I am trying to do a simple calculation on a Compute Shader, where after doing one round of computation I give the result of that round back to the Shader as an Input for the second round.
My Compute shader looks like this:
#version 440 core
layout(std430, binding = 0) buffer Result{
float out_picture[];
};
layout(std430, binding = 1) buffer In_p1{
float in_p1[];
};
layout(local_size_x = 1000) in;
void main() {
in_p1[gl_GlobalInvocationID.x] = 1.0f;
out_picture[gl_GlobalInvocationID.x] = out_picture[gl_GlobalInvocationID.x] + in_p1[gl_GlobalInvocationID.x];
}
Her is my OpenGL code:
int main(int argc, char* argv[]) {
std::vector<float> result_container;
std::vector<SSBO> ssbo_container;
SSBO ssbo_result;
ssbo_result.NUM_PIX = 1920*1080*4;
ssbo_result.WORK_GROUP_SIZE = 1000;
result_container.reserve(ssbo_result.NUM_PIX * sizeof(float));
glGenBuffers(1, &ssbo_result.handle);
glBindBufferBase(GL_SHADER_STORAGE_BUFFER, 0, ssbo_result.handle);
glBufferData(GL_SHADER_STORAGE_BUFFER, ssbo_result.NUM_PIX * sizeof(float), NULL, GL_DYNAMIC_DRAW);
for(unsigned int i = 1; i < 2; i++){
SSBO ssbo;
glGenBuffers(1, &ssbo.handle);
glBindBufferBase(GL_SHADER_STORAGE_BUFFER, i, ssbo.handle);
glBufferData(GL_SHADER_STORAGE_BUFFER, ssbo_result.NUM_PIX * sizeof(float), NULL, GL_DYNAMIC_DRAW);
ssbo_container.push_back(ssbo);
}
while (!g_win.shouldClose()) {
std::cout << "container:" << result_container[0] << std::endl;
glUseProgram(g_avg_program);
glDispatchCompute(ssbo_result.NUM_PIX / ssbo_result.WORK_GROUP_SIZE, 1, 1);
glMemoryBarrier(GL_SHADER_STORAGE_BARRIER_BIT);
glBindBufferBase(GL_SHADER_STORAGE_BUFFER, 0, 0);
glBindBuffer(GL_SHADER_STORAGE_BUFFER, ssbo_result.handle);
GLfloat *ptr = (GLfloat *) glMapBuffer(GL_SHADER_STORAGE_BUFFER, GL_READ_ONLY);
memcpy(result_container.data(), ptr, ssbo_result.NUM_PIX * sizeof(float));
glUnmapBuffer(GL_SHADER_STORAGE_BUFFER);
glBindBuffer(GL_SHADER_STORAGE_BUFFER, ssbo_result.handle);
ptr = (GLfloat *) glMapBuffer(GL_SHADER_STORAGE_BUFFER, GL_WRITE_ONLY);
memcpy(ptr, result_container.data(), ssbo_result.NUM_PIX * sizeof(float));
glUnmapBuffer(GL_SHADER_STORAGE_BUFFER);
g_win.update();
if (glfwGetKey(g_win.getGLFWwindow(), GLFW_KEY_ESCAPE) == GLFW_PRESS) {
g_win.stop();
}
}
return 0;
}
After initializing the ssbo's and calling glDispatchCompute() and glMemoryBarrier(GL_SHADER_STORAGE_BARRIER_BIT) I read out the result and saving it in std::vector<float>result_container. This fills the container with 1.0f as expected for the first run, ssbo_result.handle beeing my out_picture ssbo
I then try feeding the result back in as an input into out_picture the same way I read the data out of it by just flipping the memcpy dest and source, as I understand it that I now have my previous result in the out_picture GPU Memory
As you can see I am trying to add a value (here 1.0f) to the out_picture and feed it back as an input into out_picture for the next computation. The Idea is to just add the result as an input for the next run.
I tryed doing the same with glCopyBufferSubData with the same outcome. Only 1.0 as output everytime instead of a 1, 2, 3 ...
In the while loop 0 is bound to the binding point 0, after the compute shader was launched:
while (!g_win.shouldClose()) {
....
glDispatchCompute(ssbo_result.NUM_PIX / ssbo_result.WORK_GROUP_SIZE, 1, 1);
glMemoryBarrier(GL_SHADER_STORAGE_BARRIER_BIT);
glBindBufferBase(GL_SHADER_STORAGE_BUFFER, 0, 0);
....
