Hewlett Packard Enterprise is sending a supercomputer to the International Space Station aboard SpaceX's next resupply mission for NASA, which is currently set to launch Monday.
Officially named the "Spaceborne Computer," the Linux-based supercomputer is designed to serve in a one year experiment conducted by NASA and HPE to find out if high performance computing hardware, with no hardware customization or modification, can survive and operate in outer space conditions for a full year – the length of time, not coincidentally, it'll likely take for a crewed spacecraft to make the trip to Mars.
Typically, computers used on the ISS have to be "hardened," explained Dr. Mark Fernandez, who led the effort on the HPE side as lead payload engineer. This process involves extensive hardware modifications made to the high-performance computing (HPC) device, which incur a lot of additional cost, time and effort. One unfortunate result of the need for this physical ruggedization process is that HPCs used in space are often generations behind those used on Earth, and that means a lot of advanced computing tasks end up being shuttled off the ISS to Earth, with the results then round-tripped back to astronaut scientists in space.
Related Stories
NASA sent rodents to infest the ISS along with an HPE supercomputer:
NASA's future deep space exploration – including to Mars – is an unprecedented venture in spaceflight, requiring us to tackle challenges we've never faced before. For instance, we know the human body changes significantly while in space, and we'll need to find ways to address those effects. NASA is conducting research to learn more about the long-term impact of extended human spaceflight. One experiment that just launched, Rodent Research-9, is contributing to this goal by sending rodents to the International Space Station, to study how a lack of gravity in space affects blood vessels, eyes and joints.
Using transport and habitat technology developed at NASA's Ames Research Center in California's Silicon Valley, the mice will fly to the space station aboard the 12th SpaceX resupply mission, and return to Earth about a month later. Due to biological similarities to humans, the mouse is a good choice of model organism for research aimed at understanding biological changes caused by the space environment. By studying rodents in the short term, NASA can make predictions about long-term human biological change in space, with applications here on Earth as well.
[...] For Rodent Research-9, the agency's space biology program is sponsoring three scientists from different universities to address different issues. NASA's bio-specimen sharing allows the three investigators to work with the same group of mice, without having to send three different missions to the space station. The three complementary research investigations will be combined into one cost-effective mission, addressing questions that are fundamental to human space exploration.
Rodents, meet human guinea pigs.
Technical mission page. Story reprint.
Back in 2017 two high-powered GNU/Linux computers were sent into orbit and are still running. They are long overdue for retrieval but are, more than 530 days later, still working. The goal of the project was to test the durability of such systems in preparation for travel to Mars, where data must be processed on site because of the delay in sending it to Earth and then transmitting the results back to Mars. So far autonomous management software has handled all of the hardware problems.
The servers were placed in an airtight box with a radiator that is hooked up to the ISS water-cooling system. Hot air from the computers is guided through the radiator to cool down and than circulated back.
Mr Kasbergen said there had been problems with the redundancy power supply as well as some of the redundant solid-state drives.
But he said the failures were handled by the autonomous management software that was part of the experiment.
The devices will need to be inspected back on Earth to find out what went wrong.
Earlier on SN:
Supercomputer on ISS will soon be Available for Science Experiments (2018)
HPE "Supercomputer" on the ISS Survives for 340 Days and Counting (2018)
HPE Supercomputer to be Sent to the ISS (2017)
HPE supercomputer is still crunching numbers in space after 340 days
HPE's mini supercomputer launched into space last year has survived the harsh conditions of zero gravity and radiation for almost a year. The Spaceborne Computer isn't the greatest supercomputer and has a performance of one teraflop, runs on Red Hat Enterprise Linux and is built out of two HPE Apollo Intel x86 servers with a 56Gbps interconnect.
NASA wanted to see if a computer would last for a year - roughly the time it takes to reach Mars - inside the International Space Station (ISS). So, HPE offered to tuck its Spaceborne Computer aboard SpaceX's CRS-12 rocket and send it into the abyss. "It has now been in space for 340 days", said Mark Fernandez, America's HPC technology officer at HPE and co-principal of the experiment, during a panel talk at the ISS Research & Development Conference on Wednesday in San Francisco.
[...] The machine hasn't been radiation hardened, and relies on a few software tricks to stop it from corrupting, something Fernandez calls "autonomous self-care". Continuous health checks helps keep the computer in check, and when it detects any potential hardware failures, it runs at a slower pace or enters "idle mode", where it powers down.
