Tag Archives: Best Practices

What do you get when you mix 21st Century HPC SMEs with 1st Century BC History?

The 5th Annual Spain Conference! Hosted by the Barcelona Supercomputing Center (BSC) in partnership with the HPC Advisory Council (HPCAC) and member sponsors Dell Inc., Mellanox Technologies and DDN Storage the one day conference takes place next Wednesday in León and will feature leading collaborations taking place within and beyond Spain’s borders. This year’s agenda underscores the collaborations that are critical to deriving the ‘answer’.

We’ll meet PhD powerhouse Rosa Badia, the driving force in development of programming models for complex platforms will share insights into BSC’s Big Data initiatives. National Research prize winner and author Dr. Jose Duato, whose work influenced routing algorithm designs in Sun’s Magnum switch and supercomputing class systems IBM BlueGene/L and Cray T3E, joins from the Universitat Politècnica de València to discuss ‘rCUDA’ and ongiong developments in remote GPU virtualization including the frameworks futures in cloud computing. We’ll also welcome Álvaro Fernández González and the Fundación Centro de Supercomputación (FSCSL) – the Castiella y Llión region’s research consortium exploring everything from optimizing energy efficiency and ROI of classic HPC architectures to stimulating economic development by partnering with local industry to drive innovation into comercial R&D.

There’s also the heavy hitter line-up of technologists. Co-founder of OpenMPI and 12 year veteran of two US labs, Richard Graham will examine the Co-Design collaboration opportunities that are going to be critical in achieving new breakthroughs. Our annual Swiss Conference host, Hussein Harake joins from CSCS to share his engineering insights and parallel file system fundamentals following his in-depth evaluation of BeeGFS. We’ll also welcome Tommaso Cecchi, who joined DDN after 12 years with the Italian consortium CINECA. Cecchi does a deep dive on DDN’s Infinite Memory Engine – flash cache for PFS. Representing one of many foundation members coined (by another of our presenters) the ‘rebel alliance’, IBMer Martina Naughton reveals the force of OpenPOWER providing analysis and lessons learned from various applied research projects and the complex systems that were required to address very real world problems. Dell’s (and My Favorite) Martin Hilgeman brings perspectives of a system builder to the massively parallel performance discussion – examining the continuous advances in multi-core architectures and its impact on users and computational work.

The day starts and ends with industry insights from industry notables Dan Olds and Addison Snell, both longtime contributors to our mission – from the conferences to the student cluster competitions and so much more! DanO sheds his SCC color commentary to kick-off the day with a new take on what is seemingly the hot topic in HPC these days – High Performance Interconnects (HPI). Ever the watcher over the technology industry the former Gabriel Consulting founder’s new venture with industry strategy and research firm OrionX brings him to us for the day to expand upon their recently published analysis of the HPI market, its futures and evaluation considerations. Marking ten years of Intersect360 Research success, we commemorate this accomplishment featuring company founder and HPC veteran Addison Snell as this year’s ‘end note’ – a retrospective of the HPC industry over the last decade and predictions of what it will look like a decade from now and results from the firms most recent end-user study.

I am really excited about next week thanks to all of you – our wonderful hosts and generous sponsors, all of our presenters and participants – and your teams, organizations and yours as well! The sharing of expertise, the consideration of time and support are gifts, greatly appreciated! Having the honor of putting brilliant people together with brilliant people, where amazing things happen … is for me anyway…‘the answer’!

See you in León! If you can’t make Spain we have an incredible line-up next month as well at our China Conference! And of course save the date for Stanford (07-08 Feb, 2017) and Lugano (10-12 Apr, 2017)!

Emerging Technology ~ ‘EMiT’ 2016 ~ Register Today!

Explore the cutting edge of computing at EMiT 2016 being hosted 02-03 June, 2016 at the Barcelona Supercomputing Center.

Along with a great line-up of invited talks, registration includes a visit to the Torre Girona Chapel and conference dinner at the city harbor.

HPCAC member High End Compute (HEC) in the UK and their 2016 EMiT chair Michael Bayne invite you to meet with key figures in the emerging computing communities. Discuss cutting edge advancements in technologies and techniques. Topics will explore the latest trends in hardware development for novel computing; how to exploit emerging tech for application development and focus on new techniques, their development and how to transfer to new areas. And much more.

Additional information, agenda and registration is available at the EMiT website: www.emit.tech

Hurry and register today ~ before registration closes ~ Thursday 26 May, 2016!


HPC Applications Best Practices

Wanted to let you know that we have extended the high-performance applications best practices to:


1. Extend the applications performance, optimization and profiling guidelines to cover nearly 30 different applications, both commercial and open source – http://www.hpcadvisorycouncil.com/best_practices.php


2. We have added the first case using RoCE (RDMA over Converged Ethernet) to the performance, optimization and profiling guidelines page. It is under the same link as in item 1


3. New – installations guides – for those who asked to get a detailed description on where to get the application from, what is needed to be installed, how to install on a cluster, and how to actually run the application – it is now posted under the HPC|Works subgroup – http://www.hpcadvisorycouncil.com/subgroups_hpc_works.php. We will be focusing on open source applications, which sometime it challenging to really find this info. At the moment we have installations guides for BQCD, Espresso and NAMD, and more will come in the near future.


If you would like to propose new applications to be covered under the performance, optimization and profiling guidelines, or to be added to the installations guides, please let us know via info@hpcadvisorycouncil.com.

Best regards,