}
but ssbo_result.handle is never bound to the binding point 0 again. This causes that the computation operates only in the first cycle of the loop, because the binding to the shader storage buffer is broken in the further cycles of the loop.
It is completely superfluous to break the binding of the buffer, since the binding point is not used for anything else.
Delete the line glBindBufferBase(GL_SHADER_STORAGE_BUFFER, 0, 0); in the loop, to solve the issue. (Of course binding the buffer continuously at the begin of the while loop, would do the job, too - add glBindBufferBase(GL_SHADER_STORAGE_BUFFER, 0, ssbo_result.handle); before glDispatchCompute)
Related
I am using the following library to render text in OpenGL: fontstash. I have another header file which adds support for OpenGL 3.0+. The question is why is the render implementation with core profile much slower than the immediate mode?
Here is the render code with immediate mode:
static void glfons__renderDraw(void* userPtr, const float* verts, const float* tcoords, const unsigned int* colors, int nverts)
{
GLFONScontext* gl = (GLFONScontext*)userPtr;
if (gl->tex == 0) return;
glBindTexture(GL_TEXTURE_2D, gl->tex);
glEnable(GL_TEXTURE_2D);
glEnableClientState(GL_VERTEX_ARRAY);
glEnableClientState(GL_TEXTURE_COORD_ARRAY);
glEnableClientState(GL_COLOR_ARRAY);
glVertexPointer(2, GL_FLOAT, sizeof(float)*2, verts);
glTexCoordPointer(2, GL_FLOAT, sizeof(float)*2, tcoords);
glColorPointer(4, GL_UNSIGNED_BYTE, sizeof(unsigned int), colors);
glDrawArrays(GL_TRIANGLES, 0, nverts);
glDisable(GL_TEXTURE_2D);
glDisableClientState(GL_VERTEX_ARRAY);
glDisableClientState(GL_TEXTURE_COORD_ARRAY);
glDisableClientState(GL_COLOR_ARRAY);
}
Here is the core profile render code:
static void gl3fons__renderDraw(void* userPtr, const float* verts, const float* tcoords, const unsigned int* colors, int nverts)
{
GLFONScontext* gl = (GLFONScontext*)userPtr;
if (gl->tex == 0) return;
if (gl->shader == 0) return;
if (gl->vao == 0) return;
if (gl->vbo == 0) return;
// init shader
glUseProgram(gl->shader);
// init texture
glActiveTexture(GL_TEXTURE0);
glBindTexture(GL_TEXTURE_2D, gl->tex);
glUniform1i(gl->texture_uniform, 0);
// init our projection matrix
glUniformMatrix4fv(gl->projMat_uniform, 1, false, gl->projMat);
// bind our vao
glBindVertexArray(gl->vao);
// setup our buffer
glBindBuffer(GL_ARRAY_BUFFER, gl->vbo);
glBufferData(GL_ARRAY_BUFFER, (2 * sizeof(float) * 2 * nverts) + (sizeof(int) * nverts), NULL, GL_DYNAMIC_DRAW);
glBufferSubData(GL_ARRAY_BUFFER, 0, sizeof(float) * 2 * nverts, verts);
glBufferSubData(GL_ARRAY_BUFFER, sizeof(float) * 2 * nverts, sizeof(float) * 2 * nverts, tcoords);
glBufferSubData(GL_ARRAY_BUFFER, 2 * sizeof(float) * 2 * nverts, sizeof(int) * nverts, colors);
// setup our attributes
glEnableVertexAttribArray(0);
glVertexAttribPointer(0, 2, GL_FLOAT, GL_FALSE, 0, 0);
glEnableVertexAttribArray(1);
glVertexAttribPointer(1, 2, GL_FLOAT, GL_FALSE, sizeof(float) * 2, (void *) (sizeof(float) * 2 * nverts));
glEnableVertexAttribArray(2);
glVertexAttribPointer(2, 4, GL_UNSIGNED_BYTE, GL_TRUE, sizeof(int), (void *) (2 * sizeof(float) * 2 * nverts));
glDrawArrays(GL_TRIANGLES, 0, nverts);
glBindBuffer(GL_ARRAY_BUFFER, 0);
glBindVertexArray(0);
glUseProgram(0);
}
I made a small test for each implementation and the results show that immediate mode is significantly faster than core.
