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
172 lines
5.9 KiB
LLVM
172 lines
5.9 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
|
|
|
|
; FDIV
|
|
|
|
define <vscale x 8 x half> @fdiv_8f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) {
|
|
; CHECK-LABEL: fdiv_8f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.h
|
|
; CHECK-NEXT: fdiv z0.h, p0/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
%fdiv = fdiv fast <vscale x 8 x half> %a, %b
|
|
ret <vscale x 8 x half> %fdiv
|
|
}
|
|
|
|
define <vscale x 8 x half> @fdiv_recip_8f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
|
|
; CHECK-LABEL: fdiv_recip_8f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: frecpe z2.h, z1.h
|
|
; CHECK-NEXT: frecps z1.h, z1.h, z2.h
|
|
; CHECK-NEXT: fmul z1.h, z2.h, z1.h
|
|
; CHECK-NEXT: fmul z0.h, z1.h, z0.h
|
|
; CHECK-NEXT: ret
|
|
%fdiv = fdiv fast <vscale x 8 x half> %a, %b
|
|
ret <vscale x 8 x half> %fdiv
|
|
}
|
|
|
|
define <vscale x 4 x float> @fdiv_4f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b) {
|
|
; CHECK-LABEL: fdiv_4f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.s
|
|
; CHECK-NEXT: fdiv z0.s, p0/m, z0.s, z1.s
|
|
; CHECK-NEXT: ret
|
|
%fdiv = fdiv fast <vscale x 4 x float> %a, %b
|
|
ret <vscale x 4 x float> %fdiv
|
|
}
|
|
|
|
define <vscale x 4 x float> @fdiv_recip_4f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
|
|
; CHECK-LABEL: fdiv_recip_4f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: frecpe z2.s, z1.s
|
|
; CHECK-NEXT: frecps z3.s, z1.s, z2.s
|
|
; CHECK-NEXT: fmul z2.s, z2.s, z3.s
|
|
; CHECK-NEXT: frecps z1.s, z1.s, z2.s
|
|
; CHECK-NEXT: fmul z1.s, z2.s, z1.s
|
|
; CHECK-NEXT: fmul z0.s, z1.s, z0.s
|
|
; CHECK-NEXT: ret
|
|
%fdiv = fdiv fast <vscale x 4 x float> %a, %b
|
|
ret <vscale x 4 x float> %fdiv
|
|
}
|
|
|
|
define <vscale x 2 x double> @fdiv_2f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b) {
|
|
; CHECK-LABEL: fdiv_2f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: fdiv z0.d, p0/m, z0.d, z1.d
|
|
; CHECK-NEXT: ret
|
|
%fdiv = fdiv fast <vscale x 2 x double> %a, %b
|
|
ret <vscale x 2 x double> %fdiv
|
|
}
|
|
|
|
define <vscale x 2 x double> @fdiv_recip_2f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
|
|
; CHECK-LABEL: fdiv_recip_2f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: frecpe z2.d, z1.d
|
|
; CHECK-NEXT: frecps z3.d, z1.d, z2.d
|
|
; CHECK-NEXT: fmul z2.d, z2.d, z3.d
|
|
; CHECK-NEXT: frecps z3.d, z1.d, z2.d
|
|
; CHECK-NEXT: fmul z2.d, z2.d, z3.d
|
|
; CHECK-NEXT: frecps z1.d, z1.d, z2.d
|
|
; CHECK-NEXT: fmul z1.d, z2.d, z1.d
|
|
; CHECK-NEXT: fmul z0.d, z1.d, z0.d
|
|
; CHECK-NEXT: ret
|
|
%fdiv = fdiv fast <vscale x 2 x double> %a, %b
|
|
ret <vscale x 2 x double> %fdiv
|
|
}
|
|
|
|
; FSQRT
|
|
|
|
define <vscale x 8 x half> @fsqrt_8f16(<vscale x 8 x half> %a) {
|
|
; CHECK-LABEL: fsqrt_8f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.h
|
|
; CHECK-NEXT: fsqrt z0.h, p0/m, z0.h
|
|
; CHECK-NEXT: ret
|
|
%fsqrt = call fast <vscale x 8 x half> @llvm.sqrt.nxv8f16(<vscale x 8 x half> %a)
|
|
ret <vscale x 8 x half> %fsqrt
|
|
}
|
|
|
|
define <vscale x 8 x half> @fsqrt_recip_8f16(<vscale x 8 x half> %a) #0 {
|
|
