Supermicro 的 GPU 服务器产品线将增加基于 Fermi 架构的 “Tesla M" 系列

Edison · 发表于 2010-5-5 01:00

Supermicro have launched today their second generation of GPU computing servers, using NVIDIA Tesla 20-series GPUs.  This product line is an upgrade from their first generation servers, and features a 1U server with 2x M2050 Tesla cards; a 4U tower that supports four C2050 Tesla GPUs, three other PCI-E cards, and support for eight hot-swappable 3.5" SAS/SATA drives; and a 2U twin server that supports two hot-pluggable GPU nodes and onboard QDR InfiniBand for 40GB/sec connectivity.

The NVIDIA Tesla M2050 is a workstation level version of the GTX470 with 448 CUDA cores, but with 3GB GDDR5 ECC memory and a passive heatsink.  The C2050 is an M2050 with an increased memory bandwidth (144GB/sec to 148GB/sec) due to faster memory, and is actively cooled.

All Supermicro systems are compatible with dual Intel Xeon 5500/5600 processors (up to 16 threads) and 192GB Registered ECC DDR3-1333Mhz RAM.  Both the 1U server and 4U tower are supplied with a redundant 1400W Gold level (93%) high efficiency power supply.  Makes you wonder though for the 4U unit - four Fermi cards, two Nehalem Xeons, is 1400W enough?

NVIDIA Tesla cards and their computing languages have been welcome technologies in various computational scientific fields over these past few years - medical imaging, oil and gas exploration, quantum chemistry, financial simulation, astrophysics, folding and various BOINC projects to name but a few.  A few companies have started to offer GPU integration into their server systems, and Supermicro has always been on my list of companies to watch out for with regards Tesla workstations in my day-to-day job (computational chemistry).

In terms of pricing, think a few thousand dollars per Tesla GPU, $1000 for two Xeon 5520s and cooling, $2000 for the power supply, 4U tower, and general cooling, $1000 for the motherboard, and $500-$20000 for how much RAM you would like.  Coming soon to a Supermicro approved reseller near you (if you can afford it)!

http://www.anandtech.com/show/36 ... de-fermilevel-tesla

Edison · 发表于 2010-5-5 01:01

这是首次 Tesla M Fermi 出现在新闻中。

cool_exorcist · 发表于 2010-5-5 08:14

移动版的GTX470 能不能功率小些？

380 · 发表于 2010-5-5 09:50

提示: 作者被禁止或删除内容自动屏蔽

Edison · 发表于 2010-5-5 11:20

Tesla M ..........搞计算的还背着移动工作站去算？
380 发表于 2010-5-5 09:50

M 是针对集群的产品线。

gzpony · 发表于 2010-5-5 11:24

The NVIDIA Tesla M2050 is a workstation level version of the GTX470 with 448 CUDA cores

看来tesla也不总是480级别的。还有470级别的特斯拉啊。

gz_easy · 发表于 2010-5-5 11:29

Tom兄会对这个感兴趣。

鱼儿水中游 · 发表于 2010-5-5 11:32

那得插电源，或者电池改为发电机。

380 · 发表于 2010-5-5 11:38

提示: 作者被禁止或删除内容自动屏蔽

人为财死 · 发表于 2010-5-5 11:40

看来老黄是要转向了

yamhill · 发表于 2010-5-5 12:25

Supermicro早就有基于Tesla的产品线了

这次又将Fermi产品单独编号

比较看好

goldman948 · 发表于 2010-5-5 12:25

服务器本身就没有移动的概念

reeea · 发表于 2010-5-5 12:53

服务器本身就没有移动的概念
goldman948 发表于 2010/5/5 12:25

有，富士通以前有基于Sun的UltraSPARC(或者是更老款的SPARC？太久了记不得了)的笔记本，跑solaris的笔记本...我记得CPU是66MHZ还是100mhz来着，当年我读书的学校拿这个做文件服务器，硬盘是12.5mm的老款盘。也有SCSI-II接口，挂了个硬盘塔

不过应该算移动工作站？

tomsmith123 · 发表于 2010-5-5 13:14

回复 7# gz_easy
价格偏高。。。
还是自己买C2050 搭系统比较合适。

binbin · 发表于 2010-10-4 15:13

回复 14# tomsmith123

帐号		自动登录	找回密码
密码			注册

380 380 当前离线积分 43 IP卡狗仔卡头像被屏蔽	4^# 发表于 2010-5-5 09:50 \| 只看该作者提示: 作者被禁止或删除内容自动屏蔽
380 380 当前离线积分 43 IP卡狗仔卡头像被屏蔽
	回复支持反对使用道具举报显身卡

380 380 当前离线积分 43 IP卡狗仔卡头像被屏蔽	9^# 发表于 2010-5-5 11:38 \| 只看该作者提示: 作者被禁止或删除内容自动屏蔽
380 380 当前离线积分 43 IP卡狗仔卡头像被屏蔽
	回复支持反对使用道具举报显身卡

Supermicro 的 GPU 服务器产品线将增加基于 Fermi 架构的 “Tesla M" 系列

浏览过的版块