Both tests fill the screen with AAA... and I log the time it took to do this for each frame. This is the loop:
// Create GL stash for 512x512 texture, our coordinate system has zero at top-left.
struct FONScontext* fs = glfonsCreate(512, 512, FONS_ZERO_TOPLEFT);
// Add font to stash.
int fontNormal = fonsAddFont(fs, "sans", "fontstash/example/DroidSerif-Regular.ttf");
// Render some text
float dx = 10, dy = 10;
unsigned int white = glfonsRGBA(255,255,255,255);
std::chrono::high_resolution_clock::time_point t1 = std::chrono::high_resolution_clock::now();
fonsSetFont(fs, fontNormal);
fonsSetSize(fs, 20.0f);
fonsSetColor(fs, white);
for(int i = 0; i < 90; i++){
for( int j = 0; j < 190; j++){
dx += 10;
fonsDrawText(fs, dx, dy, "A", NULL);
}
dy += 10;
dx = 10;
}
std::chrono::high_resolution_clock::time_point t2 = std::chrono::high_resolution_clock::now();
std::chrono::duration<double, std::milli> time_span = t2 - t1;
std::cout<<"Time to render: "<<time_span.count()<<"ms"<<std::endl;
And the results show more than 400ms difference between the two:
Core profile (left) vs Immediate mode (right)
What should be changed in order to speed up performance?
I don't know exactly what gl is in this program, but it's pretty clear that, every time you want to render a piece of text, you perform the following operations:
Allocate storage for a buffer, reallocating whatever storage had been created from the last time this was called.
Perform three separate uploads of data to that buffer.
These are not good ways to stream vertex data to the GPU. There are specific techniques for doing this well, but this is not one of them. In particular, the fact that you are constantly reallocating the same buffer is going to kill performance.
The most effective way to deal with this is to have a single buffer with a fixed amount of storage. It gets allocated exactly once and never again. Ideally, whatever API you're getting vertex data from would provide it in an interleaved format, so that you would only need to perform one upload rather than three. But apparently, Fontstash is apparently not so generous.
In any case, the main idea is to avoid reallocation and synchronization. The latter means never trying to write over data that has been written to recently. So your buffer needs to be sufficiently large to hold twice the number of font vertices you ever expect to render. Essentially, you double-buffer the vertex data: writing to one set of data while the other set is being read from.
So at the beginning of the frame, you figure out what the byte offset to where you want to render will be. This will either be the start of the buffer or half-way through it. Then, for each blob of text, you write vertex data to this offset and increment the offset accordingly.
And to avoid having to change VAO state, you should interleave the vertex data manually. Instead of uploading three arrays, you should interleave the vertices so that you're effectively making one gigantic array of vertices. So you never need to call glVertexAttribPointer in the middle of this function; you just use the parameters to glDraw* to draw the part of the array you want.
This also means you only need one glBufferSubData call. But if you have access to persistent mapped buffers, you don't even need that, since you can just write to the memory directly while using the other portion of it. Though if you use persistent mapping, you will need to use a fence sync object when you switch buffer regions to make sure that you're not writing to vertex data that is still being read by the GPU.
I'm porting an older program using glBegin()/glEnd() (top picture) to glDrawArraysInstanced() (bottom picture). I expected some performance improvements, but I got the opposite. Now this is the first time I've tried using glDrawArraysInstanced() so I think I must have screwed up somewhere.
The two are basically identical and the only difference is how they draw the circles.
What have I done wrong? And if not, what makes it slower?
// This runs once at startup
std::vector<glm::mat4> transforms;
glGenBuffers(NUM_BUFFERS, VBO);
glBindBuffer(GL_ARRAY_BUFFER, VBO[TRANSFORM]);
for (int i = 0; i < 4; ++i) {
glEnableVertexAttribArray(1 + i);
glVertexAttribPointer(1 + i, 4, GL_FLOAT, GL_FALSE, sizeof(glm::mat4),
(GLvoid *)(i * sizeof(glm::vec4)));
glVertexAttribDivisor(1 + i, 1);
} // ---------
// This runs every frame
if (num_circles > transforms.size()) transforms.resize(num_circles);
int i = 0;
for (const auto &circle : circle_vec) {
transforms[i++] = circle.transform.getModel();
}
glBindBuffer(GL_ARRAY_BUFFER, VBO[TRANSFORM]);
glBufferData(GL_ARRAY_BUFFER, sizeof(glm::mat4) * num_circles, &transforms[0], GL_DYNAMIC_DRAW);
glBindBuffer(GL_ARRAY_BUFFER, 0);
glBindVertexArray(VAO);
glDrawArraysInstanced(GL_LINE_LOOP, 0, CIRCLE_NUM_VERTICES, num_circles);
glBindVertexArray(0);
// ---------
// And this is the vertex shader
#version 410
in vec3 position;
in mat4 transform;
void main()
{
gl_Position = transform * vec4(position, 1.0);
}
What I saw at my first glimpse is that you are creating a new vector on every frame. Consider caching it.
