8 x double>)
|
|
declare float @llvm.vector.reduce.fadd.nxv8f32(float, <vscale x 8 x float>)
|
|
|
|
declare double @llvm.vector.reduce.fmax.nxv8f64(<vscale x 8 x double>)
|
|
declare half @llvm.vector.reduce.fmin.nxv16f16(<vscale x 16 x half>)
|
|
declare double @llvm.vector.reduce.fmaximum.nxv8f64(<vscale x 8 x double>)
|
|
declare half @llvm.vector.reduce.fminimum.nxv16f16(<vscale x 16 x half>)
|