Skip to main content

Osaka University researchers create flexible cloud-based computing system

osaka university
Osaka University
A group of researchers working at Osaka University in Japan have created the world’s first system capable of delivering flexible computation via cloud computing. The team created a piece of management software that allows the user to customize various aspects of the set-up to suit the task at hand.

Traditionally, when high-performance computation is carried out in the cloud, a server with a fixed configuration would be used. The drawback to this kind of system is that the initial build can be expensive, and much of its computational muscle might not be utilized in ordinary usage.

By contrast, the project that’s been carried out at Osaka University allows the user to tailor various aspects of the system to their needs. The number of servers that are in use and the network connection can be controlled in this way, but the system is also capable of making adjustments to hardware components.

Users can tweak the GPUs being used as part of the computation, or they can tweak the solid state drives being used to store data, according to a report from Phys. This functionality allows for a flexible cloud computing solution that can efficiently carry out all manner of different tasks.

Cloud computing can be implemented to help research projects crunch numbers when they don’t have capable enough hardware on-site. This kind of flexible system could potentially help researchers all over the world have better access to the computational power they need to carry out their work.

It’s hoped that this project, which was led by visiting professor Takashi Yoshikawa, will continue to be developed, and will eventually be widely used. The system was previously shown at the Supercomputing 16 conference which was held in Salt Lake City, Utah, in November 2016.

Brad Jones
Former Digital Trends Contributor
Brad is an English-born writer currently splitting his time between Edinburgh and Pennsylvania. You can find him on Twitter…
A dangerous new jailbreak for AI chatbots was just discovered
the side of a Microsoft building

Microsoft has released more details about a troubling new generative AI jailbreak technique it has discovered, called "Skeleton Key." Using this prompt injection method, malicious users can effectively bypass a chatbot's safety guardrails, the security features that keeps ChatGPT from going full Taye.

Skeleton Key is an example of a prompt injection or prompt engineering attack. It's a multi-turn strategy designed to essentially convince an AI model to ignore its ingrained safety guardrails, "[causing] the system to violate its operators’ policies, make decisions unduly influenced by a user, or execute malicious instructions," Mark Russinovich, CTO of Microsoft Azure, wrote in the announcement.

Read more