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
76 lines
4.3 KiB
C
76 lines
4.3 KiB
C
// RUN: %libomptarget-compile-generic \
|
|
// RUN: -gline-tables-only -fopenmp-extensions
|
|
// RUN: env LIBOMPTARGET_INFO=63 %libomptarget-run-amdgcn-amd-amdhsa 2>&1 | \
|
|
// RUN: %fcheck-amdgcn-amd-amdhsa -allow-empty -check-prefixes=INFO,AMDGPU
|
|
|
|
|
|
|
|
// FIXME: Fails due to optimized debugging in 'ptxas'.
|
|
// UNSUPPORTED: nvptx64-nvidia-cuda-LTO
|
|
|
|
#include <omp.h>
|
|
#include <stdio.h>
|
|
|
|
#define N 64
|
|
|
|
#pragma omp declare target
|
|
int global;
|
|
#pragma omp end declare target
|
|
|
|
extern void __tgt_set_info_flag(unsigned);
|
|
|
|
int main() {
|
|
int A[N];
|
|
int B[N];
|
|
int C[N];
|
|
int val = 1;
|
|
|
|
// clang-format off
|
|
// INFO: info: Entering OpenMP data region with being_mapper at amd_info.c:{{[0-9]+}}:{{[0-9]+}} with 3 arguments:
|
|
// INFO: info: alloc(A[0:64])[256]
|
|
// INFO: info: tofrom(B[0:64])[256]
|
|
// INFO: info: to(C[0:64])[256]
|
|
// INFO: info: Creating new map entry with HstPtrBase={{.*}}, HstPtrBegin={{.*}}, TgtPtrBegin={{.*}}, Size=256, DynRefCount=1, HoldRefCount=0, Name=A[0:64]
|
|
// INFO: info: Creating new map entry with HstPtrBase={{.*}}, HstPtrBegin={{.*}}, TgtPtrBegin={{.*}}, Size=256, DynRefCount=0, HoldRefCount=1, Name=B[0:64]
|
|
// INFO: info: Copying data from host to device, HstPtr={{.*}}, TgtPtr={{.*}}, Size=256, Name=B[0:64]
|
|
// INFO: info: Creating new map entry with HstPtrBase={{.*}}, HstPtrBegin={{.*}}, TgtPtrBegin={{.*}}, Size=256, DynRefCount=1, HoldRefCount=0, Name=C[0:64]
|
|
// INFO: info: Copying data from host to device, HstPtr={{.*}}, TgtPtr={{.*}}, Size=256, Name=C[0:64]
|
|
// INFO: info: OpenMP Host-Device pointer mappings after block at amd_info.c:{{[0-9]+}}:{{[0-9]+}}:
|
|
// INFO: info: Host Ptr Target Ptr Size (B) DynRefCount HoldRefCount Declaration
|
|
// INFO: info: {{.*}} {{.*}} 256 1 0 C[0:64] at amd_info.c:{{[0-9]+}}:{{[0-9]+}}
|
|
// INFO: info: {{.*}} {{.*}} 256 0 1 B[0:64] at amd_info.c:{{[0-9]+}}:{{[0-9]+}}
|
|
// INFO: info: {{.*}} {{.*}} 256 1 0 A[0:64] at amd_info.c:{{[0-9]+}}:{{[0-9]+}}
|
|
// INFO: info: Entering OpenMP kernel at amd_info.c:{{[0-9]+}}:{{[0-9]+}} with 1 arguments:
|
|
// INFO: info: firstprivate(val)[4]
|
|
// INFO: info: Launching kernel __omp_offloading_{{.*}}main{{.*}} with {{[0-9]+}} blocks and {{[0-9]+}} threads in Generic mode
|
|
// AMDGPU: AMDGPU device {{[0-9]}} info: #Args: {{[0-9]}} Teams x Thrds: {{[0-9]+}}x {{[0-9]+}} (MaxFlatWorkGroupSize: {{[0-9]+}}) LDS Usage: {{[0-9]+}}B #SGPRs/VGPRs: {{[0-9]+}}/{{[0-9]+}} #SGPR/VGPR Spills: {{[0-9]+}}/{{[0-9]+}} Tripcount: {{[0-9]+}}
|
|
// INFO: info: OpenMP Host-Device pointer mappings after block at amd_info.c:{{[0-9]+}}:{{[0-9]+}}:
|
|
// INFO: info: Host Ptr Target Ptr Size (B) DynRefCount HoldRefCount Declaration
|
|
// INFO: info: {{.*}} {{.*}} 256 1 0 C[0:64] at amd_info.c:{{[0-9]+}}:{{[0-9]+}}
|
|
// INFO: info: {{.*}} {{.*}} 256 0 1 B[0:64] at amd_info.c:{{[0-9]+}}:{{[0-9]+}}
|
|
// INFO: info: {{.*}} {{.*}} 256 1 0 A[0:64] at amd_info.c:{{[0-9]+}}:{{[0-9]+}}
|
|
// INFO: info: Exiting OpenMP data region with end_mapper at amd_info.c:{{[0-9]+}}:{{[0-9]+}} with 3 arguments:
|
|
// INFO: info: alloc(A[0:64])[256]
|
|
// INFO: info: tofrom(B[0:64])[256]
|
|
// INFO: info: to(C[0:64])[256]
|
|
// INFO: info: Copying data from device to host, TgtPtr={{.*}}, HstPtr={{.*}}, Size=256, Name=B[0:64]
|
|
// INFO: info: Removing map entry with HstPtrBegin={{.*}}, TgtPtrBegin={{.*}}, Size=256, Name=C[0:64]
|
|
// INFO: info: Removing map entry with HstPtrBegin={{.*}}, TgtPtrBegin={{.*}}, Size=256, Name=B[0:64]
|
|
// INFO: info: Removing map entry with HstPtrBegin={{.*}}, TgtPtrBegin={{.*}}, Size=256, Name=A[0:64]
|
|
// INFO: info: OpenMP Host-Device pointer mappings after block at amd_info.c:[[#%u,]]:[[#%u,]]:
|
|
// INFO: info: Host Ptr Target Ptr Size (B) DynRefCount HoldRefCount Declaration
|
|
// INFO: info: [[#%#x,]] [[#%#x,]] 4 INF 0 global at unknown:0:0
|
|
// clang-format on
|
|
#pragma omp target data map(alloc : A[0 : N]) \
|
|
map(ompx_hold, tofrom : B[0 : N]) map(to : C[0 : N])
|
|
#pragma omp target firstprivate(val)
|
|
{ val = 1; }
|
|
|
|
__tgt_set_info_flag(0x0);
|
|
// INFO-NOT: omptarget device 0 info: {{.*}}
|
|
#pragma omp target
|
|
{}
|
|
|
|
return 0;
|
|
}
|