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
33 lines
1.5 KiB
LLVM
33 lines
1.5 KiB
LLVM
; RUN: llc -mtriple=amdgcn < %s | FileCheck -check-prefix=GCN %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=fiji < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
declare i64 @llvm.amdgcn.qsad.pk.u16.u8(i64, i32, i64) #0
|
|
|
|
; GCN-LABEL: {{^}}v_qsad_pk_u16_u8:
|
|
; GCN: v_qsad_pk_u16_u8 v[0:1], v[4:5], s{{[0-9]+}}, v[{{[0-9]+:[0-9]+}}]
|
|
; GCN-DAG: v_mov_b32_e32 v5, v1
|
|
; GCN-DAG: v_mov_b32_e32 v4, v0
|
|
define amdgpu_kernel void @v_qsad_pk_u16_u8(ptr addrspace(1) %out, i64 %src) {
|
|
%tmp = call i64 asm "v_lsrlrev_b64 $0, $1, 1", "={v[4:5]},v"(i64 %src) #0
|
|
%tmp1 = call i64 @llvm.amdgcn.qsad.pk.u16.u8(i64 %tmp, i32 100, i64 100) #0
|
|
%tmp2 = call i64 asm ";; force constraint", "=v,{v[4:5]}"(i64 %tmp1) #0
|
|
store i64 %tmp2, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}v_qsad_pk_u16_u8_non_immediate:
|
|
; GCN: v_qsad_pk_u16_u8 v[0:1], v[2:3], v4, v[6:7]
|
|
; GCN-DAG: v_mov_b32_e32 v3, v1
|
|
; GCN-DAG: v_mov_b32_e32 v2, v0
|
|
define amdgpu_kernel void @v_qsad_pk_u16_u8_non_immediate(ptr addrspace(1) %out, i64 %src, i32 %a, i64 %b) {
|
|
%tmp = call i64 asm "v_lsrlrev_b64 $0, $1, 1", "={v[2:3]},v"(i64 %src) #0
|
|
%tmp1 = call i32 asm "v_mov_b32 $0, $1", "={v4},v"(i32 %a) #0
|
|
%tmp2 = call i64 asm "v_lshlrev_b64 $0, $1, 1", "={v[6:7]},v"(i64 %b) #0
|
|
%tmp3 = call i64 @llvm.amdgcn.qsad.pk.u16.u8(i64 %tmp, i32 %tmp1, i64 %tmp2) #0
|
|
%tmp4 = call i64 asm ";; force constraint", "=v,{v[2:3]}"(i64 %tmp3) #0
|
|
store i64 %tmp4, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind readnone }
|