FPGA Acceleration of Binary Weighted Neural Network Inference
White Paper FPGA Acceleration of Binary Weighted Neural Network Inference One of the features of YOLOv3 is multiple-object recognition in a single image. We used
The Xiphera MACsec family provides high-speed IP cores implementing the MACsec (Media Access Control security) protocol as standardized in IEEE Std 802.1AE-2018. The MACsec protocol defines a security infrastrucure for Layer 2 (as per the OSI model) traffic by assuring that a received frame has been sent by a transmitting station that claimed to send it. The traffic between stations is also encrypted to provide data confidentiality and authenticated to provide data integrity.
Typical MACsec applications require high data bandwidths such as 10G, 25G, 40G, or 100G and often benefit greatly from FPGA-based acceleration. The Xiphera MACsec IP runs on BittWare’s IA-840f and IA-420f Agilex FPGA-based PCIe cards.
Moderate resource requirements:
Performance:
Standard Compliance:
Test Vector Compliance:
OSI Network Model
The Xiphera MACsec IP uses Advanced Encryption Standard with a 256-bit key in Galois Counter Mode (AES-GCM) to protect data confidentiality, data integrity and data origin authentication. XIP1213H is best suited for data traffic on 25 Gbps links, and XIP1213E is suited for traffic on 100 Gbps links.
The original use case for MACsec is protecting communications in wired local area networks. MACsec can also be used for the following:
To protect critical control messages in communications networks
To protect sensitive measurement data in industrial automation applications
To secure point-to-point video links
Encrypted source code, a comprehensive VHDL testbench and a detailed datasheet are included. The MACsec IP is available in four variants:
RS-XI-1213B | MACsec AES256-GCM |
RS-XI-1213H | MACsec AES256-GCM, high-speed |
RS-XI-1213E | MACsec AES256-GCM extreme-speed |
Hardware-based security solutions using standardized cryptographic algorithms. Learn more about the company on their website, Xiphera.com.
Our technical sales team is ready to provide availability and configuration information, or answer your technical questions.
"*" indicates required fields
White Paper FPGA Acceleration of Binary Weighted Neural Network Inference One of the features of YOLOv3 is multiple-object recognition in a single image. We used
BittWare On-Demand Webinar Enterprise-class FPGA Servers: The TeraBox Approach FPGA-based cards are maturing into critical devices for data centers and edge computing. However, there’s a
PCIe Gen4 data mover IP from Atomic Rules. Achieve up to 220 Gb/s using BittWare’s PCIe Gen4 cards, saving your development team when you need more performance than standard DMA. Features: DPDK and AXI standards, work with packets or any other data format, operate at any line rate up to 400 GbE.
BittWare On-Demand Webinar High Performance Computing with Next-Generation Intel® Agilex™ FPGAs