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
49 lines
2.3 KiB
LLVM
49 lines
2.3 KiB
LLVM
; RUN: llc -global-isel=0 -mtriple=amdgcn < %s | FileCheck -check-prefix=SI -check-prefix=GCN %s
|
|
; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck -check-prefix=VI -check-prefix=GCN %s
|
|
; RUN: llc -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck -check-prefix=VI -check-prefix=GCN %s
|
|
|
|
declare float @llvm.amdgcn.div.fixup.f32(float, float, float) nounwind readnone
|
|
declare double @llvm.amdgcn.div.fixup.f64(double, double, double) nounwind readnone
|
|
|
|
; GCN-LABEL: {{^}}test_div_fixup_f32:
|
|
; SI-DAG: s_load_dword [[SA:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x13
|
|
; SI-DAG: s_load_dword [[SB:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x1c
|
|
; SI-DAG: s_load_dword [[SC:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x25
|
|
|
|
; VI-DAG: s_load_dword [[SA:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x4c
|
|
; VI-DAG: s_load_dword [[SB:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x70
|
|
; VI-DAG: s_load_dword [[SC:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x94
|
|
|
|
; GCN-DAG: v_mov_b32_e32 [[VC:v[0-9]+]], [[SC]]
|
|
; GCN-DAG: v_mov_b32_e32 [[VB:v[0-9]+]], [[SB]]
|
|
; GCN: v_div_fixup_f32 [[RESULT:v[0-9]+]], [[SA]], [[VB]], [[VC]]
|
|
; GCN: buffer_store_dword [[RESULT]],
|
|
; GCN: s_endpgm
|
|
define amdgpu_kernel void @test_div_fixup_f32(ptr addrspace(1) %out, [8 x i32], float %a, [8 x i32], float %b, [8 x i32], float %c) nounwind {
|
|
%result = call float @llvm.amdgcn.div.fixup.f32(float %a, float %b, float %c) nounwind readnone
|
|
store float %result, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}test_div_fixup_f64:
|
|
; GCN: v_div_fixup_f64
|
|
define amdgpu_kernel void @test_div_fixup_f64(ptr addrspace(1) %out, double %a, double %b, double %c) nounwind {
|
|
%result = call double @llvm.amdgcn.div.fixup.f64(double %a, double %b, double %c) nounwind readnone
|
|
store double %result, ptr addrspace(1) %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}test_div_fixup_f32_vgpr:
|
|
; GCN: v_div_fixup_f32
|
|
define float @test_div_fixup_f32_vgpr(float %a, float %b, float %c) {
|
|
%result = call float @llvm.amdgcn.div.fixup.f32(float %a, float %b, float %c)
|
|
ret float %result
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}test_div_fixup_f64_vgpr:
|
|
; GCN: v_div_fixup_f64
|
|
define double @test_div_fixup_f64_vgpr(double %a, double %b, double %c) {
|
|
%result = call double @llvm.amdgcn.div.fixup.f64(double %a, double %b, double %c)
|
|
ret double %result
|
|
}
|