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
50 lines
1.5 KiB
LLVM
50 lines
1.5 KiB
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=verde < %s | FileCheck -check-prefix=GCN -check-prefix=VCCZ-BUG %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=bonaire < %s | FileCheck -check-prefix=GCN -check-prefix=VCCZ-BUG %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
; GCN-LABEL: {{^}}vccz_workaround:
|
|
; GCN: s_load_dword [[REG:s[0-9]+]], s[{{[0-9]+:[0-9]+}}],
|
|
; GCN: v_cmp_neq_f32_e64 {{[^,]*}}, [[REG]], 0{{$}}
|
|
; VCCZ-BUG: s_waitcnt lgkmcnt(0)
|
|
; VCCZ-BUG: s_mov_b64 vcc, vcc
|
|
; GCN-NOT: s_mov_b64 vcc, vcc
|
|
; GCN: s_cbranch_vccnz [[EXIT:.L[0-9A-Za-z_]+]]
|
|
; GCN: buffer_store_dword
|
|
; GCN: [[EXIT]]:
|
|
; GCN: s_endpgm
|
|
define amdgpu_kernel void @vccz_workaround(ptr addrspace(4) %in, ptr addrspace(1) %out, float %cond) {
|
|
entry:
|
|
%cnd = fcmp oeq float 0.0, %cond
|
|
%sgpr = load volatile i32, ptr addrspace(4) %in
|
|
br i1 %cnd, label %if, label %endif
|
|
|
|
if:
|
|
store i32 %sgpr, ptr addrspace(1) %out
|
|
br label %endif
|
|
|
|
endif:
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}vccz_noworkaround:
|
|
; GCN: v_cmp_neq_f32_e32 vcc, 0, v{{[0-9]+}}
|
|
; GCN-NOT: s_waitcnt lgkmcnt(0)
|
|
; GCN-NOT: s_mov_b64 vcc, vcc
|
|
; GCN: s_cbranch_vccnz [[EXIT:.L[0-9A-Za-z_]+]]
|
|
; GCN: buffer_store_dword
|
|
; GCN: [[EXIT]]:
|
|
; GCN: s_endpgm
|
|
define amdgpu_kernel void @vccz_noworkaround(ptr addrspace(1) %in, ptr addrspace(1) %out) {
|
|
entry:
|
|
%vgpr = load volatile float, ptr addrspace(1) %in
|
|
%cnd = fcmp oeq float 0.0, %vgpr
|
|
br i1 %cnd, label %if, label %endif
|
|
|
|
if:
|
|
store float %vgpr, ptr addrspace(1) %out
|
|
br label %endif
|
|
|
|
endif:
|
|
ret void
|
|
}
|