Being SC17 General Chair also means that I am SC16 Deputy Chair “shadowing” the SC16 General Chair John West which means that I watch and learn from him at all meetings and at the conference in 2016, so I am well prepared for the conference organization work “my” year.

Snow blizzard in Salt Lake City -- Picture by Bernd Mohr

Snow blizzard in Salt Lake City — Picture by Bernd Mohr

The SC16 Organization Committee met in Salt Lake City, where the SC conference will be this year, for a first planning meeting on March 22nd and 23rd. The first morning, a tour of the Salt Palace Convention Center (SPCC) was on our schedule.  Just in time, when we wanted to start walking to the Convention Center , it started snowing heavily 😉  Luckily, I was prepared and I had packed some warm clothing.

Salt Lake City Convention Center, ready for ComicCon -- Picture by Bernd Mohr

Salt Palace Convention Center, ready for ComicCon — Picture by Bernd Mohr

When we arrived at the Convention Center we saw that preparations were in full swing to get ready for Comic Con Salt Lake which was scheduled to open just a few days later.

SPCC main ballroom -- Picture by Bernd Mohr

SPCC main ballroom — Picture by Bernd Mohr

 

When we toured the Convention Center, we could also watch the preparations in the main ball room which seats up to 4900 people. We will use it for the keynote and invited talks at SC16.

 

There is not much to report from the actual meeting: the progress in the different areas of the conference (technical program, finance, infrastructure, local arrangements, communications, student@SC, SCinet, and exhibition) is discussed. About 60 people, almost all volunteers from all other the world, typically attend such a meeting.

Me presenting at the Multicore@Siemens 2016 conference -- Picture by Siemens

Me presenting at the Multicore@Siemens 2016 conference — Picture by Siemens

Yesterday, I gave an invited talk at the Multicore@Siemens 2016 conference in Nürnberg about the performance analysis of parallel applications. While in our high-performance computing center at JSC, we have to deal with large-scale scientific applications running on our world-class very scalable HPC systems like JURECA or JUQUEEN, software developers in general deal with much smaller systems.

Multicore@Siemens 2016 conference — Picture by Bernd Mohr

However, everyone has to deal with parallel (multicore) systems now: smartphones, tablets, or laptops nowadays typically have two or four compute cores and a graphics accelerator and the same is true for embedded computers in consumer devices like washing machines or process automation control systems. Multicore computers are everywhere and so every software developer has to learn and understand parallel programming in these days and quickly finds out: (a) it is complicated to get right and (b) it is even more complicated to make it efficient, that means that the software really makes use of all the computer power available by all the cores on the chip.

If you are interested in the topic, here are the slides. I gave a very similar talk at the Multicore Day 2016 organized by SICS in Stockholm, Sweden and they even videotaped it.

In my talk, I presented some of the results of the RAPID ((Runtime Analysis of Parallel applications for Industrial software Development) project, which is a collaboration between the Corporate Technology Multicore Expert Center of Siemens AG and Jülich Supercomputing Centre.

RAPID (Runtime Analysis of Parallel applications for Industrial software Development) project Logo

RAPID (Runtime Analysis of Parallel applications for Industrial software Development) project logo

The goal of this project was to adapt the measurement and analysis tools Score-P and Scalasca, which we develop at Jülich in my team for many years now, to the needs of industrial applications. As industrial applications are parallelized differently than scientific application codes, it meant that we had to integrate support for threading models like POSIX threads, Windows threads, Qt threads, and ACE threads into Score-P. In addition, support for leveraging task parallelism using MTAPI, the Multicore Association Tasking API,  was also developed. Besides supporting new programming paradigms, additional work had to be done with regards to portability. Although Score-P is already quite portable as it is running on all relevant supercomputer architectures, systems like Windows and operating systems for embedded systems had not been targeted so far, but are of course very important in an industrial context. On the analysis side, new methods targeting thread-based communication patterns, e.g., a lock contention analysis, were implemented in Scalasca. Meanwhile, our software was successfully used in the work of the Multicore Expert Center to understand and optimize important Siemens industry codes.

