Class Description

Class Information

Lectures

1. 01/8/2007: Intro to the course: Why study the GPU     Slides: PPT
   Videos used in lecture:

   • ATI Animusic Demo
   • Simulation of Cloud Dynamics on Graphics Hardware (Harris/Baxter/SCheuermann/Lastra).
   • Real-Time Depth Contours (Mustafa/Krishnan/V.)

   Reading:

   • Why Is Graphics Hardware So Fast by Pat Hanrahan
   • The GPU Enters Computing's Mainstream by Michael Macedonia.
   • The Graphics Card As A Stream Computer by S.V.
   Assignment 0: Fill out the in classs survey
   
   
2. 01/8/2007: The Fixed-Function Pipeline    Slides: PPT
   Reading:

   • Programming Graphics Hardware (Eurographics 2004 Tutorial): Fernando, Harris, Wloka and Zeller.
   • Interactive Multipass Programmable Shading (Peercy, Olano, Airey and Ungar). SIGGRAPH 2000. This is one of the first papers to view the fixed-function pipeline as a general purpose SIMD Processor.
   • Fast Computation of Generalized Voronoi Diagrams using graphics hardware (Hoff, Culver, Keyser, Lin, Manocha). SIGGRAPH 99. This page also has downloadable code.
   • 7 years of Graphics, by Thomas Monk. An interesting perspective on the history of PC cards. Contains the pictures used in the presentation.

   Assignment 1: Graphics Pipleline (Given out) : Due Jan 22, 2007
   
   
3. 01/22/2007: The Programmable Pipeline / Memory Models    Slides: PPT
   Reading:

   • The Cg book: Chapter 1 (The History of the pipeline)
   • Extremetech articles: What happened in 2004, what to look forward to in 2005, what ATI and NVIDIA see in the future.
   
   
4. 01/22/2007: Cg Programming Tutorial (Joe)    Slides: PPT | PDF
   
   • Code examples are below
   • Visit the GPGPU.org forums for a wealth of information on Cg hacking.

   Assignment 2: CG and FBOs (Given out) : Due Feb 5, 2007


5. 01/29/2007: Fast Texture Transfers    
   Reading:

   • Nvidia Developer Paper on Fast Texture Transfers
   • Using Vertex buffer objects
   • Using Vertex textures
   
   
6. 01/29/2007: Rendering Gooey Materials / Reflections from Bumpy Surfaces    
   Reading:

   • Rendering Gooey Materials with Multiple Layers
   • ShaderX 3: Chapter 2.13 Rendering Semitransparent Layered Media (Chris Oat)
   • ShaderX 3: Chapter 2.3 Reflections from Bumpy Surfaces (Henning Mortveit)
   
   
7. 02/5/2007: Sorting And Searching    Slides: PPT
   
   Reading:

   • GPU = Parallel Machine II: Sorting and Hashing (Scribed by Joe Kider)
   • Improved Sorting on the GPU, by Kipfer and Westermann (Ch 46, GPU Gems II)
   • GPUSort: High Performance Sorting using Graphics Processors by Govindaraju et al.
   • GPUTeraSort: High Performance Graphics Coprocessor Sorting for Large Database Management by Naga K. Govindaraju; Jim Gray; Ritesh Kumar; Dinesh Manocha (SIGMOD 2006)
   • GPU-ABiSort: Optimal Parallel Sorting on Stream Architectures by Alexander Gress and Gabriel Zachmann (IPDPS 2006)
   
   
8. 02/5/2007: Matrix Operations    Slides: PPT
   
   Reading:

   • Fast matrix multiplies using graphics hardware by Larsen and McAllister (SC 2001)
   • Dense Matrix Multiplication by Ádám Moravánszky
   • Cache and Bandwidth Aware Matrix Multiplication on the GPU by Hall, Carr and Hart (Tech Report UIUCDCS-R-2003-2328-1)
   • Understanding the Efficiency of GPU Algorithms for Matrix-Matrix Multiplication by Fatahalian, Sugerman, Hanrahan (Graphics Hardware 2004)
   • Linear algebra operators for GPU implementation of numerical algorithms by Krüger and Westermann (SIGGRAPH 2003)
   • Sparse Matrix Solvers on the GPU: Conjugate Gradients and Multigrid by Bolz, Farmer, Grinspun and Schröder. (SIGGRAPH 2003)
   
