Index: openmp/trunk/libomptarget/src/omptarget.cpp =================================================================== --- openmp/trunk/libomptarget/src/omptarget.cpp +++ openmp/trunk/libomptarget/src/omptarget.cpp @@ -732,8 +732,11 @@ uint64_t ltc = 0; TblMapMtx.lock(); auto I = Device.LoopTripCnt.find(__kmpc_global_thread_num(NULL)); - if (I != Device.LoopTripCnt.end()) - std::swap(ltc, I->second); + if (I != Device.LoopTripCnt.end()) { + ltc = I->second; + Device.LoopTripCnt.erase(I); + DP("loop trip count is %lu.\n", ltc); + } TblMapMtx.unlock(); // Launch device execution. Index: openmp/trunk/libomptarget/test/offloading/looptripcnt.c =================================================================== --- openmp/trunk/libomptarget/test/offloading/looptripcnt.c +++ openmp/trunk/libomptarget/test/offloading/looptripcnt.c @@ -0,0 +1,36 @@ +// RUN: %libomptarget-compile-aarch64-unknown-linux-gnu && env LIBOMPTARGET_DEBUG=1 %libomptarget-run-aarch64-unknown-linux-gnu 2>&1 | %fcheck-aarch64-unknown-linux-gnu -allow-empty -check-prefix=DEBUG +// RUN: %libomptarget-compile-powerpc64-ibm-linux-gnu && env LIBOMPTARGET_DEBUG=1 %libomptarget-run-powerpc64-ibm-linux-gnu 2>&1 | %fcheck-powerpc64-ibm-linux-gnu -allow-empty -check-prefix=DEBUG +// RUN: %libomptarget-compile-powerpc64le-ibm-linux-gnu && env LIBOMPTARGET_DEBUG=1 %libomptarget-run-powerpc64le-ibm-linux-gnu 2>&1 | %fcheck-powerpc64le-ibm-linux-gnu -allow-empty -check-prefix=DEBUG +// RUN: %libomptarget-compile-x86_64-pc-linux-gnu && env LIBOMPTARGET_DEBUG=1 %libomptarget-run-x86_64-pc-linux-gnu 2>&1 | %fcheck-x86_64-pc-linux-gnu -allow-empty -check-prefix=DEBUG +// REQUIRES: libomptarget-debug + +/* + Test for looptripcount being popped from runtime stack. +*/ +#include +#include +int main() +{ + int N = 128; + int NN = 1024; + int num_teams[NN]; + int num_threads[NN]; + + printf("#pragma omp target teams distribute parallel for thread_limit(4)\n"); +#pragma omp target teams distribute parallel for thread_limit(4) + for (int j = 0; j< N; j++) { + num_threads[j] = omp_get_num_threads(); + num_teams[j] = omp_get_num_teams(); + } + printf("num_threads %d num_teams %d\n", num_threads[0], num_teams[0]); +// DEBUG: loop trip count is 128 + printf("#pragma omp target teams distribute parallel for\n"); +#pragma omp target teams distribute parallel for + for (int j = 0; j< N; j++) { + num_threads[j] = omp_get_num_threads(); + num_teams[j] = omp_get_num_teams(); + } + printf("num_threads %d num_teams %d\n", num_threads[0], num_teams[0]); +// DEBUG: loop trip count is 128 + return 0; +}