VERISILICON
29.2.2024 01:01:36 CET | Business Wire | Press release
VeriSilicon (688521.SH) today announced that it has reached a milestone achievement with its Neural Network Processor (NPU) IP integrated into over 100 million AI-enabled chips across 10 major application sectors worldwide, including Internet of Things (IoT), wearables, smart TVs, smart home, security monitoring, servers, automotive electronics, smartphones, tablets, and smart healthcare. As a global leader in embedded AI/NPU over the past seven years, VeriSilicon’s NPU IP has been successfully integrated into 128 AI SoCs supplied by 72 licensees in these varied market segments.
VeriSilicon’s NPU IP is a high-performance AI processor IP designed with a low-power, programmable, and scalable architecture. It can be easily configured to meet licensees’ requirements for chip sizes and power budgets, making it a cost-effective neural network acceleration engine. This IP also ships with extensive and mature Software Development Kit (SDK) supporting all major deep learning frameworks, ensuring fast product deployment in the market.
VeriSilicon’s latest VIP9000 series NPU IP offers scalable and high-performance processing capabilities for both Transformer and Convolutional Neural Network (CNN). Coupled with Acuity toolkits, this powerful IP supports all major frameworks including PyTorch, ONNX, and TensorFlow. Additionally, it features 4-bit quantization and compression technologies to address bandwidth constraints, facilitating the deployment of AI Generated Content (AIGC) and Large Language Model (LLM) algorithms such as Stable Diffusion and Llama 2 on embedded devices.
By leveraging VeriSilicon’s FLEXA® technology, VIP9000 can be seamlessly integrated with VeriSilicon’s Image Signal Processor (ISP) and video encoders to form low-latency AI-ISP and AI-Video subsystems without requiring DDR memory. It can be further customized to balance cost and flexibility for power- and space-constrained environments in deeply embedded applications.
“AI capability is now an essential part of every smart device across different applications, ranging from MCUs to high-performance application processors. Leveraging our expertise in Graphics Processor Unit (GPU), we have architected low-power, programmable, and scalable NPU processor IPs capable of handling various types of neural networks and computational tasks within the NPU itself. Such efficiency, combined with minimized data traffic, serves as key enablers for embedded smart devices,” said Wei-Jin Dai, Executive VP and GM of IP Division at VeriSilicon. “With the rapid advancement of AI, we have achieved a level of human-like reasoning that paves the way for intelligent human assistants. VeriSilicon is leveraging our highly efficient AI computing capabilities and vast experience in deploying over 100 million AI-enabled chips to bring server-level AIGC capabilities to embedded devices.”
About VeriSilicon
VeriSilicon is committed to providing customers with platform-based, all-around, one-stop custom silicon services and semiconductor IP licensing services leveraging its in-house semiconductor IP. For more information, please visit: www.verisilicon.com
To view this piece of content from cts.businesswire.com, please give your consent at the top of this page.
View source version on businesswire.com: https://www.businesswire.com/news/home/20240228352652/en/
About Business Wire
Subscribe to releases from Business Wire
Subscribe to all the latest releases from Business Wire by registering your e-mail address below. You can unsubscribe at any time.
