- Amazon S3 Files is the "first and only cloud object store" of its kind, built for AI
- It brings low-latency access without your data ever having to leave the AWS environment
- The new storage system reduces some of the layers and complexities, making AI simpler and cheaper
Amazon Web Services (AWS) has announced Amazon S3 Files, which it describes as the "first and only cloud object store that provides fully-featured, high-performance file system access to your data."
S3 Files is a new feature that turns S3 into a shared file system to eliminate the need to move or duplicate data between storage points, all in a bid to reduce some of the friction enterprises face when balancing data storage and AI workloads.
Key to S3 Files is the low-latency, high-performance file access, without data ever leaving the AWS environment.
Amazon S3 Files is the perfect data storage for AI workloads
"Built using Amazon EFS, S3 Files gives you the performance and simplicity of a file system with the scalability, durability, and cost-effectiveness of S3," the company wrote in a post.
Up until now, organizations have been storing their data and data lakes in S3, however file-based tools, agents and applications have been unable to access that date without either a separate file system, duplicating the data or building complex pipelines.
S3 Files essentially makes the data accessible through the file system and via S3 APIs, meaning that "thousands of compute resources can connect to the same... file system simultaneously."
Compared with rival systems, AWS now stands out for much simpler developer workflows and making both structured and unstructured data accessible. As for the broader trend, it shows Amazon reducing storage layers to make AI development faster and simpler for developers, and cheaper for customers.
"There are no data silos, no synchronization complexities, and no tradeoffs," AWS concluded.
S3 Files is already generally available across 34 of AWS' Regions.
