Here’s a collection of highlights, selected totally subjectively, from the recent enterprise HPC news stream as reported at insideHPC.com.
Too busy to keep up? Make your commute productive and subscribe to the Weekly Takeout, insideHPC.com’s weekly podcast summary of the HPC news week in review.
Sun to OEM Windows Server
Sun’s CEO Jonathan Schwartz is definitely not your father’s CEO. Not if you father’s CEO was Scott McNealy, anyway.
Microsoft announced today that Sun is going to become a Windows Server OEM. (More on this enterprise HPC news item)
Appro’s new 1U HPC server for SMB
insideHPC.com has learned that Appro will announce a new 1U server on Monday targeted at HPC in small and medium-sized businesses.
Appro logoAppro’s new 1U XtremeServer 1512H has one socket for a dual or quadcore Opteron processor, support for up to 1.5TB hot-swap SATA HDDs and up to 32GB of memory. (More on this enterprise HPC news item)
Intel’s new Clovertown Xeons scale well, sip power. But watts with those FB-DIMMs?
AMD’s newly-released Barcelona “native” quad-core offering was not available for testing at the time. However, based on the article’s detailed breakdown of each server component’s power drain (did you know Intel’s FB-DIMMS consume 862% more power than the AMD DIMMs?!), it looks as if Barcelona will be a very promising contender for the performance-per-watt-per-Kelvin crown.
(More on this enterprise HPC news item)
All your public keys are belong to us!
New Scientist reports (pay per view) that it might be sooner than you think before your private data is cracked.
…the advent of quantum computers that can run a routine called Shor’s algorithm could have profound consequences. It means the most dangerous threat posed by quantum computing - the ability to break the codes that protect our banking, business and e-commerce data - is now a step nearer reality.
A blog post at New Scientist explains how the algorithm works. What’s troubling is that there are 2 teams working on the same problem, which makes me wonder if there’s an equivalent of Moores law to encryption cracking. Just how long do we have until this standard has to be scrapped?