EdgeCortix DNA IP Leads in Edge AI Inference Latency

April 26, 2021
The Linley Group Microprocessor Report on EdgeCortix
Renowned semiconductor industry analysts The Linley Group released its latest Microprocessor Report titled "EdgeCortix IP Lowers AI Latency", which concludes that EdgeCortix's unique Dynamic Neural Accelerator (DNA) architecture delivers best-in-class latency, and that the ''IP [deep-learning accelerator] achieves top scores among Level 3 ADAS (*) accelerators for batch=1 performance on ResNet-50 and Yolo v3, with equally impressive power efficiency. ''
The Linley Group's report provides detailed overview of the novel EdgeCortix AI processor architecture and the forthcoming EdgeCortix DNA-A800 AI co-processor chip, showcasing more than 5x lead in AI inference latency and power-efficiency over the competition. You can download a copy of the full Microprocessor Report here,
In real-time workloads under low-power, which are highly sensitive to latency (response time) and require streaming data or small batches, EdgeCortix DNA-A800 with 54 TOPS of compute in single-core configuration, delivers breakthrough batch-size 1 throughput of 2500 IPS (images per second) for ResNet-50 v1.5, and 555 IPS for Yolo v3, while consuming under 10 Watts of power. This translates into more than 15x IPS/Watt (power-efficiency) advantage over competing architectures.
To learning more about EdgeCortix, sign up for our mailing list at https://www.edgecortix.com/contact

ResNet-50 v1.5 is an inference benchmark for image classification, and is part of a suite of MLPerf standards for measuring performance of deep learning hardware accelerators.

Yolo v3 is the state of the art inference benchmark for real-time object detection in images and videos.

* ADAS is the abbreviation for Advanced Driver-Assistance Systems in automobiles.
The Linley Group's Microprocessor Report (*) writes about EdgeCortix's Dynamic Neural Accelerator ™  AI Processor IP -
" EdgeCortix is taking aim at the high-end edge market with its custom intellectual property (IP), delivering class-leading efficiency and latency for AI inference through a dual-accelerator approach."
* The Microprocessor Report is the microprocessor industry's leading technical publication, published since 1987.
DOWNLOAD FULL REPORT