Part of the  

Chip Design Magazine

  Network

About  |  Contact

Posts Tagged ‘GPU’

Blog Review – Monday, June 26, 2017

Monday, June 26th, 2017

This week, hot on the heels of DAC, a review of the Austin event; Intel administers a dose of precision medicine; Challenges for drivers; How to choose between a GPU or FPGA and a blockchain reaction for the IoT

DAC 2017 took place in Austin, Texas, and Paul MeLellan, Cadence Design Systems, was there and has collated a wide-ranging report, with day-by-day news, including bats and bagpipes from the 54 th incarnation of the event.

Writing from a very personal viewpoint, Bryce Olson, Intel, advocates precision medicine, and looks at Intel’s scalable reference architecture to speed up the research and answers in medical care.

Vehicle safety is critical, and Stephen Pateras, Mentor Graphics, looks at self-test and monitoring in autonomous cars, using the Tessent MissionMode architecture. He explains in a clear, detailed manner, the IC test capabilities and simulation for self-driving cars.

Still with vehicle design, Robert Vamosi, Synopsys, flags up the security hazards around the connected car as sensors proliferate and hackers ramp up their assaults. He advocates software security and the communication protection afforded by the IEEE 802.11p protocol.

A handy white paper is brought to our attention by Steve Leibson, Xilinx, for those deciding whether a GPU is better than an FPGA in cloud computing, machine leaning, video and image processing applications.

I learned a couple of things from Christine Young, Maxim Integrated this week. One is that there is a job title of ‘chief IoTologist’, the other was to put the term ‘blockchain’ into context for the IoT. She reports from the IoT World Conference about how blockchain, using advanced cryptography, provides a “tamper-proof distributed record of transactions” and how the IoT Alliance is occupied in developing a shared blockchain protocol as a common identifier to secure IoT products.

Starstruck John Blyler, looks at the reality behind the stardust and conducts an interview with Dr Clifford Johnson, physicist at University of Southern California and script adviser for the National Geographic Channel’s TV program, Genius, about Albert Einstein.

Blog Review – Monday, October 10, 2016

Monday, October 10th, 2016

This week, bloggers look at the newly released ARM Cortex-R52 and its support, NVIDIA floats the idea of AI in automotives, Dassault Systèmes looks at underwater construction, Intrinsic-ID’s CEO shares about security, and there is a glimpse into the loneliness of the long distance debugger

There is a peek into the Xilinx Embedded Software Community Conference as Steve Leibson, Xilinx, shares the OKI IDS real-time, object-detection system using a Zynq SoC.

The lure of the ocean, and the glamor of Porsche and Volvo SUVs, meant that NVIDIA appealed to all-comers at its inaugural GPU Technology Conference Europe. It parked a Porsche Macan and a Volvo XC90 on top of the Ocean Diva, docked at Amsterdam. Making waves, the Xavier SoC, the Quadro demonstration and a discussion about AI in the automotive industry.

Worried about IoT security, Robert Vamosi, Synopsys, looks at the source code that targets firmware on IoT devices, and fears where else it may be used.

Following the launch of the ARM Cortex-R52 processor, which raises the bar in terms of functional safety, Jason Andrews looks at the development tools available for the new ARMv8-R architecture, alongside a review of what’s new in the processor offering.

If you are new to portable stimulus, Tom A, Cadence, has put together a comprehensive blog about the standard designed to help developers with verification reuse, test automation and coverage. Of course, he also mentions the role of the company’s Perspec System Verifier, but this is an informative blog, not a marketing pitch.

Undersea hotels sounds like the holiday of the future, and Deepak Datye, Dassault Systèmes, shows how structures for wonderful pieces of architecture can be realized with the company’s , the 3DExperience Platform.

Capturing the frustration of an engineer mid-debug, Rich Edelman, Mentor Graphics, contributes a long, blow-by-blow account of that elusive, thankless task, that he names UVM Misery, where a customer’s bug, is your bug now.

Giving Pim Tuyls, CEO of Intrinsic-ID, a grilling about security, Gabe Moretti, Chip Design magazine, teases out the difference between security and integrity and how to increase security in ways that will be adopted across the industry.

Blog Review – Monday May 16, 2016

Monday, May 16th, 2016

Ramifications for Intel; Verification moves to ASIC; Connected cars; Deep learning is coming; NXP TFT preview

Examining the industry’s transition to 5G, Dr. Venkata Renduchintala, Intel, describes the revolution of connectivity and why the company is shifting its SoC focus and exploit its ecosystem.

Coming from another angle, Chris Ciufo, Intel Embedded, assess the impacts of the recently announced changes at Intel, including the five pillars designed to support the company: data center, memory, FPGAs, IoT and 5G, with his thoughts on what it has in its arsenal to achieve the new course.

As FPGA verification flows move closer to those of ASICs, Dr. Stanley Hyduke, Aldec, looks at why the company has extended its verification tools for digital ASIC design, including the steps involved.

Software in vehicles is a sensitive topic for some, since the VW emissions scandal, but Synopsys took the opportunity of the Future Connect Cars Conference in Santa Clara, to highlight its Software Integrity Platform. Robert Vamosi, Synopsys, reports on some of the presentations at the event on the automotive industry.

Identifying excessive blocking in sequential programming as evil, Miro Samek, ARM, write a spirited and interesting blog on real-time design strategy and the need to keep it flexible, from the earliest stages.

