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
84 lines
3.9 KiB
LLVM
84 lines
3.9 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
|
|
|
|
; Fold fadda(ptrue, x, select(mask, y, -0.0)) -> fadda(mask, x, y)
|
|
|
|
define float @pred_fadda_nxv2f32(float %x, <vscale x 2 x float> %y, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: pred_fadda_nxv2f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: // kill: def $s0 killed $s0 def $z0
|
|
; CHECK-NEXT: fadda s0, p0, s0, z1.s
|
|
; CHECK-NEXT: // kill: def $s0 killed $s0 killed $z0
|
|
; CHECK-NEXT: ret
|
|
%sel = select <vscale x 2 x i1> %mask, <vscale x 2 x float> %y, <vscale x 2 x float> splat(float -0.000000e+00)
|
|
%fadda = call float @llvm.vector.reduce.fadd.nxv2f32(float %x, <vscale x 2 x float> %sel)
|
|
ret float %fadda
|
|
}
|
|
|
|
define float @pred_fadda_nxv4f32(float %x, <vscale x 4 x float> %y, <vscale x 4 x i1> %mask) {
|
|
; CHECK-LABEL: pred_fadda_nxv4f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: // kill: def $s0 killed $s0 def $z0
|
|
; CHECK-NEXT: fadda s0, p0, s0, z1.s
|
|
; CHECK-NEXT: // kill: def $s0 killed $s0 killed $z0
|
|
; CHECK-NEXT: ret
|
|
%sel = select <vscale x 4 x i1> %mask, <vscale x 4 x float> %y, <vscale x 4 x float> splat(float -0.000000e+00)
|
|
%fadda = call float @llvm.vector.reduce.fadd.nxv4f32(float %x, <vscale x 4 x float> %sel)
|
|
ret float %fadda
|
|
}
|
|
|
|
define double @pred_fadda_nxv2f64(double %x, <vscale x 2 x double> %y, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: pred_fadda_nxv2f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0
|
|
; CHECK-NEXT: fadda d0, p0, d0, z1.d
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $z0
|
|
; CHECK-NEXT: ret
|
|
%sel = select <vscale x 2 x i1> %mask, <vscale x 2 x double> %y, <vscale x 2 x double> splat(double -0.000000e+00)
|
|
%fadda = call double @llvm.vector.reduce.fadd.nxv2f64(double %x, <vscale x 2 x double> %sel)
|
|
ret double %fadda
|
|
}
|
|
|
|
define half @pred_fadda_nxv2f16(half %x, <vscale x 2 x half> %y, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: pred_fadda_nxv2f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: // kill: def $h0 killed $h0 def $z0
|
|
; CHECK-NEXT: fadda h0, p0, h0, z1.h
|
|
; CHECK-NEXT: // kill: def $h0 killed $h0 killed $z0
|
|
; CHECK-NEXT: ret
|
|
%sel = select <vscale x 2 x i1> %mask, <vscale x 2 x half> %y, <vscale x 2 x half> splat(half -0.000000e+00)
|
|
%fadda = call half @llvm.vector.reduce.fadd.nxv2f16(half %x, <vscale x 2 x half> %sel)
|
|
ret half %fadda
|
|
}
|
|
|
|
define half @pred_fadda_nxv4f16(half %x, <vscale x 4 x half> %y, <vscale x 4 x i1> %mask) {
|
|
; CHECK-LABEL: pred_fadda_nxv4f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: // kill: def $h0 killed $h0 def $z0
|
|
; CHECK-NEXT: fadda h0, p0, h0, z1.h
|
|
; CHECK-NEXT: // kill: def $h0 killed $h0 killed $z0
|
|
; CHECK-NEXT: ret
|
|
%sel = select <vscale x 4 x i1> %mask, <vscale x 4 x half> %y, <vscale x 4 x half> splat(half -0.000000e+00)
|
|
%fadda = call half @llvm.vector.reduce.fadd.nxv4f16(half %x, <vscale x 4 x half> %sel)
|
|
ret half %fadda
|
|
}
|
|
|
|
define half @pred_fadda_nxv8f16(half %x, <vscale x 8 x half> %y, <vscale x 8 x i1> %mask) {
|
|
; CHECK-LABEL: pred_fadda_nxv8f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: // kill: def $h0 killed $h0 def $z0
|
|
; CHECK-NEXT: fadda h0, p0, h0, z1.h
|
|
; CHECK-NEXT: // kill: def $h0 killed $h0 killed $z0
|
|
; CHECK-NEXT: ret
|
|
%sel = select <vscale x 8 x i1> %mask, <vscale x 8 x half> %y, <vscale x 8 x half> splat(half -0.000000e+00)
|
|
%fadda = call half @llvm.vector.reduce.fadd.nxv8f16(half %x, <vscale x 8 x half> %sel)
|
|
ret half %fadda
|
|
}
|
|
|
|
declare float @llvm.vector.reduce.fadd.nxv2f32(float, <vscale x 2 x float>)
|
|
declare float @llvm.vector.reduce.fadd.nxv4f32(float, <vscale x 4 x float>)
|
|
declare double @llvm.vector.reduce.fadd.nxv2f64(double, <vscale x 2 x double>)
|
|
declare half @llvm.vector.reduce.fadd.nxv2f16(half, <vscale x 2 x half>)
|
|
declare half @llvm.vector.reduce.fadd.nxv4f16(half, <vscale x 4 x half>)
|
|
declare half @llvm.vector.reduce.fadd.nxv8f16(half, <vscale x 8 x half>)
|