Kyoto University supercomputer system ‘accidentally’ erases 77TB of data after suffering from technical error


[ad_1]

A supercomputer system based at Japan’s largest research center, Kyoto University, suffered from a technical error. The issue resulted in a massive loss of 77 terabytes of data that was being routinely backed up at that time.

Millions of deleted files would come from several research organizations.

Supercomputer system technical problem

(Photo: STR / JIJI PRESS / AFP via Getty Images)
TOPSHOT – This photo taken on June 16, 2020 shows Japan’s Fugaku supercomputer at the Riken Center for Computational Science in Kobe, Hyogo Prefecture. – The Fugaku supercomputer, built with government support and used in the fight against the COVID-19 coronavirus, is now ranked as the fastest in the world, its developers announced on June 22, 2020.

According to a recent report by Gizmodo on Friday, December 31, the incident allegedly took place between December 14 and 16. The unexpected error erased millions of files that could grow to around 34 million.

The report adds that these files come from 14 different research institutes that rely on Kyoto University’s supercomputers. In addition, the Japanese academy manages the Data Direct ExaScaler storage as well as the Hewlett Packard (HP) Cray computer system which are fully utilized for research studies.

At the time of writing, the university has yet to identify the exact nature of the deleted files or the root cause of the technical error. The school announced earlier that files from at least four groups will no longer be recovered.

Related article: AMD Fits Singapore’s Fastest Supercomputer With EPYC Processors

How much does supercomputing research cost

Like Beeping computer As pointed out in his report, compute-intensive research is not something that should be easily dismissed. Depending on the severity of the research, the hourly operation alone could cost hundreds of dollars.

After the unexpected incident that Kyoto experienced this month, the university has released further information about the loss of supercomputer storage data.

This is what the school posted on their page (translated into English).

Dear users of high-performance computing services

Today, a bug in the storage system backup program caused a crash in which some files in / LARGE0 were lost. We have stopped addressing the issue, but we may have lost close to 100TB of files and are investigating the extent of the impact.

We will contact the persons concerned individually.

We apologize for the inconvenience to all users.

The most interesting thing about supercomputing is that it goes beyond the usual work done on normal computing. It uses very complex mathematical calculations to perform computer processes in the system.

Additionally, experts are exploring its uses by incorporating supercomputers in several fields, including physics, climate change, and other areas of research.

In a December 25 report from Interesting engineering, the Jean Zay supercomputer from France became the first HPC to have a photonic coprocessor. Instead of using electric current, the machine relies on light to process all information.

Predictive supercomputers

Earlier this year, Tech Times reported that astronomers used the ATERU II supercomputer to simulate 4,000 instances of the universe. Researchers who operate from the National Astronomical Observatory of Japan (NAOJ) have mapped models to see the primitive state of the universe.

Another report from the same tech publication in February discussed how the world’s fastest computer could predict tsunamis in real time. Thanks to the application of artificial intelligence (AI), experts could finally create 20,000 possible scenarios for natural disasters.

Since Japan is in the Pacific Ring of Fire, experts must take action in this situation. That way, they could warn people in advance if there is an impending tidal wave that will hit a specific area.

Also read: Tesla: Fifth Most Powerful Supercomputer In The World To Run Autopilot And Autonomous AI: Is It Special?

This article is the property of Tech Times

Written by Joseph Henry

2021 TECHTIMES.com All rights reserved. Do not reproduce without permission.

[ad_2]

Comments are closed.