Skip to content
This repository
tree: 98c789e4c5
Fetching contributors…

Cannot retrieve contributors at this time

executable file 398 lines (314 sloc) 11.032 kb
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398
// CIS565 CUDA Raytracer: A parallel raytracer for Patrick Cozzi's CIS565: GPU Computing at the University of Pennsylvania
// Written by Yining Karl Li, Copyright (c) 2012 University of Pennsylvania
// This file includes code from:
// Rob Farber for CUDA-GL interop, from CUDA Supercomputing For The Masses: http://www.drdobbs.com/architecture-and-design/cuda-supercomputing-for-the-masses-part/222600097
// Varun Sampath and Patrick Cozzi for GLSL Loading, from CIS565 Spring 2012 HW5 at the University of Pennsylvania: http://cis565-spring-2012.github.com/
// Yining Karl Li's TAKUA Render, a massively parallel pathtracing renderer: http://www.yiningkarlli.com

#include "main.h"

//-------------------------------
//-------------MAIN--------------
//-------------------------------

int main(int argc, char** argv){

#ifdef __APPLE__
// Needed in OSX to force use of OpenGL3.2
glfwOpenWindowHint(GLFW_OPENGL_VERSION_MAJOR, 3);
glfwOpenWindowHint(GLFW_OPENGL_VERSION_MINOR, 2);
glfwOpenWindowHint(GLFW_OPENGL_FORWARD_COMPAT, GL_TRUE);
glfwOpenWindowHint(GLFW_OPENGL_PROFILE, GLFW_OPENGL_CORE_PROFILE);
#endif

  // Set up pathtracer stuff
  bool loadedScene = false;
  finishedRender = false;

  targetFrame = 0;
  singleFrameMode = false;

  // Load scene file
  for(int i=1; i<argc; i++){
    string header; string data;
    istringstream liness(argv[i]);
    getline(liness, header, '='); getline(liness, data, '=');
    if(strcmp(header.c_str(), "scene")==0){
      renderScene = new scene(data);
      loadedScene = true;
    }else if(strcmp(header.c_str(), "frame")==0){
      targetFrame = atoi(data.c_str());
      singleFrameMode = true;
    }
  }

  if(!loadedScene){
    cout << "Error: scene file needed!" << endl;
    return 0;
  }

  // Set up camera stuff from loaded pathtracer settings
  iterations = 0;
  renderCam = &renderScene->renderCam;
  width = renderCam->resolution[0];
  height = renderCam->resolution[1];

  if(targetFrame>=renderCam->frames){
    cout << "Warning: Specified target frame is out of range, defaulting to frame 0." << endl;
    targetFrame = 0;
  }

  // Launch CUDA/GL

#ifdef __APPLE__
init();
#else
init(argc, argv);
#endif

  initCuda();

  initVAO();
  initTextures();

  GLuint passthroughProgram;
  passthroughProgram = initShader("shaders/passthroughVS.glsl", "shaders/passthroughFS.glsl");

  glUseProgram(passthroughProgram);
  glActiveTexture(GL_TEXTURE0);

#ifdef __APPLE__
// send into GLFW main loop
while(1){
display();
if (glfwGetKey(GLFW_KEY_ESC) == GLFW_PRESS || !glfwGetWindowParam( GLFW_OPENED )){
exit(0);
}
}

glfwTerminate();
#else
glutDisplayFunc(display);
glutKeyboardFunc(keyboard);

glutMainLoop();
#endif
  return 0;
}

//-------------------------------
//---------RUNTIME STUFF---------
//-------------------------------

void runCuda(){

  // Map OpenGL buffer object for writing from CUDA on a single GPU
  // No data is moved (Win & Linux). When mapped to CUDA, OpenGL should not use this buffer
  
  if(iterations<renderCam->iterations){
    uchar4 *dptr=NULL;
    iterations++;
    cudaGLMapBufferObject((void**)&dptr, pbo);
  
    //pack geom and material arrays
    geom* geoms = new geom[renderScene->objects.size()];
    material* materials = new material[renderScene->materials.size()];
    
    for(int i=0; i<renderScene->objects.size(); i++){
      geoms[i] = renderScene->objects[i];
    }
    for(int i=0; i<renderScene->materials.size(); i++){
      materials[i] = renderScene->materials[i];
    }
    