   
9. 02/12/2007: Directx10    
   
   Reading:

   • DirectX10 Effects Sarah Tariq (SIGGRAPH 2006)
   • DirectX10 Sysytem David Blythe, Microsoft Corporation (2006)
   • DirectX10 for Techies Nick Thibieroz, ATI/AMD (2006)
   • DirectX10 Technical Brief Nvidia (2006)
   Final Project: Description and Guidelines (Given out)
   
   
10. 02/12/2007: CUDA and the GeForce 8800    
    
    Reading:

    • CUDA Programming Guide 0.8   New!
    • CUDA Code Examples
    • GeForce 8800 & NVIDIA CUDA Slides A New Architecture for Computing on the GPU
    Assignment 3: Matrix Operations and CUDA Programming (Given Out): Due Mar 2, 2007
    
    
11. 02/19/2007: Skin Rendering    Slides: PPT
    
    Reading:

    • Real Time Dawn Demos NVIDIA (2002)
    • Skin in the "Dawn" Demo Curtis Beeson and Kevin Bjorke (GPU GEMS)
    • Real-Time Texture-Space Skin Rendering by David Gosselin (ShaderX 3)
    • Real-Time Skin Rendering on Graphics Hardware Sander, Gosselin, Mitchell (SIGGRAPH 2004)
    
    
12. 02/19/2007: Animation and Morphing    Slides: PPT
    
    Reading:

    • Morphing between two different Objects by Ronny Burkersroda (ShaderX 3)
    • Morph Target Animation by Christian Kleinhuis (ShaderX 4)
    • Real-Time Character Animation on the GPU by Michael Nischt (ShaderX 4)
    
    
13. 02/26/2007: GPGPU I: Basic Learning and Solving Linear Systems    Supplemental Slides: PPT
    
    Reading:

    • An Introduction to the Conjugate Gradient Method Without the Agonizing Pain, by Jonathan Shewchuk
    • Sparse Matrix Solvers on the GPU: Conjugate Gradients and Multigrid by Bolz, Farmer, Grinspun and Schröder. (SIGGRAPH 2003)
    • LU-GPU: Efficient Algorithms for Solving Dense Linear Systems on Graphics Hardware Nico Galoppo, Naga K. Govindaraju, Michael Henson, Dinesh Manocha (SuperComputing 2005)
    
    
14. 02/26/2007: GPGPU II: Physical Simulation the GPU    Slides: PPT1 | PPT2
    
    Reading:

    • A multigrid solver for boundary value problems using programmable graphics hardware, by Goodnight, Woolley, Lewin, Luebke, and Humphreys (SIGGRAPH 2003)
    • Physically-based visual simulation on graphics hardware, by Harris, Coombe, Scheuermann, and Lastra (GH 2002)
    • Physically-Based Visual Simulation on Graphics Hardware (Video)
    • Mapping Computational Concepts to GPUs Mark Harris
    • Asymmetric Physics Processing with ATI Crossfire
    
    
15. 03/12/2007: Abstracting GPGPU: SlabOps    Slides: PPT
    
    Reading:

    • Mark Harris' Research Noteblog on SlabOps
    • Code: Basic Add SlabOp Implementation with FBOs Example(Zip File)
    • Code: Basic Saxpy SlabOp Implementation with FBOs Example(Zip file)
    • Automatic shader level of detail by Olano, Kuehne and Simmons (GH 2003)
    • A real-time procedural shading system for programmable graphics hardware by Proudfoot, Mark, Tzvetkov and Hanrahan (SIGGRAPH 2001)
    
    
16. 03/12/2007: Collision Detection using Graphics Hardware    Slides: PPT
    
    Reading:

