Sign in to follow this  
Nairou

OpenGL Expense of modifying/replacing loaded textures

Recommended Posts

How well does OpenGL (3.2, if it matters) handle modifying or replacing textures that have already been uploaded to the GPU?

 

I always had the impression that messing with textures was always much more expensive than replacing VBO data, even if the texture is far smaller in byte size, but I'm starting to think this might not be the case.

 

Is there perhaps a list somewhere that shows what sort of operations are most expensive in OpenGL?

 

For context, I'm working on a terrain system where the terrain colors can change frequently. I figure I can either do texture mapping, and modify the texture pixels, or put the color in the terrain vertices and rebuild the VBO for each change. I'm accustomed to continually rebuilding dynamic VBOs for other tasks, but in this case I am thinking that a texture would be a lot less data to upload than the block of geometry.

 

Share this post


Link to post
Share on other sites

you may need to test this...

 

for example, I have had reasonably good success doing things like streaming videos into textures (such as 8 video streams at a time), but on some older hardware (~ 10 years ago), this would put some hurt on the performance.

Share this post


Link to post
Share on other sites
This is one of those things that could be reasonably cheap or could be horribly expensive, depending how you need to do the update, what formats you use, and so on.

First thing is to batch up your updates. A single glTexSubImage call updating the entire texture will perform better than lots of calls updating tiny subrects of it.

Try to divide your workload into updating, then drawing. If you need to update/draw/update/draw/etc your performance will tank, especially on Intel or AMD hardware (NV tolerates this pattern better, but it's still a slower path).

Watch your formats; you absolutely must match the data you feed to glTexSubImage with the drivers preferred internal representation. Normally that means using a BGRA format. Don't fall into the trap of using RGB because you think it will "save memory" - the driver will need to unpack and reswizzle the data as a slow software process and again your performance will tank. Experiment with different values for the type param - GL_UNSIGNED_INT_8_8_8_8_REV can work well here.

Finally, and if you can schedule the update for a few frames ahead of when the texture is needed, consider using a PBO to get an asynchronous transfer. If you need to update in the same frame as the texture is used don't bother with the PBO - it's just extra overhead.

Share this post


Link to post
Share on other sites

The OpenGL drivers are one factor, which means it depends on a very wide number of factors, so what works best for you may not for another.

 

One universal truth however is that if you update a texture while it is still being used by the GPU the GPU will perform a synchronous flush in order to allow you to update the texture safely on the CPU side.

 

This will be terrible performance no matter what API you use or hardware you have etc.

 

If you need to update the texture frequently or if your updates always cover the whole body of the texture, you should double-buffer the texture, or possibly triple-buffer it.

 

 

L. Spiro

Share this post


Link to post
Share on other sites

One universal truth however is that if you update a texture while it is still being used by the GPU the GPU will perform a synchronous flush in order to allow you to update the texture safely on the CPU side.

 

I would hope that in this case drivers are at least reasonably intelligent and copy off the data to temp storage for updating at a later time when the resource is no longer in use (similar to the D3D10+ case for UpdateSubresource where there is contention, although unfortunately OpenGL doesn't seem to specify a behaviour here).

Share this post


Link to post
Share on other sites

One universal truth however is that if you update a texture while it is still being used by the GPU the GPU will perform a synchronous flush in order to allow you to update the texture safely on the CPU side.

 

I would hope that in this case drivers are at least reasonably intelligent and copy off the data to temp storage for updating at a later time when the resource is no longer in use (similar to the D3D10+ case for UpdateSubresource where there is contention, although unfortunately OpenGL doesn't seem to specify a behaviour here).

 

when messing around with multithreaded OpenGL and texture uploading (with the rendering and texture-uploading being done in different threads), I observed some interesting behaviors here:

the glTexImage2d() or glCompressedTexImage2d() calls were completing immediately;

within the main render thread, it would often be up to several seconds later until the texture image actually appeared (otherwise, it would be the prior contents and/or garbage).

 

typically, having the uploader threads call glFinish() would cause them to stall temporarily, but results in the next frame in all of the textures being correct.

 

judging by this, I suspect the driver is lazily updating the textures in this case.

 

 

I am less certain what happens in the single-threaded case, but have made another general observation:

if you do something, and try to immediately make use of the results, there will be a stall.

 

this seems to happen with both VBOs and also things like occlusion queries, like there is a delay between when the upload call is made, and when it can be bound or used.

typically, in my case this means "batching" things and doing them in a partly interleaved order (say, all the draw requests for occlusion queries before fetching any of the results, or uploading all the updated VBOs before the rest of the drawing pass begins, ...).

 

granted, I am not sure how much of this is driver/hardware specific. in this case, I am using a GeForce GTX 460...

Edited by cr88192

Share this post


Link to post
Share on other sites

If you need to update the texture frequently or if your updates always cover the whole body of the texture, you should double-buffer the texture, or possibly triple-buffer it.

