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
60 lines
3.0 KiB
LLVM
60 lines
3.0 KiB
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=bonaire < %s | FileCheck -check-prefix=GCN %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=fiji < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
declare <4 x i32> @llvm.amdgcn.mqsad.u32.u8(i64, i32, <4 x i32>) #0
|
|
|
|
; GCN-LABEL: {{^}}v_mqsad_u32_u8_inline_integer_immediate:
|
|
; GCN-DAG: v_mov_b32_e32 v0, v2
|
|
; GCN-DAG: v_mov_b32_e32 v1, v3
|
|
; GCN: v_mqsad_u32_u8 v[2:5], v[0:1], v6, v[{{[0-9]+:[0-9]+}}]
|
|
define amdgpu_kernel void @v_mqsad_u32_u8_inline_integer_immediate(ptr addrspace(1) %out, i64 %src, i32 %a) {
|
|
%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 <4 x i32> @llvm.amdgcn.mqsad.u32.u8(i64 %tmp, i32 %tmp1, <4 x i32> <i32 10, i32 20, i32 30, i32 40>) #0
|
|
%tmp3 = call <4 x i32> asm ";; force constraint", "=v,{v[2:5]}"(<4 x i32> %tmp2) #0
|
|
store <4 x i32> %tmp3, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}v_mqsad_u32_u8_non_immediate:
|
|
; GCN-DAG: v_mov_b32_e32 v0, v2
|
|
; GCN-DAG: v_mov_b32_e32 v1, v3
|
|
; GCN: v_mqsad_u32_u8 v[2:5], v[0:1], v6, v[{{[0-9]+:[0-9]+}}]
|
|
define amdgpu_kernel void @v_mqsad_u32_u8_non_immediate(ptr addrspace(1) %out, i64 %src, i32 %a, <4 x i32> %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 <4 x i32> @llvm.amdgcn.mqsad.u32.u8(i64 %tmp, i32 %tmp1, <4 x i32> %b) #0
|
|
%tmp3 = call <4 x i32> asm ";; force constraint", "=v,{v[2:5]}"(<4 x i32> %tmp2) #0
|
|
store <4 x i32> %tmp3, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}v_mqsad_u32_u8_inline_fp_immediate:
|
|
; GCN-DAG: v_mov_b32_e32 v0, v2
|
|
; GCN-DAG: v_mov_b32_e32 v1, v3
|
|
; GCN: v_mqsad_u32_u8 v[2:5], v[0:1], v6, v[{{[0-9]+:[0-9]+}}]
|
|
define amdgpu_kernel void @v_mqsad_u32_u8_inline_fp_immediate(ptr addrspace(1) %out, i64 %src, i32 %a) {
|
|
%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 <4 x i32> @llvm.amdgcn.mqsad.u32.u8(i64 %tmp, i32 %tmp1, <4 x i32> <i32 1065353216, i32 0, i32 0, i32 0>) #0
|
|
%tmp3 = call <4 x i32> asm ";; force constraint", "=v,{v[2:5]}"(<4 x i32> %tmp2) #0
|
|
store <4 x i32> %tmp3, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}v_mqsad_u32_u8_use_sgpr_vgpr:
|
|
; GCN-DAG: v_mov_b32_e32 v0, v2
|
|
; GCN-DAG: v_mov_b32_e32 v1, v3
|
|
; GCN: v_mqsad_u32_u8 v[2:5], v[0:1], v6, v[{{[0-9]+:[0-9]+}}]
|
|
define amdgpu_kernel void @v_mqsad_u32_u8_use_sgpr_vgpr(ptr addrspace(1) %out, i64 %src, i32 %a, ptr addrspace(1) %input) {
|
|
%in = load <4 x i32>, ptr addrspace(1) %input
|
|
%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 <4 x i32> @llvm.amdgcn.mqsad.u32.u8(i64 %tmp, i32 %tmp1, <4 x i32> %in) #0
|
|
%tmp3 = call <4 x i32> asm ";; force constraint", "=v,{v[2:5]}"(<4 x i32> %tmp2) #0
|
|
store <4 x i32> %tmp3, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind readnone }
|