Archive Home arrow Tech Affiliates: arrow Tech News arrow NVIDIA CUDA: Week in Review - Issue 63
NVIDIA CUDA: Week in Review - Issue 63
Written by NVIDIA - Calisa Cole   
Monday, 24 October 2011

NVIDIA CUDA: Week in Review - Issue 63

CUDA SPOTLIGHT: GPU-Accelerated Climate Simulation

This week's Spotlight is on William Putman, a NASA research meteorologist in the Global Modeling and Assimilation Office (GMAO) in the Earth Sciences Division of Goddard Space Flight Center's Sciences and Exploration Directorate. Here's an extract from our interview:

NVIDIA: Bill, what does your group do?

Bill: Our research and development activities aim to maximize the impact of satellite observations in climate, weather and atmospheric composition prediction using comprehensive global models and data assimilation.

To achieve this goal, the GMAO develops models and assimilation systems for the atmosphere, ocean, and land surface, generates products to support NASA instrument teams and the NASA Earth Science program, and undertakes scientific research to inform system development pathways.

Within the GMAO we have a group of developers (Dr. Max Suarez, Dr. Matthew Thompson and myself) tasked with the restructuring of NASA's Goddard Earth Observing System atmospheric general circulation model version 5 (GEOS-5) to take advantage of new accelerator technologies including GPUs.

NVIDIA: What are the benefits of using CUDA?

Bill: The Portland Group (PGI) offers us an opportunity to explicitly program for GPUs using CUDA Fortran and also provides a directive-based accelerator model. GEOS-5 is primarily written in Fortran, thus the PGI CUDA Fortran syntax allows us to develop GPU kernels in GEOS-5 using a familiar coding environment. Like CUDA C, CUDA Fortran allows for low-level management of the initialization, data transfer, and coding details of a project without the need to translate legacy Fortran code into C. This aids both in speed of development and with keeping a readable (to developers) codebase within GEOS-5 while achieving much the same performance as CUDA C.

Read the complete interview here.

CUDA DEVELOPER NEWS

October CUDA Webinar Lineup

  • Tues., Oct. 11: PGI Accelerator for C - Simplified GPU Programming Using Directives

Presented by Dr. Michael Wolfe, The Portland Group

https://www2.gotomeeting.com/register/623491562

  • Tues., Oct. 11: CUDA Optimization: Memory Bandwidth Limited Kernels + Live Q&A

Presented by Tim Schroeder, NVIDIA

https://www2.gotomeeting.com/register/936728978

  • Wed., Oct. 12: Intro to Parallel Nsight and Features (Preview of Version 2.1)

Presented by Shane Evans, NVIDIA

https://www2.gotomeeting.com/register/522390506

  • Thurs., Oct 20: Overview and Usage of LibJacket CUDA Library

Presented by James Malcolm, AccelerEyes (with NVIDIA)

https://www2.gotomeeting.com/register/378528682

  • Thurs., Oct. 27: GPU Computing with MATLAB

Presented by Sarah Wait Zaranek, MathWorks

https://www.mathworks.com/company/events/webinars/wbnr59816.html

Awards and Recognitions

The Johns Hopkins University has been named a CUDA Center of Excellence, recognizing its ground-breaking work leveraging GPU computing. As a CCOE, Johns Hopkins will utilize equipment and grants provided by NVIDIA to support a number of research and academic programs, including deployment of the "Data-Scope," a GPU-powered, ultra-high throughput supercomputer to dramatically increase the speed of scientific data analysis: https://bit.ly/qOiVRI

Boise State University, a CUDA Research Center, received two grants that build on GPU computing initiatives:

- NOAA Field Research Office collaboration to develop a CUDA Fortran version of NOAA's HYSPLIT Air Dispersion model: https://ready.arl.noaa.gov/HYSPLIT.php

- NSF CAREER Grant for multi-scale modeling of short-term forecasting and grid integration of wind energy: https://1.usa.gov/p3xWRu

This year's PRACE (Partnership for Advanced Computing in Europe) Award goes to a paper titled "Astrophysical Particle Simulations with Large Custom GPU Clusters on Three Continents." Prof. Richard Kenway, Chairman of the PRACE Scientific Steering Committee, noted that "the work points the way to exploit exascale technologies for problems at the forefront of science." https://www.prace-project.eu/news/the-prace-award-winners-2011-announced

CUDA on the Web

A new video on "Volt: Interactive Volume Rendering with CUDA" has been posted by the Computer Graphics Lab at the Bonn-Rhine-Sieg University of Applied Sciences. Volt is an interactive direct volume renderer that takes advantage of GPUs for high quality interactive ray casting.

- https://cg.inf.fh-bonn-rhein-sieg.de/?page_id=2700

The Irish Center for High-End Computing (ICHEC) launched a new website dedicated to GPU computing. ICHEC's Director, Prof. James Slevin, said: "Computer simulation has now reached a level of predictability that firmly grounds its impact and importance along with theory and experimentation as the third pillar of science research."

- https://gpgpu.ichec.ie/

Industrial Mathematics KTN released a new report on "The GPU Computing Revolution: from Multi-Core CPUs to Many-Core Graphics Processors." Produced in collaboration with the London Mathematical Society, it was written by Simon McIntosh-Smith of the University of Bristol.

- https://connect.innovateuk.org/web/mathsktn/articles/-/blogs/the-gpu-computing-revolution

Read CUDA: Week in Review on the web at: https://developer.nvidia.com/cuda-news


Related Articles:
 

Comments have been disabled by the administrator.

Search Benchmark Reviews Archive