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
2.0 KiB
LLVM
58 lines
2.0 KiB
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
; GCN-LABEL: {{^}}inline_asm_input_v2i16:
|
|
; GCN: s_mov_b32 s{{[0-9]+}}, s{{[0-9]+}}
|
|
define amdgpu_kernel void @inline_asm_input_v2i16(ptr addrspace(1) %out, <2 x i16> %in) #0 {
|
|
entry:
|
|
%val = call i32 asm "s_mov_b32 $0, $1", "=r,r"(<2 x i16> %in) #0
|
|
store i32 %val, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}inline_asm_input_v2f16:
|
|
; GCN: s_mov_b32 s2, s{{[0-9]+}}
|
|
define amdgpu_kernel void @inline_asm_input_v2f16(ptr addrspace(1) %out, <2 x half> %in) #0 {
|
|
entry:
|
|
%val = call i32 asm "s_mov_b32 $0, $1", "=r,r"(<2 x half> %in) #0
|
|
store i32 %val, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}inline_asm_output_v2i16:
|
|
; GCN: s_mov_b32 s{{[0-9]+}}, s{{[0-9]+}}
|
|
define amdgpu_kernel void @inline_asm_output_v2i16(ptr addrspace(1) %out, i32 %in) #0 {
|
|
entry:
|
|
%val = call <2 x i16> asm "s_mov_b32 $0, $1", "=r,r"(i32 %in) #0
|
|
store <2 x i16> %val, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}inline_asm_output_v2f16:
|
|
; GCN: v_mov_b32 v{{[0-9]+}}, s{{[0-9]+}}
|
|
define amdgpu_kernel void @inline_asm_output_v2f16(ptr addrspace(1) %out, i32 %in) #0 {
|
|
entry:
|
|
%val = call <2 x half> asm "v_mov_b32 $0, $1", "=v,r"(i32 %in) #0
|
|
store <2 x half> %val, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}inline_asm_packed_v2i16:
|
|
; GCN: v_pk_add_u16 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}
|
|
define amdgpu_kernel void @inline_asm_packed_v2i16(ptr addrspace(1) %out, <2 x i16> %in0, <2 x i16> %in1) #0 {
|
|
entry:
|
|
%val = call <2 x i16> asm "v_pk_add_u16 $0, $1, $2", "=v,r,v"(<2 x i16> %in0, <2 x i16> %in1) #0
|
|
store <2 x i16> %val, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}inline_asm_packed_v2f16:
|
|
; GCN: v_pk_add_f16 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}
|
|
define amdgpu_kernel void @inline_asm_packed_v2f16(ptr addrspace(1) %out, <2 x half> %in0, <2 x half> %in1) #0 {
|
|
entry:
|
|
%val = call <2 x half> asm "v_pk_add_f16 $0, $1, $2", "=v,r,v"(<2 x half> %in0, <2 x half> %in1) #0
|
|
store <2 x half> %val, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|