High-Efficiency, Low-Area ML Inference Processor
Overview
Optimized for the most cost and battery-life sensitive designs, Ethos-N37 delivers premium AI experiences in entry phones, digital TVs, and other endpoint devices. The Arm AI platform combines the highest performance, open-source software framework, and the largest AI ecosystem, to make it easy to develop on Arm.
Key Features
- High Efficiency
- Delivers up to 1 TOP/s within 1mm2 using 512 8-Bit MACs.
- Lowest Area
- Smallest-area inference NPU brings battery life savings and quick integration for cost-effective and thermally constrained designs.
- Optimized Design
- Up to 225% convolution performance uplift using Winograd on 3x3 kernels, delivering up to 90% MAC utilization.
- Futureproof
- Supports a wide range of existing ML operations and future innovations through firmware updates and compiler technology.
Technical Specifications
Related IPs
- ML Inference Processor with Balanced Efficiency and Performance
- Highly Scalable and Efficient Second-Generation ML Inference Processor
- DES Encryption and Decryption Processor
- Embedded Configuration and Test Processor
- 32-bit RISC Processor To Deliver High Performance In Low-Cost Microcontroller Applications
- 16/32/64-bit Application Adaptive Processor