The workshop is open for researchers, students and scientific and industrial partners. The intention is to present and discuss the state-of-the-art in high-performance and parallel scientific computing. Presentations will focus on algorithms, applications, and software issues related to high-performance parallel computing. The focus of the workshop on Monday February 6 will be “Scalable Heterogeneous Computing and Programming Models for Computational Science”.
More information and a registration page for the Colloquium or Colloquium+Tutorial are available here »
The fees are:
Colloquium: CHF 50, free for students
Tutorial : CHF 150, CHF 50 for students
The Colloquium Day, February 6, 2012
The following invited speakers will present and discuss the state-of-the-art in high-performance and parallel scientific computing (6 talks of 45 minutes each + poster session):
Prof. Jeff Vetter (Oak Ridge National Laboratory)
Dr. Peter Tang (Intel)
Dr. Brad Chamberlain (Cray)
Prof. Paolo Bientinesi (RWTH Aachen)
Prof. Dimitri Komatitsch (CNRS)
Prof. Bastien Chopard (University of Geneva)
To promote fast exchange of information in our community, a poster session with contributed posters will take place also on Feb 6. Please, encourage your collaborators to register with a poster title and upload an abstract for their posters, the deadline is January 28, 2012.
The Tutorial Day, Feb 7, 2012
On February 7 Speedup will organize a tutorial on Intel Threading Building Blocks taught by Hans Pabst (Intel).
The HPC Advisory Council and the Swiss National Supercomputing Centre will host again the HPC Advisory Council Switzerland Conference 2012 in the
Lugano Convention Centre, Lugano, Switzerland, March 13-15, 2012
The conference will focus on High-Performance Computing education, training (including hands-on) and overview of new developments. The conference will include the following sections per day:
High Speed Networks
High Performance and Parallel I/O
Communication libraries: MPI, SHMEM, PGAS
GPU computing, CUDA, OpenCL
Big Data
Advanced topics / Technologies / development / the road to Exascale
It will bring together system managers, researchers, developers, computational scientists, students and industry affiliates for cross-training and to discuss recent HPC developments and future advancements.
There are the last available days to submit papers for the ACM International Conference on Computing Frontiers to be held in May 15th to 17th, 2012 in Cagliari, Italy (deadline for submission is January 9th, 2012).
The increasing complexity, performance, cost and energy efficiency needs of current and future applications require novel and innovative approaches for the design of computing systems. Boundaries between state of the art and revolutionary innovation constitute the computing frontiers that must be pushed forward to provide the support required for the advancement of science, engineering and information technology. The Computing Frontiers conference focuses on a wide spectrum of advanced technologies and radically new solutions relevant to the development of the whole spectrum of computer systems, from embedded to high-performance computing.
Authors are invited to submit full papers to the main conference and Ph.D. students are invited to submit an extended abstract for a special Ph.D. forum and poster session.
Papers are solicited in, but not limited to, the following areas:
Applications, programming and performance analysis of advanced architectures
Next-generation high performance computing and systems
Accelerators: many-core, GPU, custom, reconfigurable, embedded, and hybrid
Defect- and variability-tolerant designs, dependable computing
Power and energy efficiency: architectures, compilers and algorithms
Virtualization and virtual machines
Cloud-, internet-scale, service-oriented and smart infrastructure computing
Compilers and operating systems: adaptive, run-time, and auto-tuning
System management and security
Quantum and nano-scale computing
Impact of novel technology (e.g. NV memory, silicon photonics) on computing
Computational neuroscience, neuromorphic and biologically-inspired architectures
Computational aspects of intelligent systems and robotics
Reconfigurable, autonomic, organic, and self-organizing computation and systems
Interfaces and visualization for emerging applications and systems
Novel frontiers in computational science and scientific data repositories
Storing, managing, analyzing, and searching large data sets (” big data “)
In the two previous posts we presented the simulation of the spatial structure of the light emitted in early galaxies. We asked Rick Wagner of SDSC to discuss with Venkartram Vishwanath of Argonne the challenges of creating visualizations of very large numerical scale.
The simulation of Rick produces for example 256 GB of data for a small set of the field and up to many TB of data for the entire one. Traditionally they write the snapshots to disk and analyze them later. According to Rick this approach is not sustainable in the future since larger and larger sets of data will be produced.
Venkartram agrees that one challenge of next generation simulations is that I/O will not keep up with the growth rate of computing capability. In his group at Argonne they are now working on efficient infrastructure and software to reduce the amount of data being written to storage to perform analysis, as well as in-situ visualization while the simulation is progress. This will facilitate the transformation of the data into insight.
Venkartram is developing methods that will allow a non-intrusive integration of the simulation with the visualization. Not a single line of the code has to be modified. The data is buffered, staged and written out, maintaining the integrity of the data formats that are produced. This method can also be used to increase the speed data is written to disk.
Joe Insley (Argonne National Lab) has been working together with Rick Wagner of SDSC (see previous interview) on the visualization of the spatial structure of the light emitted in early galaxies. The visualization compares variables from two different simulations.
To compare of the two different simulations visually, Joe used vl3, a hardware-accelerated volume rendering library and application developed at the University of Chicago and Argonne.
The visualization for smaller data sets can be rendered in real time on a half-dozen nodes with 20 frames per second. The visualization can also be streamed from Argonne to SDSC over a dedicated network using a software developed at Argonne, and is controlled through a web-based client
