TOP500

From Wikipedia, the free encyclopedia

The TOP500 project ranks and details the 500 most powerful publicly-known computer systems in the world. The project was started in 1993 and publishes an updated list of the supercomputers twice a year. The project aims to provide a reliable basis for tracking and detecting trends in high-performance computing and bases rankings on HPL, a portable implementation of the High-Performance LINPACK benchmark for distributed-memory computers.

The TOP500 list is compiled by Hans Meuer of the University of Mannheim, Germany, Jack Dongarra of the University of Tennessee, Knoxville, Erich Strohmaier and Horst Simon of NERSC/Lawrence Berkeley National Laboratory.

The list is updated twice a year. The first of these updates always coincides with the International Supercomputer Conference in June, the second one is presented in November at the IEEE Super Computer Conference in the USA.

1 Project History
- 1.1 The Systems Ranked #1 Since 1993
2 Current List (November 2006)
3 References
4 External links

[edit] Project History

In the early nineties a new definition of supercomputer was needed to produce meaningful statistics. After experimenting with metrics based on processor count in 1992 the idea was born at the University of Mannheim to use a detailed listing of installed systems as the basis. Early 1993 Jack Dongarra was convinced to join the project with his Linpack benchmark. A first test version was produced in May 1993 partially based on data available on the internet, including the following sources[1][2]:

Mannheim Supercomputer Statistics 1986-1992
one was "List of the World's Most Powerful Computing Sites" [3] maintained by Gunter Ahrendt
another was through David Kahaner, who had an immense amount of data.

The information from those sources was used for the first two lists. Since June 1993 the TOP500 is produced bi-annually based on site and vendor submissions only.

[edit] The Systems Ranked #1 Since 1993

IBM Blue Gene/L (since 2004.11)
NEC Earth Simulator (2002.06 - 2004.11)
IBM ASCI White (2000.11 - 2002.06)
Intel ASCI Red (1997.06 - 2000.11)
Hitachi CP-PACS (1996.11 - 1997.06)
Hitachi SR2201 (1996.06 - 1996.11)
Fujitsu Numerical Wind Tunnel (1994.11 - 1996.06)
Intel Paragon XP/S140 (1994.06 - 1994.11)
Fujitsu Numerical Wind Tunnel (1993.11 - 1994.06)
TMC CM-5 (1993.06 - 1993.11)

[edit] Current List (November 2006)

The following table gives the Top 10 positions of the 28th TOP500 List released during the Supercomputing Conference (SC06), November 11-17, 2006 in Tampa, Florida.http://sc06.supercomputing.org/

Rank	Site/Country/Year	Name/Computer/Processors	Manufacturer	Rmax/Rpeak (Gflops)
1	Lawrence Livermore National Laboratory United States / 2005	BlueGene/L eServer Blue Gene Solution / 131072 (Power)	IBM	280600/367000
2	Sandia National Laboratories United States / 2006	Red Storm Cray XT3 / 26544 (Opteron)	Cray	101400/127411
3	IBM Thomas J. Watson Research Center United States / 2005	BGW eServer Blue Gene Solution / 40960 (Power)	IBM	91290/114688
4	Lawrence Livermore National Laboratory United States / 2005	ASC Purple eServer pSeries p5 575 1.9 GHz / 12208 (Power)	IBM	75760/92781
5	Barcelona Supercomputing Center Spain / 2006	MareNostrum BladeCenter JS21, 2.3 GHz, Myrinet / 10240 (Power)	IBM	62630/94208
6	Sandia National Laboratories United States / 2006	Thunderbird Dell PowerEdge 1850 3.6 GHz, Infiniband / 9024 (Xeon)	Dell	53000/64972.8
7	Commissariat à l'Énergie Atomique France / 2006	Tera-10 NovaScale 5160, 1.6 GHz, Quadrics / 9968 (Itanium 2)	Bull SA	52840/63795.2
8	NASA Ames Research Center United States / 2004	Columbia SGI Altix 3700 1.5 GHz, Voltaire Infiniband / 10160 (Itanium 2)	SGI	51870/60960
9	GSIC Center, Tokyo Institute of Technology Japan / 2006	TSUBAME Grid Cluster Sun Fire X6400 Cluster, 2.4/2.6 GHz, ClearSpeed accelerators, Infiniband / 11088 (Opteron)	NEC and Sun	47380/82124.8
10	Oak Ridge National Laboratory United States / 2006	Jaguar Cray XT3 / 10424 (Opteron)	Cray	43480/54204.8

[edit] Highlights from the Top 10

Taken from the official TOP500 site:

Unchallenged leader remains the DOE's IBM BlueGene/L system, installed at DOE’s Lawrence Livermore National Laboratory (LLNL).
The new No. 2 systems is Sandia National Laboratories’ Cray Red Storm supercomputer, only the second system ever to be recorded to exceed the 100 Tflops mark with 101.4 Tflops.
The new No. 5 is the largest system in Europe, an IBM JS21 cluster installed at the Barcelona Supercomputing Center
The Earth Simulator, built by NEC, which held the No. 1 spot for five lists, has now slipped out of the TOP10 and is ranked at No 14.

[edit] General highlights from the Top 500 since the last edition

Taken from the official TOP500 site:

The entry level to the list moved up to the 2.7369 Tflops mark on the Linpack benchmark, compared to 2.026 Tflops six months ago.
The entry point for the top 100 increased in six months from 4.71 Tflops to 6.62 Tflops.
The last system on the newest list was listed at position 362 in the last TOP500 just six months ago. This is a medium turnover rate for the TOP500. Please verify the medium turnover rate claim
Total accumulated performance has grown to 3.53 Pflops, compared to 2.79 Pflops six months ago and 2.30 Pflops one year ago.

[edit] Trends

A paper^[1] made available in early 2007 presents the results of some statistical analyzes of the Top 500 from 1993 to 2006. Some of the conclusions are:

Each list exhibits a Zipf distribution
Speeds increase by about 90% per year.
The relative power of the bottom of the list as compared to the top of the list has increased each year.

[edit] Systems of Interest

The MDGRAPE-3 supercomputer reportedly reached a one Petaflop calculation speed, faster than any of those on the TOP500 list, though it does not qualify as a general-purpose supercomputer, and cannot run the benchmarking software used to gauge the speeds computed for the list.