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
54 lines
2.1 KiB
LLVM
54 lines
2.1 KiB
LLVM
; RUN: llc -mtriple=amdgcn < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
; GCN-LABEL: {{^}}store_v2i32_as_v4i16_align_4:
|
|
; GCN: s_load_dwordx2
|
|
; GCN: ds_write2_b32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} offset1:1{{$}}
|
|
define amdgpu_kernel void @store_v2i32_as_v4i16_align_4(ptr addrspace(3) align 4 %out, <2 x i32> %x) #0 {
|
|
%x.bc = bitcast <2 x i32> %x to <4 x i16>
|
|
store <4 x i16> %x.bc, ptr addrspace(3) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}store_v4i32_as_v8i16_align_4:
|
|
; GCN: s_load_dwordx4
|
|
; GCN-DAG: ds_write2_b32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} offset0:2 offset1:3
|
|
; GCN-DAG: ds_write2_b32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} offset1:1{{$}}
|
|
define amdgpu_kernel void @store_v4i32_as_v8i16_align_4(ptr addrspace(3) align 4 %out, <4 x i32> %x) #0 {
|
|
%x.bc = bitcast <4 x i32> %x to <8 x i16>
|
|
store <8 x i16> %x.bc, ptr addrspace(3) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}store_v2i32_as_i64_align_4:
|
|
; GCN: s_load_dwordx2
|
|
; GCN: ds_write2_b32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} offset1:1{{$}}
|
|
define amdgpu_kernel void @store_v2i32_as_i64_align_4(ptr addrspace(3) align 4 %out, <2 x i32> %x) #0 {
|
|
%x.bc = bitcast <2 x i32> %x to <4 x i16>
|
|
store <4 x i16> %x.bc, ptr addrspace(3) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}store_v4i32_as_v2i64_align_4:
|
|
; GCN: s_load_dwordx4
|
|
; GCN-DAG: ds_write2_b32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} offset0:2 offset1:3
|
|
; GCN-DAG: ds_write2_b32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} offset1:1{{$}}
|
|
define amdgpu_kernel void @store_v4i32_as_v2i64_align_4(ptr addrspace(3) align 4 %out, <4 x i32> %x) #0 {
|
|
%x.bc = bitcast <4 x i32> %x to <2 x i64>
|
|
store <2 x i64> %x.bc, ptr addrspace(3) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}store_v4i16_as_v2i32_align_4:
|
|
; GCN: s_load_dword s
|
|
; GCN-NEXT: s_load_dwordx2 s
|
|
; GCN-NOT: {{buffer|flat|global}}
|
|
|
|
; GCN: ds_write2_b32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} offset1:1{{$}}
|
|
define amdgpu_kernel void @store_v4i16_as_v2i32_align_4(ptr addrspace(3) align 4 %out, <4 x i16> %x) #0 {
|
|
%x.bc = bitcast <4 x i16> %x to <2 x i32>
|
|
store <2 x i32> %x.bc, ptr addrspace(3) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|