HPC Project

Supercomputing Europe in Dresden, Germany (ISC08) is over and brought its new announcements in High Performance Computing. This year, two major symbolic milestones have been announced: the first machine over one PFLOPS (10^15 floating operations per second), the IBM Roadrunner, and the first main-stream chips reaching one TFLOPS (10^12 floating operations per second), the GPUs from nVidia and AMD/ATI.

Well, symbols are nothing else than abstract concepts but these symbols remind us that as the computing world evolves faster and faster, both applications and their programmers need to evolve to use these new sources of efficiency.

Compared with last Supercomputing show in Reno, there were fewer application and tools vendors at the exhibit. However, major hardware vendors and many research institutes were attending.

The pre-conference and the Exhibitor Forum were the occasion for interesting technological presentations and announcements. From the hot-chip point of view, here's what we've noticed:

• a special session for the IBM Roadrunner breaking the PFLOPS barrier by using both AMD Opteron and Cell CBE processors;
• AMD presentation about its new 45-nm 4-core Shanghai for 2008 and the coming 6-core Istanbul in 2009. These chips will also come out of the fab just in Dresden by the way...
• Intel presentation on its enterprise-class processor lines
• • the Itanium 9000
  • the Xeon MP 7000 and 5000, respectively for an expandable and energy efficient version
  • the Nehalem as their second generation 4-core 2-SMT processor due for the end of 2008
• AMD/ATI presentation on the FireStream 9250, reaching the TFLOPS with 8 GFLOPS/W -many programming environments are available (Brook+, ACML, RapidMind, CAL, OpenCL, HMPP...)
• nVidia presentation about the for 240-core T10P with 1.4 G transistors, also reaching the TFLOPS around 6.3 GFLOPS/W

If the hardware is only one (big) part of the HPC, many presentations were focused on how to program such "beasts".

Parallelism has been announced as a the inescapable way for higher performance for more than 50 years (« A Computer Oriented Toward Spatial Problems », S. H. Unger, 1958 for a SIMD computer or « Gamma 60 », Bull, 1957 for a SMT computer). However, up to now, hardware architects have been kind enough to squeeze the Moore's law to just make the classical Von Neumann & Co fast enough for most of the humans.

But now, the Moore's law no longer means faster processors but rather more cores at the same speed... So programs must be parallelized to run faster.

As usual, Thomas Sterling from Louisiana State University made an interesting presentation with a humorous slide to sum up the situation:  Core Trek (the next generation?)  In Exascale Computing: Space is the "final frontier" To Boldly Code, where no thread has gone before...

So, what can we imagine regarding the future of programming ?

Express more and more things by hand by using old programming languages. This require the programmers to be expert in deep computer architecture whereas they are often experts in their application domains which are more and more complex by themselves. Therefore, we'll have to have teams of experts in both domains: application and HPC (!)...

Another solution would be to rewrite the applications to use higher level languages that can hide the hardware complexity to the programmer but allow more parallelism exposition. Of course, it generaly requires a major - and costly - reengineering of the original code.

Last possibility : go on and program in the classical way... and wait for other solutions to appear. We may have some ideas here, at HPC Project...

Paris and Vancouver, - July 21, 2008 – Following the announcement of their strategic partnership last April, HPC Project and Parallel Geometry will be presenting this week at the GeoWeb 2008 conference their common vision of next generation computational environment for urban and other complex geospatial modeling.

This presentation will prefigure the roll-out of a common product planned for the fourth quarter of this year. This forthcoming product will take advantage of the unique capabilities of Parallel Geometry technology to enable real-time visualization and interaction with complex models. The product architecture will be based on the high-performance middleware developed by HPC Project for an unprecedented fluid manipulation and fly-through capacity involving large 3D complex scenes.

 “Recent discussions with our customers have demonstrated that the market is waiting for a turn-key solution for powering 3D urban modeling and geospatial simulation” said Pierre Fiorini, HPC Project Founder and CEO. “We will provide with Parallel Geometry the right mix of innovative algorithms and architecture innovation to fulfill this need. This product will fuel a whole new range of applications for large geodata sets and the wonder of it will be the ease of operation for the end-user.”

According to Jean-François Rotgé, President and CSO of Parallel Geometry, “For this first product coming out of our strategic partnership with HPC Project, we have decided to focus on the great challenge of eliminating the root cause of bottlenecks that currently limit the performance of GeoWeb 3D applications".

"Our technology offers the unique opportunity to unify multi-source spatial data (CAD, BIM, GIS…) in a single 3D/3D reference model, and to address at the same time the fundamental issues of multiscale and real-time interaction with complex models. The GeoWeb is an ideal business case to harness this potential. HPC Project, with its new class of computing environment, offers us the right form factor and high performance environment, to fully demonstrate a new generation of 3D visualization and simulation pipelines" added Rotgé.

This breakthrough initiative will result in a new class of geospatial appliance that will support very low cost processing of massive quantities of heterogeneous spatial data, and foster a new wave of 3-D geospatial applications for urban planners, civil engineers, scientists, homeland security professionals, emergency responders… "It represents an exciting opportunity for us and the GeoWeb community” added Pierre Fiorini.

During the last EUROSATORY show, held at Paris, France (June, 16-20), HPC Project showcased the latest innovations in simulation.  This was the first case EUROSATORY dedicated a display area specifically for the Training & Smulation sector. In this context, the showcase was featuring the latest simulation, computation and man-machine interface technologies. It was located in the middle of the Training & Simulation area.

The showcase highlighted the latest and cutting-edge simulation technologies, gathering ten leading companies of the field. The goal of the showcase was to demonstrate technologies that are critical in the context of the integration of simulation into operational systems.

Featured demos included:

• Multitouch surfaces for collaborating (pictured)
• New generation solution for tactical training
• Tools for rapid synthetic environment generation
• Virtual maintenance trainer (using virtual reality and immersive displays)
• Real-time tactical communication modelling
• Optimizing 3d hyper complex simulations
• High performance simulation
• Physics-based light & vision simulation
• Real time procedural terrain simulation

In addition, a series of conference on the future of simulation was held, and gathered both operational and specialists of the field. Keynote speeches were delivered by Tim Bloechl (Microsoft), Warren Katz (VT MAK) and Patrice Commune (PRESAGIS) - pictured. Two tracks were held : integration of simulation in operational systems and serious gaming/virtual universes. More information available at http://www.innov-in-simulation.com/InnovationShowcase.