tag: AI

Automotive, AI Drive Big Changes In Test
By Ann Mutschler - 25 Apr, 2019 - Comments: 0

Design for test is becoming enormously more challenging at advanced nodes and in increasingly heterogeneous designs, where there may be dozens of different processing elements and memories. Historically, test was considered a necessary but rather mundane task. Much has changed over the past year or so. As systemic complexity rises, and as the role of ICs in safety-critical markets continues ... » read more

Verification At 7/5nm
By Ed Sperling - 25 Apr, 2019 - Comments: 0

Christen Decoin, senior director of business development at Synopsys, talks about what’s missing in verification, how is that affected by complex chips such as 7nm SoCs or AI chips, and why more steps need to be done concurrently. https://youtu.be/bz6KyJh67sI » read more

Redefining Expectations for Test
By Synopsys - 24 Apr, 2019 - Comments: 0

New and rapidly expanding applications, such as artificial intelligence and automotive, are increasing in design size and complexity. These evolving market segments require unprecedented levels of quality and long-term reliability, which has created a fundamental shift in both the importance and need for integration of advanced semiconductor test. Synopsys unveiled a new family of test products... » read more

Safety-Critical Coverage
By Ed Sperling - 24 Apr, 2019 - Comments: 0

Dave Landoll, solutions architect at OneSpin Solutions, discusses verification in safety-critical designs, why it’s more of a challenge in automotive than in avionics, and why verification of these systems includes what the system should not be doing as well as what it should be doing. https://youtu.be/Ze3WwEARfx0 » read more

System Bits: April 23
By Jeff Dorsch - 23 Apr, 2019 - Comments: 0

AI tool can clean up dirty data Researchers at the University of Waterloo, collaborating with colleagues at the University of Wisconsin and Stanford University, came up with HoloClean, an artificial intelligence tool to comb through dirty data and to detect information errors. “More and more machines are making decisions for us, so all our lives are touched by dirty data daily,” said Ih... » read more

Week in Review: IoT, Security, Auto
By Jeff Dorsch - 19 Apr, 2019 - Comments: 0

Internet of Things Combining artificial intelligence with unmanned aerial vehicles could provide a quicker and safer alternative to inspecting roadways for cracks, potholes, and other damage, according to a paper posted on arvix.org. “[M]anual visual inspection [is] not only tedious, time-consuming, and costly, but also dangerous for the personnel. Furthermore, the detection results are alwa... » read more

The Precision Knob
By Ed Sperling - 18 Apr, 2019 - Comments: 0

Precision used to be a goal, but increasingly it is being used as a tool. This is true for processing and algorithms, where less precision can greatly improve both performance and battery life. And it is true in manufacturing, where more precision can help minimize the growing impact of variation. Moreover, being able to dial precision up or down can help engineers see the impact on a system... » read more

Blog Review: April 17
By Jesse Allen - 17 Apr, 2019 - Comments: 0

In a video, Mentor's Colin Walls digs into power management in embedded software with a particular look at the Power Pyramid model. Synopsys' Taylor Armerding checks out the state of application security at this year's RSA and finds that while organizations are paying attention to security through training and dedicated teams, roadblocks still remain. Cadence's Paul McLellan considers how... » read more

Power/Performance Bits: April 16
By Jesse Allen - 16 Apr, 2019 - Comments: 0

Faster CNN training Researchers at North Carolina State University developed a technique that reduces training time for deep learning networks by more than 60% without sacrificing accuracy. Convolutional neural networks (CNN) divide images into blocks, which are then run through a series of computational filters. In training, this needs to be repeated for the thousands to millions of images... » read more

Multi-Layer Processing Boosts Inference Throughput/Watt
By Geoff Tate - 15 Apr, 2019 - Comments: 0

The focus in discussion of inference throughput is often on the computations required. For example, YOLOv3, a power real time object detection and recognition model, requires 227 BILLION MACs (multiply-accumulates) to process a single 2 Mega Pixel image! This is with the Winograd Transformation; it’s more than 300 Billion without it. And there is a lot of discussion of the large size ... » read more

← Older posts Newer posts →

  • Sponsors

About

Navigation

Connect With Us

Copyright ©2013-2025 SMG   |  Terms of Service  |  Privacy Policy