On the CSC blog, Olli-Pekka Lehto explains in detail how problems with their parallel filesystem led to a service outage of three days, and how they returned to normal services. He writes: "A month ago CSC's high-performance computing services suffered the most severe unplanned outage in years. The outage was due to data corruption that occurred in the parallel filesystem that houses the work directory. While this is intended to be a temporary storage space we recognized that there was a significant quantity of data that needed to be recovered, which took time. In total approximately 1.7 petabytes and 850 million files were recovered." Then follows a long report. Read further...

Peter Kelly-Detwiler runs a ten-page in-depth story in Forbes titled "With Super-Computing, The Process of Disruptive Innovation In Energy Is Likely To Accelerate". His conclusion: "At the end of the day, today's machines are already delivering enormous value. These powerful machines highly leverage the intelligence and manipulative capability of the human species. They will only get faster and smarter in the visible future, with significant implications for innovation and disruptive technologies. We will likely soon see better solar panels, more powerful and robust batteries, more durable wind turbines, and we may even someday see small modular nuclear reactors and nuclear fusion." Read further...

The HPC event organisation ISC published a video interview with Jack Dongarra, one of the chairs for ISC 16 in Frankfurt. Read further...

Futura-Science runs an exclusive interview with Olivier Thomine, who invented a compression algorithm that is 1000x faster than LZW. He thinks his algorithm is especially useful for HPC applications such as bioinformatics, engineering, and pharmaceutical. The interview is in French. Read further...