Slashdot Mirror
SpaceX Will Deliver The First Supercomputer To The ISS (hpe.com)
Slashdot reader #16,185, Esther Schindler writes:
"By NASA's rules, not just any computer can go into space. Their components must be radiation hardened, especially the CPUs," reports HPE Insights. "Otherwise, they tend to fail due to the effects of ionizing radiation. The customized processors undergo years of design work and then more years of testing before they are certified for spaceflight." As a result, the ISS runs the station using two sets of three Command and Control Multiplexer DeMultiplexer computers whose processors are 20MHz Intel 80386SX CPUs, right out of 1988. "The traditional way to radiation-harden a spacecraft computer is to add redundancy to its circuits or by using insulating substrates instead of the usual semiconductor wafers on chips. That's expensive and time consuming. HPE scientists believe that simply slowing down a system in adverse conditions can avoid glitches and keep the computer running."
So, assuming the August 15 SpaceX Falcon 9 rocket launch goes well, there will be a supercomputer headed into space -- using off-the-shelf hardware. Let's see if the idea pans out. "We may discover a set of parameters with which a supercomputer can successfully run for at least a year without errors," says Dr. Mark R. Fernandez, the mission's co-principal investigator for software and SGI's HPC technology officer. "Alternately, one or more components of the system will fail, in which case we will then do the typical failure analysis on Earth. That will let us learn what to change to make the systems more reliable in the future."
The article points out that the New Horizons spacecraft that just flew past Pluto has a 12MHz Mongoose-V CPU, based on the MIPS R3000 CPU. "You may remember its much faster ancestor: the chip that took you on adventures in the original Sony PlayStation, circa 1994."
So, assuming the August 15 SpaceX Falcon 9 rocket launch goes well, there will be a supercomputer headed into space -- using off-the-shelf hardware. Let's see if the idea pans out. "We may discover a set of parameters with which a supercomputer can successfully run for at least a year without errors," says Dr. Mark R. Fernandez, the mission's co-principal investigator for software and SGI's HPC technology officer. "Alternately, one or more components of the system will fail, in which case we will then do the typical failure analysis on Earth. That will let us learn what to change to make the systems more reliable in the future."
The article points out that the New Horizons spacecraft that just flew past Pluto has a 12MHz Mongoose-V CPU, based on the MIPS R3000 CPU. "You may remember its much faster ancestor: the chip that took you on adventures in the original Sony PlayStation, circa 1994."
The part you seemed to have missed is: This is an experiment to learn whether an alternative approach to hardening can be developed. If it's successful, the benefits would be obvious.
Experiments are the raison d'etre for the ISS... so why is this a problem?
#DeleteChrome
Those laptops aren't running life support systems.
Exactly. If the laptops freeze is a minor inconvenience. If the main computers of the ISS freeze the humans inside will freeze too.
Mexico: 100% conservative's America now!
If you look at the ISS webcam when it switches to the interior cam, there's a few laptops (one running Ubuntu) tied to the sides of the walls.
The laptops don't run any essential systems directly. The 80386SX variants they're talking about control lifesystems. The laptops are for user interfaces and monitoring. There's somewhere around 80 of them on board the station, between station interfaces and payload interfaces. In 2013, a bunch of them were migrated to Linux, specifically Debian 6, according to reports. They used to run Windows NT and XP. The article is a press release written to overemphasize the hardened CPUs, which are by far the minority on board, to make this experimental launch of a pair of HP Apollo pc40s seem more impressive than it is.
Information about the reliability of the laptops is damn hard to find. I'm guessing NASA signed some sort of agreement with IBM to prevent publication of such information. IBM had the exclusive right to fly laptops to the US side of the space station for years, and Lenovo retained that right for some time. It was only recently that they lost it and NASA selected HP to provide the newest laptops.
Random forum posts from people involved indicate that the laptops crash with monotonous regularity. I suspect they would be a lot more stable if they had ECC RAM with aggressive scrubbing, but laptops with ECC RAM didn't exist until 2015 when Lenovo finally released a laptop with a Xeon in it. Odds are that none of the laptops on the ISS right now have ECC RAM.
These two HP Apollo modules do have ECC RAM. They're Broadwell core Xeon CPUs with 12 DDR4 DIMM slots and up to 4 nVidia Tesla P100 boards in them. Either the linked article is crap, or the Apollo units don't have any Teslas installed, because the article says their "speed is over 1 TeraFLOP", which is pretty feeble. With 4 P100s in them, each Apollo should be able to produce ~38 single-precision TeraFLOPS. The article is very poor, but at a guess, the P100 boards are not installed for cooling reasons. As it is, they're having to include a liquid cooling cabinet for them, because air cooling doesn't behave too well in microgravity. Either that or the P100s are installed, the liquid cooling can handle them, and the article is garbage. Between the ECC RAM and underclocking the CPUs, they're hoping these machines can run long enough between crashes to be useful.
Why not do the heavy computing down here on the ground, where it is so much easier?
Bandwidth. ISS has 3 megabit upstream, 10 megabit downstream. Yes, megabit, not gigabit. And that's a massive upgrade over what it had for years, which was 2400 baud. There's any number of science experiments people would like to run that would benefit from beefy local processing handling large amounts of data. So much data that neither transmitting it off station nor storing it and physically transporting it off station is currently feasible. The bandwidth isn't available or the storage is too expensive.
That may change in the 2020s. I'd bet a pizza that SpaceX will be including upward-facing antennas in their satellites, not just Earthward-facing, in order to talk to their own rockets at high bandwidth regardless of where they are in their trajectories. Still, it's going to be quite some time before that option exists, so experiments to determine the feasibility of local processing are worth conducting.
Ive put a lot of hardware on ISS. Have a few systems going tomorrow on Spx12 actually so I have a bit of inside info here. I asked at a flight qualification panel about this a few years ago and was told that to date, no cots cpu hardware has experienced either an SEI or had problems due to TID. Apparently the biggest problems experienced were infant mortality on thinkpads that went up in 2010ish, but the same failures existed terrestrially so it was linked to a bad lot of HDs.
Thus far, weve had beaglebones, raspberry pis, and a few odroids running on station for years and havent seen a single problem.
LEO isnt really a hostile environment for silicon.