// This runs every frame
std::vector<glm::mat4> transforms;
In my base program (C++/OpenGL 4.5) I have copied the content of the Vertex Buffer to an Shader Storage Buffer (SSBO):
float* buffer = (float*) glMapBuffer(GL_ARRAY_BUFFER, GL_READ_ONLY);
glBindBufferBase(GL_SHADER_STORAGE_BUFFER, 3, ssbo[2]);
glBufferData(GL_SHADER_STORAGE_BUFFER, sizeof(GLfloat)*size,buffer, GL_DYNAMIC_DRAW);
glBindBufferBase(GL_SHADER_STORAGE_BUFFER, 3, 0);
glUnmapBuffer(GL_ARRAY_BUFFER);
In the Vertex Shader this data is bound to an array:
#version 430
#extension GL_ARB_shader_storage_buffer_object : require
layout(shared, binding = 3) buffer storage
{
float array[];
}
But when I'm trying to overwrite an array entry in the main function like this:
array[index_in_bounds] = 4.2;
nothing happens.
What am I doing wrong? Can I change the buffer from within the Vertex Shader? Is this only possible in a Geometry Shader? Do I have to do this with Transform Feedback (that I have never used before)?
edit:
I'm mapping the buffers for test purposes in my main program, just to see if the data changes:
float* buffer = (float*) glMapBuffer(GL_ARRAY_BUFFER, GL_READ_ONLY);
float* ssbo = (float*) glMapNamedBuffer(3, GL_READ_ONLY);
for(int i = 0; i < SIZE_OF_BUFFERS; i++)
printf("% 5f | % 5f\n", ssbo[i], buffer[i]);
glUnmapNamedBuffer(3);
glUnmapBuffer(GL_ARRAY_BUFFER);
Okay, I have found the problem using the red book. I have not bound the buffer correctly and binding the buffer base has to happen after buffering the data:
float* buffer = (float*) glMapBuffer(GL_ARRAY_BUFFER, GL_READ_ONLY);
glBindBuffer(GL_SHADER_STORAGE_BUFFER, &ssbo); // bind buffer
// switched these two:
glBufferData(GL_SHADER_STORAGE_BUFFER, sizeof(GLfloat)*size,buffer, GL_DYNAMIC_DRAW);
glBindBufferBase(GL_SHADER_STORAGE_BUFFER, 3, &ssbo);
glBindBuffer(GL_SHADER_STORAGE_BUFFER, 0); // unbind buffer
glUnmapBuffer(GL_ARRAY_BUFFER);
I am trying to render 3D models with textures using Assimp. The conversion goes perfect, all textures positions and what not gets loaded. I have tested the texture images by drawing them to the screen in 2D.
For some reason it does not render the textures to the model.
I am a beginner in OpenGL so forgive me if i dont explain it right.
The tutorial I have based the code on is from here, but i stripped a big part since I have my own camera/movement system.
The model renders like this: http://i.stack.imgur.com/5sK9K.png
whilest the texture in use looks like this: http://i.stack.imgur.com/sWGp7.jpg
The relevant rendering code is the following:
Generating textures from data file:
int Mesh::LoadGLTextures(const aiScene* scene){
if (scene->HasTextures()) return -1; //yes this is correct
/* getTexture Filenames and Numb of Textures */
for (unsigned int m = 0; m<scene->mNumMaterials; m++){
int texIndex = 0;
aiReturn texFound;
aiString path; // filename
while ((texFound = scene->mMaterials[m]->GetTexture(aiTextureType_DIFFUSE, texIndex, &path)) == AI_SUCCESS){
textureIdMap[path.data] = NULL; //fill map with textures, pointers still NULL yet
texIndex++;
}
}
int numTextures = textureIdMap.size();
/* create and fill array with GL texture ids */
GLuint* textureIds = new GLuint[numTextures];
/* get iterator */
std::map<std::string, GLuint>::iterator itr = textureIdMap.begin();
std::string basepath = getBasePath(path);
ALLEGRO_BITMAP *image;
for (int i = 0; i<numTextures; i++){
std::string filename = (*itr).first; // get filename
(*itr).second = textureIds[i]; // save texture id for filename in map
itr++; // next texture
