Inference Moves To The Network


Machine-learning inference started out as a data-center activity, but tremendous effort is being put into inference at the edge. At this point, the “edge” is not a well-defined concept, and future inference capabilities will reside not only at the extremes of the data center and a data-gathering device, but at multiple points in between. “Inference isn't a function that has to resid... » read more

Vehicle Communications Network Is Due For Overhaul


The Controller Area Network (CAN), one of the main communications networks in an automobile, is headed for a security overhaul — if not a wholesale replacement. Initially devised in the 1980s to allow electronic components in a vehicle to communicate directly without a central computer in between, the CAN bus has become a growing security risk as more functions are automated and integrated... » read more

Optimizing Embedded Narrowband IoT Modem Solutions To Meet IoT Connectivity Challenges


As the concept of the internet-of-things (IoT) was taking shape, the communications industry started addressing the anticipated need to connect these “billions of IoT devices” (Figure 1). Since these devices are meant to address low-cost, low-power (battery operated) applications, cellular technology trends to increase bandwidth – driven largely by mobile phones – needed to be revisite... » read more

Blog Review: May 6


In a blog for Arm, Javier Fernandez-Marques of Oxford University digs into how to make the best use of quantized neural network models and why it's so important to consider what algorithms will be running when deciding which model architecture to implement, and which quantization strategy to adopt for the model. Synopsys' Taylor Armerding explains why, with a largely remote workforce, it may... » read more

A New Co-Simulation Approach for Tolerance Analysis on Vehicle Propulsion Subsystem


An increasing demand for reducing cost and time effort of the design process via improved CAE (ComputerAided Engineer) tools and methods has characterized the automotive industry over the past two decades. One of the main challenges involves the effective simulation of a vehicle’s propulsion system dealing with different physical domains: several examples have been proposed in the literature ... » read more

Key Drivers In New Chip Industry Outlook


How well the semiconductor industry fares over the next 12 to 24 months depends upon the evolution of a virus. That alone will determine the correct model for an economic rebound — V, U, extended U, or maybe even a double U. But what's also becoming clear is those models don't apply uniformly to all sectors or sub-sectors of the semiconductor industry. Looked at as a whole, the entire indu... » read more

Week In Review: Auto, Security, Pervasive Computing


Data center, 5G security Nvidia won approval for its Mellanox Technologies Ltd. deal from China, according to an article on Bloomberg. Mellanox chips split up and manage AI datasets for parallel processing, which can be used in data centers for computing. Rambus has released security for 800 Gigbit Ethernet MAC (media access control) for enhanced data center and 5G infrastructure. It secure... » read more

Week In Review: Design, Low Power


Nvidia completed its $7 billion acquisition of Mellanox. The acquisition, initially announced over a year ago, brings Mellanox’s high-performance networking and interconnect technology to Nvidia's server efforts and gives the company full end-to-end offerings in the data center space. To date, this is the largest acquisition in Nvidia's history. Tools & IP Synopsys debuted its 3DIC Co... » read more

Inevitable Bugs


Are bug escapes inevitable? That was the fundamental question that Oski Technology recently put to a group of industry experts. The participants are primarily simulation experts who, in many cases, help direct the verification directions for some of the largest systems companies. In order to promote free discussion, all comments have been anonymized, distilling the primary thoughts of the parti... » read more

Blog Review: April 29


Arm's Paul Whatmough checks out SCALE-Sim, an open source cycle-accurate simulator specifically for neural processing unit (NPU) architectures. Mentor's Neil Johnson shows how a complete verification methodology requires complementary deployment of multiple techniques, with different options at each level of abstraction. Cadence's Paul McLellan checks out challenges in automotive reliabil... » read more

← Older posts Newer posts →