My new coffee mug from the Siemens Multicore Expert Center -- Picture By Bernd Mohr

My new coffee mug from the Siemens Multicore Expert Center — Picture By Bernd Mohr

At the end of my talk, they gave me a Siemens Multicore Expert Center coffee mug — not sure whether they read my blog article about my coffee mug collection, but anyhow, the mug will get a prominent spot in my bookshelf 😉

Travel for my job often means visiting colleagues all over the world at their high-performance computing centers. As they are hosting some of the most powerful, and therefore very expensive, computers in the world, it is clear that this requires a little bit more than a large enough room in the basement of your university or research center institute. For one thing, they require quite some power: a typical top25 HPC system installation with the actual computer, the high-speed network, enough storage and cooling needs anything between 5 and 25 MW.

In this first part of a new mini-series (“HPC Centres Around the World”), I would like to show you the most beautiful HPC machine room of the world at the Barcelona Supercomputing Center (BSC).

Mare Nostrum Supercomputer at BSC -- picture by BSC (2003)

Mare Nostrum Supercomputer at BSC — picture by BSC (2003)

As you can see, it is actually inside a church, a de-secularized church to be precise 😉  The stories (at least how I remember it) is that in 2003, IBM wanted to demonstrate that it is possible to build a world-class HPC system out if industry-standard compute blades. A partner, the Universitat Politècnica de Catalunya (UPC) at Barcelona, was quickly found. UPC would get a special deal, however, there was the requirement that the system would be up and running in a year. The problem then was to find a building suitable to be able to host a supercomputer, as constructing a new one would have taken too long. The University had a church building on campus which at that time was used for chorus singing. This is actually the reason why the roof of the church inside is covered with a red carpet — it was installed to improve the acoustics for singing. In order to avoid having to cool the whole building a steel / glass frame was constructed inside the church housing the computer. During a sight-seeing tour, visitors are taken to the gallery in the backside of the church, with nice movie theater like seating, with a great view down to the computer. The tour guide can actually walk on top of the glass cage and this way can easily show and explain the different parts of the computer.

If you are interested in more pictures just search for “marenostrum” and “bsc” at Google Images. And, if you visit Barcelona in the future — a good idea anyhow — make sure to reserve some time for the “Temple of HPC Technology” as I call it 😉

BSC machine room from the outside -- Picture by Bernd Mohr

BSC machine room from the outside — Picture by Bernd Mohr

Hilton Head island beach - Picture by Bernd Mohr

Hiking the Hilton Head island beach in a meeting break – Picture by Bernd Mohr

After the conference (see past blog entry) is before the conference! So the SC committee met last week in the picturesque Hilton Head island in South Carolina. This is the so-called “Turnover” meeting: the outgoing SC committee (SC15 this time) meets with the now-in-charge committee for this year’s conference (SC16) to exchange ideas and experiences, discuss issues and problems and suggestions how to fix them for the next conference. This is one instrument SC uses to ensure quality and continuity over the years although the organizing committee changes from year to year. The other is the SC Steering committee which also meets in the same place for two additional days to discuss strategy and policies.

These face-to-face planning meetings are important for the success of the conference as SC is mainly organized by a large group of volunteers with the help of a few contractors. The typical committee size is around 500 people. Of course, only the committee and subcommittee chairs come to these meetings but this still can be easily 60 to 80 people. (And in case you were wondering about it: yes, the home organizations of the people are paying for the travel and hotel!) Besides exchanging experiences, face-to-face meetings also ensure that the different subcommittees (e.g. technical program, exhibition, infrastructure, finance, or local arrangements) get to know each other better and learn more about the work of the other subcommittees.

The Turnover meeting is traditionally in a “warmer” location (as it is always mid to end of January), and while it was warmer than many places people came from (e.g. in Jülich it was snowing ;-)) it was not as warm as expected: the temperature was more in the single-digit degrees Celsius and with the cold wind it was feeling more like freezing. At least we were not hit by “Snowzilla”, the blizzard which went over the Northeast of the US at the end of the week. A few committee members actually got stuck in Hilton Head Island for a few extra days as there home airport was closed a few days.

This is the second part of my “Things you never wanted to learn about SC, but I tell you anyhow!” (TynwtlaSC,bItya!)  posts 😉

My SC drinking mug, glasses, and bottles collection -- Picture by Bernd Mohr

My SC drinking mug, glasses, and bottles collection — Picture by Bernd Mohr

If you go to the same conference every year for a long time you collect some nice experiences and memories, but also you collect quite some souvenirs (ask my wife about it!). My typical souvenir is some conference logo wear like a t-shirt, polo shirt or sweater. If you have met me at work, you know that I wear them every day! Unfortunately, I collected so much SC pieces of clothing over the years that it will be quite some effort to get them out of my closets and arrange them all nicely on the floor, so I can take a picture of it. But if I ever get around to find the time for it, you will see it first here on this blog, I promise!

