utils.h File Reference

This file contains standard utility functions provide within the NVIDIA CUDA software development toolkit (SDK). The remainder of the file contains a function that defines the standard neuron models. More...

#include <cstdlib>
#include <iostream>
#include <string>
#include <cuda.h>
#include <cuda_runtime.h>

Go to the source code of this file.

Macros
#define	_UTILS_H_
	macro for avoiding multiple inclusion during compilation More...
#define	CHECK_CU_ERRORS(call)   call
	Macros for catching errors returned by the CUDA driver and runtime APIs. More...
#define	CHECK_CUDA_ERRORS(call)
#define	B(x, i)   ((x) & (0x80000000 >> (i)))
	Bit tool macros. More...
#define	setB(x, i)   x= ((x) | (0x80000000 >> (i)))
	Set the bit at the specified position i in x to 1. More...
#define	delB(x, i)   x= ((x) & (~(0x80000000 >> (i))))
	Set the bit at the specified position i in x to 0. More...
#define	USE(expr)   do { (void)(expr); } while (0)
	Miscellaneous macros. More...

Functions
CUresult	cudaFuncGetAttributesDriver (cudaFuncAttributes *attr, CUfunction kern)
	Function for getting the capabilities of a CUDA device via the driver API. More...
void	gennError (const string &error)
	Function called upon the detection of an error. Outputs an error message and then exits. More...
size_t	theSize (const string &type)
	Tool for determining the size of variable types on the current architecture. More...
void	writeHeader (CodeStream &os)
	Function to write the comment header denoting file authorship and contact details into the generated code. More...

Detailed Description

This file contains standard utility functions provide within the NVIDIA CUDA software development toolkit (SDK). The remainder of the file contains a function that defines the standard neuron models.

Macro Definition Documentation

_UTILS_H_

#define _UTILS_H_

macro for avoiding multiple inclusion during compilation

B

#define B	(		x,
			i
	)		((x) & (0x80000000 >> (i)))

Bit tool macros.

Extract the bit at the specified position i from x

CHECK_CU_ERRORS

#define CHECK_CU_ERRORS

(

call

)

call

Macros for catching errors returned by the CUDA driver and runtime APIs.

CHECK_CUDA_ERRORS

#define CHECK_CUDA_ERRORS

(

call

)

Value:

{                                                                \
    cudaError_t error = call;                                        \
    if (error != cudaSuccess)                                        \
      {                                                                \
        cerr << __FILE__ << ": " <<  __LINE__;                        \
        cerr << ": cuda runtime error " << error << ": ";        \
        cerr << cudaGetErrorString(error) << endl;                \
        exit(EXIT_FAILURE);                                        \
      }                                                                \
  }

delB

#define delB	(		x,
			i
	)		x= ((x) & (~(0x80000000 >> (i))))

Set the bit at the specified position i in x to 0.

setB

#define setB	(		x,
			i
	)		x= ((x) | (0x80000000 >> (i)))

Set the bit at the specified position i in x to 1.

USE

#define USE

(

expr

)

do { (void)(expr); } while (0)

Miscellaneous macros.

Silence 'unused parameter' warnings

Function Documentation

cudaFuncGetAttributesDriver()

CUresult cudaFuncGetAttributesDriver	(	cudaFuncAttributes *	attr,
		CUfunction	kern
	)

Function for getting the capabilities of a CUDA device via the driver API.

gennError()

void gennError ( const string &  error )

inline

Function called upon the detection of an error. Outputs an error message and then exits.

theSize()

size_t theSize

(

const string &

type

)

Tool for determining the size of variable types on the current architecture.

writeHeader()

void writeHeader

(

CodeStream &

os

)

Function to write the comment header denoting file authorship and contact details into the generated code.