rand_app.cu File Reference

CUDPP application-level rand routine for MD5. More...

#include "cudpp.h"
#include "cudpp_util.h"
#include "cudpp_plan.h"
#include <cutil.h>
#include <cstdlib>
#include <cstdio>
#include <assert.h>
#include "cta/rand_cta.cu"
#include "kernel/rand_kernel.cu"

Functions
Rand Functions
void	launchRandMD5Kernel (unsigned int *d_out, unsigned int seed, size_t numElements)
	Launches the MD5 Random number generator kernel.
void	cudppRandDispatch (void *d_out, size_t numElements, const CUDPPRandPlan *plan)
	Dispatches the rand function based on the plan.

---

Detailed Description

CUDPP application-level rand routine for MD5.

rand_md5_app.cu

---

Function Documentation

void launchRandMD5Kernel	(	unsigned int *	d_out,
		unsigned int	seed,
		size_t	numElements
	)

Launches the MD5 Random number generator kernel.

The MD5 Random number generator works by generating 128 bit digests which are then broken down into 32 bit chunks and stored inside d_out. d_out is expected to be of type unsigned int and can hold numElements elements.

An analysis of the stastical distribution of the MD5 random number generator can be found in the original paper Parallel white noise generation on a GPU via cryptographic hash. The optimizations mentioned in the paper are also present in the CUDPP version of the MD5 Random number generator.

It is also worth pointing out that the GPU version will not generate the same output * as the CPU version. This is due to the difference in the floating point accuracy and several optimizations that have been used (i.e. calculating sin using device hardware rather than storing it in an array that the original implementation does). However, the distribution of the numbers is well suited for random number generation, even without the CPU-GPU invariance.

Parameters:

[out]	d_out	the array of unsigned integers allocated on device memory
[in]	seed	the random seed used to vary the output
[in]	numElements	the number of elements in d_out

See also:

gen_randMD5()

cudppRand()

Todo:

: chose a better block size, perhaps a multiple of two is optimal

void cudppRandDispatch	(	void *	d_out,
		size_t	numElements,
		const CUDPPRandPlan *	plan
	)

Dispatches the rand function based on the plan.

This is the dispatch call which looks at the algorithm specified in plan and calls the appropriate random number generation algorithm.

Parameters:

[out]	d_out	the array allocated on device memory where the random numbers will be stored must be of type unsigned int
[in]	numElements	the number of elements in the array d_out
[in]	plan	pointer to CUDPPRandPlan which contains the algorithm to run