Dynamic Load Balance 3.6.1+32-59d1
Data Fields
dlb_monitor_t Struct Reference

#include <dlb_talp.h>

Data Fields

const char * name
 
int num_cpus
 
float avg_cpus
 
int64_t cycles
 
int64_t instructions
 
int num_measurements
 
int num_resets
 
int64_t num_mpi_calls
 
int64_t num_omp_parallels
 
int64_t num_omp_tasks
 
int64_t num_gpu_runtime_calls
 
int64_t start_time
 
int64_t stop_time
 
int64_t elapsed_time
 
int64_t useful_time
 
int64_t mpi_time
 
int64_t omp_load_imbalance_time
 
int64_t omp_scheduling_time
 
int64_t omp_serialization_time
 
int64_t gpu_runtime_time
 
int64_t gpu_useful_time
 
int64_t gpu_communication_time
 
int64_t gpu_inactive_time
 
void * _data
 

Detailed Description

TALP public structure

Field Documentation

◆ name

const char* name

Name of the monitor

◆ num_cpus

int num_cpus

Number of active CPUs

◆ avg_cpus

float avg_cpus

Average of CPUs assigned to the process during the region execution

◆ cycles

int64_t cycles

Number of measured cycles

◆ instructions

int64_t instructions

Number of measured instructions

◆ num_measurements

int num_measurements

Number of times that the region has been started and stopped

◆ num_resets

int num_resets

Number of times that the region has been reset

◆ num_mpi_calls

int64_t num_mpi_calls

Number of measured MPI calls

◆ num_omp_parallels

int64_t num_omp_parallels

Number of measured OpenMP parallel regions

◆ num_omp_tasks

int64_t num_omp_tasks

Number of measured OpenMP explicit tasks

◆ num_gpu_runtime_calls

int64_t num_gpu_runtime_calls

Number of measured GPU Runtime calls

◆ start_time

int64_t start_time

Absolute time (in nanoseconds) of the last time the region was started

◆ stop_time

int64_t stop_time

Absolute time (in nanoseconds) of the last time the region was stopped

◆ elapsed_time

int64_t elapsed_time

Time (in nanoseconds) of the accumulated elapsed time inside the region

◆ useful_time

int64_t useful_time

Time (in nanoseconds) of the accumulated CPU time of useful computation inside the region

◆ mpi_time

int64_t mpi_time

Time (in nanoseconds) of the accumulated CPU time (not useful) in MPI inside the region

◆ omp_load_imbalance_time

int64_t omp_load_imbalance_time

Time (in nanoseconds) of the accumulated CPU time (not useful) spent due to load imbalance in OpenMP parallel regions

◆ omp_scheduling_time

int64_t omp_scheduling_time

Time (in nanoseconds) of the accumulated CPU time (not useful) spent inside OpenMP parallel regions due to scheduling and overhead, not counting load imbalance

◆ omp_serialization_time

int64_t omp_serialization_time

Time (in nanoseconds) of the accumulated CPU time (not useful) spent outside OpenMP parallel regions

◆ gpu_runtime_time

int64_t gpu_runtime_time

Time (in nanoseconds) of the accumulated CPU time (not useful) in GPU calls inside the region

◆ gpu_useful_time

int64_t gpu_useful_time

TBD

◆ gpu_communication_time

int64_t gpu_communication_time

TBD

◆ gpu_inactive_time

int64_t gpu_inactive_time

TBD

◆ _data

void* _data

Internal data


The documentation for this struct was generated from the following file: