DavidPoliakoff

int init_my_tool(bool verbose){
  if(verbose){
    gotcha_wrap(a_few_functions);
  }
  else{
    gotcha_wrap(all_the_functions);
  }
}

DavidPoliakoff

ssize_t (*orig_read)(int fildes, void *buf, size_t nbyte);
ssize_t read_wrapper(int fildes, void* buf, size_t nbyte){
  cali::Annotation("bytes_read").set(nbyte);
  return orig_read(fildes, buf, nbyte);
}

struct gotcha_binding_t wrap_actions[] = {
     { "read", read_wrapper, &orig_read }
};
void init_bytecounter_tool(){

DavidPoliakoff

ssize_t (*orig_read)(int fildes, void *buf, size_t nbyte);
ssize_t read_wrapper(int fildes, void* buf, size_t nbyte){
  TAU_REGISTER_CONTEXT_EVENT(event, "Bytes read");
  TAU_CONTEXT_EVENT(event, nbyte);
  return orig_read(fildes, buf, nbyte);
}

struct gotcha_binding_t wrap_actions[] = {
     { "read", read_wrapper, &orig_read }
};

DavidPoliakoff

bash-4.2$ ./autogen.sh
Running autoreconf -i ...
libtoolize: putting auxiliary files in AC_CONFIG_AUX_DIR, `config'.
libtoolize: copying file `config/ltmain.sh'
libtoolize: putting macros in AC_CONFIG_MACRO_DIR, `m4'.
libtoolize: copying file `m4/libtool.m4'
libtoolize: copying file `m4/ltoptions.m4'
libtoolize: copying file `m4/ltsugar.m4'
libtoolize: copying file `m4/ltversion.m4'
libtoolize: copying file `m4/lt~obsolete.m4'

DavidPoliakoff

int MPI_Send(const void *buf, int count, 
  MPI_Datatype datatype, int dest, int tag,
  MPI_Comm comm){


  // MPI Things

}

DavidPoliakoff

struct gotcha_binding_t mpi_wrappers[] = {
  { "MPI_Init", mpi_init_wrapper, &orig_mpi_init_handle },
  // other wrappers as desired
};

static int mpi_init_wrapper(int* argc, char*** argv )
{
   typeof(&puts) orig_init = gotcha_get_wrappee(orig_mpi_init_handle);
   /** do tool_things */
   return orig_init(str);

DavidPoliakoff

int MPI_Send( /* Args */ ){
    
  // typical MPI code
  
}

DavidPoliakoff

Kokkos::TeamPolicy<Kokkos::Cuda> execution_policy(total_amount_of_work, 
                                  outer_parallelism_batch_size,
                                  inner_parallelism_batch_size);

Kokkos::parallel_for("implement_psychics", execution_policy, 
                     KOKKOS_LAMBDA (team_member outer_handle) {
  // some outer level work
  double sum = psychics;                     
  parallel_reduce (ThreadVectorRange (outer_handle, loop_count),
          [=] (int& i, Scalar& lsum) {

DavidPoliakoff

extern "C" void kokkosp_begin_parallel_for(const char* name, const uint32_t devID, uint64_t* kID){
 if(name matches a regex){
   jonathans_api_wrapper_start();
   *kID = 1;
 }
}
extern "C" void kokkosp_end_parallel_for(uint64_t kID){
  if(kID==1){
   jonathans_api_wrapper_stop();
  }

DavidPoliakoff

Introduction

Simple Tools

Caliper

Third Party Tools

Autotuning