sales@hkmjd.com
Service Telephone:86-755-83294757
Eindhoven, Netherlands, February 10, 2025 - NXP Semiconductors N.V. (NASDAQ: NXPI today announced that it has entered into a definitive agreement to acquire Kinara, Inc., a leader in the high-performance, low-power, programmable discrete neural proces…
Eindhoven, Netherlands, February 10, 2025 - NXP Semiconductors N.V. (NASDAQ: NXPI today announced that it has entered into a definitive agreement to acquire Kinara, Inc., a leader in the high-performance, low-power, programmable discrete neural processing unit (NPU) industry. The company's products support a wide range of edge AI applications, including multimodal generative AI models. The acquisition will be an all-cash transaction of $307 million and is expected to close in the first half of 2025, subject to regulatory approvals and other customary closing conditions.
Intelligent systems of the future will require edge AI processing that is safe, cost-effective, and energy efficient. As a result, the edge AI processing market is experiencing rapid growth. Advanced edge AI enables critical decisions to be made locally and independently, without relying on the cloud, improving response times, enhancing data privacy, and reducing costs.
Kinara's innovative NPU and its comprehensive software support enable energy-efficient AI performance across a range of neural networks, including traditional and generative AI, to meet the rapidly growing AI needs of the industrial and automotive markets. The acquisition will allow NXP to integrate discrete Npus and powerful AI software into its processor, connectivity, security, and advanced simulation solutions portfolio, further enhancing NXP's ability to deliver a complete, scalable AI platform from TinyML to generative AI.
NXP and Kinara are long-standing partners, and Kinara's NPU can be easily integrated into NXP's industry-leading industrial and iot processor portfolio. The two sides will deepen solution integration and jointly build a scalable AI platform to meet the various AI reasoning needs of the industrial and automotive sectors.
Kinara split NPU to drive edge AI innovation
Kinara's discrete Npus, including Ara-1 and Ara-2, are among the industry leaders in terms of performance and energy efficiency, making them ideal for emerging AI applications such as vision, voice, gesture, and a variety of other multimodal implementations powered by generative AI. Both devices feature innovative architectures that map inference graphs for efficient execution on Kinara's programmable proprietary neural processing unit to maximize edge AI performance. Given that AI algorithms will continue to evolve from CNN to generative AI in the future, and even develop new methods such as agent AI, this programmability ensures the adaptability of the system.
The Ara-1 is the first generation discrete NPU capable of advanced edge AI reasoning. The Ara-2 is a second-generation NPU capable of up to 40 TOPS (trillion operations per second) and is optimized for generative AI for system-level performance. The Ara-1 and Ara-2 Npus can be easily integrated with embedded systems to enhance their AI performance, including upgrades to existing field systems.
Kinara also offers a wide range of software development kits that allow customers to optimize AI model performance and simplify deployment processes. Kinara's AI software portfolio includes an extensive model library and model optimization tools that will be integrated into NXP's eIQ AI/ML software development environment, enabling customers to quickly and easily create end-to-end AI systems.
For more information, visit NXP.com.cn/EmbeddedWorld
Company website: www.hkmjd.com
Time:2025-03-10
Time:2025-03-10
Time:2025-03-10
Time:2025-03-10
Contact Number:86-755-83294757
Enterprise QQ:1668527835/ 2850151598/ 2850151584/ 2850151585
Business Hours:9:00-18:00
E-mail:sales@hkmjd.com
Company Address:Room1239, Guoli building, Zhenzhong Road, Futian District, Shenzhen, Guangdong
CopyRight ©2022 Copyright belongs to Mingjiada Yue ICP Bei No. 05062024-12
Official QR Code
Links: