Licensible IP core accelerates neural networks
By Peter Clarke, EETimes Europe
February 25, 2016
French researchers have developed a IP for deep neural networks that is available for licensing to run in software, for implementation in FPGA fabric, for synthesis within an SoC.
The Pneuro Engine is a multipurpose energy-optimized accelerator designed for neural networks and image processing chains. It utilizes a clustered SIMD architecture optimized for MAC operations (as found in SIMD extensions of popular processor architectures) but with a distributed memory optimized for near neighbourhood accesses and design reuse management.
The research team is from CEA List based at Saclay-Paris and at Embedded World demonstrated the use of an FPGA-based Pneuro on a GlobalSensing Technologies board to perform face recognition. The same technology has also been ported to a Raspberry Pi 2B containing a quad-core Cortex-A7, and to an Odroid XU3 board based on a quad Cortex-A15 processor.
E-mail This Article | Printer-Friendly Page |
Related News
- Socionext Prototypes Low-Power AI Chip with Quantized Deep Neural Network Engine
- OIF Members Demonstrate How Interoperability Accelerates Solutions for Today's and Future Global Networks at OFC 2022
- BSC executes, for the first time, big encrypted neural networks using Intel Optane Persistent Memory and Intel Xeon Scalable Processors
- Expedera Introduces Its Origin Neural Engine IP With Unrivaled Energy-Efficiency and Performance
- Imec and GLOBALFOUNDRIES Announce Breakthrough in AI Chip, Bringing Deep Neural Network Calculations to IoT Edge Devices
Breaking News
- Micon Global and Silvaco Announce New Partnership
- Arm loses out in Qualcomm court case, wants a re-trial
- Jury is out in the Arm vs Qualcomm trial
- Ceva Seeks To Exploit Synergies in Portfolio with Nano NPU
- Synopsys Responds to U.K. Competition and Markets Authority's Phase 1 Announcement Regarding Ansys Acquisition