About: Fujitsu VP2000     Goto   Sponge   NotDistinct   Permalink

An Entity of Type : yago:Whole100003553, within Data Space : dbpedia.demo.openlinksw.com associated with source document(s)
QRcode icon
http://dbpedia.demo.openlinksw.com/describe/?url=http%3A%2F%2Fdbpedia.org%2Fresource%2FFujitsu_VP2000&invfp=IFP_OFF&sas=SAME_AS_OFF

The VP2000 was the second series of vector supercomputers from Fujitsu. Announced in December 1988, they replaced Fujitsu's earlier FACOM VP Model E Series. The VP2000 was succeeded in 1995 by the VPP300, a massively parallel supercomputer with up to 256 vector processors. One of the major complaints about the earlier VP series was their limited memory bandwidth—while the machines themselves had excellent performance in the processors, they were often starved for data. For the VP2000 series this was addressed by adding a second load/store unit to the scalar units, doubling memory bandwidth.

AttributesValues
rdf:type
rdfs:label
  • Fujitsu VP2000 (en)
  • Fujitsu VP2000 (it)
  • VP2000 (ja)
rdfs:comment
  • The VP2000 was the second series of vector supercomputers from Fujitsu. Announced in December 1988, they replaced Fujitsu's earlier FACOM VP Model E Series. The VP2000 was succeeded in 1995 by the VPP300, a massively parallel supercomputer with up to 256 vector processors. One of the major complaints about the earlier VP series was their limited memory bandwidth—while the machines themselves had excellent performance in the processors, they were often starved for data. For the VP2000 series this was addressed by adding a second load/store unit to the scalar units, doubling memory bandwidth. (en)
  • Il VP2000 era la seconda linea di supercomputer vettoriali prodotti da Fujitsu. La linea rimpiazzo la Fujitsu VP e venne presentata nel 1990 e venne venduta per un breve periodo prima di venir rimpiazzata da macchine basate su parallelismo massivo. Come molte altre compagnie Fujitsu decise di basare i suoi nuovi supercomputer sul parallelismo massivo e la famiglia VP2000 non fu venduta a lungo, sebbene furono vendute più di 100 unità. (it)
  • VP2000は、富士通のベクトル型スーパーコンピュータの第二段のシリーズ。 1988年12月に発表され、富士通の以前のFACOM VPモデルEシリーズの後継となった。 VP2000の後継として、1995年に、最大256個のベクトルプロセッサを備えた超並列スーパーコンピュータであるVPP300が登場した。 VP2000は、パフォーマンス向上のためにレジスタベースのベクトルプロセッサを使用しており、以前の設計と多くの点で類似しており、Cray-1とも類似していた。パフォーマンスを向上させるために、ベクトルユニットは、クロックサイクルごとに2つの結果をリタイアできる特別な乗算および加算命令をサポートしていた。この命令「チェーン」は、多くのスーパーコンピューターアプリケーションで一般的に採用されている。 もう1つの違いは、プロセッサのメインスカラーユニットがベクトルユニットの半分の速度で実行されたことである。アムダールの法則によれば、コンピュータは最も遅いユニットの速度で実行される傾向があり、この場合、プログラムがほとんどの時間をベクトルユニットで費やさない限り、スカラーのパフォーマンスが遅いと、同じ速度でもCray-1のパフォーマンスの1/2になってしまう。 (ja)
dcterms:subject
Wikipage page ID
Wikipage revision ID
Link from a Wikipage to another Wikipage
sameAs
dbp:wikiPageUsesTemplate
title
years
has abstract
  • The VP2000 was the second series of vector supercomputers from Fujitsu. Announced in December 1988, they replaced Fujitsu's earlier FACOM VP Model E Series. The VP2000 was succeeded in 1995 by the VPP300, a massively parallel supercomputer with up to 256 vector processors. The VP2000 was similar in many ways to their earlier designs, and in turn to the Cray-1, using a register-based vector processor for performance. For additional performance the vector units supported a special multiply-and-add instruction that could retire two results per clock cycle. This instruction "chain" is particularly common in many supercomputer applications. Another difference is that the main scalar units of the processor ran at half the speed of the vector unit. According to Amdahl's Law computers tend to run at the speed of their slowest unit, and in this case unless the program spent most of its time in the vector units, the slower scalar performance would make it 1/2 the performance of a Cray-1 at the same speed. The reason for this seemingly odd "feature" is unclear. One of the major complaints about the earlier VP series was their limited memory bandwidth—while the machines themselves had excellent performance in the processors, they were often starved for data. For the VP2000 series this was addressed by adding a second load/store unit to the scalar units, doubling memory bandwidth. Several versions of the machines were sold at different price points. The low-end VP2100 ran at an 8 ns cycle time and delivered only 0.5 GFLOPS (about 4-8 times the performance of a Cray), while the VP2200 and VP2400 decreased the cycle time to 4 ns and delivered between 1.25 and 2.5 GFLOPS peak. The high-end VP2600 ran at 3.2 ns and delivered 5 GFLOPS. All of the models came in the /10 versions with a single scalar processor, or the /20 with a second, while the 2200 and 2400 also came in a /40 configuration with four. Due to the additional load/store units, adding additional scalar units improved performance by increasing memory bandwidth, as well as allowing several programs to run at the same time and thereby increase the chance there was something to process on the vector unit. Each unit is said to increase performance 1.5 times, allowing the VP2400/40 to match the performance of the earlier VP2600/20. The machines were supplied with either the Unix-compatible UXP/M or the MVS-compatible VSP/S operating systems, both supplied by Amdahl. The later was used for Fortran programs while the former was typically used for C, and vectorizing compilers were supplied for both languages. Like most companies, Fujitsu turned to massive parallelism for future machines, and the VP2000 family were not on the market for very long. Nevertheless, over 100 were sold, and in July 1993, there were 180 installed. (en)
  • VP2000は、富士通のベクトル型スーパーコンピュータの第二段のシリーズ。 1988年12月に発表され、富士通の以前のFACOM VPモデルEシリーズの後継となった。 VP2000の後継として、1995年に、最大256個のベクトルプロセッサを備えた超並列スーパーコンピュータであるVPP300が登場した。 VP2000は、パフォーマンス向上のためにレジスタベースのベクトルプロセッサを使用しており、以前の設計と多くの点で類似しており、Cray-1とも類似していた。パフォーマンスを向上させるために、ベクトルユニットは、クロックサイクルごとに2つの結果をリタイアできる特別な乗算および加算命令をサポートしていた。この命令「チェーン」は、多くのスーパーコンピューターアプリケーションで一般的に採用されている。 もう1つの違いは、プロセッサのメインスカラーユニットがベクトルユニットの半分の速度で実行されたことである。アムダールの法則によれば、コンピュータは最も遅いユニットの速度で実行される傾向があり、この場合、プログラムがほとんどの時間をベクトルユニットで費やさない限り、スカラーのパフォーマンスが遅いと、同じ速度でもCray-1のパフォーマンスの1/2になってしまう。 以前のVPシリーズに関する主な不満の1つは、メモリ帯域幅が限られていたことだった。マシン自体はプロセッサで優れたパフォーマンスを発揮したが、データが不足することがよくあった。 VP2000シリーズの場合、これは、2番目のロード/ストアユニットをスカラーユニットに追加し、メモリ帯域幅を2倍にすることで対処された。 マシンのいくつかのバージョンは、異なる価格で販売された。ローエンドVP2100は8 nsサイクルタイムで実行され、0.5 GFLOPS(Crayの約4〜8倍のパフォーマンス)であったのに対し、 VP2200およびVP2400はサイクルタイムを4 nsに短縮して、ピーク時に1.25〜2.5 GFLOPSを記録した。ハイエンドのVP2600は3.2 nsで動作し、5 GFLOPSを記録した。すべてのモデルは、スカラープロセッサを1つだけ備えた/10バージョン、または2つ備えた/20で提供され、2200および2400も4つを備えた/40構成で提供された。ロード/ストアユニットが追加されたため、スカラーユニットを追加すると、メモリ帯域幅が増加し、複数のプログラムを同時に実行できるため、ベクターユニットで何かが処理される可能性が高くなり、パフォーマンスが向上した。各ユニットのパフォーマンスは1.5倍になると言われており、VP2400/40は以前のVP2600/20のパフォーマンスと一致する。 マシンには、 UNIX互換のUXP/MまたはMVS互換のオペレーティングシステムが付属しており、どちらもアムダールから提供された。後者はFORTRANプログラムに使用され、前者は通常Cに使用され、ベクトル化コンパイラーは両方の言語に提供された。 他の企業と同様に、富士通は次世代機に超並列処理を採用し、VP2000ファミリが市場で販売されていた時間は長くはなかった。それにもかかわらず、100台以上が販売され、1993年7月には180台がインストールされた。 (ja)
  • Il VP2000 era la seconda linea di supercomputer vettoriali prodotti da Fujitsu. La linea rimpiazzo la Fujitsu VP e venne presentata nel 1990 e venne venduta per un breve periodo prima di venir rimpiazzata da macchine basate su parallelismo massivo. La VP2000 era sotto molti punti di vista simile al Cray-1, utilizzava dei processori vettoriali e un numero elevato di registri vettoriali che venivano utilizzati per accelerare le operazioni limitando gli accessi alla memoria. In aggiunta le unità vettoriali erano in grado di eseguire due operazioni di moltiplicazione e somma per ciclo di clock. Questo genere di operazioni erano molto comuni nelle applicazioni per supercomputer e quindi consentivano un netto incremento delle prestazioni. Il VP2000 a parità di frequenza di clock forniva prestazioni superiori a quelle del Cray-1. Un'altra differenza era che il sistema possedeva delle unità scalari che funzionavano alla metà della frequenza utilizzata dalle unità vettoriali. Secondo la legge di Amdahl un calcolatore tende ad andare alla velocità dell'unità più lenta a meno che i programmi non utilizzino in maniera preponderante le unità veloci. Quindi in teoria il VP2000 doveva fornire prestazioni inferiori a quelle del Cray-1 ma in realtà questo non era vero. Il motivo di questa contraddizione tra teoria e pratica non è chiaro. Uno dei maggior difetti della prima unità VP era la limitata banda passante verso la memoria che limitava le prestazioni del sistema dato che spesso i processori dovevano attendere il caricamento dei dati dalla memoria. La serie VP2000 fornì i processori di una seconda unità di caricamento dati in modo da raddoppiare la banda passante verso la memoria. Diverse versioni della macchina vennero vendute e differenti prezzi. La linea di fascia bassa partiva con il VP2100 funzionante con un ciclo di clock di 8ns (125 MHz) e generava circa 0.5 gigaFLOPS (circa da un quarto a un ottavo della velocità di un Cray). I modelli VP2200 e VP2400 incrementarono la potenza di calcolo a 1.25 e 2.5 GigaFLOPS di picco. Il sistema di fascia alta VP2600 funzionava a 3.2 ns (312.5 MHz) e sviluppava 5 GigaFLOPS di picco. Tutti i modelli erano disponibili nella versione /10 con un solo processore scalare e nella versione /20 con due processori scalari. Inoltre la serie 2200 e 2400 erano disponibili anche nella versione /40 con quattro processori scalari. Dato che ogni processore scalare aveva due unità di caricamento dei dati dalla memoria, l'aggiunta di un processore scalare incrementava la larghezza di banda, consentiva a più programmi di venire eseguiti contemporaneamente e quindi aumentava la possibilità di utilizzare le unità vettoriali. Ogni unità aumentava le prestazioni di circa 1.5 volte e difatti il VP2400/40 aveva prestazioni simili al VP2600/20. Le macchine utilizzavano un sistema operativo Unix compatibile chiamato UXP/M o il sistema operativo VSP/S compatibile con VMS. Entrambi i sistemi operativi vennero forniti dalla . VSP/M veniva utilizzato con i programmi Fortran mentre UXP/M veniva utilizzato principalmente con programmi C. Venivano forniti compilatori con ottimizzazioni per vettorializzare i programmi per entrambi i linguaggi. Come molte altre compagnie Fujitsu decise di basare i suoi nuovi supercomputer sul parallelismo massivo e la famiglia VP2000 non fu venduta a lungo, sebbene furono vendute più di 100 unità. (it)
gold:hypernym
prov:wasDerivedFrom
page length (characters) of wiki page
foaf:isPrimaryTopicOf
is Link from a Wikipage to another Wikipage of
is Wikipage redirect of
is foaf:primaryTopic of
Faceted Search & Find service v1.17_git139 as of Feb 29 2024


Alternative Linked Data Documents: ODE     Content Formats:   [cxml] [csv]     RDF   [text] [turtle] [ld+json] [rdf+json] [rdf+xml]     ODATA   [atom+xml] [odata+json]     Microdata   [microdata+json] [html]    About   
This material is Open Knowledge   W3C Semantic Web Technology [RDF Data] Valid XHTML + RDFa
OpenLink Virtuoso version 08.03.3330 as of Mar 19 2024, on Linux (x86_64-generic-linux-glibc212), Single-Server Edition (378 GB total memory, 60 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software