Santa Clara also hosted the Embedded Vision Summit, and Chris Longstaff, Imagination Technologies, writes about deep learning on mobile devices. He notes that Cadence Design Systems highlighted the increase in the number of sensors in devices today, and Google Brain’s Jeff Dean talked about the use of deep learning via GoogLeNet Inception architecture. The blog also includes examples of Convolutional Neural Networks (CNN) and how PowerVR mobile GPUs can process the complex algorithms.

This week, NXP FTF (Freescale Technology Forum), in Austin, Texas, is previewed by Ricardo Anguiano, Mentor Graphics. He looks at a demo from the company, where a simultaneous debug of a patient monitoring system runs Nucleus RTOS on the ARM Cortex-M4. He hints at what attendees can see using Sourcery CodeBench with ARM processors and a link to heterogeneous solutions from the company.

Caroline Hayes, Senior Editor

Blog Review – Monday, October 26, 2015

Monday, October 26th, 2015

Counting gates til the chickens come home to roost; Bio lab on a desk; Twin city goes digital; Back to the Future Day; Graphics SoC playground; Wearables get graphic

Something is troubling Michael Posner, Synopsys, when is a gate not a gate? He discusses the FPGA capacity of Xilinx’s UltraScale FPGAs and tries to find the answer. He also describes his Heath Robinson style light controlled chicken feeder he has installed in the chicken coop.

A desktop biolab sounds like something in a teenage boy’s room, but Amino is the ‘brainchild’ relates Atmel of Julie Legault. The Arduino-based bio-engineering system enables anyone to grow and take care of living cells. The mini lab allows the user to genetically transform an organism’s DNA through guided interactions. The Arduino-driven hardware monitors the resulting synthetic organism which needs to be fed nd kept warm. For those old enough to remember the Tamagotchi craze – it just moved up a gear.

3D computer models of buildings and cities take on a new role, demonstrated by Dassault Systèmes, whose 3DEXPERIENCity continuously generates the city as a digital twin city. Ingeborg Rocker explains how the IoT is used by the multi-dimensional data model which integrates population density, traffic density, weather, energy supply and recycling volumes data in real time to support city planners.

Recent acquisitions in the industry are analysed by Paul McLellan, Cadence Design Systems. Beginning with the acquisition of Carbon Design Systems by ARM, McLellan puts the deal in a market and engineering context. He moves on to the acquisition by Lam Research of KLA-Tencor and Western Digital which has bought SanDisk.

Putting the AMD R-Series through its paces, Christopher Hallinan, Mentor Graphics, delights in the versatility of the SoC, as discovered with Mentor Embedded Linux. He gives real-life examples of algorithms and how the visuals apply to industrial and scientific applications.

Celebrating a noteworthy date Back to the Future Day – October 21 2015 – Tobias Wilson-Bates, Georgia Tech, looks at how time travel has been portrayed in fiction. It gets philosophical: “One way to think about future speculations is to imagine that there are all these failed futures that co-exist with a present reality” but Marty would approve.

The acceptance of Mali-470 GPU to the wearables camp is complete. Dan Wilson, ARM, explains how the GPU is exploiting its OpenGL ES 2.0 graphics standard and power consumption for wearable and IoT applications.

Caroline Hayes, Senior Editor

Deeper Dive – Tues August 06, 2014

Wednesday, August 6th, 2014

Integration with a view to IP

Atmel has licensed processor and security IP from ARM, as it looks to develop low power, consumer devices for a new raft of end uses, such as wearable devices, that demand image, video and display capabilities.
By Caroline Hayes, Senior Editor

The license includes the ARM® Cortex®-A7 processor, ARM Mali™-V500 video accelerator, Mali-DP500 display processor and ARM TrustZone® technology.
The small area, ARM Mali GPU video and display processor will enable any screen-based device to offer a smooth 3D user interface, video capture and playback functionality, at HD resolution as well as secure features to protect data and content in smartphone, tablets and new devices, such as wearables, and factory automation.
The energy efficiency and small die area of the ARM Mali-V500 and Mali-DP500 enables full HD 1080p60 resolution capabilities on a single core, reducing the cost for price-sensitive consumer applications. They also both incorporate ARM TrustZone technology for hardware-backed content security from download to display, which is becoming more important as more mobile devices are used for such content downloads.
I asked Jacko Wilbrink, senior product marketing director, Atmel what the license means for both parties:

CH: What existing strengthens will Atmel bring in using the Mali IP?
JW: Low power will remain an important differentiator for Atmel MPUs including those embedding Mali IPs going forward. The Mali IPs will bring smartphone and tablet experience and applications to many products including power sensitive user interface centric wearable and battery operated products.

CH: What markets will the licensed IP address (e.g. wearables, etc.)
JW: With the cost of TFT displays coming down and the demand from consumers to improve the user interface/user experience of a fast growing range of products beyond smartphones and tablets, there is a growing need for MPUs with graphical processing and video capabilities. Industrial graded products with long life support, professional documentation and support are important benefits Atmel offers over alternative multi-core ASSPs designed for smartphones and tablets.

CH: What architectural features of Mali will be used in these areas?
JW: The licensed IPs allow Atmel to scale up their MPUs in performance and functionality including 3D graphics, HD video decoding and encoding and efficient memory bandwidth usage. The multi-core Cortex-A cores offer the ability to optimize the price performance point while maximizing software reuse across an Atmel MPU platform.

CH: What benefits of the Mali architecture will be exploited initially and how?
JW: Full compliance with video and graphics standards is critical for our customers. Power efficiency, Android support and efficient memory usage and bus bandwidth optimization are important benefits offered by the Mali IPs.

CH: When will the first Mali-based devices be rolled out?
JW: The first design is planned to sample to early customers by the end of 2015.