The Challenge Of Keeping AI Systems Current


Semiconductor Engineering sat down to discuss AI and its move to the edge with Steven Woo, vice president of enterprise solutions technology and distinguished inventor at Rambus; Kris Ardis, executive director at Maxim Integrated; Steve Roddy, vice president of Arm's Products Learning Group; and Vinay Mehta, inference technical marketing manager at Flex Logix. What follows are excerpts of that ... » read more

Performance Metrics For Convolutional Neural Network Accelerators


Across the industry, there are few benchmarks that customers and potential end users can employ to evaluate an inference acceleration solution end-to-end. Early on in this space, the performance of an accelerator was measured as a single number: TOPs. However, the limitations of using a single number has been covered in detail in the past by previous blogs. Nevertheless, if the method of cal... » read more

It’s Eternal Spring For AI


The field of Artificial Intelligence (AI) has had many ups and downs largely due to unrealistic expectations created by everyone involved including researchers, sponsors, developers, and even consumers. The “reemergence” of AI has lot to do with recent developments in supporting technologies and fields such as sensors, computing at macro and micro scales, communication networks and progre... » read more

Open-Source Hardware Momentum Builds


Open-source hardware continues to gain ground, spearheaded by RISC-V — despite the fact that this processor technology is neither free nor simple to use. Nevertheless, the open-source hardware movement has established a solid foothold after multiple prior forays that yielded only limited success, even for processors. With demand for more customized hardware, and a growing field of startups... » read more

Tracking Automotive’s Rapidly Shifting Ecosystem


The automotive ecosystem is becoming much harder to navigate as automakers, Tier 1s and IP vendors redefine their relationships based upon shifting value caused by an rapidly expanding amount of increasingly interdependent and complex electronic content. Predictions of massive change started almost a decade ago with a number of pilot programs around autonomous vehicles. But those shifts real... » read more

Optimizing Power And Performance For Machine Learning At The Edge


While machine learning (ML) algorithms are popular for running on enterprise Cloud systems for training neural networks, AI/ML chipsets for edge devices are growing at a triple digit rate, according to Tractica “Deep Learning Chipsets” (Figure 1). Edge devices include automobiles, drones, and mobile devices that are all employing AI/ML to provide valuable functionality. Figure 1: Marke... » read more

Implementing Low-Power Machine Learning In Smart IoT Applications


By Pieter van der Wolf and Dmitry Zakharov Increasingly, machine learning (ML) is being used to build devices with advanced functionalities. These devices apply machine learning technology that has been trained to recognize certain complex patterns from data captured by one or more sensors, such as voice commands captured by a microphone, and then performs an appropriate action. For example,... » read more

AI Inference Memory System Tradeoffs


When companies describe their AI inference chip they typically give TOPS but don’t talk about their memory system, which is equally important. What is TOPS? It means Trillions or Tera Operations per Second. It is primarily a measure of the maximum achievable throughput but not a measure of actual throughput. Most operations are MACs (multiply/accumulates), so TOPS = (number of MAC units) x... » read more

Building An Efficient Inferencing Engine In A Car


David Fritz, who heads corporate strategic alliances at Mentor, a Siemens Business, talks about how to speed up inferencing by taking the input from sensors and quickly classifying the output, but also doing that with low power. » read more

Power/Performance Bits: April 16


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

← Older posts