Abstract
In this talk, I will cover three topics: 1) The G80 architecture, 2) The
CUDA programming language, and 3) and recent work on N-Body simulation.
The G80 architecture supports both graphics and non-graphics
computation, using an array of custom processors on a single chip. The
programming model is neither SIMD nor MIMD, but somewhere in between,
where we can exploit the advantages of each. The current performance
part has 128 processors running at 1.3 - 1.5 GHz. With dual-issue
capabilities, this places the peak performance near 500 GFLOPS.
CUDA is the C programming language with a few extensions for programming
the G80. These include thread launch/terminate, synchronization,
sharing, and atomic operations.
In a collaborative effort with Jan Prins (UNC CS) and Mark Harris
(NVIDIA), we have written an N-Body simulator using CUDA that runs on
NVIDIA hardware. We achieve a sustained computational rate of 210
GFLOPS, or 16k bodies interacting at nearly 30 steps/second. This is
substantially faster than a conventional CPU, as the core of the
computation relies on 1/sqrt(x), a optimized function on the G80, as it
is required in graphics (and physics) for normalizing vectors.
I'll summarize with thoughts about the availability of accelerated
computing.
Biography
Lars Nyland is a senior architect in the "compute" group at NVIDIA,
where he designs, develops and tests architectural features to support
non-traditional uses of graphics processors. Prior to joining NVIDIA,
Lars was an associate professor of computer science at the Colorado
School of Mines in Golden, Colorado. He ran the Thunder Graphics Lab,
where demanding computational applications were coupled with immersive,
3D graphics. Between Lars' PhD and his position in Colorado, he was a
member of the research faculty at UNC, Chapel Hill. Some notable
achievements were the development of the DeltaSphere scene digitizer and
its use at Monticello to provide an immersive experience for visitors to
the New Orleans Museum of Art's "Jefferson and Napoleon" exhibit. He
also spent considerable time studying N-Body algorithms, parallelism of
N-Body algorithms for Molecular Dynamics, and parallel programming
languages. Lars earned his PhD at Duke University in 1991 under the
direction of John Reif, exploring high-level parallel programming
languages.
