State of the Cell

December 23, 2007

Originally posted at, and thus, looks much better there.

The Cell Broadband Engine Architecture (which we shall refer to as simply the Cell architecture) was designed as a compromise between the general-purpose but slower CPU and the specific-purpose and faster GPU. It is a heterogeneous architecture: it contains processing units that specialize in different tasks. However, critics (and even some fans) of the Cell architecture claim that it is incredibly difficult to produce good, fast code on it. Having spent the last quarter working with the Cell architecture, we agree with this sentiment. But why?

Read the rest of this entry »

Multigrid Methods with CUDA

December 20, 2007

Originally posted at, and thus, looks much better there.

Over the last quarter I have been investigating how to implement a multigrid algorithm with CUDA, a new language aimed at making General Purpose Computation on GPUs (GPGPU) easier. This web page documents this experience.

Read the rest of this entry »


December 20, 2007

Grades are in!

GPGPU and 3D User Interfaces: A

Parallel Architectures: A+

Directed Research: S

Cognitive Science Seminar: S

I don’t know what an S means (satisfactory?), but the first quarter rocked! I’ll put up versions of my work here soon!

New Topics for Fall 2007

September 14, 2007

So I start up classes at UCSB in two weeks, so don’t be surprised to see some new posts deviating from the normal formula (MATLAB 🙂 ) Specifically, I’m taking a class on “GPU Power and 3D User Interfaces”, “Parallel Computer Architectures”, and an intro seminar to Cognitive Science.

At the moment, I’m looking into exploiting the GPGPU and virtualization on the Cell architecture, but I’ll write more about it when I have some more concrete details.