derek/TheRock
1
0 Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
1a182e2dac58879f215c0fad0f5f78c76dcafe56
TheRock/compiler/amd-llvm/llvm/test/CodeGen/LoongArch/lasx/fsqrt.ll
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
Details
CodeQL / Analyze (python) (push) Canceled after 0s
Details
pre-commit / pre-commit (push) Canceled after 0s
Details
Multi-Arch CI / setup (push) Canceled after 0s
Details
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Details
Setup (Multi-Arch) / setup (push) Canceled after 0s
Details
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Details
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
Details
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Details
Multi-Arch CI / CI Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Details
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Details
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

213 lines
7.3 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc --mtriple=loongarch32 --mattr=+32s,+lasx < %s | FileCheck %s --check-prefix=LA32
; RUN: llc --mtriple=loongarch64 --mattr=+lasx < %s | FileCheck %s --check-prefix=LA64
;; fsqrt
define void @sqrt_v8f32(ptr %res, ptr %a0) nounwind {
; LA32-LABEL: sqrt_v8f32:
; LA32: # %bb.0: # %entry
; LA32-NEXT: addi.w $sp, $sp, -128
; LA32-NEXT: st.w $ra, $sp, 124 # 4-byte Folded Spill
; LA32-NEXT: st.w $fp, $sp, 120 # 4-byte Folded Spill
; LA32-NEXT: addi.w $fp, $sp, 128
; LA32-NEXT: bstrins.w $sp, $zero, 4, 0
; LA32-NEXT: vld $vr0, $a1, 16
; LA32-NEXT: vst $vr0, $sp, 48
; LA32-NEXT: ld.w $a2, $a1, 12
; LA32-NEXT: st.w $a2, $sp, 44
; LA32-NEXT: ld.w $a2, $a1, 8
; LA32-NEXT: st.w $a2, $sp, 40
; LA32-NEXT: ld.w $a2, $a1, 4
; LA32-NEXT: st.w $a2, $sp, 36
; LA32-NEXT: ld.w $a1, $a1, 0
; LA32-NEXT: st.w $a1, $sp, 32
; LA32-NEXT: xvld $xr0, $sp, 32
; LA32-NEXT: xvfsqrt.s $xr0, $xr0
; LA32-NEXT: xvst $xr0, $sp, 64
; LA32-NEXT: vld $vr0, $sp, 80
; LA32-NEXT: vst $vr0, $a0, 16
; LA32-NEXT: ld.w $a1, $sp, 76
; LA32-NEXT: st.w $a1, $a0, 12
; LA32-NEXT: ld.w $a1, $sp, 72
; LA32-NEXT: st.w $a1, $a0, 8
; LA32-NEXT: ld.w $a1, $sp, 68
; LA32-NEXT: st.w $a1, $a0, 4
; LA32-NEXT: ld.w $a1, $sp, 64
; LA32-NEXT: st.w $a1, $a0, 0
; LA32-NEXT: addi.w $sp, $fp, -128
; LA32-NEXT: ld.w $fp, $sp, 120 # 4-byte Folded Reload
; LA32-NEXT: ld.w $ra, $sp, 124 # 4-byte Folded Reload
; LA32-NEXT: addi.w $sp, $sp, 128
; LA32-NEXT: ret
;
; LA64-LABEL: sqrt_v8f32:
; LA64: # %bb.0: # %entry
; LA64-NEXT: xvld $xr0, $a1, 0
; LA64-NEXT: xvfsqrt.s $xr0, $xr0
; LA64-NEXT: xvst $xr0, $a0, 0
; LA64-NEXT: ret
entry:
%v0 = load <8 x float>, ptr %a0, align 16