std::string fileloc = basepath + filename; /* Loading of image */
image = al_load_bitmap(fileloc.c_str());
if (image) /* If no error occured: */{
GLuint texId = al_get_opengl_texture(image);
//glGenTextures(numTextures, &textureIds[i]); /* Texture name generation */
glBindTexture(GL_TEXTURE_2D, texId); /* Binding of texture name */
//redefine standard texture values
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_LINEAR); /* We will use linear
interpolation for magnification filter */
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_LINEAR); /* We will use linear
interpolation for minifying filter */
textureIdMap[filename] = texId;
} else {
/* Error occured */
std::cout << "Couldn't load Image: " << fileloc.c_str() << "\n";
}
}
//Cleanup
delete[] textureIds;
//return success
return true;
}
Generating VBO/VAO:
void Mesh::genVAOsAndUniformBuffer(const aiScene *sc) {
struct MyMesh aMesh;
struct MyMaterial aMat;
GLuint buffer;
// For each mesh
for (unsigned int n = 0; n < sc->mNumMeshes; ++n){
const aiMesh* mesh = sc->mMeshes[n];
// create array with faces
// have to convert from Assimp format to array
unsigned int *faceArray;
faceArray = (unsigned int *)malloc(sizeof(unsigned int) * mesh->mNumFaces * 3);
unsigned int faceIndex = 0;
for (unsigned int t = 0; t < mesh->mNumFaces; ++t) {
const aiFace* face = &mesh->mFaces[t];
memcpy(&faceArray[faceIndex], face->mIndices, 3 * sizeof(unsigned int));
faceIndex += 3;
}
aMesh.numFaces = sc->mMeshes[n]->mNumFaces;
// generate Vertex Array for mesh
glGenVertexArrays(1, &(aMesh.vao));
glBindVertexArray(aMesh.vao);
// buffer for faces
glGenBuffers(1, &buffer);
glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, buffer);
glBufferData(GL_ELEMENT_ARRAY_BUFFER, sizeof(unsigned int) * mesh->mNumFaces * 3, faceArray, GL_STATIC_DRAW);
// buffer for vertex positions
if (mesh->HasPositions()) {
glGenBuffers(1, &buffer);
glBindBuffer(GL_ARRAY_BUFFER, buffer);
glBufferData(GL_ARRAY_BUFFER, sizeof(float) * 3 * mesh->mNumVertices, mesh->mVertices, GL_STATIC_DRAW);
glEnableVertexAttribArray(vertexLoc);
glVertexAttribPointer(vertexLoc, 3, GL_FLOAT, 0, 0, 0);
}
// buffer for vertex normals
if (mesh->HasNormals()) {
glGenBuffers(1, &buffer);
glBindBuffer(GL_ARRAY_BUFFER, buffer);
glBufferData(GL_ARRAY_BUFFER, sizeof(float) * 3 * mesh->mNumVertices, mesh->mNormals, GL_STATIC_DRAW);
glEnableVertexAttribArray(normalLoc);
glVertexAttribPointer(normalLoc, 3, GL_FLOAT, 0, 0, 0);
}
// buffer for vertex texture coordinates
if (mesh->HasTextureCoords(0)) {
float *texCoords = (float *)malloc(sizeof(float) * 2 * mesh->mNumVertices);
for (unsigned int k = 0; k < mesh->mNumVertices; ++k) {
texCoords[k * 2] = mesh->mTextureCoords[0][k].x;
texCoords[k * 2 + 1] = mesh->mTextureCoords[0][k].y;
}
glGenBuffers(1, &buffer);
glEnableVertexAttribArray(texCoordLoc);
glBindBuffer(GL_ARRAY_BUFFER, buffer);
glBufferData(GL_ARRAY_BUFFER, sizeof(float) * 2 * mesh->mNumVertices, texCoords, GL_STATIC_DRAW);
glVertexAttribPointer(texCoordLoc, 2, GL_FLOAT, GL_FALSE, 0, 0);
}
// unbind buffers
glBindVertexArray(0);
glBindBuffer(GL_ARRAY_BUFFER, 0);
glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, 0);
// create material uniform buffer
aiMaterial *mtl = sc->mMaterials[mesh->mMaterialIndex];
aiString texPath; //contains filename of texture
if (AI_SUCCESS == mtl->GetTexture(aiTextureType_DIFFUSE, 0, &texPath)){
//bind texture
unsigned int texId = textureIdMap[texPath.data];
aMesh.texIndex = texId;
aMat.texCount = 1;
} else {
aMat.texCount = 0;
}
float c[4];
set_float4(c, 0.8f, 0.8f, 0.8f, 1.0f);
aiColor4D diffuse;
