Going On the Edge


Emmanuel Sabonnadière, chief executive of Leti, sat down with Semiconductor Engineering to talk about artificial intelligence (AI), edge computing and chip technologies. What follows are excerpts of that conversation. SE: Where is AI going in the future? Sabonnadière: I am a strong believer that edge AI will change our lives. Today’s microelectronics are organized with 80% of things i... » read more

Checkmate: Breaking The Memory Wall With Optimal Tensor Rematerialization


Source: Published on arXiv 10/7/ 2019   Paras Jain Ajay Jain Aniruddha Nrusimha Amir Gholami Pieter Abbeel Kurt Keutzer Ion Stoica Joseph E. Gonzalez A recent paper published on arXiv by a team of UC Berkeley researchers notes that neural networks are increasingly impeded by the limited capacity of on-device GPU memory. The UC Berkeley team uses off-the-shel... » read more

Using FPGAs For AI


Artificial intelligence (AI) and machine learning (ML) are progressing at a rate that is outstripping Moore's Law. In fact, they now are evolving faster than silicon can be designed. The industry is looking at all possibilities to provide devices that have the necessary accuracy and performance, as well as a power budget that can be sustained. FPGAs are promising, but they also have some sig... » read more

Using Multiple Inferencing Chips In Neural Networks


Geoff Tate, CEO of Flex Logix, talks about what happens when you add multiple chips in a neural network, what a neural network model looks like, and what happens when it’s designed correctly vs. incorrectly. » read more

New Vision Technologies For Real-World Applications


Computer vision – the ability of a machine to ‘infer’ or extract useful information from a two-dimensional image or an uncompressed video stream of images – has the ability to change our lives. It can enable self-driving cars, empower robots or drones to see their way to delivering packages to your doorstep, and can turn your face into a payment method (Figure 1). To achieve these advan... » read more

Blog Review: Sept. 4


Synopsys' Taylor Armerding checks out Apple's newly expanded bug bounty program, with bounty payouts are increasing to compete with malicious actors, and why even with security-oriented development the practice of bug bounties will remain needed. Mentor's Colin Walls shares a few more embedded software tips, this time on external variables, delay loops in real time systems, and meaningful pa... » read more

Inferencing At The Edge


David Fritz, head of corporate strategic alliances at Mentor, a Siemens Business, shows how to apply YOLO (you only look once) at the edge, allowing automotive companies to move from a GPU to a much more efficient processor. That allows inferencing to move much closer to the sensor, so neural networks can be tailored to the type of data being produced. From there the data can be abstracted and ... » read more

Memory Options And Tradeoffs


Steven Woo, Rambus fellow and distinguished inventor, talks with Semiconductor Engineering about different memory options, why some are better than others for certain tasks, and what the tradeoffs are between the different memory types and architectures.     Related Articles/Videos Memory Tradeoffs Intensify In AI, Automotive Applications Why choosing memories and archi... » read more

Do Large Batches Always Improve Neural Network Throughput?


Common benchmarks like ResNet-50 generally have much higher throughput with large batch sizes than with batch size =1. For example, the Nvidia Tesla T4 has 4x the throughput at batch=32 than when it is processing in batch=1 mode. Of course, larger batch sizes have a tradeoff: latency increases which may be undesirable in real-time applications. Why do larger batches increase throughput... » read more

Holes In AI Security


Mike Borza, principal security technologist in Synopsys’ Solutions Group, explains why security is lacking in AI, why AI is especially susceptible to Trojans, and why small changes in training data can have big impacts on many devices. » read more

← Older posts