IEEE SCV Monterey Bay Subsection

and IEEE Computer Society (co-sponsor)

Parallel Computing with CUDA on GPUs

Speakers:
Dr. John Nickolls and Dr. Massimiliano Fatica

from NVIDIA CORPORATION.

You can access a PDF of this presentation by clicking HERE.

(Note this is a 31Mb file so allow enough download time.)
Abstract and speaker's biography follows.

Date:

Wed., Oct. 1, 2008.

Time:

6:00 pm - Refreshments, Food, and Social Time
7:00pm - Technical Presentation

Place:

Simularium Room at the University of California in Santa Cruz
Room 180, Engineering Bldg 2. Click here for directions and parking Information. There will be a two dollar fee for parking. .

To assess food, please RSVP via email to Marcelo Siero at siero@ee.com

Parallel Computing with CUDA on GPUs

Dr. John Nickolls, and Dr. Massimiliano Fatica. , Nvidia Corporation.

Abstract

The CUDA parallel programming model provides a straightforward means of describing inherently parallel computations. It lets programmers write scalable parallel programs with a minimal extension of the C language. NVIDIA's Tesla GPU architecture delivers high computational throughput on massively parallel problems. This talk describes how to write CUDA C programs, outlines the parallel computing architecture of a 240-processor GPU, and surveys applications of CUDA to different problems and the parallel speedups obtained on GPUs over traditional sequential CPU codes.

Biographies of Speakers

John Nickolls, Ph.D.
Director of Architecture
NVIDIA Corporation.

About the Speaker: John Nickolls is director of architecture at NVIDIA for GPU computing. He was previously with Broadcom, Silicon Spice, Sun Microsystems, and was a co-founder of MasPar Computer. His interests include parallel processing systems, languages, and architectures. Nickolls has a BS in electrical engineering and computer science from the University of Illinois, and MS and PhD degrees in electrical engineering from Stanford University.

Massimiliano Fatica, Ph.D.
NVIDIA Corporation.

Massimiliano Fatica is a Senior Applied Engineer at NVIDIA where he works in the area of GPU computing (high-performance computing and clusters). Prior to joining NVIDIA, he was a research staff member at Stanford University where he worked on applications for the Stanford Streaming Supercomputer. He holds a laurea in Aeronautical Engineering and a PhD in Theoretical and Applied Mechanics from the University of Rome "La Sapienza".

DIRECTIONS

For directions to UCSC from different parts of the bay area, click here .

The Baskin Engineering Buildings are located in the northwest corner of UCSC, on "Science Hill." Once at UCSC proceed up Coolidge Drive following the main road onto McLaughlin Drive. as McLaughlin Drive ends, turn left onto Heller Drive, then left again into the multi-level "West Core Parking" Structure (the closest parking to Baskin Engineering).

The best parking choice is to buy a Core West night parking permits at the Main Entrance Kiosk (Bay & High) for $2. The kiosk is open until 7:00AM to 8:00 p.m., Monday-Friday. These permits will be valid for any Core West Parking space (except specially marked spaces). For any additional details related to parking in Core West click here. You can also just feed a meter as an alternative. A complete UCSC campus map(.pdf) is available, as is a web site dedicated to UCSC maps.

To get to the Simularium go to the streeet level floor of the Parking Space, cross the street go past the Baskin Engineering Bldg 1 to Bldg 2, the Simularium is off the courtyard lying between Baskin (E1) and Engineering 2 (E2) buildings.


For more information on other scheduled IEEE talks please visit the IEEE Grid site.
For more information about the IEEE Monterey Bay Subsection please click Here