  
    // execute the kernel
    cudaRaytraceCore(dptr, renderCam, targetFrame, iterations, materials, renderScene->materials.size(), geoms, renderScene->objects.size() );
    
    // unmap buffer object
    cudaGLUnmapBufferObject(pbo);
  }else{

    if(!finishedRender){
      //output image file
      image outputImage(renderCam->resolution.x, renderCam->resolution.y);

      for(int x=0; x<renderCam->resolution.x; x++){
        for(int y=0; y<renderCam->resolution.y; y++){
          int index = x + (y * renderCam->resolution.x);
          outputImage.writePixelRGB(x,y,renderCam->image[index]);
        }
      }
      
      gammaSettings gamma;
      gamma.applyGamma = true;
      gamma.gamma = 1.0/2.2;
      gamma.divisor = renderCam->iterations;
      outputImage.setGammaSettings(gamma);
      string filename = renderCam->imageName;
      string s;
      stringstream out;
      out << targetFrame;
      s = out.str();
      utilityCore::replaceString(filename, ".bmp", "."+s+".bmp");
      utilityCore::replaceString(filename, ".png", "."+s+".png");
      outputImage.saveImageRGB(filename);
      cout << "Saved frame " << s << " to " << filename << endl;
      finishedRender = true;
      if(singleFrameMode==true){
        cudaDeviceReset();
        exit(0);
      }
    }
    if(targetFrame<renderCam->frames-1){

      //clear image buffer and move onto next frame
      targetFrame++;
      iterations = 0;
      for(int i=0; i<renderCam->resolution.x*renderCam->resolution.y; i++){
        renderCam->image[i] = glm::vec3(0,0,0);
      }
      cudaDeviceReset();
      finishedRender = false;
    }
  }
  
}

#ifdef __APPLE__

void display(){
runCuda();

string title = "CIS565 Render | " + utilityCore::convertIntToString(iterations) + " Frames";
glfwSetWindowTitle(title.c_str());

glBindBuffer( GL_PIXEL_UNPACK_BUFFER, pbo);
glBindTexture(GL_TEXTURE_2D, displayImage);
glTexSubImage2D(GL_TEXTURE_2D, 0, 0, 0, width, height,
GL_RGBA, GL_UNSIGNED_BYTE, NULL);

glClear(GL_COLOR_BUFFER_BIT);

// VAO, shader program, and texture already bound
glDrawElements(GL_TRIANGLES, 6, GL_UNSIGNED_SHORT, 0);

glfwSwapBuffers();
}

#else

void display(){
runCuda();

string title = "565Raytracer | " + utilityCore::convertIntToString(iterations) + " Frames";
glutSetWindowTitle(title.c_str());

glBindBuffer( GL_PIXEL_UNPACK_BUFFER, pbo);
glBindTexture(GL_TEXTURE_2D, displayImage);
glTexSubImage2D(GL_TEXTURE_2D, 0, 0, 0, width, height,
GL_RGBA, GL_UNSIGNED_BYTE, NULL);

glClear(GL_COLOR_BUFFER_BIT);

// VAO, shader program, and texture already bound
glDrawElements(GL_TRIANGLES, 6, GL_UNSIGNED_SHORT, 0);

glutPostRedisplay();
glutSwapBuffers();
}

void keyboard(unsigned char key, int x, int y)
{
std::cout << key << std::endl;
switch (key)
{
case(27):
exit(1);
break;
}
}

#endif




//-------------------------------
//----------SETUP STUFF----------
//-------------------------------

#ifdef __APPLE__
void init(){

if (glfwInit() != GL_TRUE){
shut_down(1);
}

// 16 bit color, no depth, alpha or stencil buffers, windowed
if (glfwOpenWindow(width, height, 5, 6, 5, 0, 0, 0, GLFW_WINDOW) != GL_TRUE){
shut_down(1);
}

// Set up vertex array object, texture stuff
initVAO();
initTextures();
}
#else
void init(int argc, char* argv[]){
glutInit(&argc, argv);
glutInitDisplayMode(GLUT_DOUBLE | GLUT_RGBA);
glutInitWindowSize(width, height);
glutCreateWindow("565Raytracer");

