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
76 lines
2.4 KiB
LLVM
76 lines
2.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc --mtriple=loongarch32 --mattr=+32s,+lsx < %s | FileCheck %s --check-prefixes=CHECK,LA32
|
|
; RUN: llc --mtriple=loongarch64 --mattr=+lsx < %s | FileCheck %s --check-prefixes=CHECK,LA64
|
|
|
|
;; fsqrt
|
|
define void @sqrt_v4f32(ptr %res, ptr %a0) nounwind {
|
|
; CHECK-LABEL: sqrt_v4f32:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: vld $vr0, $a1, 0
|
|
; CHECK-NEXT: vfsqrt.s $vr0, $vr0
|
|
; CHECK-NEXT: vst $vr0, $a0, 0
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%v0 = load <4 x float>, ptr %a0, align 16
|
|
%sqrt = call <4 x float> @llvm.sqrt.v4f32 (<4 x float> %v0)
|
|
store <4 x float> %sqrt, ptr %res, align 16
|
|
ret void
|
|
}
|
|
|
|
define void @sqrt_v2f64(ptr %res, ptr %a0) nounwind {
|
|
; CHECK-LABEL: sqrt_v2f64:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: vld $vr0, $a1, 0
|
|
; CHECK-NEXT: vfsqrt.d $vr0, $vr0
|
|
; CHECK-NEXT: vst $vr0, $a0, 0
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%v0 = load <2 x double>, ptr %a0, align 16
|
|
%sqrt = call <2 x double> @llvm.sqrt.v2f64 (<2 x double> %v0)
|
|
store <2 x double> %sqrt, ptr %res, align 16
|
|
ret void
|
|
}
|
|
|
|
;; 1.0 / (fsqrt vec)
|
|
define void @one_div_sqrt_v4f32(ptr %res, ptr %a0) nounwind {
|
|
; CHECK-LABEL: one_div_sqrt_v4f32:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: vld $vr0, $a1, 0
|
|
; CHECK-NEXT: vfrsqrt.s $vr0, $vr0
|
|
; CHECK-NEXT: vst $vr0, $a0, 0
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%v0 = load <4 x float>, ptr %a0, align 16
|
|
%sqrt = call <4 x float> @llvm.sqrt.v4f32 (<4 x float> %v0)
|
|
%div = fdiv <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %sqrt
|
|
store <4 x float> %div, ptr %res, align 16
|
|
ret void
|
|
}
|
|
|
|
define void @one_div_sqrt_v2f64(ptr %res, ptr %a0) nounwind {
|
|
; LA32-LABEL: one_div_sqrt_v2f64:
|
|
; LA32: # %bb.0: # %entry
|
|
; LA32-NEXT: vld $vr0, $a1, 0
|
|
; LA32-NEXT: vfsqrt.d $vr0, $vr0
|
|
; LA32-NEXT: vldi $vr1, -912
|
|
; LA32-NEXT: vfdiv.d $vr0, $vr1, $vr0
|
|
; LA32-NEXT: vst $vr0, $a0, 0
|
|
; LA32-NEXT: ret
|
|
;
|
|
; LA64-LABEL: one_div_sqrt_v2f64:
|
|
; LA64: # %bb.0: # %entry
|
|
; LA64-NEXT: vld $vr0, $a1, 0
|
|
; LA64-NEXT: vfrsqrt.d $vr0, $vr0
|
|
; LA64-NEXT: vst $vr0, $a0, 0
|
|
; LA64-NEXT: ret
|
|
entry:
|
|
%v0 = load <2 x double>, ptr %a0, align 16
|
|
%sqrt = call <2 x double> @llvm.sqrt.v2f64 (<2 x double> %v0)
|
|
%div = fdiv <2 x double> <double 1.0, double 1.0>, %sqrt
|
|
store <2 x double> %div, ptr %res, align 16
|
|
ret void
|
|
}
|
|
|
|
declare <4 x float> @llvm.sqrt.v4f32(<4 x float>)
|
|
declare <2 x double> @llvm.sqrt.v2f64(<2 x double>)
|