tag: AI

Securing Accelerator Blades For Datacenter AI/ML Workloads
By Emma-Jane Crozier - 25 Oct, 2022 - Comments: 0

Data centers handle huge amounts of AI/ML training and inference workloads for their individual customers. Such a vast number of workloads calls for efficient processing, and to handle these workloads we have seen many new solutions emerge in the market. One of these solutions is pluggable accelerator blades, often deployed in massively parallel arrays, that implement the latest state-of-the-ar... » read more

Week In Review: Design, Low Power
By Marie C. Baca - 21 Oct, 2022 - Comments: 0

Tools and IP Electronic system design revenue hit a record $3.75 billion in the second quarter, according to a report from ESD Alliance, a SEMI Technology Community. That number represents a 17.5% year-over-year increase. Walden C. Rhines, the report’s executive sponsor, said it was the largest such jump in over a decade and that all product categories and geographic regions recorded second ... » read more

Research Bits: Oct. 18
By Jesse Allen - 18 Oct, 2022 - Comments: 0

Modular AI chip Engineers at the Massachusetts Institute of Technology (MIT), Harvard University, Stanford University, Lawrence Berkeley National Laboratory, Korea Institute of Science and Technology, and Tsinghua University created a modular approach to building stackable, reconfigurable AI chips. The design comprises alternating layers of sensing and processing elements, along with LEDs t... » read more

HBM3 In The Data Center
By Ed Sperling - 17 Oct, 2022 - Comments: 0

Frank Ferro, senior director of product management at Rambus, talks about the forthcoming HBM3 standard, why this is so essential for AI chips and where the bottlenecks are today, what kinds of challenges are involved in working with this memory, and what impact chiplets and near-memory compute will have on HBM and bandwidth.     » read more

Complex Tradeoffs In Inferencing Chips
By John Koon - 17 Oct, 2022 - Comments: 0

Designing AI/ML inferencing chips is emerging as a huge challenge due to the variety of applications and the highly specific power and performance needs for each of them. Put simply, one size does not fit all, and not all applications can afford a custom design. For example, in retail store tracking, it's acceptable to have a 5% or 10% margin of error for customers passing by a certain aisle... » read more

Designing A Better Clock Network
By Ann Mutschler - 13 Oct, 2022 - Comments: 0

Laying the proper clock network architecture foundation makes all the difference for the best performance, power, and timing of a chip, particularly in advanced node SoCs packed with billions of transistors. Each transistor, which acts like a standard cell, needs a clock. An efficient clock network should ensure the switching transistors save power. In today’s advanced nodes, when a design... » read more

Beyond Autonomous Cars
By Marie C. Baca - 12 Oct, 2022 - Comments: 0

As the automotive industry takes a more measured approach to self-driving cars and long-haul trucks for safety and security reasons, there is a renewed focus on other types of vehicles utilizing autonomous technology. The list is long and growing. It now includes autonomous trains, helicopters, tractors, ships, submarines, drones, delivery robots, motorcycles, scooters, and bikes, all of whi... » read more

Training a ML model On An Intelligent Edge Device Using Less Than 256KB Memory
By Technical Paper Link - 11 Oct, 2022 - Comments: 0

A new technical paper titled "On-Device Training Under 256KB Memory" was published by researchers at MIT and MIT-IBM Watson AI Lab. “Our study enables IoT devices to not only perform inference but also continuously update the AI models to newly collected data, paving the way for lifelong on-device learning. The low resource utilization makes deep learning more accessible and can have a bro... » read more

More Efficient Matrix-Multiplication Algorithms with Reinforcement Learning (DeepMind)
By Technical Paper Link - 11 Oct, 2022 - Comments: 0

A new research paper titled "Discovering faster matrix multiplication algorithms with reinforcement learning" was published by researchers at DeepMind. "Here we report a deep reinforcement learning approach based on AlphaZero for discovering efficient and provably correct algorithms for the multiplication of arbitrary matrices," states the paper. Find the technical paper link here. Publis... » read more

Simplifying AI Edge Deployment
By Ed Sperling - 10 Oct, 2022 - Comments: 0

Barrie Mullins, vice president of product at Flex Logix, explains how a programmable accelerator chip can simplify semiconductor design at the edge, where chips need to be high performance as well as low power, yet developing everything from scratch is too expensive and time-consuming. Programmability allows these systems to stay current with changes in algorithms, which can affect everything f... » read more

← Older posts Newer posts →

  • Sponsors

About

Navigation

Connect With Us

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