TOP 500 COMPUTERS IN THE WORLD
The TOP500 venture positions and points of interest the 500 most capable non-appropriated PC frameworks on the planet. The undertaking was begun in 1993 and distributes an upgraded rundown of the supercomputers twice per year. The first of these upgrades dependably corresponds with the International Supercomputing Conference in June, and the second is introduced in November at the ACM/IEEE Supercomputing Conference. The venture means to give a solid premise to following and distinguishing patterns in superior processing and constructs rankings in light of HPL,[1] a convenient usage of the elite LINPACK benchmark written in Fortran for dispersed memory PCs. Starting July 2016, the Sunway TaihuLight is the most effective supercomputer, achieving 93.015 petaflops on the LINPACK benchmarks. The TOP500 rundown is incorporated by Jack Dongarra of the University of Tennessee, Knoxville, Erich Strohmaier and Horst Simon of NERSC/Lawrence Berkeley National Laboratory (and, from 1993 until his demise in 2014, Hans Meuer of the University of Mannheim, Germany.)
HISTORY:
In the mid 1990s, another meaning of supercomputer was expected to deliver important measurements. In the wake of trying different things with measurements in light of processor check in 1992, the thought was conceived at the University of Mannheim to utilize a definite posting of introduced frameworks as the premise. In mid 1993, Jack Dongarra was convinced to join the venture with his LINPACK benchmark. A first test rendition was created in May 1993, incompletely in light of information accessible on the Internet, including the accompanying sources:[2][3]
"Rundown of the World's Most Powerful Computing Sites" kept up by Gunter Ahrendt[4]
David Kahaner, the chief of the Asian Technology Information Program (ATIP),[5] in 1992 had distributed a report titled "Kahaner Report on Supercomputer in Japan"[3] which had a colossal measure of data.[citation needed]
The data from those sources was utilized for the initial two records. Since June 1993, the TOP500 is created bi-every year taking into account site and seller entries as it were.
Since 1993, execution of the #1 positioned position has relentlessly developed in concurrence with Moore's law, multiplying generally at regular intervals. As of November 2014, the quickest framework, the Tianhe-2 with a Rpeak[6] of 54.9024 PFLOPS, is more than 419,102 times speedier than the speediest framework in November 1993, the Connection Machine CM-5/(1024 centers) with Rpeak of 131.0 GFLOPS.[7]
Architecture and operating systems:
As of November 2015, TOP500 supercomputers are generally in view of x86-64 CPUs (Intel EMT64 and AMD AMD64 guideline set design), with couple of special cases (all RISC-based) including 39 supercomputers in view of Power Architecture utilized by IBM POWER microchips, seven SPARC (all Fujitsu/SPARC-based, one of which shockingly made the top in 2011 without a GPU, presently positioned fourth), and one ShenWei-based (positioned 11 in 2011, positioned 65th in November 2014) making up the rest of. Before the ascendance of 32-bit x86 and later 64-bit x86-64 in the mid 2000s, an assortment of RISC processor families made up the dominant part of TOP500 supercomputers, including RISC designs, for example, SPARC, MIPS, PA-RISC and Alpha.
As of late heterogeneous registering, for the most part utilizing Nvidia's representation preparing units (GPU) as coprocessors, has turned into a mainstream approach to achieve a superior execution for each watt proportion and higher total execution; it is verging on required for good execution and to make the top (or main 10), with a few special cases, for example, the specified SPARC PC with no coprocessors. A x86-based coprocessor, Xeon Phi, has additionally been utilized.
TOP 10 RANKING:
Rank |
Name |
Model |
Processor |
Vendor |
Site |
|
Country, year |
||||||
1 | Sunway TaihuLight | Sunway MPP | SW26010 | NRCPC | National Supercomputing Center in Wuxi | |
|
||||||
China, 2016[14] | ||||||
2 | Tianhe-2 | TH-IVB-FEP | Xeon E5–2692, Xeon Phi 31S1P | NUDT | National Supercomputing Center in Guangzhou | |
|
||||||
3 | Titan | Cray XK7 | Opteron 6274, Tesla K20X | Cray Inc. | Oak Ridge National Laboratory | |
|
||||||
United States, 2012 | ||||||
4 | Sequoia | Blue Gene/Q | PowerPC A2 | IBM | Lawrence Livermore National Laboratory | |
|
||||||
United States, 2013 | ||||||
5 | K computer | K computer | SPARC64 VIIIfx | Fujitsu | RIKEN | |
|
||||||
Japan, 2011 | ||||||
6 | Mira | Blue Gene/Q | PowerPC A2 | IBM | Argonne National Laboratory | |
|
||||||
7 | Trinity | Cray XC40 | Xeon E5-2698v3 | Cray Inc. |
|
|
United States, 2015 | ||||||
8 | Piz Daint | Cray XC30 | Xeon E5–2670, Tesla K20X | Cray Inc. | Swiss National Supercomputing Centre | |
|
||||||
Switzerland, 2013 | ||||||
9 | Hazel Hen | Cray XC40 | Xeon E5-2680v3 | Cray Inc. |
|
|
Germany, 2015 | ||||||
10 | Shaheen II | Cray XC40 | Xeon E5–2698v3 | Cray Inc. | King Abdullah University of Science and Technology | |
|
Legend:
- Rank – Position within the TOP500 ranking. In the TOP500 list table, the computers are ordered first by their Rmax value. In the case of equal performances (Rmax value) for different computers, the order is by Rpeak. For sites that have the same computer, the order is by memory size and then alphabetically.
- Rmax – The highest score measured using the LINPACK benchmark suite. This is the number that is used to rank the computers. Measured in quadrillions of floating point operations per second, i.e. petaflops.
- Rpeak – This is the theoretical peak performance of the system. Measured in PFLOPS.
- Name – Some supercomputers are unique, at least on its location, and are therefore named by their owner.
- Computer – The computing platform as it is marketed.
- Processor cores – The number of active processor cores actively used running LINPACK. After this figure is the processor architecture of the cores named. If the interconnect between computing nodes is of interest, it's also included here.
- Vendor – The manufacturer of the platform and hardware.
- Site – The name of the facility operating the supercomputer.
- Country – The country in which the computer is situated.
- Year – The year of installation/last major update.
- Operating system – The operating system that the computer uses
No comments:
Post a Comment