c9062e8f78
The plugin was not getting built as the build_generic_elf64 macro assumes the LLVM triple processor name matches the CMake processor name, which is unfortunately not the case for SystemZ. Fix this by providing two separate arguments instead. Actually building the plugin exposed a number of other issues causing various test failures. Specifically, I've had to add the SystemZ target to - CompilerInvocation::ParseLangArgs - linkDevice in ClangLinuxWrapper.cpp - OMPContext::OMPContext (to set the device_kind_cpu trait) - LIBOMPTARGET_ALL_TARGETS in libomptarget/CMakeLists.txt - a check_plugin_target call in libomptarget/src/CMakeLists.txt Finally, I've had to set a number of test cases to UNSUPPORTED on s390x-ibm-linux-gnu; all these tests were already marked as UNSUPPORTED for x86_64-pc-linux-gnu and aarch64-unknown-linux-gnu and are failing on s390x for what seem to be the same reason. In addition, this also requires support for BE ELF files in plugins-nextgen: https://github.com/llvm/llvm-project/pull/85246
60 lines
2.0 KiB
C++
60 lines
2.0 KiB
C++
// clang-format off
|
|
// RUN: %libomptarget-compilexx-generic
|
|
// RUN: env OMPX_APU_MAPS=1 HSA_XNACK=1 LIBOMPTARGET_INFO=30 %libomptarget-run-generic 2>&1 \
|
|
// RUN: | %fcheck-generic -check-prefix=INFO_ZERO -check-prefix=CHECK
|
|
|
|
// RUN: %libomptarget-compilexx-generic
|
|
// RUN: env HSA_XNACK=0 LIBOMPTARGET_INFO=30 %libomptarget-run-generic 2>&1 \
|
|
// RUN: | %fcheck-generic -check-prefix=INFO_COPY -check-prefix=CHECK
|
|
|
|
// UNSUPPORTED: aarch64-unknown-linux-gnu
|
|
// UNSUPPORTED: aarch64-unknown-linux-gnu-LTO
|
|
// UNSUPPORTED: nvptx64-nvidia-cuda
|
|
// UNSUPPORTED: nvptx64-nvidia-cuda-LTO
|
|
// UNSUPPORTED: x86_64-pc-linux-gnu
|
|
// UNSUPPORTED: x86_64-pc-linux-gnu-LTO
|
|
// UNSUPPORTED: s390x-ibm-linux-gnu
|
|
// UNSUPPORTED: s390x-ibm-linux-gnu-LTO
|
|
|
|
// REQUIRES: unified_shared_memory
|
|
|
|
// clang-format on
|
|
|
|
#include <cstdio>
|
|
|
|
int main() {
|
|
int n = 1024;
|
|
|
|
// test various mapping types
|
|
int *a = new int[n];
|
|
int k = 3;
|
|
int b[n];
|
|
|
|
for (int i = 0; i < n; i++)
|
|
b[i] = i;
|
|
|
|
// clang-format off
|
|
// INFO_ZERO: Return HstPtrBegin 0x{{.*}} Size=4096 for unified shared memory
|
|
// INFO_ZERO: Return HstPtrBegin 0x{{.*}} Size=4096 for unified shared memory
|
|
|
|
// INFO_COPY: Creating new map entry with HstPtrBase=0x{{.*}}, HstPtrBegin=0x{{.*}}, TgtAllocBegin=0x{{.*}}, TgtPtrBegin=0x{{.*}}, Size=4096,
|
|
// INFO_COPY: Creating new map entry with HstPtrBase=0x{{.*}}, HstPtrBegin=0x{{.*}}, TgtAllocBegin=0x{{.*}}, TgtPtrBegin=0x{{.*}}, Size=4096,
|
|
// INFO_COPY: Mapping exists with HstPtrBegin=0x{{.*}}, TgtPtrBegin=0x{{.*}}, Size=4096, DynRefCount=1 (update suppressed)
|
|
// INFO_COPY: Mapping exists with HstPtrBegin=0x{{.*}}, TgtPtrBegin=0x{{.*}}, Size=4096, DynRefCount=1 (update suppressed)
|
|
// clang-format on
|
|
#pragma omp target teams distribute parallel for map(tofrom : a[ : n]) \
|
|
map(to : b[ : n])
|
|
for (int i = 0; i < n; i++)
|
|
a[i] = i + b[i] + k;
|
|
|
|
int err = 0;
|
|
for (int i = 0; i < n; i++)
|
|
if (a[i] != i + b[i] + k)
|
|
err++;
|
|
|
|
// CHECK: PASS
|
|
if (err == 0)
|
|
printf("PASS\n");
|
|
return err;
|
|
}
|