VeriSilicon High-Performance and High-Quality AI Video Processor Powers Leading Datacenters
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.”
VeriSilicon Microelectronics (Shanghai) Co., Ltd. (VeriSilicon, 688521.SH) is committed to providing customers with platform-based, all-round, one-stop custom silicon services and semiconductor IP licensing services leveraging its in-house semiconductor IP. Under the unique “Silicon Platform as a Service” (SiPaaS) business model, depending on the comprehensive IP portfolio, VeriSilicon can create silicon products from definition to test and package in a short period of time, and provides high performance and cost-efficient semiconductor alternative products for IDM, Fabless, system vendors (OEM/ODM) and large Internet companies, etc. VeriSilicon’s business covers consumer electronics, automotive electronics, computer and peripheral, industry, data processing, Internet of Things and other applications.
VeriSilicon presents a variety of customized silicon solutions, including high-definition video, high-definition audio and voice, In-Vehicle Infotainment, video surveillance, IoT connectivity, data center, etc. In addition, VeriSilicon has five types of in-house processor IPs, namely GPU IP, NPU IP, VPU, DSP IP and ISP IP, and more than 1,400 analog and mixed signal IPs and RF IPs.
Founded in 2001 and headquartered in Shanghai, China, VeriSilicon has 6 design and R&D centers in China and the United States, as well as 11 sales and customer service offices worldwide. VeriSilicon currently has more than 1000 employees.