VeriSilicon AI video processor powers leading datacentersMonday, March 1st, 2021
VeriSilicon High-Performance and High-Quality AI Video Processor Powers Leading Datacenters
- Hantro Video technology has been selected by 12 of the top 20 cloud platform solution providers and selected by 3 of the top 5 internet providers
SHANGHAI — VeriSilicon (688521.SH) announces the next generation of video processing: The combination of its newly improved VC9000 video codec and its VIP9400 artificial intelligence (AI) and neural network processing technology to process video streams in data centers more efficiently.
The increasing number of live and on-demand gaming and video-streaming services, continuing expansion of broadband availability, and the need to deliver video to wide range of devices continues to require cloud platform companies to adopt the latest video-processing solutions like VC9000 coupled with VIP9400. VeriSilicon VC9000 and VIP9400 together offer leading AI Video processing, including high throughput and scalability, real-time AI video content analysis, scene-based video encoding, and AI pixel enhancements.
VeriSilicon VC9000 video processor family offers high-performance, high-quality, area and power-efficient multi-format video decoding and encoding. It supports 8K@120fps, supports all popular video codecs, including AV1 and HEVC, supports FLEXA API to enable user applications to develop content-based encoding strategies, and it also has a built-in embedded RISC-V core for multi-core scaling of up to 256 streams. VC9000 builds on proven VeriSilicon Hantro technology that has been widely developed in use cases that demand the most performance and quality from data centers to low power AIoT devices.
VeriSilicon VIP9400 family offers programmable, scalable, and extendable solutions for real-time processing by powerful AI devices. It supports all popular deep learning frameworks while providing up to 200 TOPS of computing ability under its scalable architecture and conforming to OpenCL 3.0 and OpenVX 1.2. The patented Neural Network engine and Tensor-Processing Fabric of VIP9400 deliver superb neural network performance with industry-leading power- and area-efficiency.
“Video now occupies over 80% of total consumer internet bandwidth,” said Wei-Jin Dai, Executive Vice President and General Manager of Intellectual Property Division at VeriSilicon, “We believe this percentage will only increase and have invested accordingly in developing video and AI technology for data center applications. VeriSilicon Vivante Neural Network Processing Unit (NPU) has been deployed and designed into AIoT to Data Center devices for over 60 SoCs. We closely partner with leading internet companies and global cloud platform providers and delivered effective solutions.”