日本 Tsubame 2.0 超级计算机将采用 4224 片 Tesla 2050

Edison

Professor Takayuki Aoki from the Tokyo Institute of Technology just finished giving a fascinating look under the hood of the university’s Tsubame supercomputer, which has been used (among other things) in collaboration with a number of agencies in Japan to provide complex computational fluid dynamics modeling.

The Tsubame is notable because it leverages GPU clusters, and its success is one of the milestones for GPU’s in supercomputing. The Tsubame 1.0 uses Tesla S1070 in a 680 GPU cluster. With it, scientists have been able to experience speed ups of up to 80x in problems like weather modeling. Coming in December, the next-generation Tsubame 2.0 will use the Tesla 2050 with 4224 GPUs and provide performance of more than 3 PFLOPs.

Performance metrics are an important scorecard with supercomputers. But Professor Aoki explained how performance achieved really depends on the application as well as tuning and optimization – and gave some insights into how his group has been able to improve results. With full GPU implementation, Tsubame experienced acceleration of 10x to 100x over CPU-only performance, but notes that the numbers depended on the application.

With such intensive computation, any performance increase makes a huge difference – as do any bottlenecks. Communication issues between GPUs over cluster nodes can create some additional overhead, and Professor Aoki explained an overlapping technique they’ve developed at Tokyo Tech to deal with this.

While sessions was highly technical, audience members of all comfort levels could appreciate the incredible demos of CFD simulations, including water splashing into a container, a milk crown, and dendrite solidification in metal.

angelahj

nv发财了。

itany

哎，固态硬盘比GPU YY

binbin

NV又要发了上千万美金又要到手了
不过这是旧闻了
日本东京工业大学日前宣布，将在校内搭建一台使用NVIDIA ...
love571437 发表于 2010-9-22 14:36

   

love571437

4224x2499（2070价格过高？）

love571437

NV又要发了上千万美金又要到手了
不过这是旧闻了
日本东京工业大学日前宣布，将在校内搭建一台使用NVIDIA Tesla通用计算卡的超级计算机TSUBAME 2.0。其双精度运算性能预计将达到2.4PFLOPS，成为全球最强超级计算机，同时也是全球首台以GPU为主要运算能力来源的顶级超级计算机。

　　TSUBAME 2.0将在该校原有TSUBAME 1的基础上升级完成，主要运算节点“Thin Node”搭载两颗Intel Westmere-EP 2.93GHz（TurboBoost频率3.196GHz）至强处理器以及三块NVIDIA Tesla M2050通用计算卡，合计包含12个CPU核心以及1344个GPU核心（通用计算单元）。

　　TSUBAME 2.0计划搭建1408个Thin节点，CPU 2816颗核心数量共计17664个，GPU 4224颗，通用计算单元数量高达189万个。总运算能力2391.35TFLOPS，其中CPU运算能力215.99TFLOPS，GPU运算能力2175.36TFLOPS。

　　整套系统共将使用约100TB内存，内存带宽720TB/sec，200TB固态硬盘存储，7.13PB硬盘存储，另有8PB存储子系统。节点和存储系统间使用Infiniband光网络连接，子系统和外部连接使用10Gb以太网，支持Windows HPC和SUSE Linux操作系统。

　　TSUBAME 2.0的设计和管理由NEC公司完成，惠普则负责开发制造各运算节点。整套系统预计占地200平方米，通过液冷散热系统和高效率电源的应用，能效比将是第一代系统的30倍。

　　东京工业大学表示，将从8月中旬开始逐步关停TSUBAME 1，8月份开始拆卸节点，9月份启动新机安装，10月份开始进行试验，年内实现TSUBAME 2.0稳定运行。预计搭建TSUBAME 2.0和未来四年运行费用合计在32亿日元以下