Collaborating Authors

New InfiniteIO Platform Reduces Latency and Accelerates Performance for Machine Learning, AI and Analytics


InfiniteIO, the world's fastest metadata platform to reduce application latency, today announced the new Application Accelerator, which delivers dramatic performance improvements for critical applications by processing file metadata independently from on-premises storage or cloud systems. The new platform provides organizations across industries the lowest possible latency for their mission-critical applications, such as AI/machine learning, HPC and genomics, while minimizing disruption to IT teams. This press release features multimedia. "Bandwidth and I/O challenges have been largely overcome, yet reducing latency remains a significant barrier to improving application performance," said Henry Baltazar, vice president of research at 451 Research. "Metadata requests are a large part of file system latency, making up the vast majority of requests to a storage system or cloud. InfiniteIO's approach to abstracting metadata from file data offers IT managers a nondisruptive way to immediately accelerate application performance."

YouTube improves stream performance and simplifies live chats


YouTube announced a handful of new features available now for its livestream function. The changes, including reduced latency and simpler chat moderation, are aimed at making YouTube Live a more functional and efficient feature for users. First up, streamers now have the option to enable ultra-low latency, which will bring down streaming video latency to just a couple of seconds. That will make functions like answering questions during a livestream easier and more timely. YouTube has also made moderating chats easier and more efficient.

Google reduces Cloud latency with updated Andromeda SDN stack


Google on Wednesday took the wraps off latest version of its Andromeda, the a software-defined network (SDN) stack that underpins the Google Cloud Platform (GCP). With this release, packets on the network are able to securely bypass the hypervisor and go directly to the Andromeda software packet processor. This should reduce latency between Compute Engine VMs by 40 percent over the previous version of Andromeda. Since Google launched Andromeda in 2014, it's been able to reduce Compute Engine latency by nearly a factor of eight. "Without having to do anything, [customers'] code in some cases will run noticeably faster and better," Google engineering fellow Amin Vadhat told ZDNet.

SK Telecom reduces latency to 2 milliseconds for 5G


SK Telecom and Nokia have successfully reduced latency between the handset and base station to 2 milliseconds (ms) on its LTE network, the telco said. SK Telecom said the 2ms latency technology will facilitate development of real-time services such as autonomous driving, AR, and VR services on the way to 5G. The latency between handsets and base stations in current LTE networks is around 25ms or under. The International Telecommunication Union states that technologies designed for 5G must reach a peak data transfer rate of up to 20Gbps in latency under 1ms. For autonomous driving, the lowered latency will allow seamless services that require real-time transmission of data, which is difficult for existing LTE networks.

LG Display develops AI to reduce VR latency


LG Display, together with Sogang University, has developed artificial intelligence (AI) technology that reduces latency and blur in virtual reality (VR) content. Head-mounted displays for VR are conventionally highly immersive, but latency and motion blur can cause dizziness. The problem is especially pronounced for higher-resolution displays that require more calculations. LG's technology brings an algorithm that converts low-resolution videos to higher tones in real time. It has deep learning that allows use of only internal memory of the device to do so, instead of requiring additional external ones.