By rge21
Our paper describing how we implemented the Real Time System (RTS) of the Murchison Widefield Array (MWA) on GPUs has now been accepted by Computer Physics Communications, and is online at arxiv. GPU acceleration was key to this project, a demanding signal processing application.
By admin
The Murchison Widefield Array is using a real-time GPU correlator to enable engineering and early science for a 5% prototype. Read more about how this system works! See online coverage of the MWA showcasing GPU computing efficiency, as described at the NVIDIA GPU Technology Conference, San Jose 2009. Take a look at the related talk, [click on link for more...]
By admin
A paper by:
Randall B. Wayth, Lincoln J. Greenhill (Harvard-Smithsonian Center for Astrophysics) and
Frank H. Briggs (Research School of Astronomy and Astrophysics, Australian National University)
Modern graphics processing units (GPUs) are inexpensive commodity hardware that offer Tflop/s theoretical computing capacity. GPUs are well suited to many compute-intensive tasks including digital signal processing. We describe the implementation and [click on link for more...]
By admin
Slides from a talk describing the Murchison Widefield Array given at the NVIDIA GPU Technology Conference in San Jose, CA on 3rd October 2009.
Download slides [1.6 MB]: NVIDIA-GTC-MWA
By admin
A popular account of the SciGPU project has been posted online by the Harvard News Office.
Writer Alvin Powell describes the “trio of projects at Harvard whose massive computing needs have prompted investigators to join forces to pioneer new computing techniques that will benefit not just radio astronomy, but quantum chemistry and neuroscience as well.”
In interviews [click on link for more...]
By admin
The SciGPU collaborators welcomed four students who came to Harvard for NSF-funded Research Experiences for Undergraduates during summer 2009: Dominik Gothe (University of South Carolina; astronomy), Matthias Lee (Wentworth Institute; time series analysis), Beatrice Perez (University of Puerto Rico; quantum chemistry), and Bo Wang (University of Pittsburgh; neuroscience). The SciGPU REU students were among [click on link for more...]
By admin
Our four summer Research Experience for Undergraduates (REU) students (Dominik Gothe, Matthias Lee, Beatrice Perez and Bo Wang) recently gave excellent presentations on the research they conducted this summer. Their work covered the Murchison Widefield Array, Quantum Chemistry, the Connectome and the Time Series Centre. Copies of their talks are now available for download.
Gothe_MWA_Areas
Lee_GPU_Searching
Perez_Quantum_Chemistry
Wang_Segmenting_Axons
By admin
High Performance Computing as Linchpin in Next-generation Radio Telescopes
IIC Colloquium Series
April 15, 2009
Dr. Lincoln Greenhill
Abstract
———-
Frontier astronomy facilities in the next decade will pose serious and data-intensive science challenges. In a new paradigm for radio astronomy, high-performance computing will be front and center as a critical element of the interferometric arrays that will make tomographic maps [click on link for more...]
By admin
The Murchison Widefield Array (MWA) is a radio telescope currently under construction in Australia. It is an interferometer, consisting of over 500 antenna tiles spread over an area of about a square kilometer. The signals from these tiles are synthesized into images by the Real Time System (RTS).
In this talk, Richard Edgar describes why [click on link for more...]
By admin
The following news was released April 2, 2009 by NVIDIA Corporation. The company’s release can be found here.
SANTA CLARA, CA—NVIDIA Corporation, inventor of the GPU, today announced that Harvard University has been recognized as a CUDA Center of Excellence for its commitment to teaching GPU Computing and its integration of CUDA™-enabled GPUs for a host [click on link for more...]