• Advertisement
Sign in to follow this  

OpenGL My Bachelor Thesis "Software Renderer Accelerated by CUDA Technology"

This topic is 2039 days old which is more than the 365 day threshold we allow for new replies. Please post a new topic.

If you intended to correct an error in the post then please contact us.

Recommended Posts

Hey guys,

A few days back I finished my bachelor thesis and a project that accompanies the thesis. Shortly speaking, my project was about implementing a selected subset of OpenGL/Direct3D fuctionality and see how much it can be speed up with CUDA. If you're interested, want to share opinions, etc., here's the www-site of the project: http://maxest.gct-game.net/vainmoinen/index.html
Note that I have put a lot of effort to explain in details the vertex and pixel processing phases, including software implementation of texture mapping with bilinear filtering and mip-mapping. I hope someone will ever learn something from this :)

Share this post


Link to post
Share on other sites
Advertisement
Yeah, definitely :). I have been using OpenGL and Direct3D for a few years and I never knew how they actually work internally. Now I finally do :)

Share this post


Link to post
Share on other sites
Right. Today everything (in real-time graphics) goes around OpenGL/Direct3D and shaders. Sometimes I wish I had been born maybe 10 years earlier so I could start my graphics adventure with software graphics, when the whole graphics industry was emerging :).

Share this post


Link to post
Share on other sites
Congrats on getting that out of the way. Definitely feels nice to have that off your shoulders, doesn't it?

If you are going to use slides in the future, and you are certainly going to, almost regardless of what you'll end up doing professionally, you might want to include slide numbers on every slide. It helps a lot for people to go back to a specific slide with a question. Undergraduate classmates don't like doing this (either due to a general lack of interest, due to a desire to get the class over with early, or due to being afraid to ask something that you won't be able to answer and thus messing up your grade) but eventually someone will ask something :D


The paper itself does have a couple of flaws. First, even for a practical paper documenting an implementation, the thesis itself is a bit on the short side, especially the literature list. Your introduction does not do much to introduce the topic, instead diving straight into definitions. I would have started out with a somewhat expanded version of your abstract there. The implementation section could've done with a bit more explanation, also. The research itself looks good, I can see you put a lot of time into that. I would also include the full (or the critical parts if its really long) source code in an appendix, although that's more of a preference and depends on what your professor wants. It does tend to make the paper longer, which does wonders for when you print a bound copy :P

Second, you're not using citations. Is your professor cool with that? Mine would've killed me :o Every time you have some kind of statement that you did not come up with yourself, whether it's some equation you read in a book or some value judgement or whatever, you really ought to back it up by a citation, otherwise people will assume that it's your original thought, which leads down the unpleasant road of plagiarism charges (which can get you kicked out of university or make you fail the course, plus it'll follow your reputation for life, not a very pleasant thing). Especially potentially contentious statements such as the last sentence of the first paragraph on page 4 need citations.

Oh, and I see you're studying in Wroc?aw. I was there in 2008 on an IT law seminar. Nice place, especially that Japanese garden :D

Share this post


Link to post
Share on other sites
Thanks for your suggestions stanirya.

As for the literature; I have included only those books/articles that actually used in my research.
The introduction is pretty short, yes. Computer graphics rookies might find my paper harder to read than people who have some background in OpenGL/Direct3D.
I also have not put enough attention into implementation section. I though there was no need to do so as the implementation is pretty straightforward (when you know the theory, which I mostly focused on). However, on page 35 there is a flow diagram that explains in pseudocode what the renderer does.

We have a Japenese garden? I guess I should take more routes than lodging <-> university :D

Share this post


Link to post
Share on other sites
That's pretty cool! Good job. The performance comparisons in Test 2 is OpenGL with 2500 draw calls of cubes (25ms) and then CUDA with one draw call and 2500 instanced cubes (33ms)? The CUDA implementation requires 415ms in the case you do 2500 draw calls of cubes?

Share this post


Link to post
Share on other sites
Thank you :).

And yes, OpenGL looks not that good in comparisons to even the software renderer running without CUDA. The problem is of course neither vertex nor pixel processing but CPU-GPU communication. So the time of 22ms of OGL is actually the time needed to call glDrawElements 2500 times :).
CUDA with one draw call (One-Call-Many-Triangles) uses quite a lot of additional global memory to store "processing information", so to speak. This way I avoided calling CUDA for every single triangle but for the cost of memory accesses, what has proven to be very expensive (Test 1). However, it is not that expensive when there is a lot of triangles to process, where One-Call-One-Triangle's performance significantly drops, and One-Call-Many-Triangles still behaves decently.

I have some loose further concepts on how to utilize CUDA to speed the rendering, with different strategies. I am sure I'll get back to the project when I have some spare time and more robust ideas :)

Share this post


Link to post
Share on other sites
Hey folks,

After almost 1.5 years I got back to Vainmoinen. You can check the news on the website http://maxest.gct-game.net/vainmoinen/index.html

Cheers, Wojtek

Share this post


Link to post
Share on other sites
Sign in to follow this  

  • Advertisement
  • Advertisement
  • Popular Now

  • Advertisement
  • Similar Content

    • By khawk
      We've just released all of the source code for the NeHe OpenGL lessons on our Github page at https://github.com/gamedev-net/nehe-opengl. code - 43 total platforms, configurations, and languages are included.
      Now operated by GameDev.net, NeHe is located at http://nehe.gamedev.net where it has been a valuable resource for developers wanting to learn OpenGL and graphics programming.

      View full story
    • By TheChubu
      The Khronos™ Group, an open consortium of leading hardware and software companies, announces from the SIGGRAPH 2017 Conference the immediate public availability of the OpenGL® 4.6 specification. OpenGL 4.6 integrates the functionality of numerous ARB and EXT extensions created by Khronos members AMD, Intel, and NVIDIA into core, including the capability to ingest SPIR-V™ shaders.
      SPIR-V is a Khronos-defined standard intermediate language for parallel compute and graphics, which enables content creators to simplify their shader authoring and management pipelines while providing significant source shading language flexibility. OpenGL 4.6 adds support for ingesting SPIR-V shaders to the core specification, guaranteeing that SPIR-V shaders will be widely supported by OpenGL implementations.
      OpenGL 4.6 adds the functionality of these ARB extensions to OpenGL’s core specification:
      GL_ARB_gl_spirv and GL_ARB_spirv_extensions to standardize SPIR-V support for OpenGL GL_ARB_indirect_parameters and GL_ARB_shader_draw_parameters for reducing the CPU overhead associated with rendering batches of geometry GL_ARB_pipeline_statistics_query and GL_ARB_transform_feedback_overflow_querystandardize OpenGL support for features available in Direct3D GL_ARB_texture_filter_anisotropic (based on GL_EXT_texture_filter_anisotropic) brings previously IP encumbered functionality into OpenGL to improve the visual quality of textured scenes GL_ARB_polygon_offset_clamp (based on GL_EXT_polygon_offset_clamp) suppresses a common visual artifact known as a “light leak” associated with rendering shadows GL_ARB_shader_atomic_counter_ops and GL_ARB_shader_group_vote add shader intrinsics supported by all desktop vendors to improve functionality and performance GL_KHR_no_error reduces driver overhead by allowing the application to indicate that it expects error-free operation so errors need not be generated In addition to the above features being added to OpenGL 4.6, the following are being released as extensions:
      GL_KHR_parallel_shader_compile allows applications to launch multiple shader compile threads to improve shader compile throughput WGL_ARB_create_context_no_error and GXL_ARB_create_context_no_error allow no error contexts to be created with WGL or GLX that support the GL_KHR_no_error extension “I’m proud to announce OpenGL 4.6 as the most feature-rich version of OpenGL yet. We've brought together the most popular, widely-supported extensions into a new core specification to give OpenGL developers and end users an improved baseline feature set. This includes resolving previous intellectual property roadblocks to bringing anisotropic texture filtering and polygon offset clamping into the core specification to enable widespread implementation and usage,” said Piers Daniell, chair of the OpenGL Working Group at Khronos. “The OpenGL working group will continue to respond to market needs and work with GPU vendors to ensure OpenGL remains a viable and evolving graphics API for all its customers and users across many vital industries.“
      The OpenGL 4.6 specification can be found at https://khronos.org/registry/OpenGL/index_gl.php. The GLSL to SPIR-V compiler glslang has been updated with GLSL 4.60 support, and can be found at https://github.com/KhronosGroup/glslang.
      Sophisticated graphics applications will also benefit from a set of newly released extensions for both OpenGL and OpenGL ES to enable interoperability with Vulkan and Direct3D. These extensions are named:
      GL_EXT_memory_object GL_EXT_memory_object_fd GL_EXT_memory_object_win32 GL_EXT_semaphore GL_EXT_semaphore_fd GL_EXT_semaphore_win32 GL_EXT_win32_keyed_mutex They can be found at: https://khronos.org/registry/OpenGL/index_gl.php
      Industry Support for OpenGL 4.6
      “With OpenGL 4.6 our customers have an improved set of core features available on our full range of OpenGL 4.x capable GPUs. These features provide improved rendering quality, performance and functionality. As the graphics industry’s most popular API, we fully support OpenGL and will continue to work closely with the Khronos Group on the development of new OpenGL specifications and extensions for our customers. NVIDIA has released beta OpenGL 4.6 drivers today at https://developer.nvidia.com/opengl-driver so developers can use these new features right away,” said Bob Pette, vice president, Professional Graphics at NVIDIA.
      "OpenGL 4.6 will be the first OpenGL release where conformant open source implementations based on the Mesa project will be deliverable in a reasonable timeframe after release. The open sourcing of the OpenGL conformance test suite and ongoing work between Khronos and X.org will also allow for non-vendor led open source implementations to achieve conformance in the near future," said David Airlie, senior principal engineer at Red Hat, and developer on Mesa/X.org projects.

