Files
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

191 lines
4.5 KiB
LLVM

; RUN: llc -mtriple=amdgcn < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -mattr=-enable-ds128 < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-enable-ds128 < %s | FileCheck -check-prefixes=GCN,SICIVI,FUNC %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -mattr=-enable-ds128 < %s | FileCheck -check-prefixes=GCN,GFX9,FUNC %s
; RUN: llc -mtriple=r600 -mcpu=redwood < %s | FileCheck -check-prefixes=EG,FUNC %s
; Testing for ds_read/write_b128
; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=+enable-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -mattr=+enable-ds128 < %s | FileCheck -check-prefixes=CIVI,FUNC %s
; FUNC-LABEL: {{^}}local_load_i64:
; SICIVI: s_mov_b32 m0
; GFX9-NOT: m0
; GCN: ds_read_b64 [[VAL:v\[[0-9]+:[0-9]+\]]], v{{[0-9]+}}{{$}}
; GCN: ds_write_b64 v{{[0-9]+}}, [[VAL]]
; EG: LDS_READ_RET
; EG: LDS_READ_RET
define amdgpu_kernel void @local_load_i64(ptr addrspace(3) %out, ptr addrspace(3) %in) #0 {
%ld = load i64, ptr addrspace(3) %in
store i64 %ld, ptr addrspace(3) %out
ret void
}
; FUNC-LABEL: {{^}}local_load_v2i64:
; SICIVI: s_mov_b32 m0
; GFX9-NOT: m0
; GCN: ds_read2_b64
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
define amdgpu_kernel void @local_load_v2i64(ptr addrspace(3) %out, ptr addrspace(3) %in) #0 {
entry:
%ld = load <2 x i64>, ptr addrspace(3) %in
store <2 x i64> %ld, ptr addrspace(3) %out
ret void
}
; Tests if ds_read/write_b128 gets generated for the 16 byte aligned load.
; FUNC-LABEL: {{^}}local_load_v2i64_to_128:
; CIVI: ds_read_b128
; CIVI: ds_write_b128
define amdgpu_kernel void @local_load_v2i64_to_128(ptr addrspace(3) %out, ptr addrspace(3) %in) {
entry:
%ld = load <2 x i64>, ptr addrspace(3) %in, align 16
store <2 x i64> %ld, ptr addrspace(3) %out, align 16
ret void
}
; FUNC-LABEL: {{^}}local_load_v3i64:
; SICIVI: s_mov_b32 m0
; GFX9-NOT: m0
; GCN-DAG: ds_read2_b64
; GCN-DAG: ds_read_b64
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
define amdgpu_kernel void @local_load_v3i64(ptr addrspace(3) %out, ptr addrspace(3) %in) #0 {
entry:
%ld = load <3 x i64>, ptr addrspace(3) %in
store <3 x i64> %ld, ptr addrspace(3) %out
ret void
}
; FUNC-LABEL: {{^}}local_load_v4i64:
; SICIVI: s_mov_b32 m0
; GFX9-NOT: m0
; GCN: ds_read2_b64
; GCN: ds_read2_b64
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
define amdgpu_kernel void @local_load_v4i64(ptr addrspace(3) %out, ptr addrspace(3) %in) #0 {
entry:
%ld = load <4 x i64>, ptr addrspace(3) %in
store <4 x i64> %ld, ptr addrspace(3) %out
ret void
}
; FUNC-LABEL: {{^}}local_load_v8i64:
; SICIVI: s_mov_b32 m0
; GFX9-NOT: m0
; GCN: ds_read2_b64
; GCN: ds_read2_b64
; GCN: ds_read2_b64
; GCN: ds_read2_b64
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
define amdgpu_kernel void @local_load_v8i64(ptr addrspace(3) %out, ptr addrspace(3) %in) #0 {
entry:
%ld = load <8 x i64>, ptr addrspace(3) %in
store <8 x i64> %ld, ptr addrspace(3) %out
ret void
}
; FUNC-LABEL: {{^}}local_load_v16i64:
; SICIVI: s_mov_b32 m0
; GFX9-NOT: m0
; GCN: ds_read2_b64
; GCN: ds_read2_b64
; GCN: ds_read2_b64
; GCN: ds_read2_b64
; GCN: ds_read2_b64
; GCN: ds_read2_b64
; GCN: ds_read2_b64
; GCN: ds_read2_b64
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
; EG: LDS_READ_RET
define amdgpu_kernel void @local_load_v16i64(ptr addrspace(3) %out, ptr addrspace(3) %in) #0 {
entry:
%ld = load <16 x i64>, ptr addrspace(3) %in
store <16 x i64> %ld, ptr addrspace(3) %out
ret void
}
attributes #0 = { nounwind }