Week In Review: Design, Low Power


Processors Arm rolled out a micro neural processing unit that, when combined with its newest microcontroller, can increase machine learning performance by up to 480 times. The company is aiming the MCU and co-processor across a wide swath of applications. Worth noting is that Arm calls its Cortex-M55 an AI-capable processor, rather than a microcontroller, as the lines between the various proce... » read more

Week In Review: Auto, Security, Pervasive Computing


AI/Edge Arm putting AI (artificial intelligence) and machine learning (ML) on the Cortex-M processor by offering IP for a microNPU for Cortex-M. The company says in a press release that it will deliver a 480x uplift in ML performance. The new Cortex-M IP is Arm Ethos-U55 NPU, which Arm says is the industry’s first microNPU (neural processing unit). Arm is hoping the new IP will start an expl... » read more

Where Is The Edge AI Market And Ecosystem Headed?


Until recently, most AI was in datacenters and most was training. Things are changing quickly. Projections are AI sales will grow rapidly to $10s of billions by the mid 2020s, with most of the growth in Edge AI Inference. Edge inference applications Where is the Edge Inference market today? Let’s look at the markets from highest throughput to lowest. Edge Servers Recently Nvidia annou... » read more

Will In-Memory Processing Work?


The cost associated with moving data in and out of memory is becoming prohibitive, both in terms of performance and power, and it is being made worse by the data locality in algorithms, which limits the effectiveness of cache. The result is the first serious assault on the von Neumann architecture, which for a computer was simple, scalable and modular. It separated the notion of a computatio... » read more

June’19 Startup Funding


During the month of June, there were 15 startups that brought in funding rounds of $100 million or more, as investors continued to chase deals in cybersecurity, automotive technology, semiconductors, and a variety of services. There were no billion-dollar deals as spring slid into summer; yet, those 15 companies together raised a total of about $3.13 billion. Aurora Innovation, the developer... » read more

Week In Review: Manufacturing, Test


Market research In the second quarter of 2019, TrendForce said that the top-5 foundry rankings remained identical with that of last year. But sixth to tenth place showed some changes. Who is up or down in what is a tough business climate? Global fab equipment spending will rebound in 2020, growing 20% to $58.4 billion after dropping 19% to $48.4 billion in 2019, according to SEMI. However, ... » read more

Week In Review: Design, Low Power


M&A Intel will acquire Barefoot Networks, a maker of programmable Ethernet switch silicon and the P4 networking programming language for data centers. Founded in 2013, the Santa Clara-based company has raised $155.4 million in funding. Terms of the deal were not disclosed, but Intel expects the acquisition to be final in the third quarter of this year. Tools & IP Mentor extended it... » read more

Accelerating Endpoint Inferencing


Chipmakers are getting ready to debut inference chips for endpoint devices, even though the rest of the machine-learning ecosystem has yet to be established. Whatever infrastructure does exist today is mostly in the cloud, on edge-computing gateways, or in company-specific data centers, which most companies continue to use. For example, Tesla has its own data center. So do most major carmake... » read more

Engineering Talent Shortage Now Top Risk Factor


Demand is increasing for engineers and related technical fields in the IC industry, but companies are struggling to find enough talent. The problem is even worse in hot new markets such as AI and 5G, where competition is fierce for experienced workers. The talent shortfall starts with college graduates and professionals in the fields of science, technology, engineering and mathematics (STEM)... » read more

In-Memory Vs. Near-Memory Computing


New memory-centric chip technologies are emerging that promise to solve the bandwidth bottleneck issues in today’s systems. The idea behind these technologies is to bring the memory closer to the processing tasks to speed up the system. This concept isn’t new and the previous versions of the technology fell short. Moreover, it’s unclear if the new approaches will live up to their billi... » read more

← Older posts