BenchmarkUtils Namespace Reference

Classes
struct	BenchmarkResult
	Structure to hold benchmark results for a single run. More...
class	ResultCollector
	Class to collect and output benchmark results. More...
struct	ScalingConfig
	Configuration for scaling tests. More...
class	Timer
	High-resolution timer using MPI_Wtime for consistency. More...

Functions
double	compute_efficiency (const double t1, const double tp, int p)
	Compute parallel efficiency.
double	compute_speedup (const double t1, const double tp)
	Compute speedup.
double	get_process_memory_mb ()
	Get memory info from /proc/self/status (Linux specific)

Function Documentation

compute_efficiency()

double BenchmarkUtils::compute_efficiency ( const double t1, const double tp, int p )

inline

Compute parallel efficiency.

Parameters

t1	Time with 1 process (or baseline)
tp	Time with p processes
p	Number of processes

Returns

Parallel efficiency (ideal = 1.0)

compute_speedup()

double BenchmarkUtils::compute_speedup ( const double t1, const double tp )

inline

Compute speedup.

get_process_memory_mb()

double BenchmarkUtils::get_process_memory_mb ( )

inline

Get memory info from /proc/self/status (Linux specific)