Encompassing the Whole World Front Page /// Beowulf Cluster /// Site Index


In the ancient saga of Beowulf, Wiglaf was his trusted aid.

In this case, Beowulf is a relatively new way of building supercomputers out of clusters of inexpensive, commodity off the shelf computers, and Wiglaf is the first example of this Extreme way of building massively parallel computers.

The Wiglaf Beowulf cluster was started at nasa in 1994 when they needed a supercomputer for data analysis, but couldn't buy one of sufficient power for a cheap enough price. It was built out of 16 pc's that were 66 Mhz 486 processors, with standard off-the-shelf network cards, and the free operating system Linux.

It was quickly upgraded to use 100 Mhz DX4 486's, and even with this primitive level of technology, was able to compete with contemporary massively parallel processing supercomputers like the TMC CM5 connection machine (for problems that were suitable for it's architecture).

Sustained performance of 4.6 Mflops per node (74 Mflops total) was achieved for certain types of compute intensive applications.

When they built the second Beowulf Hrothgar using pentium based pc's the figures went up to 17.5 Mflops per node and 280 Mflops total.

When the third generation of these machines came along, one of them (Avalon) produced a sustained performance of 48 Gflops, putting it 113th on a popular list of the world's 500 most powerful computers in 1998.

The plans for the current generation of Beowulf Clusters include machines with thousands of processors, using multiprocessor pc's, with the fastest currently available processors in each pc.