 

Very interesting, I didn't know textures could be double-buffered. Do you have any links on doing this in OpenGL?

Share this post


Link to post
Share on other sites

If you need to update the texture frequently or if your updates always cover the whole body of the texture, you should double-buffer the texture, or possibly triple-buffer it.

 

Very interesting, I didn't know textures could be double-buffered. Do you have any links on doing this in OpenGL?

 

There's no specific OpenGL technique for this.  Instead you allocate two textures (let's call them 0 and 1), then update texture 0/draw using texture 1 and vice-versa on alternate frames.

Share this post


Link to post
Share on other sites

There's no specific OpenGL technique for this.  Instead you allocate two textures (let's call them 0 and 1), then update texture 0/draw using texture 1 and vice-versa on alternate frames.

 

But I'm assuming you can't have both textures bound for this to work, right? If you updated texture 0, and the shaders knew to only sample from texture 1 this frame, would the GPU really know that texture 0 wasn't accessed? Or would you still end up with a synchronous flush from updating texture 0?

Share this post


Link to post
Share on other sites

There's no specific OpenGL technique for this.  Instead you allocate two textures (let's call them 0 and 1), then update texture 0/draw using texture 1 and vice-versa on alternate frames.

 

But I'm assuming you can't have both textures bound for this to work, right? If you updated texture 0, and the shaders knew to only sample from texture 1 this frame, would the GPU really know that texture 0 wasn't accessed? Or would you still end up with a synchronous flush from updating texture 0?

 

AFAICT, "the magic" happens when you try to bind and draw using the texture or similar.

so, if the texture is updated but never used, there wont really be a stall (and the driver will update it later at some point).

Edited by cr88192

Share this post


Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

Sign in to follow this  

  • Forum Statistics

    • Total Topics
      628291
    • Total Posts
      2981862
  • Similar Content

    • By mellinoe
      Hi all,
      First time poster here, although I've been reading posts here for quite a while. This place has been invaluable for learning graphics programming -- thanks for a great resource!
      Right now, I'm working on a graphics abstraction layer for .NET which supports D3D11, Vulkan, and OpenGL at the moment. I have implemented most of my planned features already, and things are working well. Some remaining features that I am planning are Compute Shaders, and some flavor of read-write shader resources. At the moment, my shaders can just get simple read-only access to a uniform (or constant) buffer, a texture, or a sampler. Unfortunately, I'm having a tough time grasping the distinctions between all of the different kinds of read-write resources that are available. In D3D alone, there seem to be 5 or 6 different kinds of resources with similar but different characteristics. On top of that, I get the impression that some of them are more or less "obsoleted" by the newer kinds, and don't have much of a place in modern code. There seem to be a few pivots:
      The data source/destination (buffer or texture) Read-write or read-only Structured or unstructured (?) Ordered vs unordered (?) These are just my observations based on a lot of MSDN and OpenGL doc reading. For my library, I'm not interested in exposing every possibility to the user -- just trying to find a good "middle-ground" that can be represented cleanly across API's which is good enough for common scenarios.
      Can anyone give a sort of "overview" of the different options, and perhaps compare/contrast the concepts between Direct3D, OpenGL, and Vulkan? I'd also be very interested in hearing how other folks have abstracted these concepts in their libraries.
    • By aejt
      I recently started getting into graphics programming (2nd try, first try was many years ago) and I'm working on a 3d rendering engine which I hope to be able to make a 3D game with sooner or later. I have plenty of C++ experience, but not a lot when it comes to graphics, and while it's definitely going much better this time, I'm having trouble figuring out how assets are usually handled by engines.
      I'm not having trouble with handling the GPU resources, but more so with how the resources should be defined and used in the system (materials, models, etc).
      This is my plan now, I've implemented most of it except for the XML parts and factories and those are the ones I'm not sure of at all:
      I have these classes:
      For GPU resources:
      Geometry: holds and manages everything needed to render a geometry: VAO, VBO, EBO. Texture: holds and manages a texture which is loaded into the GPU. Shader: holds and manages a shader which is loaded into the GPU. For assets relying on GPU resources:
      Material: holds a shader resource, multiple texture resources, as well as uniform settings. Mesh: holds a geometry and a material. Model: holds multiple meshes, possibly in a tree structure to more easily support skinning later on? For handling GPU resources:
      ResourceCache<T>: T can be any resource loaded into the GPU. It owns these resources and only hands out handles to them on request (currently string identifiers are used when requesting handles, but all resources are stored in a vector and each handle only contains resource's index in that vector) Resource<T>: The handles given out from ResourceCache. The handles are reference counted and to get the underlying resource you simply deference like with pointers (*handle).  
      And my plan is to define everything into these XML documents to abstract away files:
      Resources.xml for ref-counted GPU resources (geometry, shaders, textures) Resources are assigned names/ids and resource files, and possibly some attributes (what vertex attributes does this geometry have? what vertex attributes does this shader expect? what uniforms does this shader use? and so on) Are reference counted using ResourceCache<T> Assets.xml for assets using the GPU resources (materials, meshes, models) Assets are not reference counted, but they hold handles to ref-counted resources. References the resources defined in Resources.xml by names/ids. The XMLs are loaded into some structure in memory which is then used for loading the resources/assets using factory classes:
      Factory classes for resources:
      For example, a texture factory could contain the texture definitions from the XML containing data about textures in the game, as well as a cache containing all loaded textures. This means it has mappings from each name/id to a file and when asked to load a texture with a name/id, it can look up its path and use a "BinaryLoader" to either load the file and create the resource directly, or asynchronously load the file's data into a queue which then can be read from later to create the resources synchronously in the GL context. These factories only return handles.
      Factory classes for assets:
      Much like for resources, these classes contain the definitions for the assets they can load. For example, with the definition the MaterialFactory will know which shader, textures and possibly uniform a certain material has, and with the help of TextureFactory and ShaderFactory, it can retrieve handles to the resources it needs (Shader + Textures), setup itself from XML data (uniform values), and return a created instance of requested material. These factories return actual instances, not handles (but the instances contain handles).
       
