High Performance GPU Computing with NVIDIA, CUDA, and Fermi
Mark Harris (NVIDIA)
COMPUTER SYSTEMS SEMINARDATE: 2010-07-15
TIME: 09:15:00 - 15:30:00
LOCATION: CSIT Seminar Room, N101
CONTACT: JavaScript must be enabled to display this email address.
ABSTRACT:
This event (see also http://cs.anu.edu.au/systems/GPUWorkshop2010) is a workshop and discussion presented by
Mark Harris (NVIDIA) with
Dragan Dimitrovici (Xenon Systems),
John Taylor (CSIRO),
Eric McCreath (ANU College of Engineering and Computer Science), and
Joseph Antony (NCI).
The workshop is free, but please email Eric.McCreath@anu.edu.au for catering purposes. (We have capacity for at most 50 attendees.)
CONTENT:
CUDA is a parallel computing architecture and programming environment from NVIDIA that enables dramatic increases in computing performance by harnessing the power of the GPU (graphics processing unit). Computing is evolving from "central processing" on the CPU to "co-processing" on the CPU and GPU. To enable this new computing paradigm, NVIDIA invented the CUDA parallel computing architecture. With over 100 million CUDA-enabled GPUs sold to date, software developers, scientists and researchers are finding broad-ranging uses for CUDA, including image and video processing, computational biology and chemistry, fluid dynamics simulation, CT image reconstruction, seismic analysis, financial computing, ray tracing, and much more.
The latest CUDA-enabled GPU architecture from NVIDIA, code-named "Fermi", is now available in the form of the Tesla 20 series GPU computing solutions, which support many amust havea features for technical and enterprise computing. These include ECC memory for uncompromised accuracy and scalability, support for C++ and 8x the double precision performance compared to Tesla 10-series GPU computing products. NVIDIA Tesla GPUs are being used in 100s of clusters and data centers around the world, including the Nebulae cluster, currently the 2nd fastest supercomputer in the world.
In this workshop you will learn about CUDA, the Fermi architecture, and Tesla GPU Computing products. You will learn about the basics of programming GPUs using CUDA C and C++, the variety of available computational libraries for CUDA, tools for profiling and debugging CUDA applications, and approaches for optimizing CUDA parallel applications. You will also learn about CUDA-enabled desktop, workstation, and cluster computing solutions provided by Xenon Systems. The workshop will also include brief presentations on some of the ways these technologies have been used at CSIRO, NCI, and the ANU College of Engineering and Computer Science.
BIO:
