China's fastest super computer "Tianhe-1" is to be equipped this year with China-made central processing unit (CPU) chips...
2010年03月10日 中国最快的超级计算机"天河一号"今年将安装中国自行设计制造的"飞腾"CPU芯片,替换这台计算机上唯一进口的部件。"天河一号"和"飞腾"芯片都由中国国防大学研制。
中国国防大学校长张育林8号表示,"飞腾"CPU芯片是专门为"天河一号"量身定制的。"在安装'飞腾'芯片后,'天河一号'的峰值速度和运算效率将大大提高。"
"天河一号"总投资6亿元人民币,拥有每秒钟1206万亿次的峰值速度,和每秒钟563.1万亿次的Linpack实测性能。这意味着,如果用"天河一号"计算一天,一台当前主流双核个人电脑得计算160年。"天河一号"的存储量,则相当于4个国家图书馆藏书量之和。
2010-03-10 China's fastest super computer "Tianhe-1" is to be equipped this year with China-made central processing unit (CPU) chips, named "Feiteng", replacing the only part of the computer that is currently imported.
Zhang Yulin, president of the National University of Defense Technology (NUDT) which developed the computer, said on Monday that the chips, also developed by the NUDT, are customized for this super computer.
"The new CPUs will greatly raise the peak speed and computing efficiency of 'Tianhe-1'," Zhang said.
Tianhe cost 600 million yuan. Its peak performance reaches 1.206 petaflops, and it runs at 563.1 teraflops (1,000 teraflops equals one petaflop) on the Linpack benchmark
A single-day task for Tianhe might take a mainstream dual-core personal computer 160 years to complete, working non-top.
Tianhe is able to store books over four times those in the National Library of China.
新闻来源 Read the Article
理解 Comprehension:
1. 关于"天河一号",下面几个选项中说法正确的是_____。(可以选择多个选项)
A. "天河一号"的峰值运算速度是每秒钟1206万亿次。
B. "天河一号"的寿命为160年。
C. "天河一号"的重量为150吨。
D. "天河一号"的存储量相当于4个国家图书馆藏书量。
E. "天河一号"在天津国家级超级计算中心研制而成。
F. "天河一号"是目前中国计算速度最快的超级计算机。
2. 目前,"天河一号"的那个部件不是中国生产的?
A. 显卡
B. 声卡
C. CPU芯片
D. 硬盘
Ranking
Myanmar to take part in int'l film festival i...
Myanmar will take Indian film festival
China's railway freight down 2.9 percent year...
China's railway freight transportation
China's voluntary bone marrow donors hit 1 mi...
China's voluntary bone marrow donors
Volkswagen sets to expand capacity in China (...
Volkswagen AG
Copyright © 2009 Confucius Institute Online beijing ICP 08002516 | About Us | Join us | Disclaimer | Copyright Info | Suggestions | Contact Us