Previously: HPE Supercomputer to be Sent to the ISS
Related: Rodent Research-9 Experiments Sent to the ISS
(Score: 2) by RamiK on Monday August 14 2017, @02:10AM (11 children)
A lot of that ruggedization is there to protect the crew from debris and toxic chemical in case of blunt physical damage or fire... And say a year passes without an incident, all that proves is that they didn't have a big enough solar flare to fry the electronics or were lucky enough to bump too hard against the box and cause a mechanical part of a spark.
Well, it's a good publicity stunt for HP I guess. Provided they don't kill the crew that is...
compiling...
(Score: 1) by khallow on Monday August 14 2017, @04:10AM (9 children)
Which is a significant thing to show. Not really seeing the point of your post. For example, we don't die very often by computer fire so why would space with a similar concentration of oxygen be different?
(Score: 2) by RamiK on Monday August 14 2017, @04:39AM (8 children)
You don't die from "computer fires" because there's a shit ton of regulation governing everything from the power supplies to the materials used in the boards and chips that were written with gravity and the ability to crack open a window and leave the office when there's a fire in mind. Non of those apply to space. That's where the "ruggedization" came into place: NASA engineers sat down, assessed the risks, and wrote rules to prevent everything from power supply caps sparking the rich atmosphere to EM leaking and interfering with on-board equipment. And HP calling it an "experiment" to just ignore all that and "see what happens" is no more science than holding a book in front of you and letting someone shoot you to demonstrate an internet rumor without any previous trials.
compiling...
(Score: 2) by kaszz on Monday August 14 2017, @05:57AM (4 children)
Maybe they have encountered "HP" Carly Fiorina? ;)
(Score: 2) by RamiK on Monday August 14 2017, @07:06AM (3 children)
Nah it's a more fundamental problem than a specific pay-off: NASA used to be able to fund their activities thanks to launching communication satellites into orbits. However, between the Russians, Europeans, SpaceX and the Indians, along with the budget cuts... Well, lets just say that "safety first" only applies when you can stay afloat.
Desperate times call for desperate measures I guess...
compiling...
(Score: 2) by kaszz on Monday August 14 2017, @08:35AM (1 child)
Budget cuts = Trump..
(Score: 1, Funny) by Anonymous Coward on Monday August 14 2017, @09:11AM
Budget cuts = Trump = Desperate times = desperate measures = Trump... AGHAGHAGHAGHAAHAHAHAHAHAHAH!!!!
(Score: 1) by khallow on Monday August 14 2017, @11:51AM
No, that was never, ever true. First, when they did try that with the really terrible idea of a Space Shuttle monopoly on launching US things into space (roughly from 1975-1984), the end result was almost nothing commercial got launched due to the high launch costs of the Shuttle and the fact that it didn't offer launches for most of that period. Second, any revenue gained from such activities goes into the US's general fund to be disposed of by US Congress as it sees fit. The real advantage from NASA's point of view was that they could increase launch rate and generate more activity of the Shuttle for the same cost (launch rate being a huge factor in how expensive the launch vehicle is per launch). Finally, NASA has never had a launch vehicle reliable enough that paying customers could depend on it. That's why they gave up on commercial launch back in the late 80s and the US military gave up on the Shuttle for the most part by 1990.
I notice you include "SpaceX" in there even though NASA's last commercial or DOD missions ended about ten years prior to the creation of the business in 2002. SpaceX was completely irrelevant to the end of NASA's commercial launch activities. And really the whole observation is irrelevant. NASA gets a huge pile of money and does crap with it.
"Safety first"? There's a simple solution here. Don't have people in space, if you really care about safety first. But if you have to have people in the dangerous environment of space, that implies by default that you have a higher priority than safety. Figure out what that priority is.
(Score: 1) by khallow on Monday August 14 2017, @11:31AM (2 children)
It's not a "rich atmosphere". They're not in an Apollo 1 situation.
So what? NASA is notorious for playing it way too safe, until those assessments interfere with the political forces driving NASA, and then they get ignored. That's why they've never had a back up structure for the Vehicle Assembly Building, built more Space Shuttles, or stopped the Constellation/SLS crap.
But let's suppose your concerns were even remotely close to being a real problem. Wouldn't that "rich atmosphere" be a solid indication that NASA engineers aren't assessing risks properly? After all, shit happens. Bad capacitors aren't the only possible thing in the world that can spark. Human hair can do it with rubber, for example, and you would have the fuel-air combination right there as well. If NASA is going to risk everything by having humans aboard, then might as well do something useful while they're at it.
