At SC08 NVIDIA announces the Tesla? Personal Supercomputer. Experience cluster level computing performance?up to 250 times faster than standard PCs and workstations?right at your desk. The NVIDIAŽ Tesla Personal Supercomputer is based on the revolutionary NVIDIA CUDA? parallel computing architecture and powered by up to 960 parallel processing cores.
Jacket is Accelereyes GPU engine for MATLAB. This allows users to run MATLAB code and Jacket then takes that code and compiles it down to CUDA for GPU acceleration
Jim Hardwick describes TechniScans experience in moving their production SW onto CUDA. The engineering team had a strong background in Fortran and Jim talks about the results of this project.
Gene Poole of ANSYS talks about their work with CUDA and the integration with a 3rd party (Acceleware) into their most important solver. Cluster support in the future he believes is similar to turbo charging the solver to gain an order of magnitude in performance. He believes their success is due to the maturing of the technology and the language development of CUDA
Andrew Belliner is a senior student at Grand Valley State University in Allendale Michigan. He built a personal supercomputer to investigate GPU Computing as part of his university program. He is a C programmer and ported his work to CUDA using Smith-Waterman as the projects test bed.
Serban Georgescu University of Tokyo talks about his work with CUDA and acclerating his finite element solver. He believes to solve a FE simulation with his interactive solver is well suited for parallel architectures and their high bandwidth.
Darren Schmidt pioneered the first work at National Instruments with CUDA for LabVIEW. He talks about his initial work and what he found in moving his programs over to the GPU.
Ian Buck talks about threads and programming with CUDA. With CUDA the objective is to launch thousands to ten thousand threads which offers tremendous benefits to the programmer
John Stone of University of Illinois is part of the Theoretical and Computational Biology team. He has now worked with CUDA for 1 ˝ years and talks about his research experience with GPU computing. John Stone was interviewed at SC08.
Schoeller Porter of Mathematica talks about his experience programming with CUDA. Mathematica 7 was shown at SC08 and in the background of the video shown some initial CUDA work.
David Dynerman works in computational biology and found 2 orders of magnitude (100X) performance increase using GPU acceleration for predicting docked structure of proteins.
Joost Batenburg discusses how the University of Antwerp is researching and has already developed practical uses for Tomography using CUDA Technology in industries from Medical Science Imaging and cutting diamonds in order to maximise yields to observing nano structures in 3D.
Exegy designs and sells Ticker Plants for the finance market. Naveen is using GPU's downstream from the FPGA's to enable complex real time financial computations for risk evaluation.
Joost Batenburg discusses how the University of Antwerp is researching and has already developed practical uses for Tomography using CUDA Technology in industries from Medical Science Imaging and cutting diamonds in order to maximise yields to observing nano structures in 3D.
Eric Greffier confirms that Dell will be producing NVIDIA multi GPU workstations from early 2009 capable of supercomputing speed and efficiency supported through NVIDIAs CUDA and TESLA technologies intended for use by researchers, scientists and engineers in fields ranging from Medical Science Imaging to Video Transcoding.
