Skip to main content


Showing posts from 2018


When part of a team, your group can become more capable than a single individual, but only if your team can work together and communicate effectively. Having members of a group talk over each other leads to nothing but a cacophony, and nothing gets done. For this reason protocols need to be established, such as letting others speak without interruption, or facing those you are addressing. The same is necessary with electronics, especially with system on chip (SoC) designs.

Introducing the AXI ProtocolThe protocol used by many SoC designers today is AXI, or Advanced eXtensible Interface, and is part of the Arm Advanced Microcontroller Bus Architecture (AMBA) specification. It is especially prevalent in Xilinx’s Zynq devices, providing the interface between the processing system and programmable logic sections of the chip.My first introduction with the interface was in a tutorial I was following that was to be implemented on Aldec’s own development board based off the Zynq XC7Z030, theT…

Xilinx Announces the Acquisition of DeePhi Tech

Deal to Accelerate Data Center and Intelligent Edge Applications the leader in adaptive and intelligent computing, announced today that it has acquired DeePhi Technology Co., Ltd (DeePhi Tech), a Beijing-based privately held start-up with industry-leading capabilities in machine learning, specializing in deep compression, pruning, and system-level optimization for neural networks.

DeePhi Tech has been developing its machine learning solutions on Xilinx technology platforms, and the two companies have worked closely together since DeePhi Tech’s inception in 2016. DeePhi Tech’s neural network pruning technology has been optimized to run on Xilinx FPGAs, enabling breakthrough performance with best-in-class energy efficiency. Xilinx has been a major investor in DeePhi Tech, alongside other prominent international investors, since 2017.

“We are excited to continue our strong partne…

International Field Programmable Logic & Applications

Placement Strategies for 2.5D FPGA Fabric Architectures

FPGAs take advantage of 2.5D stacking technology to manufacture large capacity and high performance heterogeneous devices at reasonable costs. EDA tools need to be aware of and exploit physical characteristics of such devices, for example the reduced connection count between SLRs, the infrequency of SLL channel occurrence in the fabric, and the aspect ratios of individual SLRs. We implement a partition driven places to explore various EDA options to take advantage of architectural features in 2.5D FPGAs. We improve the routability of designs by optimizing the place for discrete SLL channels and reduced connection counts. We propose a cut schedule for the partitioner to orient the placement with awareness of the aspect ratio of SLRs to improve track demands within each SLR.

I. Introduction

2.5D stacking  enables FPGAs to meet the twin demands of higher logic capacity and heterogeneity. 2.5D stacking also permits lower latency co…

FPGA-based neural network accelerator outperforms GPUs

Xilinx Developer Forum: Claimed to be the highest performance convolutional neural network (CNN) on an fpga, Omnitek’s CNN is available now. The deep learning processing unit (DPU) is future-proofed, explained CEO Roger Fawcett, due to the programmability of the fpga.
It was demonstrated as a GoogLeNet Inception-v1 CNN, using eight-bit integer resolution. It achieved 16.8 terra operations per second (TOPS) and can inference over 5,300 images per second on a XilinxVirtex UltraScale+ XCVU9P-3 fpga. The modular, scalable approach, makes it suitable for object detection and video processing applications at the edge and in the cloud, explained Fawcett, as well as for inference in data centres and intelligent cameras.

The DPU can be configured to provide optimal compute performance for neural network topologies in machine learning applications, using the parallel DSP architecture, distributed memory and reconfigurability of logic and connectivity for different algorithms. The DPU achieves o…



Acceleration Applications Alveo Data Center accelerator cards can deliver dramatic acceleration across a broad set of applications and are reconfigurable to provide an ideal fit for the changing workloads of the modern data center. Compare how Alveo Data Center accelerator cards perform compared to traditional CPU architectures.

Accelerator Cards That Fit Your Performance Needs

Samsung Electronics Unveils Xilinx-Based SmartSSD Solution

Samsung Debuts Semiconductor Innovations at Samsung Tech Day that Maximize Data Center Efficiencies and Enable AI, Enterprise and Emerging TechnologiesIt has been an exciting couple of weeks for Xilinx, with the Versal and Alveo announcements and all of the activities at XDF Silicon Valley and XDF Beijing. Adding to this momentum, at last week’s Samsung Tech Day, Samsung Electronics announced SmartSSD, a Xilinx-based (FPGA) SSD that enables high-performance accelerated computing closer to the data, bypassing CPU limitations. Technologies introduced at the event include 7nm LPP EUV, SmartSSD and 256GB 3DS RDIMM

Helping to enable future innovations in the next-generation of data centers like high-performance computing, artificial intelligence and emerging applications, Samsung’s SmartSSD powered by Xilinx FPGAs will increase speed and efficiency, and lower operating costs by pushing intelligence to where data lives. For example, you are looking for an image of a cat. Normally the system …

new chips with 3-D transistors

Intel's new chips with 3-D transistors: Cutting edge technology to catch up on tablet & smartphone market 

SAN FRANCISCO: Intel Corp. said Wednesday that it has redesigned the electronic switches on its chips so that computers can keep getting cheaper and more powerful. 

The switches, known as transistors, have typically been flat. By adding a third dimension - "fins" that jut up from the base - Intel will be able to make the transistors and chips smaller. Think of how skyscrapers address the need for more office space when land is scarce. 
Intel expects to use the new technology to make PC and server chips, code-named Ivy Bridge, by the end of 2011 and will later use it to make improved processors for mobile devices. 

The cutting-edge technology - which Intel says breaks new ground by moving away from flat circuitry to a three-dimensional model - may eventually challenge rival ARM Holdings, whose chip technology is favored in devices like Apple's iPad. 

The company s…

world smallest resonator

Murata claims world’s smallest 32.768 kHz MEMS resonator

Murata claims to have developed the world’s smallest 32.768 kHz MEMS resonator (the WMRAG series).
Based on miniature MEMS technology, the new resonators exhibit stable frequency characteristics with a temperature drift of <160 ppm across their operating range of -30 to 85 °C. Initial frequency accuracy is ±20 ppm which is at the level expected of a more sophisticated (and expensive) crystal resonator. An in-built 6.9pf capacitor reduces the components necessary for the circuit that generates the reference clock signal, thereby reducing the space required as well as giving designers more flexibility in designing their solution. Measuring 0.9 x 0.6 x 0.3 mm (W x L x H), the new MEMS resonator is over 50 % smaller than a conventional 32.768 kHz crystal resonator that measures 1.2 x 1.0 x 0.3 mm. Available in silicon-based wafer-level chip scale packaging (WL-CSP), the device can be integrated into an IC made of a homogeneous semicond…

ARM architecture

Why ARM is Most Popular? ARM Architecture
Introduction of ARM: ARM stands for Advanced RISC (reduced instruction set computer) machine.  ARM started life as part of Acorn makers of the BCC computer, and now designs chip for apple iPad. The first ARM was established in Cambridge University in 1978. The Acorn group computers have developed the first ARM commercial RISC processor in 1985. ARM was founded and very popular in 1990. The ARM using more than 98% of the mobile phones in 2007 and 10 billion processors are shipped in 2008. ARM is the latest technology which replaced by microcontroller and microprocessors. Basically ARM is a 16 bit/ 32 bit Processors or Controllers. ARM is heart of the advanced digital products like mobile phones automotive systems digital cameras and home networking and wireless technologies.
Why ARM is most popular:
arm is the most popular processors, particularlyused in portable devices due to its low power consumption and reasonable performance.  arm has got bette…