Barba Receives Prestigious High-Performance Computing Fellowship

By Mark Dwortzan

Assistant Professor Lorena Barba (ME)
Assistant Professor Lorena Barba (ME)

Widely used in science, engineering and other computationally driven fields since its introduction in 2006, CUDA is a parallel computing platform and programming model developed by the NVIDIA Corporation that uses graphics processing units (GPUs) to dramatically boost the speed of computer applications, from global climate models to video games.

An early adopter of this technology for scientific computing and expert in computational fluid dynamics, Assistant Professor Lorena Barba (ME) has promoted the use of the CUDA architecture and GPU computing throughout the Americas. Now, in recognition of her trailblazing efforts, the NVIDIA Corporation has named Barba one of four new CUDA Fellows. Fellows receive financial support for their leading GPU computing research, a travel stipend to enable them to share their expertise at universities and technical conferences around the world, and some of the latest NVIDIA GPU hardware and software.

“By recognizing me as a CUDA Fellow, NVIDIA has given an extra boost of confidence to my efforts, both research and educational, to advance GPU computing for science,” said Barba. Such support is especially meaningful when you consider that computational science and engineering often falls in the cracks of organizational structures and traditional disciplinary boundaries.”

Barba is the first female appointee to the invitation-only CUDA Fellows program, which has honored only nine global leaders in GPU computing since its inception in 2008. The other 2012 Fellows are based at University of Malaga, Amazon.com and Tokyo Institute of Technology. 

“Each of these individuals has demonstrated a passion and commitment to using CUDA and the power of GPU computing to help solve some of the world’s most challenging computational problems,” said Bill Dally, chief scientist at NVIDIA. “We look forward to working with them to continue spreading the word about the industry-changing impact GPU computing offers to developers, researchers and academics worldwide.”

A faculty fellow of the Boston University Rafik Hariri Institute for Computing and Computational Science & Engineering and a visiting research professor at the Scientific and Technological Center of Valparaíso in Chile, Barba was the first to advocate GPUs as a gateway for scientifically developing countries to access high-performance computing.

Last year she oversaw the adoption of GPUs at her alma mater, Universidad Técnica Federico Santa María in Valparaiso, Chile, which became the first CUDA Teaching Center in Chile. She also organized the National Science Foundation and Department of Energy-funded Pan-American Advanced Studies Institute “Scientific Computing in the Americas: the Challenge of Massive Parallelism in Chile, where about 70 graduate students and postdoctoral fellows from the U.S. and Latin America received instruction on parallel computing and GPUs from leaders in the field.

Barba has a leading role in the first Innovative Parallel Computing conference, InPar’12, a new academic publication venue of the GPU Technology Conference which convenes in mid-May in San Jose, California. A recent recipient of the prestigious NSF CAREER award for GPU-related research and a NVIDIA Academic Partner award recipient in 2011, she is also co-principal investigator of an NSF grant that brought to BU the first GPU cluster—a computer cluster in which each node contains a GPU accelerator.

Fueling all of these achievements is a strong belief in the potential of GPU technology to vastly improve computing performance.

“We all know that parallel programming is hard, but the crux is that parallelism is the only avenue for increasing computing performance in the foreseeable future,” said Barba in a recent NVIDIA interview. “So if most coding will have to be parallel, why not take the plunge and take advantage of the most parallel hardware around? That is the GPU right now, and will be for the foreseeable future.” 

Back to news headlines