    • CULLIDE: Interactive Collision Detection Between Complex Models in Large Environments using Graphics Hardware by Naga Govindaraju, Stephane Redon, Ming C. Lin and Dinesh Manocha (Graphics Hardware 2003)
    • Quick-CULLIDE: Efficient Inter- and Intra-Object Collision Culling using Graphics Hardware by Naga Govindaraju, Ming C. Lin and Dinesh Manocha (IEEE VR 2005)
    • Fast and Reliable Collision Culling using Graphics Processors by Naga Govindaraju, Ming C. Lin and Dinesh Manocha (VRST 2004)
    • Practical Collision Detection on the GPU (Case Study) Markus Malmsten and Simon Klasén
    • Fast and Reliable Collision Culling using Graphics Processors by Naga Govindaraju, Ming C. Lin and Dinesh Manocha (VRST 2004)
    • Streaming Collision Detection Using Programmable GPU by Zhaowei Fan, Huagen Wan, Shuming Gao
    
    
17. 03/19/2007: Particle Systems on the GPU    
    
    Reading:

    • Slides: A GPU-based Particle Engine (SIGGRAPH 2004)
    • Building a Million Particle System by Lutz Latta (GDC 2004)
    • UberFlow: A GPU-Based Particle Engine by Peter Kipfer, Mark Segal, Rüdiger Westermann (Graphics Hardware 2004)
    
    
18. 03/19/2007: Optimizations for Graphics Hardware    Slides:  NVIDA PDF | ATI PDF
    
    Reading:

    • A Memory Model for Scientific Algorithms on Graphics Processors by Naga K. Govindaraju; Scott Larsen; Jim Gray; Dinesh Manocha(SuperComputing 2006)
    • Benchmarking and Profiling on the GPU Slides by: Suresh Venkatasubramanian (2004)
    • Graphics Performance Optimization, by John Spitzer (NVIDIA)
    • High-Performance GPGPU (SUPERCOMPUTING 2006 Tutorial on GPGPU):
      • GPGPU Strategies and Tricks, by John Owens
      • Performance Analysis and Architecture Insights, by Mike Houston
    • Effective GPGPU Programming: Tricks and Traps (Siggraph 2005 GPGPU Course):
      • GPU Program Optimization, by Cliff Woolley
      • GPU Memory Model Overview, by Aaron Lefohn
      • GPU Data Structures, by Aaron Lefohn
    • Understanding The Efficiency of GPU Algorithms for Matrix-Matrix multiplication, by Fatahalian, Sugerman and Hanrahan (GH 2004)
    • A small list of helpful optimization, performance, and pseudo-debugging tools can be found here: Link to Tools
    
    
19. 03/26/2007: Modeling & Simulation     - Guest Lecturer: Mike Hakos (Lockhead Martin)
    
    Reading:

    • Benchmarking and Implementation of Probability-Based Simulations on Programmable Graphics Cards by Stanimire Tomov, Michael McGuigan, Robert Bennett, Gordon Smith, John Spiletic
    • Radiative Heat Transfer Simulation Using Programmable Graphics Hardware by Hiroyuki Takizawa, Noboru Yamada, Seigo Sakai, and Hiroaki Kobayashi (IEEE/ACIS 2006)
    • Numerical Simulation Using GPUs (PPT) by Stan Tomov (2003)
    
    
20. 03/26/2007: Fast Fourier Transforms on the GPU    Slides: PPT
    
    Reading:

    • CUDA FFT Library Version 0.8 Reference Documentation by Nvidia
    • GPUFFTW: High Performance Power-of-Two FFT Library using Graphics Processors by Naga Govindaraju and Dinesh Manocha (SuperComputing 2006)
    • The FFT on a GPU by Kenneth Moreland and Edward Angel (Graphics Hardware 2003)
    • Implementing a GPU-Efficient FFT by John Spitzer (2003)
    • Medical Image Reconstruction with FFT by Sumanaweera and Liu (Graphics Gems 2)
    
    
21. 04/02/2007: Parallel Architectures: Cell Architecture and Programming     - Steven Crowe
    
    Reading:

    • Lecture Slides: Multicore Programming Primer: Learn and Compete in Programming the PLAYSTATION®3 Cell Processor by Prof. Saman Amarasinghe and Dr. Rodric Rabbah (MIT)
    • IBM Online Course on Cell
    • Cell Broadband Engine Documents from Sony Computer Entertainment
    • IBM Hands-On Tutorial on Cell Programming
    • Introduction to the Cell Multiprocessor by Kahle et Al. (IBM Research)
    • Molecular Dynamics on the Cell Processor by Olivier, Prins, Derby, and Vu
    • The Potential of the Cell Processor for Scientific Computing by Williams, Shalf, Oliker, Kamil, Husbands, and Yelick
    
    
22. 04/02/2007: Parallel Architectures: GPU 8800 Compute Core and CUDA Programming Tricks    
    
    Reading:

    • Slides and Podcasts: UIUC COURSE: Programming Massively Parallel Processors by Wen-Mei Hwu and David Kirk. (4/2/07 Lecture from UIUC's Lectures 6,7 CUDA Memory Model & Programming and Lectures 8,9 GPU Compute Core)   New and Highly Recommended!
    
    
23. 04/09/2007: Global Illumination on the GPU    
    
    Reading:

    • Lecture Slides: GPUGI: Global Illumination Effects on the GPU by László Szirmay-Kalos, László Szécsi, Mateu Sbert (EuroGraphics 2006)
    • Tutorial of GPUGI: Global Illumination Effects on the GPU by László Szirmay-Kalos, László Szécsi, Mateu Sbert (EuroGraphics 2006)
    • Fast Approximations for Global Illumination on Dynamic Scenes by Alex Evans
      Slides
      Course Notes, Chapter 9: Pg. 153-171 (SIGGRAPH 2006)
    • Radiance Cache Splatting: A GPU-Friendly Global Illumination Algorithm by Gautron, Krivánek, Bouatouch, Pattanaik (2005)
    • Global Illumination using Progressive Refinement Radiosity by Greg Coombe and Mark Harris
      (GPU GEMS 2: Chapter 39)
      Radiosity on graphics hardware (Graphics Interface 2004)
    • High-Quality Global Illumination Rendering Using Rasterization by Toshiya Hachisuka (GPU GEMS 2: Chapter 38)
    • ShaderX5: Section 6 - Global Illumination Effects (Carsten Dachsbacher)
    
    
24. 04/09/2007: Student Project Alpha Reviews    
    
    
    
25. 04/16/2007: Parallax Mapping on the GPU    
    
    Reading:

    • Lecture Slides: Practical Dynamic Parallax Occlusion Mapping by Natalya Tatarchuk (SIGGRAPH Sketch 2005)
      GDC Presentation
    • Dynamic Parallax Occlusion Mapping with Approximate Soft Shadows. In Proceedings of ACM SIGGRAPH Symposium on Interactive 3D by Natalya Tatarchuk, Graphics and Games (SI3D '06), pp. 63-69
    • Practical Parallax Occlusion Mapping with Approximate Soft Shadows for Detailed Surface Rendering by Natalya Tatarchuk, (ACM SIGGRAPH 2006: Proceedings of the conference on SIGGRAPH 2006 course notes, course 26, Advanced Real-Time Rendering in 3D Graphics and Games, pp. 87-118)
    • Practical Parallax Occlusion Mapping For Highly Detailed Surface Rendering by Natalya Tatarchuk, (GDC 2006) (2005)
    • Detailed Shape Representation with Parallax Mapping
      (ICAT 2001)
      Original Basis Paper (non-gpu)
    
    
26. 04/16/2007: CUDA Performance    
    
    Reading:

    • Slides and Podcasts: UIUC COURSE: Programming Massively Parallel Processors by Wen-Mei Hwu and David Kirk
    
    
27. 04/16/2007: Future Trends (GPU or Multicore Processor: Who will win?)    
    
    We had some slides here, but they mostly prompted discussion topics with the class.

    • Edge Workshop (UNC)
    
    

Homework and Final Project Information

Extra Slides

Drivers

Code Tutorial and Examples

GPU optimization, performance, and pseudo-debugging Tools

Useful Links

Acknowledgement of Sources