October 21, 2013
In a recent interview with Total Trading magazine, Jeffrey Birnbaum of 60East Technologies offers his take on a range of technologies relevant to the intersection of high performance computing and trading. As the CEO and Co-founder of 60 East Technologies, which specializes in real-time streaming database software for the financial services sector, Mr. Birnbaum has a unique perch from which to view this quickly evolving space.
Birnbaum believes the most significant advancement of the last last two decades for this sector is the institution of non-volatile memory as a persistent memory tier. "We are only scratching the surface of how this new memory tier can be used to build systems that outperform and outscale similar systems that were built in the last few years," says the CEO. "This technology allows reinventing all kind of software from database to messaging systems."
The need for reinvention is a recurring theme in Birnbaum's worldview. Making effective use of the high core counts in today's NUMA-based machines is a challenge. As platforms continually evolve, processing, network and storage IO must be brought into balance. New programming techniques and architectural designs emerge to keep up with higher performance mandates as old systems become outdated.
Birnbaum is no stranger to big-C changes. A big investment bank that he worked for made the transition from Unix to Linux under his direction and now, a decade later, he remarks that "Linux and Intel Xeon are the de-facto standard platform for trading."
As for what technologies will be the next game-changers, Birnbaum suggests keeping an eye on these three trends:
1. Software Defined Networking (SDN) – combining highly parallel compute with high velocity networking offers the benefits of increased scalability with lower latency.
2. Advancements in Non-Volatile Memory – better performance/scale.
3. Software transaction memory – a concurrency control mechanism, which Birnbaum believes will enable more robust code.
Since 2010 60East Technologies has focused on bringing the power of HPC to the financial services space with its flagship software called AMPS (Advanced Message Processing System), a highly-scalable low latency publish and subscribe engine that was designed for next generation computing environments. According to the company's website, "AMPS is designed to lower the latency in real-world messaging deployments by focusing on the entire lifetime of a message from the message's origin to its consumption by end-user clients."
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?