%sqrt = call <8 x float> @llvm.sqrt.v8f32 (<8 x float> %v0)
store <8 x float> %sqrt, ptr %res, align 16
ret void
}
define void @sqrt_v4f64(ptr %res, ptr %a0) nounwind {
; LA32-LABEL: sqrt_v4f64:
; LA32: # %bb.0: # %entry
; LA32-NEXT: addi.w $sp, $sp, -128
; LA32-NEXT: st.w $ra, $sp, 124 # 4-byte Folded Spill
; LA32-NEXT: st.w $fp, $sp, 120 # 4-byte Folded Spill
; LA32-NEXT: addi.w $fp, $sp, 128
; LA32-NEXT: bstrins.w $sp, $zero, 4, 0
; LA32-NEXT: vld $vr0, $a1, 16
; LA32-NEXT: vst $vr0, $sp, 48
; LA32-NEXT: ld.w $a2, $a1, 12
; LA32-NEXT: st.w $a2, $sp, 44
; LA32-NEXT: ld.w $a2, $a1, 8
; LA32-NEXT: st.w $a2, $sp, 40
; LA32-NEXT: ld.w $a2, $a1, 4
; LA32-NEXT: st.w $a2, $sp, 36
; LA32-NEXT: ld.w $a1, $a1, 0
; LA32-NEXT: st.w $a1, $sp, 32
; LA32-NEXT: xvld $xr0, $sp, 32
; LA32-NEXT: xvfsqrt.d $xr0, $xr0
; LA32-NEXT: xvst $xr0, $sp, 64
; LA32-NEXT: vld $vr0, $sp, 80
; LA32-NEXT: vst $vr0, $a0, 16
; LA32-NEXT: ld.w $a1, $sp, 76
; LA32-NEXT: st.w $a1, $a0, 12
; LA32-NEXT: ld.w $a1, $sp, 72
; LA32-NEXT: st.w $a1, $a0, 8
; LA32-NEXT: ld.w $a1, $sp, 68
; LA32-NEXT: st.w $a1, $a0, 4
; LA32-NEXT: ld.w $a1, $sp, 64
; LA32-NEXT: st.w $a1, $a0, 0
; LA32-NEXT: addi.w $sp, $fp, -128
; LA32-NEXT: ld.w $fp, $sp, 120 # 4-byte Folded Reload
; LA32-NEXT: ld.w $ra, $sp, 124 # 4-byte Folded Reload
; LA32-NEXT: addi.w $sp, $sp, 128
; LA32-NEXT: ret
;
; LA64-LABEL: sqrt_v4f64:
; LA64: # %bb.0: # %entry
; LA64-NEXT: xvld $xr0, $a1, 0
; LA64-NEXT: xvfsqrt.d $xr0, $xr0
; LA64-NEXT: xvst $xr0, $a0, 0
; LA64-NEXT: ret
entry:
%v0 = load <4 x double>, ptr %a0, align 16
%sqrt = call <4 x double> @llvm.sqrt.v4f64 (<4 x double> %v0)
store <4 x double> %sqrt, ptr %res, align 16
ret void
}
;; 1.0 / (fsqrt vec)
define void @one_div_sqrt_v8f32(ptr %res, ptr %a0) nounwind {
; LA32-LABEL: one_div_sqrt_v8f32:
; LA32: # %bb.0: # %entry
; LA32-NEXT: addi.w $sp, $sp, -128
; LA32-NEXT: st.w $ra, $sp, 124 # 4-byte Folded Spill
; LA32-NEXT: st.w $fp, $sp, 120 # 4-byte Folded Spill
; LA32-NEXT: addi.w $fp, $sp, 128
; LA32-NEXT: bstrins.w $sp, $zero, 4, 0
; LA32-NEXT: vld $vr0, $a1, 16
; LA32-NEXT: vst $vr0, $sp, 48
; LA32-NEXT: ld.w $a2, $a1, 12
; LA32-NEXT: st.w $a2, $sp, 44
; LA32-NEXT: ld.w $a2, $a1, 8
; LA32-NEXT: st.w $a2, $sp, 40
; LA32-NEXT: ld.w $a2, $a1, 4
; LA32-NEXT: st.w $a2, $sp, 36
; LA32-NEXT: ld.w $a1, $a1, 0
; LA32-NEXT: st.w $a1, $sp, 32
; LA32-NEXT: xvld $xr0, $sp, 32
; LA32-NEXT: xvfrsqrt.s $xr0, $xr0
; LA32-NEXT: xvst $xr0, $sp, 64
; LA32-NEXT: vld $vr0, $sp, 80
; LA32-NEXT: vst $vr0, $a0, 16
; LA32-NEXT: ld.w $a1, $sp, 76
; LA32-NEXT: st.w $a1, $a0, 12
; LA32-NEXT: ld.w $a1, $sp, 72
; LA32-NEXT: st.w $a1, $a0, 8