So, to get started, I took a picture of the various mugs, glasses, and bottles I collected at SC (see above). As you can see, SC makes quite some effort to have a large collection of shapes, volumes, and colors available over the years.

My mug and classes collection -- Picture by Bernd Mohr

My mug and glasses collection — Picture by Bernd Mohr

The SC glasses are actual just a small part of my collection of drinking classes from my business trips from all over the world. If you visit me in my office, I am happy to show them to you in detail. And if someone ever wonders what gift she or he wants to give to me when you are visiting Jülich, now you know … wink! wink!

Update Jan 29: Found some more glasses at home (see below) 😉

My SC drink glass collection - Picture by Bernd Mohr

My SC drink glass collection – Picture by Bernd Mohr

Me introducing the SC15 invited plenary speakers -- Photo by SC15

Me introducing the SC15 invited plenary speakers — Photo by SC15

Wow! What a conference! SC15, the 27th international conference of high performance computing, networking, storage and analysis, from November 15 to 20, 2016 in Austin, Texas, again broke all records and with 12, 862 registered attendees from 65 countries is now officially the largest SC conference ever. There were 4830 people attending the technical program. It featured 78 technical paper presentations, 15 invited speakers, 41 tutorials, 42 workshops, 123 posters, 75 BoFs, and 12 panels. In parallel to the technical program, the attached exhibit hall featured 343 exhibitors from industry, academia and research organizations from around the world in approx. 137,000 net square feet of exhibit space, again the largest of all SC conferences. It certainly sets a high bar for me looking forward to 2017!

SC15 Technical Program Networking Event in Austin Football Stadium - Photo by Bernd Mohr

SC15 Technical Program Networking Event in Austin Football Stadium – Photo by Bernd Mohr

So where do have the customary technical program social event during the conference when you have over 4000 people coming? Answer: at the University of Texas at Austin football stadium! The food court was easily able to handle this crowd. 😉

Also, as a leading high-tech IT conference, attendees expect the latest and best networking support. So, during the conference, Austin also became the hub for the world’s fastest conference computer network – SCinet – which made 1.63 TeraBits of bandwidth available to exhibitors and attendees.  The network featured 89 miles of fiber deployed throughout the convention center and was constructed and maintained by 130 volunteers from 15 countries using US$22 million in loaned equipment. 337 wireless access points provided excellent service to about 6000 concurrent wireless clients roaming the Austin convention center during the conference.

But after the conference is before the conference! Let’s get SC16 organized in Salt Lake City!

This is the first part of my “Things you never wanted to learn about SC, but I tell you anyhow!” (TynwtlaSC,bItya!)  posts 😉

When you organize a conference for over 10,000 people, even simple things like stuffing the conference bags become a large task! SC, the world-largest international conference on high performance computing, networking, storage and analysis, has almost 5,000 people from all over the world attending the Technical Program. Each of them gets a conference bag which includes the printed conference programs, various sheets with announcements and useful information, sponsor advertisement material and sometimes small gifts. So, your task suddenly becomes: stuff 18 different item into each of the 5,500 conference bags as fast as possible!

[SC15 Conference Bag Stuffing]

SC15 Conference Bag Stuffing – Picture by Oliver Mohr

How do you do this? Of course, HPC specialists use a parallel processing based on a multi-pipelined approach!

First, you build up the pipelines: the material gets placed on a long row of tables, twice, on each side of the table. The volunteers walk done one side of the table picking up and collecting the different items along the way. At the end of the table, they hand it to another volunteer which inserts it into a conference bag, closes it, and in turn hands it to another set of volunteers which collect the bags and stack them for later behind the registration desk. Meanwhile, the first set of volunteers walk back the other side of the table, collecting the material for the next bag, and so on, before the start the cycle again. So each volunteer stuffs two bags per cycle.

Depending on the number of volunteers (and available space)  you can use now multiple of these pipelines in parallel. For SC15 in Austin, three pipelines were used (as can be seen in the picture).

Result: 5,500 conference bags stuffed in less than 4 hours by about 40 people!