00001 /*!@file CUDA/cudadefs.h CUDA/GPU definitions */ 00002 00003 // //////////////////////////////////////////////////////////////////// // 00004 // The iLab Neuromorphic Vision C++ Toolkit - Copyright (C) 2000-2005 // 00005 // by the University of Southern California (USC) and the iLab at USC. // 00006 // See http://iLab.usc.edu for information about this project. // 00007 // //////////////////////////////////////////////////////////////////// // 00008 // Major portions of the iLab Neuromorphic Vision Toolkit are protected // 00009 // under the U.S. patent ``Computation of Intrinsic Perceptual Saliency // 00010 // in Visual Environments, and Applications'' by Christof Koch and // 00011 // Laurent Itti, California Institute of Technology, 2001 (patent // 00012 // pending; application number 09/912,225 filed July 23, 2001; see // 00013 // http://pair.uspto.gov/cgi-bin/final/home.pl for current status). // 00014 // //////////////////////////////////////////////////////////////////// // 00015 // This file is part of the iLab Neuromorphic Vision C++ Toolkit. // 00016 // // 00017 // The iLab Neuromorphic Vision C++ Toolkit is free software; you can // 00018 // redistribute it and/or modify it under the terms of the GNU General // 00019 // Public License as published by the Free Software Foundation; either // 00020 // version 2 of the License, or (at your option) any later version. // 00021 // // 00022 // The iLab Neuromorphic Vision C++ Toolkit is distributed in the hope // 00023 // that it will be useful, but WITHOUT ANY WARRANTY; without even the // 00024 // implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR // 00025 // PURPOSE. See the GNU General Public License for more details. // 00026 // // 00027 // You should have received a copy of the GNU General Public License // 00028 // along with the iLab Neuromorphic Vision C++ Toolkit; if not, write // 00029 // to the Free Software Foundation, Inc., 59 Temple Place, Suite 330, // 00030 // Boston, MA 02111-1307 USA. // 00031 // //////////////////////////////////////////////////////////////////// // 00032 // 00033 // Primary maintainer for this file: 00034 // $HeadURL: svn://isvn.usc.edu/software/invt/trunk/saliency/src/CUDA/cudadefs.h $ 00035 // $Id: cudadefs.h 12962 2010-03-06 02:13:53Z irock $ 00036 // 00037 00038 #ifndef CUDADEFS_H_DEFINED 00039 #define CUDADEFS_H_DEFINED 00040 00041 #include <math.h> 00042 00043 // Saliency C++ Toolkit implements Pixels as a template 00044 // that takes the dimensionality as a template argument 00045 // That definition will not work in CUDA C, so we are left 00046 // with this ugliness 00047 00048 // 24-bit multiplication is faster on G80, but we must be sure to 00049 // multiply integers only within [-8M, 8M - 1] range 00050 #define IMUL(a, b) __mul24(a, b) 00051 00052 //! Structure to handle 3 dimensional float 00053 typedef struct 00054 { 00055 float p[3]; 00056 } float3_t; 00057 00058 //! Structure to handle 4 dimensional float 00059 typedef struct 00060 { 00061 float p[4]; 00062 } float4_t; 00063 00064 // The tile size should be the same across all CUDA functions within a particular device and run, since one function might call another 00065 #define MAX_CUDA_DEVICES 4 00066 #define CUDA_TILE_W 16 00067 #define CUDA_TILE_H 16 00068 #define CUDA_1D_TILE_W 256 00069 #define PI 3.14159265358979f 00070 00071 //Round a / b to nearest higher integer value 00072 inline int iDivUp(int a, int b) { return (a % b != 0) ? (a / b + 1) : (a / b); } 00073 00074 //Round a / b to nearest higher integer value in CUDA code 00075 #define IDIVUP(a, b) ((a % b != 0) ? (a / b + 1) : (a / b)) 00076 00077 // Find min/max 00078 #define MIN(a,b) ((a<b) ? a : b) 00079 #define MAX(a,b) ((a>b) ? a : b) 00080 00081 #endif