       
      Is this a good or commonly used approach? Is this going to bite me in the ass later on? Are there other more preferable approaches? Is this outside of the scope of a 3d renderer and should be on the engine side? I'd love to receive and kind of advice or suggestions!
      Thanks!
    • By nedondev
      I 'm learning how to create game by using opengl with c/c++ coding, so here is my fist game. In video description also have game contain in Dropbox. May be I will make it better in future.
      Thanks.
    • By Abecederia
      So I've recently started learning some GLSL and now I'm toying with a POM shader. I'm trying to optimize it and notice that it starts having issues at high texture sizes, especially with self-shadowing.
      Now I know POM is expensive either way, but would pulling the heightmap out of the normalmap alpha channel and in it's own 8bit texture make doing all those dozens of texture fetches more cheap? Or is everything in the cache aligned to 32bit anyway? I haven't implemented texture compression yet, I think that would help? But regardless, should there be a performance boost from decoupling the heightmap? I could also keep it in a lower resolution than the normalmap if that would improve performance.
      Any help is much appreciated, please keep in mind I'm somewhat of a newbie. Thanks!
    • By test opty
      Hi,
      I'm trying to learn OpenGL through a website and have proceeded until this page of it. The output is a simple triangle. The problem is the complexity.
      I have read that page several times and tried to analyse the code but I haven't understood the code properly and completely yet. This is the code:
       