; LA32-NEXT: ld.w $a1, $sp, 68
; LA32-NEXT: st.w $a1, $a0, 4
; LA32-NEXT: ld.w $a1, $sp, 64
; LA32-NEXT: st.w $a1, $a0, 0
; LA32-NEXT: addi.w $sp, $fp, -128
; LA32-NEXT: ld.w $fp, $sp, 120 # 4-byte Folded Reload
; LA32-NEXT: ld.w $ra, $sp, 124 # 4-byte Folded Reload
; LA32-NEXT: addi.w $sp, $sp, 128
; LA32-NEXT: ret
;
; LA64-LABEL: one_div_sqrt_v8f32:
; LA64: # %bb.0: # %entry
; LA64-NEXT: xvld $xr0, $a1, 0
; LA64-NEXT: xvfrsqrt.s $xr0, $xr0
; LA64-NEXT: xvst $xr0, $a0, 0
; LA64-NEXT: ret
entry:
%v0 = load <8 x float>, ptr %a0, align 16
%sqrt = call <8 x float> @llvm.sqrt.v8f32 (<8 x float> %v0)
%div = fdiv <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %sqrt
store <8 x float> %div, ptr %res, align 16
ret void
}
define void @one_div_sqrt_v4f64(ptr %res, ptr %a0) nounwind {
; LA32-LABEL: one_div_sqrt_v4f64:
; LA32: # %bb.0: # %entry
; LA32-NEXT: addi.w $sp, $sp, -128
; LA32-NEXT: st.w $ra, $sp, 124 # 4-byte Folded Spill
; LA32-NEXT: st.w $fp, $sp, 120 # 4-byte Folded Spill
; LA32-NEXT: addi.w $fp, $sp, 128
; LA32-NEXT: bstrins.w $sp, $zero, 4, 0
; LA32-NEXT: vld $vr0, $a1, 16
; LA32-NEXT: vst $vr0, $sp, 48
; LA32-NEXT: ld.w $a2, $a1, 12
; LA32-NEXT: st.w $a2, $sp, 44
; LA32-NEXT: ld.w $a2, $a1, 8
; LA32-NEXT: st.w $a2, $sp, 40
; LA32-NEXT: ld.w $a2, $a1, 4
; LA32-NEXT: st.w $a2, $sp, 36
; LA32-NEXT: ld.w $a1, $a1, 0
; LA32-NEXT: st.w $a1, $sp, 32
; LA32-NEXT: xvld $xr0, $sp, 32
; LA32-NEXT: xvfsqrt.d $xr0, $xr0
; LA32-NEXT: xvldi $xr1, -912
; LA32-NEXT: xvfdiv.d $xr0, $xr1, $xr0
; LA32-NEXT: xvst $xr0, $sp, 64
; LA32-NEXT: vld $vr0, $sp, 80
; LA32-NEXT: vst $vr0, $a0, 16
; LA32-NEXT: ld.w $a1, $sp, 76
; LA32-NEXT: st.w $a1, $a0, 12
; LA32-NEXT: ld.w $a1, $sp, 72
; LA32-NEXT: st.w $a1, $a0, 8
; LA32-NEXT: ld.w $a1, $sp, 68
; LA32-NEXT: st.w $a1, $a0, 4
; LA32-NEXT: ld.w $a1, $sp, 64
; LA32-NEXT: st.w $a1, $a0, 0
; LA32-NEXT: addi.w $sp, $fp, -128
; LA32-NEXT: ld.w $fp, $sp, 120 # 4-byte Folded Reload
; LA32-NEXT: ld.w $ra, $sp, 124 # 4-byte Folded Reload
; LA32-NEXT: addi.w $sp, $sp, 128
; LA32-NEXT: ret
;
; LA64-LABEL: one_div_sqrt_v4f64:
; LA64: # %bb.0: # %entry
; LA64-NEXT: xvld $xr0, $a1, 0
; LA64-NEXT: xvfrsqrt.d $xr0, $xr0
; LA64-NEXT: xvst $xr0, $a0, 0
; LA64-NEXT: ret
entry:
%v0 = load <4 x double>, ptr %a0, align 16
%sqrt = call <4 x double> @llvm.sqrt.v4f64 (<4 x double> %v0)
%div = fdiv <4 x double> <double 1.0, double 1.0, double 1.0, double 1.0>, %sqrt
store <4 x double> %div, ptr %res, align 16
ret void
}
declare <8 x float> @llvm.sqrt.v8f32(<8 x float>)
declare <4 x double> @llvm.sqrt.v4f64(<4 x double>)
Reference in new issue View Git Blame Copy Permalink