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
40 lines
1.6 KiB
LLVM
40 lines
1.6 KiB
LLVM
; RUN: llc -mtriple=amdgcn < %s | FileCheck --check-prefixes=GCN,GCN-FMF,GCN-SAFE %s
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
|
|
|
|
; Test that the -enable-no-signed-zeros-fp-math flag works
|
|
|
|
; GCN-LABEL: {{^}}fneg_fsub_f32_fmf:
|
|
; GCN: v_sub_f32_e32 [[SUB:v[0-9]+]], {{v[0-9]+}}, {{v[0-9]+}}
|
|
; GCN-FMF-NOT: xor
|
|
define amdgpu_kernel void @fneg_fsub_f32_fmf(ptr addrspace(1) %out, ptr addrspace(1) %in) #0 {
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%add = add i32 %tid, 1
|
|
%gep = getelementptr float, ptr addrspace(1) %in, i32 %tid
|
|
%b_ptr = getelementptr float, ptr addrspace(1) %in, i32 %add
|
|
%a = load float, ptr addrspace(1) %gep, align 4
|
|
%b = load float, ptr addrspace(1) %b_ptr, align 4
|
|
%result = fsub fast float %a, %b
|
|
%neg.result = fsub fast float -0.0, %result
|
|
store float %neg.result, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}fneg_fsub_f32_safe:
|
|
; GCN: v_sub_f32_e32 [[SUB:v[0-9]+]], {{v[0-9]+}}, {{v[0-9]+}}
|
|
; GCN-SAFE: v_xor_b32_e32 v{{[0-9]+}}, 0x80000000, [[SUB]]
|
|
define amdgpu_kernel void @fneg_fsub_f32_safe(ptr addrspace(1) %out, ptr addrspace(1) %in) #0 {
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%add = add i32 %tid, 1
|
|
%gep = getelementptr float, ptr addrspace(1) %in, i32 %tid
|
|
%b_ptr = getelementptr float, ptr addrspace(1) %in, i32 %add
|
|
%a = load float, ptr addrspace(1) %gep, align 4
|
|
%b = load float, ptr addrspace(1) %b_ptr, align 4
|
|
%result = fsub float %a, %b
|
|
%neg.result = fsub float -0.0, %result
|
|
store float %neg.result, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|