SCIENCE & ENGINEERING NEWS

Mannheim, GERMANY — To provide a basis for statistics on high-performance computers, Hans W. Meuer, Erich Strohmaier and Jack J. Dongarra have put together the TOP500 Supercomputer List. The list is a collection of the sites that, according to stipulated criteria, have the 500 most powerful computer systems installed. The next release of the TOP500 Supercomputer List will be presented at the SC2000, November 4-10 in Dallas, TX.

The deadline for submitting entries is October 6, 2000. All systems reported have to be installed by October 30, 2000.

The List’s maintainers are interested in new entries as well as entries that are no longer valid. Following is a transcript of the guidelines for submission of entries.

To provide a better basis for statistics on high-performance computers, we list twice a year the sites that have the 500 most powerful computer systems installed. The best Linpack benchmark performance achieved is used as a performance measure in ranking the computers.

SUBMISSIONS

Companies or individuals may submit entries for inclusion to us. Submissions should contain the following information:

Manufacturer Manufacturer or vendor Computer system Type indicated by manufacturer or vendor Installation Site Customer – Full name of company or institution Location Location and country Year Year of installation/last major update Field of Application type of customer (university, government, industry,
…) as well as typical application (geophysics,
automotive, chemical, benchmarking, …) Processors Number of processors (as well as type if necessary) Memory Main memory configuration of the system

LINPACK PERFORMANCE

Performance numbers for the Linpack benchmark are collected and updated by Jack Dongarra ([email protected]). Please report any Linpack performance numbers directly to him.

METHOD OF SOLUTION

In an attempt to obtain uniformity across all computers in performance reporting, the algorithm used in solving the system of equations in the benchmark procedure must confirm to the standard operation count for LU factorization with partial pivoting. In particular, the operation count for the algorithm must be 2/3 n^3 + O(n^2) floating point operations. This excludes the use of a fast matrix multiply algorithm like “Strassian’s Method”. This is done to provide a comparable set of performance numbers across all computers.

VERIFICATION

In addition to cross checking different sources of information, we select randomly a statistical representative sample of the first 500 systems of our database. For these systems we ask the supplier of the information to establish direct contact between the installation site and us to verify the given information. This gives us basic information about the quality of the list in total.

RESTRICTIONS

As the TOP500 should provide a basis for statistics on the market of high-performance computers, we limit the number of systems installed at vendor sites. This is done for each vendor separately by limiting the accumulated performance of systems at vendor sites to a maximum of 5 percent of the total accumulated installed performance of this vendor. Rounding is done in favor of the vendor in question.

The TOP500 List keepers can be reached by sending mail to [email protected]

The current list of the TOP500, as well as the former lists, is available at the following Web sites:

http://www.top500.org/

http://www.netlib.org/benchmark/top500.html

============================================================