if (AI_SUCCESS == aiGetMaterialColor(mtl, AI_MATKEY_COLOR_DIFFUSE, &diffuse))
color4_to_float4(&diffuse, c);
memcpy(aMat.diffuse, c, sizeof(c));
set_float4(c, 0.2f, 0.2f, 0.2f, 1.0f);
aiColor4D ambient;
if (AI_SUCCESS == aiGetMaterialColor(mtl, AI_MATKEY_COLOR_AMBIENT, &ambient))
color4_to_float4(&ambient, c);
memcpy(aMat.ambient, c, sizeof(c));
set_float4(c, 0.0f, 0.0f, 0.0f, 1.0f);
aiColor4D specular;
if (AI_SUCCESS == aiGetMaterialColor(mtl, AI_MATKEY_COLOR_SPECULAR, &specular))
color4_to_float4(&specular, c);
memcpy(aMat.specular, c, sizeof(c));
set_float4(c, 0.0f, 0.0f, 0.0f, 1.0f);
aiColor4D emission;
if (AI_SUCCESS == aiGetMaterialColor(mtl, AI_MATKEY_COLOR_EMISSIVE, &emission))
color4_to_float4(&emission, c);
memcpy(aMat.emissive, c, sizeof(c));
float shininess = 0.0;
unsigned int max;
aiGetMaterialFloatArray(mtl, AI_MATKEY_SHININESS, &shininess, &max);
aMat.shininess = shininess;
glGenBuffers(1, &(aMesh.uniformBlockIndex));
glBindBuffer(GL_UNIFORM_BUFFER, aMesh.uniformBlockIndex);
glBufferData(GL_UNIFORM_BUFFER, sizeof(aMat), (void *)(&aMat), GL_STATIC_DRAW);
myMeshes.push_back(aMesh);
}
}
Rendering model:
void Mesh::recursive_render(const aiScene *sc, const aiNode* nd){
// draw all meshes assigned to this node
for (unsigned int n = 0; n < nd->mNumMeshes; ++n){
glEnable(GL_TEXTURE_2D);
glBindTexture(GL_TEXTURE_2D, myMeshes[nd->mMeshes[n]].texIndex);
// bind VAO
glBindVertexArray(myMeshes[nd->mMeshes[n]].vao);
// draw
glDrawElements(GL_TRIANGLES, myMeshes[nd->mMeshes[n]].numFaces * 3, GL_UNSIGNED_INT, 0);
}
// draw all children
for (unsigned int n = 0; n < nd->mNumChildren; ++n){
recursive_render(sc, nd->mChildren[n]);
}
}
Any other relevant code parts can be found in my open github project https://github.com/kwek20/StrategyGame/tree/master/Strategy
Mesh.cpp is relevant, as well as main.cpp and Camera.cpp.
As far as I understaind I followed the guidelines well, created a VAO, created VBOs, added data and enabled the proper vertex array attriute tot render the scene with.
I have checked all the data variables and everything is filled according to plan
Could anyone here spot the mistake I have made and or explain it?
Some links are typed weird because of the limit I have :(
It would help if you posted your shaders also.
I can post some rendering code with textures if that helps you out:
Generating the texture for opengl and loading a grayscale (UC8) image with width and height into the GPU
void GLRenderer::getTexture(unsigned char * image, int width, int height)
{
glActiveTexture(GL_TEXTURE0);
glGenTextures(1, &mTextureID);
glBindTexture(GL_TEXTURE_2D, mTextureID);
glTexStorage2D(GL_TEXTURE_2D, 1, GL_RGB8, width, height);
glTexSubImage2D(GL_TEXTURE_2D, 0, 0, 0, width, height, GL_BGR, GL_UNSIGNED_BYTE, image);
if (aux::checkGlErrors(__LINE__, __FILE__))assert(false);
glBindTexture(GL_TEXTURE_2D, 0);
}
Loading the vertices from assimp onto the gpu
//** buffer a obj file-style model, initialize the VAO
void GLRenderer::bufferModel(float* aVertexArray, int aNumberOfVertices, float* aNormalArray, int aNumberOfNormals, float* aUVList, int aNumberOfUVs, unsigned int* aIndexList, int aNumberOfIndices)
{
//** just to be sure we are current
glfwMakeContextCurrent(mWin);
//** Buffer all data in VBOs
glGenBuffers(1, &mVertex_buffer_object);
glBindBuffer(GL_ARRAY_BUFFER, mVertex_buffer_object);
glBufferData(GL_ARRAY_BUFFER, sizeof(float) * aNumberOfVertices * 3, aVertexArray, GL_STATIC_DRAW);
glGenBuffers(1, &mNormal_buffer_object);
glBindBuffer(GL_ARRAY_BUFFER, mNormal_buffer_object);
glBufferData(GL_ARRAY_BUFFER, sizeof(float) * aNumberOfNormals * 3, aNormalArray, GL_STATIC_DRAW);
glGenBuffers(1, &mUV_buffer_object);
glBindBuffer(GL_ARRAY_BUFFER, mUV_buffer_object);
glBufferData(GL_ARRAY_BUFFER, sizeof(float) * aNumberOfUVs * 2, aUVList, GL_STATIC_DRAW);
glGenBuffers(1, &mIndex_buffer_object);
glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, mIndex_buffer_object);
glBufferData(GL_ELEMENT_ARRAY_BUFFER, sizeof(unsigned int) * aNumberOfIndices, aIndexList, GL_STATIC_DRAW);
if (aux::checkGlErrors(__LINE__, __FILE__))assert(false);
//** VAO tells our shaders how to match up data from buffer to shader input variables
glGenVertexArrays(1, &mVertex_array_object);
glBindVertexArray(mVertex_array_object);
//** vertices first
glEnableVertexAttribArray(0);
glBindBuffer(GL_ARRAY_BUFFER, mVertex_buffer_object);
glVertexAttribPointer(0, 3, GL_FLOAT, GL_FALSE, 0, NULL);
//** normals next
if (aNumberOfNormals > 0){
glEnableVertexAttribArray(1);
glBindBuffer(GL_ARRAY_BUFFER, mNormal_buffer_object);
glVertexAttribPointer(1, 3, GL_FLOAT, GL_FALSE, 0, NULL);
}
//** UVs last
if (aNumberOfUVs > 0){
glEnableVertexAttribArray(2);
glBindBuffer(GL_ARRAY_BUFFER, mUV_buffer_object);
glVertexAttribPointer(2, 2, GL_FLOAT, GL_FALSE, 0, NULL);
}
//** indexing for reusing vertices in triangle-meshes
glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, mIndex_buffer_object);
//** check errors and store the number of vertices
if (aux::checkGlErrors(__LINE__, __FILE__))assert(false);
mNumVert = aNumberOfVertices;
mNumNormals = aNumberOfNormals;
mNumUVs = aNumberOfUVs;
mNumIndices = aNumberOfIndices;
}
The code above is called like:
//read vertices from file
std::vector<float> vertex, normal, uv;
std::vector<unsigned int> index;
//assimp-wrapping function to load obj to vectors
aux::loadObjToVectors("Resources\\vertices\\model.obj", vertex, normal, index, uv);
mPtr->bufferModel(&vertex[0], static_cast<int>(vertex.size()) / 3, &normal[0], static_cast<int>(normal.size()) / 3, &uv[0], static_cast<int>(uv.size()) / 2, &index[0], static_cast<int>(index.size()));
Then comes the shader-part:
In the vertex shader you just hand-through the UV-coordinate layer
#version 400 core
layout (location = 0) in vec3 vertexPosition_modelspace;
layout (location = 1) in vec3 vertexNormal_modelspace;
layout (location = 2) in vec2 vertexUV;
out vec2 UV;
[... in main then ...]
UV = vertexUV;
While in the fragment shader you assign the value to the pixel:
#version 400 core
in vec2 UV;
uniform sampler2D textureSampler;
layout(location = 0) out vec4 outColor;
[... in main then ...]
// you probably want to calculate lighting here then too, so its just the simplest way to get the texture inside
outColor = vec4(texture2D(textureSampler, UV).rgb, cosAngle);
//you can also check whether the UV coords are correctly bound by using:
outColor = vec4(UV.x, UV.y,1,1);
//and then checking the pixel-values in the resulting image (e.g. render it to a PBO and then download it onto the CPU for)
In the rendering loop also make sure that all the uniforms are correctly bound (especially texture related ones) and that the texture is active and bound
if (mTextureID != -1) {
glActiveTexture(GL_TEXTURE0);
glBindTexture(GL_TEXTURE_2D, mTextureID);
}
GLint textureLocation = glGetUniformLocation(mShaderProgram, "textureSampler");
glUniform1i(textureLocation, 0);
//**set the poligon mode
glPolygonMode(GL_FRONT_AND_BACK, GL_FILL);
//**drawElements because of indexing
glDrawElements(GL_TRIANGLES, mNumIndices, GL_UNSIGNED_INT, 0);
I hope I could help you!