      View full story
    • By _OskaR
      Hi,
      I have an OpenGL application but without possibility to wite own shaders.
      I need to perform small VS modification - is possible to do it in an alternative way? Do we have apps or driver modifictions which will catch the shader sent to GPU and override it?
    • By xhcao
      Does sync be needed to read texture content after access texture image in compute shader?
      My simple code is as below,
      glUseProgram(program.get());
      glBindImageTexture(0, texture[0], 0, GL_FALSE, 3, GL_READ_ONLY, GL_R32UI);
      glBindImageTexture(1, texture[1], 0, GL_FALSE, 4, GL_WRITE_ONLY, GL_R32UI);
      glDispatchCompute(1, 1, 1);
      // Does sync be needed here?
      glUseProgram(0);
      glBindFramebuffer(GL_READ_FRAMEBUFFER, framebuffer);
      glFramebufferTexture2D(GL_READ_FRAMEBUFFER, GL_COLOR_ATTACHMENT0,
                                     GL_TEXTURE_CUBE_MAP_POSITIVE_X + face, texture[1], 0);
      glReadPixels(0, 0, kWidth, kHeight, GL_RED_INTEGER, GL_UNSIGNED_INT, outputValues);
       
      Compute shader is very simple, imageLoad content from texture[0], and imageStore content to texture[1]. Does need to sync after dispatchCompute?
    • By Jonathan2006
      My question: is it possible to transform multiple angular velocities so that they can be reinserted as one? My research is below:
      // This works quat quaternion1 = GEQuaternionFromAngleRadians(angleRadiansVector1); quat quaternion2 = GEMultiplyQuaternions(quaternion1, GEQuaternionFromAngleRadians(angleRadiansVector2)); quat quaternion3 = GEMultiplyQuaternions(quaternion2, GEQuaternionFromAngleRadians(angleRadiansVector3)); glMultMatrixf(GEMat4FromQuaternion(quaternion3).array); // The first two work fine but not the third. Why? quat quaternion1 = GEQuaternionFromAngleRadians(angleRadiansVector1); vec3 vector1 = GETransformQuaternionAndVector(quaternion1, angularVelocity1); quat quaternion2 = GEQuaternionFromAngleRadians(angleRadiansVector2); vec3 vector2 = GETransformQuaternionAndVector(quaternion2, angularVelocity2); // This doesn't work //quat quaternion3 = GEQuaternionFromAngleRadians(angleRadiansVector3); //vec3 vector3 = GETransformQuaternionAndVector(quaternion3, angularVelocity3); vec3 angleVelocity = GEAddVectors(vector1, vector2); // Does not work: vec3 angleVelocity = GEAddVectors(vector1, GEAddVectors(vector2, vector3)); static vec3 angleRadiansVector; vec3 angularAcceleration = GESetVector(0.0, 0.0, 0.0); // Sending it through one angular velocity later in my motion engine angleVelocity = GEAddVectors(angleVelocity, GEMultiplyVectorAndScalar(angularAcceleration, timeStep)); angleRadiansVector = GEAddVectors(angleRadiansVector, GEMultiplyVectorAndScalar(angleVelocity, timeStep)); glMultMatrixf(GEMat4FromEulerAngle(angleRadiansVector).array); Also how do I combine multiple angularAcceleration variables? Is there an easier way to transform the angular values?
  • Advertisement