Comments

In this TACC podcast, Klaus Schulten of the University of Illinois at Urbana-Champaign describes the analysis and modeling of the cellulosome bond. The research could boost efforts to develop catalysts for biofuel production from non-food waste plants.

"Adaptive Routing has been added to the static routing capability available in previous switch families. InfiniBand supports moving traffic via multiple parallel paths. Adaptive routing dynamically and automatically re-routes traffic to alleviate congested ports. In networks where traffic patterns are more predictable, static routing has been shown to produce superior results. The InfiniScale IV architecture provides the best of both static and adaptive routing."The post Video: Adaptive Routing for Scalable Topologies appeared first on insideHPC.

"This talk will focus on programming models and their designs for upcoming exascale systems with millions of processors and accelerators. Current status and future trends of MPI and PGAS (UPC and OpenSHMEM) programming models will be presented. We will discuss challenges in designing runtime environments for these programming models by taking into account support for multi-core, high-performance networks, GPGPUs, Intel MIC, scalable collectives (multi-core-aware, topology-aware, and power-aware), non-blocking collectives using Offload framework, one-sided RMA operations, schemes and architectures for fault-tolerance/fault-resilience.”The post Video: High-Performance and Scalable Designs of Programming Models for Exascale Systems appeared first on insideHPC.

"We introduce a high-performance cost-effective network topology called Slim Fly that approaches the theoretically optimal network diameter. Slim Fly is based on graphs that approximate the solution to the degree-diameter problem. We analyze Slim Fly and compare it to both traditional and state-of-the-art networks. Our analysis shows that Slim Fly has significant advantages over other topologies in latency, bandwidth, resiliency, cost, and power consumption."The post Video: Slim Fly – A Cost Effective Low-Diameter Network Topology appeared first on insideHPC.

Comments

"The use of GPUs to accelerate applications is mainstream nowadays, but their adoption in cur- rent clusters presents several drawbacks. In this talk we present the last developments of the rCUDA remote GPU virtualization framework, which is the only one supporting the most recent CUDA version, in addition to leverage the InfiniBand fabric for the sake of performance."The post Video: Increasing Cluster Throughput while Reducing Energy Consumption for GPU Workloads appeared first on insideHPC.

"The DDN Infinite Memory Engine (IME) unleashes a new I/O provisioning paradigm. This breakthrough, software defined storage application introduces a whole new new tier of transparent, extendable, non-volatile memory (NVM), that provides game-changing latency reduction and greater bandwidth and IOPS performance for the next generation of performance hungry scientific, analytic and big data applications – all while offering significantly greater economic and operational efficiency than today’s traditional disk-based and all flash array storage approaches that are currently used to scale performance."The post Video: Application Experiences on DDN’s IME Burst Buffer appeared first on insideHPC.

The House Transportation Committee is underway to discuss ST3 authority and the broader transpo package. Watch live here and refresh for our updates and commentary. You may also follow us on Twitter. 6:19 Committee adjourns after nearly 3 hours of nearly unanimously favorable testimony. No committee discussion of the bills. 5:57 Clibborn is cutting off oral […]

"The drive toward exascale computing, a renewed emphasis on data-centric processing, energy efficiency concerns, and the limitations of memory and I/O performance are all working to reshape High Performance Computing platforms. Many-core accelerators, flash storage, 3D memory, integrated networking, and optical interconnects are just some of the technologies propelling these future architectures. In concert with those developments, the HPC vendor landscape has been churning in response to broader market forces, and these events are going to drive some interesting changes in the coming year."The post HPC Market Update from Intersect360 Research appeared first on insideHPC.

Comments

Comments

"The CMS detector at the Large Hadron Collider at CERN underwent a replacement of its data acquisition network to be able to process the increased data rate expected in the coming years. We will present the architecture of the system and discuss the design of its layers which are based on Infiniband as well as 10 and 40 GBit/s Ethernet."The post High Throughput Data Acquisition at the CMS experiment at CERN appeared first on insideHPC.

Comments

It is very cool that the agency itself produced these videos. CTA sees them as a tool to help riders familiarize themselves with the system and as a historical record. If you a lot of free time, check out the full-length (real time) videos!

Comments

Comments

In this video from the 2015 HPC Advisory Council Switzerland Conference, Tor Skeie from Simula Laboratory presents: The InfiniBand Subnet Manager from Fabriscale.The post Video: The InfiniBand Subnet Manager from Fabriscale appeared first on insideHPC.

Just a reminder that we’re having our first-in-a-while meet-up happy hour tomorrow, April 1, at Rock Bottom Brewery in Downtown Seattle from 5-8pm. Sound Transit’s Ric Ilgenfritz and others will be on hand to talk about ST3 and the upcoming ballot initiatives. Come chat with us STB staff and ST folks to learn more about the […]

You can rest assured that tomorrow’s posts will be as earnest and authentic as any other day’s.* We’ve had some fun with April Fools’ posts in the past (you can share your favorite in the comments), but last year’s generated much more angst than it was worth. And in any case we’ve probably outgrown that kind […]

Ensuring a reproducible result of HPC workloads no matter the platform used is key to settle the battle between operations (update fast, due to compliance / security) and end- user (never touch a running system). By pushing his docker related HPC research further, Christian is showcasing his results on Immutable Application Containers.The post Reproducibility of CAE-computations through Immutable Application Containers appeared first on insideHPC.

In this April 1 video, Scalable Informatics announces the Si Tortoise Data Security Appliance.The post April 1 Video: Si Tortoise Data Security Appliance appeared first on insideHPC.

