Scientific Computing on Graphics Hardware GPGPU Applications Examples

Scientific Computing on Graphics Hardware GPGPU Applications Examples Showcase

Overview • Interactive Demos, Videos – Computational Fluid Dynamics – Scientific Visualization – Protein Matching – Path Planning – FFT Applications – Adaptive Data Structures • Feel free to ask questions! Note: This is a small selection to show some of the possibilities and arouse further curiosity, alternative implementations to the above and many more applications exist. 2

Computational Fluid Dynamics Real-time simulation of fluid flow governed by the Navier-Stokes equations Live Demo: NVIDIA “GPGPU FLUID” Youquan Liu et al. , Pacific Graphics 2004 3 D fluid with complex obstacles 3

Scientific Visualization Jens Krüger et al. , TU München A Particle System for Interactive Visualization of 3 D Flows Winner of the IEEE Visualization Contest 05 Live Demo. . . 4

Fuzzy Protein Matching with HMMer [Daniel Horn et al. , Supercomputing 2005] Probabilistic model Junk Start F Junk R Junk N Del Junk T Del Junk P Del End Query F R G N T F T P R R T F N T F T P G R G T T F F P F N N N P F R G N F T P Database F R G T T F N P F N N N P P R G T N F T R F R N T F T P 5

Claw. HMMer Performance 6

Flexi. Plan - Path Planning for Deformable Robots in Complex Environments [Russell Gayle et al. , Systems and Science, 2005] Application: Liver Chemoembolization A long thin catheter is navigated from the femoral to the hepatic arteries near a tumor in the liver for direct drug injection. Movie. . . 7

FFT Applications [Thomas Jansen et al. , VMV 2004] Filtered Back-Projection • • Create volume from projections Fourier Volume Rendering • Inverse Filtered Back-Projection – Blending of “FFT-filtered” projections – Slice in frequency = Projection – Visualization of intermediate results! – Needs high-quality interpolation Faster by an order of magnitude! – 4. 5 min (CPU) vs. 24 sec (GPU) • 512³ rendered in >25 frames/sec – But needs slightly more space! Movie. . . 8

Glift : Generic, Efficient, Random-Access GPU Data Structures [Aaron Lefohn et al. , ACM TOG, 2006] STL-like abstraction of data containers from algorithms for GPUs Movie. . . 9

More Demos See GPGPU case studies in … • Siggraph 2005 course notes http: //www. gpgpu. org/s 2005/ • Visualization 2005 course notes http: //www. gpgpu. org/vis 2005/ 10