// Init GLEW
glewInit();
GLenum err = glewInit();
if (GLEW_OK != err)
{
/* Problem: glewInit failed, something is seriously wrong. */
std::cout << "glewInit failed, aborting." << std::endl;
exit (1);
}

initVAO();
initTextures();
}
#endif

void initPBO(GLuint* pbo){
  if (pbo) {
    // set up vertex data parameter
    int num_texels = width*height;
    int num_values = num_texels * 4;
    int size_tex_data = sizeof(GLubyte) * num_values;
    
    // Generate a buffer ID called a PBO (Pixel Buffer Object)
    glGenBuffers(1,pbo);
    // Make this the current UNPACK buffer (OpenGL is state-based)
    glBindBuffer(GL_PIXEL_UNPACK_BUFFER, *pbo);
    // Allocate data for the buffer. 4-channel 8-bit image
    glBufferData(GL_PIXEL_UNPACK_BUFFER, size_tex_data, NULL, GL_DYNAMIC_COPY);
    cudaGLRegisterBufferObject( *pbo );
  }
}

void initCuda(){
  // Use device with highest Gflops/s
  cudaGLSetGLDevice( cutGetMaxGflopsDeviceId() );

  initPBO(&pbo);

  // Clean up on program exit
  atexit(cleanupCuda);

  runCuda();
}

void initTextures(){
    glGenTextures(1,&displayImage);
    glBindTexture(GL_TEXTURE_2D, displayImage);
    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_NEAREST);
    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST);
    glTexImage2D( GL_TEXTURE_2D, 0, GL_RGBA8, width, height, 0, GL_BGRA,
        GL_UNSIGNED_BYTE, NULL);
}

void initVAO(void){
    GLfloat vertices[] =
    {
        -1.0f, -1.0f,
         1.0f, -1.0f,
         1.0f, 1.0f,
        -1.0f, 1.0f,
    };

    GLfloat texcoords[] =
    {
        1.0f, 1.0f,
        0.0f, 1.0f,
        0.0f, 0.0f,
        1.0f, 0.0f
    };

    GLushort indices[] = { 0, 1, 3, 3, 1, 2 };

    GLuint vertexBufferObjID[3];
    glGenBuffers(3, vertexBufferObjID);
    
    glBindBuffer(GL_ARRAY_BUFFER, vertexBufferObjID[0]);
    glBufferData(GL_ARRAY_BUFFER, sizeof(vertices), vertices, GL_STATIC_DRAW);
    glVertexAttribPointer((GLuint)positionLocation, 2, GL_FLOAT, GL_FALSE, 0, 0);
    glEnableVertexAttribArray(positionLocation);

    glBindBuffer(GL_ARRAY_BUFFER, vertexBufferObjID[1]);
    glBufferData(GL_ARRAY_BUFFER, sizeof(texcoords), texcoords, GL_STATIC_DRAW);
    glVertexAttribPointer((GLuint)texcoordsLocation, 2, GL_FLOAT, GL_FALSE, 0, 0);
    glEnableVertexAttribArray(texcoordsLocation);

    glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, vertexBufferObjID[2]);
    glBufferData(GL_ELEMENT_ARRAY_BUFFER, sizeof(indices), indices, GL_STATIC_DRAW);
}

GLuint initShader(const char *vertexShaderPath, const char *fragmentShaderPath){
    GLuint program = glslUtility::createProgram(vertexShaderPath, fragmentShaderPath, attributeLocations, 2);
    GLint location;

    glUseProgram(program);
    
    if ((location = glGetUniformLocation(program, "u_image")) != -1)
    {
        glUniform1i(location, 0);
    }

    return program;
}

//-------------------------------
//---------CLEANUP STUFF---------
//-------------------------------

void cleanupCuda(){
  if(pbo) deletePBO(&pbo);
  if(displayImage) deleteTexture(&displayImage);
}

void deletePBO(GLuint* pbo){
  if (pbo) {
    // unregister this buffer object with CUDA
    cudaGLUnregisterBufferObject(*pbo);
    
    glBindBuffer(GL_ARRAY_BUFFER, *pbo);
    glDeleteBuffers(1, pbo);
    
    *pbo = (GLuint)NULL;
  }
}

void deleteTexture(GLuint* tex){
    glDeleteTextures(1, tex);
    *tex = (GLuint)NULL;
}
 
void shut_down(int return_code){
#ifdef __APPLE__
glfwTerminate();
#endif
  exit(return_code);
}
Something went wrong with that request. Please try again.