Well, it is an experiment. The environment has the potential to cause failures in weird ways. Further, there's the obvious question of what does it take to keep a piece of normal Earth gear running in space? Just because we have NASA engineers doesn't mean that we'll never find ourselves in a situation where non-approved gear has to be put on a spacecraft because there is no alternative choice.
And what exactly is at risk here? It's just the ISS, a two billion dollar money sink. If we're really concerned about astronaut lives or something, we could just splash the ISS and use that money stream to build a safer space station. I'm not feeling the need for huge concern here.
(Score: 2) by bob_super on Monday August 14 2017, @04:38PM (1 child)
> It's just the ISS, a two billion dollar money sink. If we're really concerned about astronaut lives or something, we could just splash the ISS and use that money stream to build a safer space station.
Like cars, maintaining the one you have is a lot cheaper than getting a new one.
Actually worse than cars, because driving a new one off the lot isn't typically a live fireworks-and-politicians event, and if you're dumping big money into a custom, they improve in value.
I'm pretty sure that HPE didn't just grab a random rack off the Chinese assembly line and just changed to metric screws for the space station. How much advertising are they expecting to pound us with is they run flawlessly? Can't have this HPE-branded thing be all over international news because it blew up in the ISS...
Back on topic: Isn't the ISS protected from most of the radiation that would affect the computers on a trip to Mars?
(Score: 1) by khallow on Tuesday August 15 2017, @01:49AM
Unless, like cars, that isn't true, like maintaining a Lamborghini for a commute to work when really what you need is an econobox. A couple of years of what is spent on the ISS could be used to buy a pretty nice space station that actually does most of what the ISS does with far lower maintenance costs.
Why would that happen? The atmosphere on the station isn't a tinder box. That's one mistake those NASA engineers aren't going to repeat.
Most, but not all. They'll still see radiation effects (both solar and cosmic rays) on their equipment.
(Score: 3, Funny) by coolgopher on Monday August 14 2017, @11:26AM
Well I sure hope they loaded ECC memory...
(Score: 0) by Anonymous Coward on Monday August 14 2017, @03:59AM (4 children)
I want to get me some satellite based supercomputers.
Like the Tree Diagram [wikia.com].
(Score: 2) by takyon on Monday August 14 2017, @05:40AM (3 children)
IRL the big problem is heat dissipation. Maybe if near-threshold computing or some amazing transistor advance [ieee.org] takes off, we can lower power consumption dramatically enough to put big computers in bad environments like that.
[SIG] 10/28/2017: Soylent Upgrade v14 [soylentnews.org]
(Score: 2) by chromas on Monday August 14 2017, @06:12AM (2 children)
I was just wondering about that myself. Does the ISS have a way to dump that much extra heat?
(Score: 0) by Anonymous Coward on Monday August 14 2017, @06:14AM (1 child)
Bigger heat sinks (possibly as inactive/redundant solar panels that already have huge surface areas).
(Score: 0) by Anonymous Coward on Monday August 14 2017, @10:47AM
If they could emanate shorter wavelengths [phys.org], then radiators could be made smaller for the same power rate.
(Score: 0) by Anonymous Coward on Monday August 14 2017, @08:41AM (2 children)
First it's product placement, then comes Native Advertising.
Next thing you know NASA will be filming a Plantronics headset commercial "on the moon"...wait, what?
(Score: 0) by Anonymous Coward on Monday August 14 2017, @05:13PM (1 child)
This.
Why/how did this fall to HP? Wouldn't it make more sense to select something really current like, for example the http://www.nvidia.com/object/drive-px.html [nvidia.com] (self-driving car supercomputer)??
(Score: 2) by takyon on Monday August 14 2017, @10:46PM
HPE is not HP, and HPE still makes supercomputers for customers.
[SIG] 10/28/2017: Soylent Upgrade v14 [soylentnews.org]
(Score: 0) by Anonymous Coward on Monday August 14 2017, @05:39PM
well this is good news.
unlike computers, humans can fix themselves. the logical thing, thus, to test advanced active shielding on, would be the computer?
i reckon more data processing power will be needed (but not enough for advertisement and excessive javascript_) on future space missions?
one would assume, that if the spaceships robo "brain" can be shielded, then humans can be too?