Comments

In this video, Vadim Karpusenko from Colfax International describes the software tools for developing applications for Intel Xeon Phi coprocessors. The session begins with software that is necessary to boot coprocessors and to run pre-compiled executables on them.The post Video: Software Tools for Intel Xeon Phi Co-processors appeared first on insideHPC.

"To achieve good scalability performance on the HPC scientific applications typically involves good understanding of the workload though performing profile analysis, and comparing behaviors of using different hardware which pinpoint bottlenecks in different areas of the HPC cluster. In this session, a selection of HPC applications will be shown to demonstrate various methods of profiling and analysis to determine the bottleneck, and the effectiveness of the tuning to improve on the application performance."The post Video: Applications Performance Optimizations – Best Practices appeared first on insideHPC.

OpenFlow? Check. Vyatta? Check. Buzzwords? Oh yes Brocade has announced a new bunch of campus switches, and with them support for new software defined network (SDN) features and a nifty ability to mix different switches in the stack as if they were all the same kind.…

Comments

One of the primary design goals of C# in the early days was to be familiar to C and C++ programmers, while eliminating many of the “gotchas” of C and C++. It is interesting to see what different choices were … Continue reading →

In many large threaded applications, synchronizing all of the threads by use of barriers can results in significant wasted processing time. If the application lends itself, loosely synchronous barriers instead of strictly synchronous barriers should be used and can recover lost time.The post Phasing Barriers for Performance appeared first on insideHPC.

"Pharmacokinetic (PK) and Pharmacodynamic(PD) parameters determine the develop-ability of a drug candidate and estimation of them are time consuming and there is an urgent need for time efficient approaches. In the present talk, we showcase the parallel implementation of Grid search method on Xeon Phi using stepwise optimization techniques as a promising approach for the robust estimation of PK-PD parameters. The solution described herein, is of great importance in decision making in Pharmaceutical Industry."The post Parallel Implementation of PK-PD Parameter Estimation on Intel Xeon Phi appeared first on insideHPC.

The ORCA Joint Board will be holding a public hearing this coming Monday, April 13, at 10:30 am, in the 8th Floor Conference Room at 201 S. Jackson St, on its proposal for making the ORCA regional multi-agency day pass permanent, and adding a Regional Reduced Fare Permit version of the day pass. Details of […]

Comments

Comments

In this video, Steve Simms from Indiana University kicks off LUG 2015 with a talk on Lustre 101. "Lustre is a mature and stable file system that through its developers has consistently been able to respond to the needs of organizations that require high performance throughput and expanding capacity."The post Video: Steve Simms Teaches Lustre 101 at LUG 2015 appeared first on insideHPC.

Last time I explained why the designers of C# wanted to have both checked and unchecked arithmetic in C#: unchecked arithmetic is fast and dangerous, checked arithmetic is slightly slower but turns subtle, easy-to-miss mistakes into program-crashing exceptions. It seems … Continue reading →

Comments

In this video from LUG 2015 in Denver, Jason Goodman from Cray presents: Cray’s Storage History and Outlook – Lustre+. "As a leader in open systems and parallel file systems, Cray builds on open source Lustre to unlock any industry-standard x86 Linux compute cluster using InfiniBand or 10/40 GbE utilizing proven Cray storage architectures."The post Video: Cray’s Storage History and Outlook – Lustre+ appeared first on insideHPC.

Gareth Wilson from Fog Creek interviewed me the other day for their series on the lives of developers; we talked about playing Dam Buster on the Commodore PET and typing in programs in WATCOM VI and all kinds of stuff. … Continue reading →

In this video from LUG 2015 in Denver, Peter Bojanic from Seagate presents: Seagate Lustre Update. "Seagate powers four of the five 1 TB/sec filesystems in the world today."The post Video: Seagate Lustre Update appeared first on insideHPC.

"Pleiades, one of the world's most powerful supercomputers, represents NASA's state-of-the-art technology for meeting the agency's supercomputing requirements, enabling NASA scientists and engineers to conduct modeling and simulation for NASA missions. Powered by Lustre, this distributed-memory SGI ICE cluster is connected with InfiniBand in a dual-plane hypercube technology."The post Video: Defending the Planet with Lustre appeared first on insideHPC.

Comments

In this video from LUG 2015 in Denver, Robert Triendl from DDN presents: Application-optimized Lustre Solutions for Big-Data Workflows.The post Video: Application-optimized Lustre Solutions for Big-Data Workflows appeared first on insideHPC.

Comments

The original Mark I trains still sound the same but the areas around the station have developed greatly.

This is a sequel to my 2009 post about division of long integers. I am occasionally asked why this code produces a bizarre error message: Console.WriteLine(Math.Round(i / 6000000000, 5)); Where i is an integer. The error is: The call is … Continue reading →

As I’ve mentioned before, I’m part of the technical group looking at updating the ECMA-334 C# standard to reflect the C# 5 Microsoft specification. I recently made a suggestion that I thought would be uncontroversial, but which caused some discussion – and prompted this “request for comment” post, effectively. What does the standard say about … Continue reading Precedence: ordering or grouping? →

Comments

Comments

Comments

Occasionally I’m asked to review code that has a lot of repetition in it. Like, for instance, someone is writing a function memoizer: static Func<A, R> Memoize<A, R>(this Func<A, R> function) { var cache = new Dictionary<A, R>(); return argument … Continue reading →