Resource Types: PDF

Linley Microprocessor Report: Ceva-NeuPro-M Enhances BF16, FP8 Support

By

Ceva has updated its licensable NeuPro-M design to better handle Transformers—the neural networks underpinning ChatGPT and Dall-E AI software and now finding application at the edge in computer vision. Architectural changes to Ceva-NeuPro-M improve its power efficiency and can increase its performance sevenfold on models that can take advantage of the new features. Critical among … Continued

Ceva-NeuPro-M Product Note – Japanese

By

Ceva NeuPro-M™ NPU エッジからクラウドまでの多様なAIの 処理負荷に対して、4～1,200 TOPSの 拡張性のあるパフォーマンスと 350 TOPS/ワットの電力効率を 提供します。

Robot Odometry Testing and Analysis – White Paper

By

Any automated machine needs to have a strong understanding of where it is in order to complete its task. A robot arm needs to be able to weld one section of a car to another, a 3D printer needs to print fine details with precision layer by layer, and consumer robots need to navigate an … Continued

Ceva-RealSpace Product Note – English

By

As consumers demand more immersive and seamless experiences, Spatial Audio has become a key technology in a broad range of applications. Whether it’s pinpointing an approaching enemy in a game, feeling the roar of the crowd at a stadium or concert, or reducing fatigue from video calls, the benefits of having a more realistic experience … Continued

Linley Microprocessor Report: Ceva-XC20 Enables Vector-Unit Sharing

By

“Ceva’s XC20 vector-DSP architecture implements a new simultaneous multithreading technique, allocating the resources of a single vector unit to two threads instruction by instruction. Vector-unit utilization increases, boosting the licensable DSP’s area efficiency. Combined with other updates, Ceva reports the first XC20-based core, the dual-thread XC22, is more efficient than the single-thread XC4500 and the … Continued