aiMotive Launches aiWare5 Automotive NPU for Scalable AI Workloads

May 15, 2026
aiMotive has released aiWare5, its latest automotive neural processing unit IP, offering enhanced scalability, safety compliance, and support for advanced AI workloads including large language models and vision transformers.

aiMotive has launched aiWare5, its newest automotive neural processing unit (NPU) IP, now available for general licensing. The release was announced in a press release following a soft launch at CES and an expanded partnership with Socionext aimed at serving Tier 1 suppliers and automakers.

aiWare5 builds on the previous aiWare4 design and maintains the same power efficiency while increasing throughput for higher performance automotive systems. It includes support for AI workloads such as large language models, vision transformers, and state space models, as well as dynamic FP8 scaling. The architecture is ISO 26262 ASIL B certified and developed as a Safety Element out of Context, simplifying integration into safety-critical systems.

The new release also includes updated development tools. The GPU optimized aiWare emulator enables faster than real time modeling before silicon availability, while aiWare Studio provides neural network optimization and performance estimation within five percent of final hardware results. These tools help reduce development time for automotive system designers preparing next generation vehicle compute platforms.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Robotics Brief or Daily AI Brief.

Also, consider following us on social media:

AI & Robotics AI Brief AI Brief (X)
Free newsletter

Robotics Brief

Weekly coverage of AI-driven robotics advances in industrial automation, autonomous vehicles, and robotic systems.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.