top of page

Netrasemi NPU system-on-chips

Embedding intelligence

in edge devices with powerful power-efficient AI chipsets.


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), a major gap that exists 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 capabilities such as Deep Neural accelerators and domain-specific hardware IP cores. We bring multiple SoCs and reference design platforms with advanced features, performance, and power efficiency needed for achieving edge-AI.

Security Cameras
In the Woods
Sound Device
Electronic Chip

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.

CPUs and Peripherals

NetraSoC family support both RISC-V and ARM cortex 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.

Heterogeneous parallel processing fabric

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.

Flexible APIs, SDKs and Application specific 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.

One architecture, Multiple go-to-market strategies

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.

Are You Ready to Explore the Power of Edge-AI computing for your IoT solution?

AI and smart IoT devices are driving new chips and computing platform requirements. Traditional SoCs with conventional CPU designs offer very limited capabilities for the new world of AI and edge-AI computing models. Emergence of on-device AI (edge-AI) computing requirements is disrupting existing chip supply chain. To become a leader in the solution space, you may need to accelerate your market entry with unique and custom domain-specific features, power efficiency, AI performance, flexible SDKs, hardware platform flexibility, cost advantage and agile go-to-market strategies. Netrasemi helps their customers to achieve these goals with their differentiated IPs, SoCs and reference designs.

+91 8129469846

2F, TrEST park, CET

Trivandrum, INDIA 695016

Subscribe to Our Newsletter

Thanks for submitting!

Follow Us On:

  • LinkedIn
  • Facebook
  • Twitter

© 2022 by Netrasemi

bottom of page