      #include <glad/glad.h> #include <GLFW/glfw3.h> #include <C:\Users\Abbasi\Desktop\std_lib_facilities_4.h> using namespace std; //****************************************************************************** void framebuffer_size_callback(GLFWwindow* window, int width, int height); void processInput(GLFWwindow *window); // settings const unsigned int SCR_WIDTH = 800; const unsigned int SCR_HEIGHT = 600; const char *vertexShaderSource = "#version 330 core\n" "layout (location = 0) in vec3 aPos;\n" "void main()\n" "{\n" " gl_Position = vec4(aPos.x, aPos.y, aPos.z, 1.0);\n" "}\0"; const char *fragmentShaderSource = "#version 330 core\n" "out vec4 FragColor;\n" "void main()\n" "{\n" " FragColor = vec4(1.0f, 0.5f, 0.2f, 1.0f);\n" "}\n\0"; //******************************* int main() { // glfw: initialize and configure // ------------------------------ glfwInit(); glfwWindowHint(GLFW_CONTEXT_VERSION_MAJOR, 3); glfwWindowHint(GLFW_CONTEXT_VERSION_MINOR, 3); glfwWindowHint(GLFW_OPENGL_PROFILE, GLFW_OPENGL_CORE_PROFILE); // glfw window creation GLFWwindow* window = glfwCreateWindow(SCR_WIDTH, SCR_HEIGHT, "My First Triangle", nullptr, nullptr); if (window == nullptr) { cout << "Failed to create GLFW window" << endl; glfwTerminate(); return -1; } glfwMakeContextCurrent(window); glfwSetFramebufferSizeCallback(window, framebuffer_size_callback); // glad: load all OpenGL function pointers if (!gladLoadGLLoader((GLADloadproc)glfwGetProcAddress)) { cout << "Failed to initialize GLAD" << endl; return -1; } // build and compile our shader program // vertex shader int vertexShader = glCreateShader(GL_VERTEX_SHADER); glShaderSource(vertexShader, 1, &vertexShaderSource, nullptr); glCompileShader(vertexShader); // check for shader compile errors int success; char infoLog[512]; glGetShaderiv(vertexShader, GL_COMPILE_STATUS, &success); if (!success) { glGetShaderInfoLog(vertexShader, 512, nullptr, infoLog); cout << "ERROR::SHADER::VERTEX::COMPILATION_FAILED\n" << infoLog << endl; } // fragment shader int fragmentShader = glCreateShader(GL_FRAGMENT_SHADER); glShaderSource(fragmentShader, 1, &fragmentShaderSource, nullptr); glCompileShader(fragmentShader); // check for shader compile errors glGetShaderiv(fragmentShader, GL_COMPILE_STATUS, &success); if (!success) { glGetShaderInfoLog(fragmentShader, 512, nullptr, infoLog); cout << "ERROR::SHADER::FRAGMENT::COMPILATION_FAILED\n" << infoLog << endl; } // link shaders int shaderProgram = glCreateProgram(); glAttachShader(shaderProgram, vertexShader); glAttachShader(shaderProgram, fragmentShader); glLinkProgram(shaderProgram); // check for linking errors glGetProgramiv(shaderProgram, GL_LINK_STATUS, &success); if (!success) { glGetProgramInfoLog(shaderProgram, 512, nullptr, infoLog); cout << "ERROR::SHADER::PROGRAM::LINKING_FAILED\n" << infoLog << endl; } glDeleteShader(vertexShader); glDeleteShader(fragmentShader); // set up vertex data (and buffer(s)) and configure vertex attributes float vertices[] = { -0.5f, -0.5f, 0.0f, // left 0.5f, -0.5f, 0.0f, // right 0.0f, 0.5f, 0.0f // top }; unsigned int VBO, VAO; glGenVertexArrays(1, &VAO); glGenBuffers(1, &VBO); // bind the Vertex Array Object first, then bind and set vertex buffer(s), //and then configure vertex attributes(s). glBindVertexArray(VAO); glBindBuffer(GL_ARRAY_BUFFER, VBO); glBufferData(GL_ARRAY_BUFFER, sizeof(vertices), vertices, GL_STATIC_DRAW); glVertexAttribPointer(0, 3, GL_FLOAT, GL_FALSE, 3 * sizeof(float), (void*)0); glEnableVertexAttribArray(0); // note that this is allowed, the call to glVertexAttribPointer registered VBO // as the vertex attribute's bound vertex buffer object so afterwards we can safely unbind glBindBuffer(GL_ARRAY_BUFFER, 0); // You can unbind the VAO afterwards so other VAO calls won't accidentally // modify this VAO, but this rarely happens. Modifying other // VAOs requires a call to glBindVertexArray anyways so we generally don't unbind // VAOs (nor VBOs) when it's not directly necessary. glBindVertexArray(0); // uncomment this call to draw in wireframe polygons. //glPolygonMode(GL_FRONT_AND_BACK, GL_LINE); // render loop while (!glfwWindowShouldClose(window)) { // input // ----- processInput(window); // render // ------ glClearColor(0.2f, 0.3f, 0.3f, 1.0f); glClear(GL_COLOR_BUFFER_BIT); // draw our first triangle glUseProgram(shaderProgram); glBindVertexArray(VAO); // seeing as we only have a single VAO there's no need to // bind it every time, but we'll do so to keep things a bit more organized glDrawArrays(GL_TRIANGLES, 0, 3); // glBindVertexArray(0); // no need to unbind it every time // glfw: swap buffers and poll IO events (keys pressed/released, mouse moved etc.) glfwSwapBuffers(window); glfwPollEvents(); } // optional: de-allocate all resources once they've outlived their purpose: glDeleteVertexArrays(1, &VAO); glDeleteBuffers(1, &VBO); // glfw: terminate, clearing all previously allocated GLFW resources. glfwTerminate(); return 0; } //************************************************** // process all input: query GLFW whether relevant keys are pressed/released // this frame and react accordingly void processInput(GLFWwindow *window) { if (glfwGetKey(window, GLFW_KEY_ESCAPE) == GLFW_PRESS) glfwSetWindowShouldClose(window, true); } //******************************************************************** // glfw: whenever the window size changed (by OS or user resize) this callback function executes void framebuffer_size_callback(GLFWwindow* window, int width, int height) { // make sure the viewport matches the new window dimensions; note that width and // height will be significantly larger than specified on retina displays. glViewport(0, 0, width, height); } As you see, about 200 lines of complicated code only for a simple triangle. 
      I don't know what parts are necessary for that output. And also, what the correct order of instructions for such an output or programs is, generally. That start point is too complex for a beginner of OpenGL like me and I don't know how to make the issue solved. What are your ideas please? What is the way to figure both the code and the whole program out correctly please?
      I wish I'd read a reference that would teach me OpenGL through a step-by-step method. 
  • Popular Now