Latest releases from Business Wire
Radial Selects Riskified to Power Payment Fraud and Refund/Return Protection for Merchant Client Portfolio9.3.2026 15:00:00 CET | Press release
The partnership brings Riskified’s AI-powered platform for payment fraud, refund claim, and return abuse protection to Radial’s global network of merchants Riskified (NYSE: RSKD), a leader in ecommerce fraud and risk intelligence, today announced a strategic partnership with Radial, a leading 3PL set to become Paxon later this year. Radial will integrate with Riskified’s AI-powered platform to help its merchants approve more legitimate orders and reduce losses from payment fraud, including many merchants that use Shopify as their ecommerce platform. Radial supports many of the world’s most recognized retail brands with a global ecommerce fulfillment network of more than 20 centers across North America, helping merchants deliver orders quickly and cost effectively. By bringing Riskified’s AI-powered fraud decisioning into its commerce ecosystem, Radial gives merchants the surgical ability to calibrate the checkout experience according to risk—without slowing fulfillment. This also suppo
Boomi Activates Data for the Enterprise9.3.2026 14:00:00 CET | Press release
New platform innovations activate contextual data to power production-scale enterprise AI, with a new European platform instance for localized control Boomi™, the data activation company, today announced new capabilities within the Boomi Enterprise Platform. Data activation brings data to life across systems and processes, delivering it with the right context and timing to power everything from AI to BI. The Boomi Enterprise Platform, the foundation that puts data in motion, now adds new semantic context to help AI agents operate on grounded business realities, expands governed SAP data movement with change data capture, enhances transparency and oversight across agentic workflows, and introduces a dedicated European platform instance for localized data control. This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20260309682526/en/ Boomi Activates Data for the Enterprise “Last year, Boomi helped enterprises move from experimentatio
Thredd Accelerates in 2026 with its Global Platform and Delivering Enterprise-Scale Outcomes9.3.2026 14:00:00 CET | Press release
Thredd, the AI-first issuer processing platform, today announced a major acceleration phase for 2026, marked by the appointment of Marilyn McDonald as Chief Technology Officer and the promotion of Ryan Dew to Chief Product Officer. Thredd has never been in a stronger position. A fully cloud-native version of its global platform is live in the United States, with end-to-end credit capabilities launching in the coming months alongside a state-of-the-art debit platform and modern unified ledger. Marilyn McDonald joins as CTO to lead the next phase of enterprise-scale execution. She succeeds Edwin Poot, who helped lead the modernisation of Thredd’s architecture and technology stack, laying the foundation for cloud-native and agentic growth. Marilyn brings global transformation experience from senior roles at Citigroup, Mastercard, Expedia Group and StubHub. Her focus is on strengthening operational readiness, bank-grade delivery, enterprise execution and continuous resilience as Thredd sca
MariaDB to Acquire GridGain: Architecting the Real-Time Foundation for the Agentic Enterprise9.3.2026 14:00:00 CET | Press release
Strategic acquisition unites MariaDB’s mission-critical relational database with GridGain’s extreme in-memory speed to power the next generation of AI applications MariaDB plc today announced that it has entered into a definitive agreement to acquire GridGain Systems, Inc., the pioneer of in-memory computing and creator of open source Apache Ignite. By merging MariaDB’s AI-ready relational database with GridGain’s scalable, in-memory power, MariaDB is setting a new industry standard: sub-millisecond data infrastructure for the agentic era. Closing the AI Latency Gap As enterprises move beyond passive chatbots toward agentic AI – autonomous systems that reason, plan and execute tasks – they are quickly becoming limited by traditional data architectures. AI agents require real-time access to massive datasets with zero friction. This acquisition bridges that gap by fusing: MariaDB’s reliability: Proven, ACID-compliant transactional integrity for the world’s most sensitive data, with nativ
Safe Software Announces the Peak of Data and AI 2027, a Premier Global Conference, in London, UK9.3.2026 14:00:00 CET | Press release
Safe Software (Safe) officially announced today the return of its global user conference, the Peak of Data and AI, taking place March 9–11, 2027, at the QEII Centre in London, UK. A Partner Summit will kick off the event on March 8, 2027, bringing together Safe’s global partner community ahead of the main conference. Hosted every two years, the Peak of Data and AI has evolved from Safe Software’s long-running user conference into a premier global event for data and AI professionals. The conference alternates between North America and international locations, with previous events held in Bonn, Germany (2023) and Seattle, Washington (2025). “At the Peak of Data and AI, we bring together the people who are shaping how organizations use data to drive real-world outcomes,” said Don Murray, CEO of Safe Software. “With London as our host city in 2027, we’re excited to connect with the global community to learn, listen, and share what’s next for data and AI.” The three-day conference will feat
In our pressroom you can read all our latest releases, find our press contacts, images, documents and other relevant information about us.
Visit our pressroom