AI SoCs for small and tiny form factors
Embedding intelligence in small and tiny devices is the latest trend in IoT. The "edge-AI" strategy is making sensors smart, cheap, responsive, and independent with minimal data to be sent to central computers. Edge-AI demands these devices to be powered with a powerful and energy-efficient system on chips (SoC) with domain specific features. Traditional SoCs and many general purpose AI chip architectures fails to achieve this requirement. This is a major gap in the semiconductor industry today. Netrasemi's NetraSoC family is addressing the on-device AI computing needs for a wide range of industry segments including IoT. Along with regular system-on-chip(SoC) features, NetraSoC family has the unique advantage of high-end hardware acceleration using Deep Neural accelerators and domain-specific hardware IP cores. We bring power efficient SoCs and reference platforms enabling advanced features for edge-AI.
Deep Neural Processor (NPU)
Netrasemi's Deep neural processor (NetraDNPU) IP core and a family of domain-specific hardware engines bring best-in-class AI/ML and feature performance. The high energy efficiency offered by our architecture is ideally suited for edge computing in a tiny form factor.
NetraSoC family support multi-core SoC variants with Linux and RTOS support. Our SoC family includes a rich portfolio of hardware accelerators, peripheral IP cores and low-power SoC features needed to achieve maximum solution flexibility, features and performance for high complexity workloads like video analytics.
Graph stream architecture
Netrasemi graph heterogeneous parallel processing fabric integrates a variety of hardware acceleration cores ensuring seamless data flow and performance without major CPU load. This allows multi-data analytics at the best power efficiency suitable for edge-AI.
Enabling customers for faster market access
Our NetraSoC architecture comes with both ASIC (high volume) and FPGA technology targets. FPGA platforms are targeted at customers having agile go-to-market plans, smaller volumes, and special customization needs. We have SoC-FPGA reference designs with AI/ML and domain-specific features.
Flexible APIs, SDKs, reference designs
NetraSoC designs come with early FPGA prototype platforms, flexible software API libraries, software development kits (SDKs), and application reference design kits (RDKs) to enable efficient and early customer engagement. Our in-house IP portfolio allows us to do customer-centric optimizations if there is a strong need.
Are You Ready to Explore the Power of Edge-AI computing for your IoT solution?
Enabling optimal computing model for smart IoT solutions
AI and smart IoT devices are driving new chips and computing platform requirements. Traditional SoCs with cloud centric computing offer very limited capabilities for the new world of AI powered IoT solutions (AioT). Emergence of real-time on-device AI (edge-AI) computing and distributed computing requirements are exposing major gap in the existing chip supply chain. To become a leader in the solution space, you may need to accelerate your market entry with optimal computing model, unique and custom domain-specific features, power-performance efficiency, flexible SDKs, platform flexibility, cost advantage and agile go-to-market strategies. Netrasemi helps their customers to achieve these goals with their differentiated IPs, SoCs, AI software development framework and reference designs.