common.h

cuda开发环境下的矩阵运算

/*
* Copyright 1993-2007 NVIDIA Corporation.  All rights reserved.
*
* NOTICE TO USER:
*
* This source code is subject to NVIDIA ownership rights under U.S. and
* international Copyright laws.  Users and possessors of this source code
* are hereby granted a nonexclusive, royalty-free license to use this code
* in individual and commercial software.
*
* NVIDIA MAKES NO REPRESENTATION ABOUT THE SUITABILITY OF THIS SOURCE
* CODE FOR ANY PURPOSE.  IT IS PROVIDED "AS IS" WITHOUT EXPRESS OR
* IMPLIED WARRANTY OF ANY KIND.  NVIDIA DISCLAIMS ALL WARRANTIES WITH
* REGARD TO THIS SOURCE CODE, INCLUDING ALL IMPLIED WARRANTIES OF
* MERCHANTABILITY, NONINFRINGEMENT, AND FITNESS FOR A PARTICULAR PURPOSE.
* IN NO EVENT SHALL NVIDIA BE LIABLE FOR ANY SPECIAL, INDIRECT, INCIDENTAL,
* OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
* OF USE, DATA OR PROFITS,  WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE
* OR OTHER TORTIOUS ACTION,  ARISING OUT OF OR IN CONNECTION WITH THE USE
* OR PERFORMANCE OF THIS SOURCE CODE.
*
* U.S. Government End Users.   This source code is a "commercial item" as
* that term is defined at  48 C.F.R. 2.101 (OCT 1995), consisting  of
* "commercial computer  software"  and "commercial computer software
* documentation" as such terms are  used in 48 C.F.R. 12.212 (SEPT 1995)
* and is provided to the U.S. Government only as a commercial end item.
* Consistent with 48 C.F.R.12.212 and 48 C.F.R. 227.7202-1 through
* 227.7202-4 (JUNE 1995), all U.S. Government End Users acquire the
* source code with only those rights set forth herein.
*
* Any use of this source code in individual and commercial software must
* include, in the user documentation and internal comments to the code,
* the above Disclaimer and U.S. Government End Users Notice.
*/

/**
**************************************************************************
* \file Common.h
* \brief Common includes header.
*
* This file contains includes of all libraries used by the project.
*/

#pragma once

#include <stdio.h>
#include <stdlib.h>
#include <math.h>
#include <cutil.h>

#include "DCT8x8_Gold.h"
#include "BmpUtil.h"


/**
*  The dimension of pixels block
*/
#define BLOCK_SIZE			8


/**
*  Square of dimension of pixels block
*/
#define BLOCK_SIZE2			64


/**
*  log_2{BLOCK_SIZE), used for quick multiplication or division by the 
*  pixels block dimension via shifting
*/
#define BLOCK_SIZE_LOG2		3


/**
*  log_2{BLOCK_SIZE*BLOCK_SIZE), used for quick multiplication or division by the 
*  square of pixels block via shifting
*/
#define BLOCK_SIZE2_LOG2	6


/**
*  This macro states that __mul24 operation is performed faster that traditional
*  multiplication for two integers on CUDA. Please undefine if it appears to be 
*  wrong on your system
*/
#define __MUL24_FASTER_THAN_ASTERIX


/**
*  Wrapper to the fastest integer multiplication function on CUDA
*/
#ifdef __MUL24_FASTER_THAN_ASTERIX
	#define FAST_INT_MUL(x,y)	(__mul24(x,y))
#else
	#define FAST_INT_MUL(x,y)	((x)*(y))
#endif


/**
*  This macro allows using aligned memory management
*/
//#define __ALLOW_ALIGNED_MEMORY_MANAGEMENT