Slashdot Mirror

← Back to Stories (view on slashdot.org)

Too Much Gold Delays World's Fastest Supercomputer

Posted by timothy on from the other-people's-problems dept.

Nerval's Lobster writes "The fastest supercomputer in the world, Oak Ridge National Laboratory's 'Titan,' has been delayed because an excess of gold on its motherboard connectors has prevented it from working properly. Titan was originally turned on last October and climbed to the top of the Top500 list of the fastest supercomputers shortly thereafter. Problems with Titan were first discovered in February, when the supercomputer just missed its stability requirement. At that time, the problems with the connectors were isolated as the culprit, and ORNL decided to take some of Titan's 200 cabinets offline and ship their motherboards back to the manufacturer, Cray, for repairs. The connectors affected the ability of the GPUs in the system to talk to the main processors. Oak Ridge Today's John Huotari noted the problem was due to too much gold mixed in with the solder."

6 of 111 comments (clear)

  1. Which is another way of saying not enough lead. by Anonymous Coward · · Score: 5, Interesting

    ROHS strikes again

    1. Re:Which is another way of saying not enough lead. by Anonymous Coward · · Score: 5, Informative

      The lead-free solder has cost billions in failures.

      http://en.wikipedia.org/wiki/Whisker_(metallurgy)
      http://nepp.nasa.gov/WHISKER/

      NASA lost satellites because of lead-free solder (despite them requesting leaded solder). The funny thing is, leaded solder completely prevents whisker formation.

      Now, you may not care about whiskers if you just throw away your electronics every year or two, but if you want longevity, these things will kill you. So for lead-free solder preventing pollution? We are producing much more garbage now thanks to whisker-caused short circuit failures.

    2. Re:Which is another way of saying not enough lead. by __aaltlg1547 · · Score: 5, Informative

      Yep. Gots to pay attention. Thick gold on the connector to connector contacts is best, but don't plate it onto the solderable end of the connector, or on the pads on in the through holes. Actually, a tiny amount is good because it prevents corrosion before you have the part soldered on, but it has to completely diffuse into the solder to avoid making a non-conductive boundary layer. If there's too much to diffuse, you're screwed. You'd think the engineers at Cray would know this.

  2. Poor supercomputer by Brentyl · · Score: 5, Funny

    Too much gold never slowed down Mr. T. I pity the fool.

  3. Re:Wish by Anonymous Coward · · Score: 5, Insightful

    No you don't.

    Midas

  4. Re:can someone please explain by ebno-10db · · Score: 5, Interesting

    What's strange is how the gold got mixed into the solder. Long gone are the days of cheap gold when they would plate every metallic surface on a connector. Now they selectively plate the mating surfaces. Certainly they don't plate the part you solder. Gold contamination of solder is a well known phenomenon, but I haven't heard of it in decades, literally. The only other thing I can figure is that sometimes they flash plate some gold on the PC board to reduce solder whiskers or something. But that's a well known process. What the hell happened here?