device_settings.cpp File Reference

Implements the function to set up the GPU related parameters. More...

#include "swarm/common.hpp"
#include "device_settings.hpp"

Go to the source code of this file.

Functions
int	optimized_system_per_block (int chunk_size, int thread_per_system, int shmem_per_system)
	Find the optimized value for system_per_block based on device parameters.
void	select_cuda_device (int dev)
	Select cuda device.
void	set_more_cache ()
	The intent is to tell CUDA driver to use more cache. More...
void	print_device_information ()
	print out the device information
int	blocks_per_mp (int blocksize, int shmem_per_block)
bool	check_cuda_limits (int blocksize, int shmem_per_block)
	Helper function to catch wrong configurations when running a kernel. More...

Detailed Description

Implements the function to set up the GPU related parameters.

Definition in file device_settings.cpp.

Function Documentation

int blocks_per_mp	(	int	blocksize,
		int	shmem_per_block
	)

Todo:

is block_warps computed correctly when blocksize is a multiple of warpSize?

Definition at line 80 of file device_settings.cpp.

Referenced by check_cuda_limits(), and optimized_system_per_block().

bool check_cuda_limits	(	int	blocksize,
		int	shmem_per_block
	)

Helper function to catch wrong configurations when running a kernel.

It uses the general guidelines from the CUDA Occupancy calculator.

Definition at line 106 of file device_settings.cpp.

References blocks_per_mp().

void set_more_cache

(

)

The intent is to tell CUDA driver to use more cache.

But it does not improve performance all the time.

Definition at line 60 of file device_settings.cpp.

Referenced by swarm::init().