• Special Topics in GPU programming and architecture from UPenn
• GPGPU: Beyond Graphics paper from nVidia is quite interesting
• Why is Graphics Hardware so fast? is an interesting presentation from Stanford Computer Graphics Laboratory; this materials presents an interesting analysis of GPU performance and evolution

Shader languages and toolkits

• Cg
  • Cg is an nVidia technology useful as "...the best way to take advantage of today's GPUs across multiple platforms and APIs. Now supporting OpenGL's ARB_vertex_program and ARB_fragment_program extensions, the compiler allows developers to create advanced visual effects for today's programmable GPUs from NVIDIA and other vendors."
  • Cg Toolkit (nVidia again!) provides a compiler for the Cg language, runtime libraries for use with both leading graphics APIs, runtime libraries for CgFX, example applications, and extensive documentation.

• Sh
  • Sh is a library that acts as a language embedded in C++, allowing you to program GPUs (Graphics Processing Units) and CPUs for graphical and general-purpose computations in novel ways.

• OpenGL Shading Language (GLSL)
  • see also Tesseract OpenGL page
  • OpenGL Shading Language on OpenGL.org

• BrookGPU
  • BrookGPU is a compiler and runtime implementation of the Brook stream program language for modern graphics hardware;

Benchmarking and related techniques

• GPUBench How much does your GPU Bench?..
  GPUBench is a benchmark suite designed to analyze the performance of programmable graphics processors in areas of particular importance to general purpose computation. Included in the suite are tests that rigorously exercise a system's GPU, determining statistics such as memory input/output bandwidth to floating point buffers, texture cache bandwidth, data download and readback rates, instruction throughput, and instruction precision. More so than being a measuring stick for GPU performance, GPUBench is intended to be a tool for developers of GPU-accelerated applications, since a more complete understanding of machine capabilities will dictate better software design decisions. Information included in GPUBench reports is useful in accurately estimating the performance of shader programs as well as determining if a particular GPU is a viable target platform for a particular computation.

  The researchers and related content linked from the page are a real trove of info on GPGPU applications and use. Read through this stuff if you are serious!

GPU Architecture, hardware and software

• Article on Hardware Geometry Processing on Beyond3d.com; older, but still quite interesting

Tutorials and other educational/programming materials

• Nice tutorial in PDF form
• Volume Rendering on GPGPU tutorial, PDF
• ShaderTech is About GPU programming
• Dominik Göddeke -- GPGPU Tutorials
• GPGPU: Math Tutorial
• ATI technology papers and presentations on their GPU
• Cg and HLSL FAQ on quite interesting fusionindustries.com
• GPGP: General Purpose Computation using Graphics Processors contains materials related to a course presented at University of North Carolina at Chapel Hill; many useful links and related background material on GPU usage
• Little collection of GPU programming links

Interesting GPU applications

• Vision and Pattern Recognition
  • OpenVIDIA Parallel GPU Computer Vision
  • Real-Time, GPU-Based Foreground-Background Segmentation
  • GPU implementation of deformable pattern recognition using prototype-parallel displacement computation; (PDF) using parallel ops in GPU for pattern recognition, in particular, handwritten character recognition
  • GPU_KLT: A GPU-based Implementation of the Kanade-Lucas-Tomasi Feature Tracker; a C++ implementation using OpenGL/Cg, of the popular KLT feature tracker which runs primarily on the graphics processing unit (GPU); contains intersting performance metrics data on vision apps on nVidia vs. ATI (hmm, ATI looks quite a bit faster.....same class GPU?)

• see GPGPU.org for many apps
• Tutorial: Data Visualization and Mining using the GPU by Suresh Venkatasubramanian, a researcher at AT&T Labs, Inc. (we miss you, Bell Labs...
• A Memory Model for Scientific Algorithms on Graphics Processors paper, PDF format; interesting comments on optimal memory usage patterns in general purpose CPUs vs GPUs
• FFT on the GPU including notes and source code
• Frogger game in a pixel shader located on Beyond3d shader competition results. No, I'm not kidding, the 1980's vintage game Frogger, implemented in shaders.....very interesting hack....

Assorted links related to GPUs and related topics

• Beyond3D.com has lots of materials on GPU and related products, including some excellent articles on performance, hardware architecture, etc. Worth some visits..

Back to Tesseract links