Facebook iconTwitter icon
B2B-Network:
Loader
Thumb original microchip   how to implement high performance power efficient deep learning on fpgas
Client: Avnet, Inc
Format: Whitepaper
Size: 742 KB
Language: English
Date: 30.11.2021

How to Implement high performance power efficient Deep Learning on FPGAs

Field Programmable Gate Arrays (FPGAs) are a compelling choice for hardware acceleration on the edge especially when adding newer capabilities for machine learning inference. Specialized neural networks called Convolutional Neural Networks (CNN) are being deployed on the edge in embedded vision systems to perform tasks such as object detection, face and gesture recognition and pose estimation.

FPGA architecture provides a unique set of features to satisfy the high computational complexity requirements along with sufficient memory access (via local and external memories) to realize CNNs efficiently. Their inherent programmability provides the flexibility to integrate and upgrade customized functions on a single device.

In this paper we share details about how Microchip’s programmable hardware along with the Core Deep Learning (CDL) framework from ASIC Design Services enable a power efficient imaging and video solution platform for embedded and edge computing applications.

Free Download
Please enter your contact information and click the download button. You will receive an email with your download link.
I have read and understood the privacy/terms and conditions and consent to the ascertainment, conversion, utilisation and dissemination of the data I have entered into this registration form. The B2B Media Group and originator/sponsor Avnet, Inc of the document may use my contact data for the purpose of B2B marketing (via e-mail, phone, display and postal) until such time as I withdraw my consent. My agreement to the company and our partner as shown below can be revoked at any time via an E-Mail to the following address: datenschutz@b2bmg.de ( Subject: Avnet, Inc)

Privacy / download conditions:

Date: 1.8.2018

Client

  • B2B Media Group GmbH, Bahnhofstraße 5, 91245 Simmelsdorf (B2B MG)

Partner

  • Avnet, Inc
Fields marked with * are mandatory