; CHECK-LABEL: fsqrt_recip_8f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: frsqrte z1.h, z0.h
|
|
; CHECK-NEXT: ptrue p0.h
|
|
; CHECK-NEXT: fcmne p0.h, p0/z, z0.h, #0.0
|
|
; CHECK-NEXT: fmul z2.h, z1.h, z1.h
|
|
; CHECK-NEXT: frsqrts z2.h, z0.h, z2.h
|
|
; CHECK-NEXT: fmul z1.h, z1.h, z2.h
|
|
; CHECK-NEXT: fmul z0.h, p0/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
%fsqrt = call fast <vscale x 8 x half> @llvm.sqrt.nxv8f16(<vscale x 8 x half> %a)
|
|
ret <vscale x 8 x half> %fsqrt
|
|
}
|
|
|
|
define <vscale x 4 x float> @fsqrt_4f32(<vscale x 4 x float> %a) {
|
|
; CHECK-LABEL: fsqrt_4f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.s
|
|
; CHECK-NEXT: fsqrt z0.s, p0/m, z0.s
|
|
; CHECK-NEXT: ret
|
|
%fsqrt = call fast <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> %a)
|
|
ret <vscale x 4 x float> %fsqrt
|
|
}
|
|
|
|
define <vscale x 4 x float> @fsqrt_recip_4f32(<vscale x 4 x float> %a) #0 {
|
|
; CHECK-LABEL: fsqrt_recip_4f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: frsqrte z1.s, z0.s
|
|
; CHECK-NEXT: ptrue p0.s
|
|
; CHECK-NEXT: fcmne p0.s, p0/z, z0.s, #0.0
|
|
; CHECK-NEXT: fmul z2.s, z1.s, z1.s
|
|
; CHECK-NEXT: frsqrts z2.s, z0.s, z2.s
|
|
; CHECK-NEXT: fmul z1.s, z1.s, z2.s
|
|
; CHECK-NEXT: fmul z2.s, z1.s, z1.s
|
|
; CHECK-NEXT: frsqrts z2.s, z0.s, z2.s
|
|
; CHECK-NEXT: fmul z1.s, z1.s, z2.s
|
|
; CHECK-NEXT: fmul z0.s, p0/m, z0.s, z1.s
|
|
; CHECK-NEXT: ret
|
|
%fsqrt = call fast <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> %a)
|
|
ret <vscale x 4 x float> %fsqrt
|
|
}
|
|
|
|
define <vscale x 2 x double> @fsqrt_2f64(<vscale x 2 x double> %a) {
|
|
; CHECK-LABEL: fsqrt_2f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: fsqrt z0.d, p0/m, z0.d
|
|
; CHECK-NEXT: ret
|
|
%fsqrt = call fast <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> %a)
|
|
ret <vscale x 2 x double> %fsqrt
|
|
}
|
|
|
|
define <vscale x 2 x double> @fsqrt_recip_2f64(<vscale x 2 x double> %a) #0 {
|
|
; CHECK-LABEL: fsqrt_recip_2f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: frsqrte z1.d, z0.d
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: fcmne p0.d, p0/z, z0.d, #0.0
|
|
; CHECK-NEXT: fmul z2.d, z1.d, z1.d
|
|
; CHECK-NEXT: frsqrts z2.d, z0.d, z2.d
|
|
; CHECK-NEXT: fmul z1.d, z1.d, z2.d
|
|
; CHECK-NEXT: fmul z2.d, z1.d, z1.d
|
|
; CHECK-NEXT: frsqrts z2.d, z0.d, z2.d
|
|
; CHECK-NEXT: fmul z1.d, z1.d, z2.d
|
|
; CHECK-NEXT: fmul z2.d, z1.d, z1.d
|
|
; CHECK-NEXT: frsqrts z2.d, z0.d, z2.d
|
|
; CHECK-NEXT: fmul z1.d, z1.d, z2.d
|
|
; CHECK-NEXT: fmul z0.d, p0/m, z0.d, z1.d
|
|
; CHECK-NEXT: ret
|
|
%fsqrt = call fast <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> %a)
|
|
ret <vscale x 2 x double> %fsqrt
|
|
}
|
|
|
|
declare <vscale x 2 x half> @llvm.sqrt.nxv2f16(<vscale x 2 x half>)
|
|
declare <vscale x 4 x half> @llvm.sqrt.nxv4f16(<vscale x 4 x half>)
|
|
declare <vscale x 8 x half> @llvm.sqrt.nxv8f16(<vscale x 8 x half>)
|
|
declare <vscale x 2 x float> @llvm.sqrt.nxv2f32(<vscale x 2 x float>)
|
|
declare <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float>)
|
|
declare <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double>)
|
|
|
|
attributes #0 = { "reciprocal-estimates"="all" }
|