Stop trying to make The Machine happen, HPE. It's not going to happen HPE will use a research grant awarded today by the US Department of Energy to develop blueprints for a Machine-based exascale supercomputer. An exascale system is a beast that can hit at least one exaflops – a billion billion floating-point math operations per second. Uncle Sam is bent on getting at least one of these mega- …
A nitpick here. Sputnik was designed, built, and launched by the USSR, not Russia. The distinction is important: most of the USSR's rocketry design and manufacturing was based in Ukraine; the launch pad was in Kazakhstan; the orbital vehicle (and later manned vehicles) were mostly designed and built in Russia; a lot of later orbital science work was prepared in the three Baltic republics.
Just because Russia became the legal successor to the Soviet Union, and managed to hang on to the most destructive parts of its legacy, both in terms or the artifacts and the mindset, does not mean we should ignore the others when we talk about the history of the space race. Until a better term comes along, let's stick to the USSR, shall we?
To be honest, the latest PR I've heard from people claiming to speak for HPE say it is all about having non-volitile memory. Presumably for non-HPE jobs this would be something cheaper than DRAM, but I'm sure it will be more expensive once somebody trots out the magic word "enterprise".
In this new form, it should basically be a drop in replacement for normal devices. Just less likely to suffer certain failures (assuming they use DRAM as a write-through cache). Expect things to be relatively simple until PHBs decide to remove code that can't fail due to the "machine's" new ideal memory.
The Register 
Biting the hand that feeds IT
Copyright. All rights reserved © 1998–2025
