The dragonfly topology has been proposed as an efficient alternative to the fat tree. This talk presents a study of the blocking and scalability characteristics of the dragonfly, and compares this to the well-known fat tree topology.
Search Results for: scalability
Over at Admin HPC, Dell’s Jeff Layton writes that parallelized applications eventually hit a scalability limit where adding processors no longer increases performance. The good news is that you can use Amdahl’s law as a guide to where to concentrate your resources to improve performance. The first explanation for this behavior is described by Amdahl’s […]
In this video, Gnodal CTO Fred Homewood describes the company’s high bandwidth, low latency 40 GigE Ethernet switch solutions for HPC and the Enterprise. The GS0072 is an order of magnitude faster than most competitive switches with congestion management and dynamic load-balancing, allowing the switches to operate at near 100% bandwidth utilization (throughput). The GS0072 […]
Erik Saule and Umit V. Catalytirek from Ohio State University have published a new paper examining the scalability of the upcoming Intel MIC architecture on Graph algorithms. Abstract Graph algorithms are notorious for not getting good speedup on parallel architectures. These algorithms tend to suffer from irregular dependencies and a high synchronization cost that prevent […]
In this video, Jason Booth and David Beer from Adaptive Computing present: Scalability — How to configure and manage scalability for Moab and Torque. Following that, Bryan Caron from Compute Canada presents a customer case study. In this talk we will outline the experiences of the centre with Moab and Torque in providing a scalable, […]
In this video, Rich Brueckner from insideHPC interviews Bill Nitzberg, CTO of PBS Works at Altair Engineering. The company recently celebrated the 20th anniversay of PBS Professional, Altair’s EAL3+ security certified, commercial-grade HPC workload management solution. Recorded at the ISC’11 Conference in Hamburg.
Today Platform Computing announced the release of Platform Symphony 5.1, its popular service oriented architecture (SOA) application. With it’s enhanced architecture, Symphony offers the following new capabilities: Easier Application On-boarding Faster, easier, less costly development and testing for applications allows customers to retain investments in existing applications. GPU Support and intelligent GPU workload scheduling exposes […]
In this podcast, I interview Victoria Livschitz, President & CEO of Grid Dynamics. As an engineering company, Grid Dynamics has helped companies like eBay, Paypal, and Microsoft build next-generation, mission-critical systems that deliver extreme scalability and elasticity. In our cloud computing survey of engineers, we learned that they are all about scalability and elasticity, the […]
Dr. Dobb’s reported this week that Intel has announced a new tool to allow developers to understand the scalability of their apps Intel’s Software Tools group has announced a cloud-based “scalability service.” The Intel Parallel Universe Portal is an on-demand cloud-computing analysis tool that tests 32-bit Windows-based parallel applications. The service lets software developers assess […]
Todd Hoff writes at highscalability.com about his recent interview in Java World on the scalability of Java, expanding on what appeared in the published article. His answer to the question, “what can we do about the multicore software challenge?” As we’ll see, Java and more importantly the JVM have become a platform for many interesting […]