Kind regards,
VdoP
I have trouble rendering some geometry by using a vertex buffer object. I intend to draw a plane of points, so basically one vertex at every discrete position in my space. However, I cannot render that plane, as every time I call glDrawElements(...), application crashes returning an access violation exception. There must be some mistake while initialization, I guess.
This is what I have so far:
#define SPACE_X 512
#define SPACE_Z 512
typedef struct{
GLfloat x, y, z; // position
GLfloat nx, ny, nz; // normals
GLfloat r, g, b, a; // colors
} Vertex;
typedef struct{
GLuint i; // index
} Index;
// create vertex buffer
GLuint vertexBufferObject;
glGenBuffers(1, &vertexBufferObject);
// create index buffer
GLuint indexBufferObject;
glGenBuffers(1, &indexBufferObject);
// determine number of vertices / primitives
const int numberOfVertices = SPACE_X * SPACE_Z;
const int numberOfPrimitives = numberOfVertices; // As I'm going to render GL_POINTS, number of primitives is the same as number of vertices
// create vertex array
Vertex* vertexArray = new Vertex[numberOfVertices];
// create index array
Index* indexArray = new Index[numberOfPrimitives];
// create planes (vertex array)
// color of the vertices is red for now
int index = -1;
for(GLfloat x = -SPACE_X / 2; x < SPACE_X / 2; x++) {
for(GLfloat z = -SPACE_Z / 2; z < SPACE_Z / 2; z++) {
index++;
vertexArray[index].x = x;
vertexArray[index].y = 0.0f;
vertexArray[index].z = z;
vertexArray[index].nx = 0.0f;
vertexArray[index].ny = 0.0f;
vertexArray[index].nz = 1.0f;
vertexArray[index].r = 1.0;
vertexArray[index].g = 0.0;
vertexArray[index].b = 0.0;
vertexArray[index].a = 1.0;
}
}
// bind vertex buffer
glBindBuffer(GL_ARRAY_BUFFER, vertexBufferObject);
// buffer vertex array
glBufferData(GL_ARRAY_BUFFER, numberOfVertices * sizeof(Vertex), vertexArray, GL_DTREAM_DRAW);
// bind vertex buffer again
glBindBuffer(GL_ARRAY_BUFFER, vertexBufferObject);
// enable attrib index 0 (positions)
glEnableVertexAttribArray(0);
// pass positions in
glVertexAttribPointer((GLuint)0, 3, GL_FLOAT, GL_FALSE, sizeof(Vertex), vertexArray);
// enable attribute index 1 (normals)
glEnableVertexAttribArray(1);
// pass normals in
glVertexAttribPointer((GLuint)1, 3, GL_FLOAT, GL_FALSE, sizeof(Vertex), &vertexArray[0].nx);
// enable attribute index 2 (colors)
glEnableVertexAttribArray(2);
// pass colors in
glVertexAttribPointer((GLuint)2, 4, GL_FLOAT, GL_FALSE, sizeof(Vertex), &vertexArray[0].r);
// create index array
for(GLunit i = 0; i < numberOfPrimitives; i++) {
indexArray[i].i = i;
}
// bind buffer
glBindBuffer(GL_ELEMENET_ARRAY_BUFFER, indexBufferObject);
// buffer indices
glBufferData(GL_ELEMENET_ARRAY_BUFFER, numberOfPrimitives * sizeof(Index), indexArray, GL_STREAM_DRAW);
// bind buffer again
glBindBuffer(GL_ELEMENET_ARRAY_BUFFER, indexBufferObject);
// AND HERE IT CRASHES!
// draw plane of GL_POINTS
glDrawElements(GL_POINTS, numberOfPrimitives, GL_UNSIGNED_INT, indexArray);
// bind default buffers
glBindBuffer(GL_ARRAY_BUFFER, 0);
glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, 0);
// delete vertex / index buffers
glDeleteBuffers(1, &vertexBufferObject);
glDeleteBuffers(1, &indexBufferObject);
delete[] vertexArray;
vertexArray = NULL;
delete[] indexArray;
indexArray = NULL;
When you are using buffer objects, the last parameters in the gl*Pointer and 4th parameter in glDrawElements are no longer addresses in main memory (yours still are!), but offsets into the buffer objects. Make sure to compute these offsets in bytes! The "offsetof" macro is very helpful there.
Look at the second example on this page and compare it to what you did: http://www.opengl.org/wiki/VBO_-_just_examples
And you have one typo: GL_DTREAM_DRAW.
The method glEnableClientState(...) is deprecated! Sorry, for some reason I had overseen that fact.