ae23be84cb
Previously an opt-in flag `-fopenmp-new-driver` was used to enable the new offloading driver. After passing tests for a few months it should be sufficiently mature to flip the switch and make it the default. The new offloading driver is now enabled if there is OpenMP and OpenMP offloading present and the new `-fno-openmp-new-driver` is not present. The new offloading driver has three main benefits over the old method: - Static library support - Device-side LTO - Unified clang driver stages Depends on D122683 Differential Revision: https://reviews.llvm.org/D122831
58 lines
2.0 KiB
C
58 lines
2.0 KiB
C
// Use the generic state machine. On some architectures, other threads in the
|
|
// main thread's warp must avoid barrier instructions.
|
|
//
|
|
// RUN: %libomptarget-compile-run-and-check-generic
|
|
|
|
// SPMDize. There is no main thread, so there's no issue.
|
|
//
|
|
// RUN: %libomptarget-compile-generic -O1 -Rpass=openmp-opt > %t.spmd 2>&1
|
|
// RUN: %fcheck-nvptx64-nvidia-cuda -check-prefix=SPMD -input-file=%t.spmd
|
|
// RUN: %fcheck-amdgcn-amd-amdhsa -check-prefix=SPMD -input-file=%t.spmd
|
|
// RUN: %libomptarget-run-generic 2>&1 | %fcheck-generic
|
|
//
|
|
// SPMD: Transformed generic-mode kernel to SPMD-mode.
|
|
|
|
// Use the custom state machine, which must avoid the same barrier problem as
|
|
// the generic state machine.
|
|
//
|
|
// RUN: %libomptarget-compile-generic -O1 -Rpass=openmp-opt \
|
|
// RUN: -mllvm -openmp-opt-disable-spmdization > %t.custom 2>&1
|
|
// RUN: %fcheck-nvptx64-nvidia-cuda -check-prefix=CUSTOM -input-file=%t.custom
|
|
// RUN: %fcheck-amdgcn-amd-amdhsa -check-prefix=CUSTOM -input-file=%t.custom
|
|
// RUN: %libomptarget-run-generic 2>&1 | %fcheck-generic
|
|
//
|
|
// Repeat with reduction clause, which has managed to break the custom state
|
|
// machine in the past.
|
|
//
|
|
// RUN: %libomptarget-compile-generic -O1 -Rpass=openmp-opt -DADD_REDUCTION \
|
|
// RUN: -mllvm -openmp-opt-disable-spmdization > %t.custom 2>&1
|
|
// RUN: %fcheck-nvptx64-nvidia-cuda -check-prefix=CUSTOM -input-file=%t.custom
|
|
// RUN: %fcheck-amdgcn-amd-amdhsa -check-prefix=CUSTOM -input-file=%t.custom
|
|
// RUN: %libomptarget-run-generic 2>&1 | %fcheck-generic
|
|
//
|
|
// CUSTOM: Rewriting generic-mode kernel with a customized state machine.
|
|
|
|
// Hangs
|
|
// UNSUPPORTED: amdgcn-amd-amdhsa
|
|
// UNSUPPORTED: amdgcn-amd-amdhsa-oldDriver
|
|
|
|
#if ADD_REDUCTION
|
|
# define REDUCTION(...) reduction(__VA_ARGS__)
|
|
#else
|
|
# define REDUCTION(...)
|
|
#endif
|
|
|
|
#include <stdio.h>
|
|
int main() {
|
|
int x = 0, y = 1;
|
|
#pragma omp target teams num_teams(1) map(tofrom:x, y) REDUCTION(+:x)
|
|
{
|
|
x += 5;
|
|
#pragma omp parallel
|
|
y = 6;
|
|
}
|
|
// CHECK: 5, 6
|
|
printf("%d, %d\n", x, y);
|
|
return 0;
|
|
}
|