本文内容非商业用途可无需授权转载，请务必注明作者及本微信公众号、微博ID：唐僧_huangliang，以便更好地与读者互动。
编者注：上图引用自2015年10月铁流的文章，如果真达到这个性能数据是可以超过目前TOP500第一名神威太湖之光的。问题在于每个节点实际只配了2块GPDSP协处理器卡，估计可能与PCIe插槽带宽、供电或者散热有关。
昨天我在top500网站正式看到新闻消息，下面转载原文并适当翻译一些要点。
The number two-ranked Tianhe-2 supercomputer, installed at the
National Super Computer Center in Guangzhou, is being upgraded to 94.97
petaflops, nearly doubling its current peak performance of 54.9
petaflops.
天河2号本次升级后的算力，从54.9
petaflops提高到94.97
petaflops。
2017年6月的top500榜单，当时排名第二的天河2号还是Intel Xeon E5 CPU + Xeon Phi协处理器的配置。如今升级后还是排在125 petaflops 的神威太湖之光后面。
扩展阅读：《
从260核异构申威看HPC Top500缩影
》
The news comes out of the International HPC Forum (IHPCF), via a series of tweets from Satoshi Matsuoka
posted on Tuesday. During the morning session, it was revealed that the
upgraded system, dubbed Tianhe-2A, will sport the new Chinese-made
Matrix-2000 GPDSP accelerators. They will replace the existing Intel
Knights Corner Xeon Phi coprocessors that were installed in the Tianhe-2
back in 2013.
The original plan was to upgrade the system with the newer Knights
Landing devices. But after the US government instituted an embargo on
these chips to certain Chinese supercomputing sites, including the
Guangzhou center, the National University of Defense Technology (NUDT)
had to come up with plan B. In this case, that meant developing their
own coprocessor. That turned out be the Matrix-2000, a DSP-type chip,
tweaked for more general-purpose computation.
国防科大研发的DSP类芯片，命名为Matrix-2000（矩阵2000）。
According to slides presented at the forum, each Matrix-2000 will
deliver 2.4576 teraflops (peak), which more than doubles the 1.0
teraflops delivered by the original Xeon Phi chip. The Matrix-2000
consists of 128 cores, each one providing 16 double precision flops per
cycle. Those flops are delivered by a 256-bit vector unit, which as
Satoshi notes, is in line with the Knights Corner chip it replaces.
At least for the time being, the system will retain the original host
CPUs from Tianhe-2, which are Intel Xeon processors. Each supercomputer
node will pair two of those Intel CPUs with two Matrix-2000
coprocessors, hooked in via PCIe. The node count is being increased from
16,000 to 17,792.
以上介绍了Matrix-2000的一些规格，升级后每个超算节点仍配置 2 块协处理器PCIe插卡替换Xeon Phi，另外集群节点数量也从16,000小幅增加到17,792。
Other enhancements include an interconnect that is 40 percent faster
interconnect (to 14 Gbps) and has 50 percent lower latency (1 us). This
is likely the TH-Express-2+ that NUDT has talked about before. In
addition, main memory has been bumped from 1.4 to 3.4 petabytes,
slightly improving the bytes-to-flops ratio of the Tianhe-2. Storage has
also been enhanced in both capacity and I/O bandwidth. All the
particulars are below, courtesy of James Lin, who tweeted some nice screen images from the presentation.
Source: James Lin, @jameslinsjtu
如上表，天河-2A的网络互连速率从10Gbps提升到14Gbps，延时降低到1
μ
s；
DRAM容量达到3.4PB，存储空间和带宽分别增加至19PB和1TB/s；能源效率有所提高，编程接口是以前介绍过的OpenMP和OpenCL。
Even though peak performance is going to nearly double, the system’s
total power draw of 18 MW is just slightly more than that of the
original system. That gives it a power efficiency of more than 5
gigaflops per watt, which would place it somewhere around the number 20
slot on the Green500 list.
Ironically, the upgrade won’t improve the system’s position in the
TOP500 rankings. The number one Sunway TaihuLight has a peak performance
of 125.4 petaflops, and attains 93 petaflops on the High Performance
Linpack (HPL) benchmark. It’s unlikely Tianhe-2A will come in at better
than 70 or 80 petaflops on HPL.
Nevertheless, the upgrade further cements China’s status as a serious
supercomputing power, and does so, once again, with domestically
produced technology. The country is currently the odds-on favorite to
stand up the first exascale system, which it intends to do in the
2019-2020 timeframe.
最后八卦一下，替换下来的 32000片 Xeon Phi 31S1P 低价处理不？谁叫你们 Intel 禁运限制我们呢：）
注
：本文只代表作者个人观点，与任何组织机构无关，如有错误和不足之处欢迎在留言中批评指正。
进一步交流
技术
，
可以
加我的
QQ/
微信：
490834312
。如果您想在这个公众号上分享自己的技术干货，也欢迎联系我：）
尊重知识，转载时请保留全文，并包括本行及如下二维码。感谢您的阅读和支持！《企业存储技术》微信公众号：
HL_Storage
长按二维码可直接识别关注
历史文章汇总
（传送门）：
http://chuansong.me/account/huangliang_storage
