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
58 lines
2.3 KiB
LLVM
58 lines
2.3 KiB
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=bonaire < %s | FileCheck -check-prefix=GCN -check-prefix=CI -check-prefix=ALL %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=carrizo -mattr=-flat-for-global < %s | FileCheck -check-prefix=GCN -check-prefix=VI -check-prefix=ALL %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -mattr=-flat-for-global < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 -check-prefix=ALL %s
|
|
|
|
; ALL-LABEL: {{^}}large_alloca_pixel_shader:
|
|
; GCN-DAG: s_mov_b32 s4, SCRATCH_RSRC_DWORD0
|
|
; GCN-DAG: s_mov_b32 s5, SCRATCH_RSRC_DWORD1
|
|
; GCN-DAG: s_mov_b32 s6, -1
|
|
|
|
; CI-DAG: s_mov_b32 s7, 0xe8f000
|
|
; VI-DAG: s_mov_b32 s7, 0xe80000
|
|
; GFX9-DAG: s_mov_b32 s7, 0xe00000
|
|
|
|
; GCN: s_add_u32 s4, s4, s0
|
|
; GCN: s_addc_u32 s5, s5, 0
|
|
|
|
; GCN: buffer_store_dword {{v[0-9]+}}, {{v[0-9]+}}, s[4:7], 0 offen
|
|
; GCN: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, s[4:7], 0 offen
|
|
|
|
; ALL: ; ScratchSize: 32772
|
|
define amdgpu_ps void @large_alloca_pixel_shader(i32 %x, i32 %y) #0 {
|
|
%large = alloca [8192 x i32], align 4, addrspace(5)
|
|
%gep = getelementptr [8192 x i32], ptr addrspace(5) %large, i32 0, i32 8191
|
|
store volatile i32 %x, ptr addrspace(5) %gep
|
|
%gep1 = getelementptr [8192 x i32], ptr addrspace(5) %large, i32 0, i32 %y
|
|
%val = load volatile i32, ptr addrspace(5) %gep1
|
|
store volatile i32 %val, ptr addrspace(1) poison
|
|
ret void
|
|
}
|
|
|
|
; ALL-LABEL: {{^}}large_alloca_pixel_shader_inreg:
|
|
; GCN-DAG: s_mov_b32 s4, SCRATCH_RSRC_DWORD0
|
|
; GCN-DAG: s_mov_b32 s5, SCRATCH_RSRC_DWORD1
|
|
; GCN-DAG: s_mov_b32 s6, -1
|
|
|
|
; CI-DAG: s_mov_b32 s7, 0xe8f000
|
|
; VI-DAG: s_mov_b32 s7, 0xe80000
|
|
; GFX9-DAG: s_mov_b32 s7, 0xe00000
|
|
|
|
; GCN: s_add_u32 s4, s4, s2
|
|
; GCN: s_addc_u32 s5, s5, 0
|
|
|
|
; GCN: buffer_store_dword {{v[0-9]+}}, {{v[0-9]+}}, s[4:7], 0 offen
|
|
; GCN: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, s[4:7], 0 offen
|
|
|
|
; ALL: ; ScratchSize: 32772
|
|
define amdgpu_ps void @large_alloca_pixel_shader_inreg(i32 inreg %x, i32 inreg %y) #0 {
|
|
%large = alloca [8192 x i32], align 4, addrspace(5)
|
|
%gep = getelementptr [8192 x i32], ptr addrspace(5) %large, i32 0, i32 8191
|
|
store volatile i32 %x, ptr addrspace(5) %gep
|
|
%gep1 = getelementptr [8192 x i32], ptr addrspace(5) %large, i32 0, i32 %y
|
|
%val = load volatile i32, ptr addrspace(5) %gep1
|
|
store volatile i32 %val, ptr addrspace(1) poison
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|