Use Inference Benchmarks Similar To Your Application


If an Inference IP supplier or Inference Accelerator Chip supplier offers a benchmark, it is probably ResNet-50. As a result, it might seem logical to use ResNet-50 to compare inference offerings. If you plan to use ResNet-50 it would be; but if your target application model is significantly different from Resnet-50 it could lead you to pick an inference offering that is not best for you. ... » read more

Achieving Flexible Processing Requirements For IoT End-Node Devices


The term Internet of Things (IoT), which used to be used broadly to describe almost all connected devices, can now be seen to fall into two segments: Critical IoT and Massive IoT. Critical IoT refers to mission-critical applications such as automotive communication, industrial machines, and medical procedures where low latency is crucial, while Massive IoT is related to the billions of connecte... » read more

Designing Networking Chips


Susheel Tadikonda, vice president of networking and storage at Synopsys, talks about what’s changed in the way networking chips are being designed to deal with a massive increase in data. One of those shifts involves software-defined networking, where the greatest complexity resides in the software. That also has a big impact on the entire design flow, from pre-silicon to post-silicon. htt... » read more

Issues In Designing 5G Beamforming Antennas


As 5G networking inches closer to reality, one of the more stubborn problems also will be one of the smallest. Several issues have yet to be cracked with beamforming and massive MIMO antennas, which will make millimeter wave (mmWave) spectrum—a key ingredient in 5G networks—work on multiple devices and base-station locations. Millimeter wave is problematic yet promising. Between bands 30... » read more

Benchmarks For The Edge


Geoff Tate, CEO of Flex Logix, talks about benchmarking in edge devices, particularly for convolutional neural networks. https://youtu.be/-beVEpKAM4M » read more

Automotive IC Design Demands Next-Generation High-Sigma Verification


By Jeff Dyck High-sigma analysis is required for verifying replicated components, like memory blocks and standard cells, and for demonstrating mission-critical reliability for automotive and medical applications. It is not feasible to verify to high-sigma using brute-force Monte Carlo, as this requires 10s of millions of simulations to reach 5-sigma and billions in order to reach 6-sigma. S... » read more

The Race To Multi-Domain SoCs


K. Charles Janac, president and CEO of Arteris IP, sat down with Semiconductor Engineering to discuss the impact of automotive and AI on chip design. What follows are excerpts of that conversation. SE: What do you see as the biggest changes over the next 12 to 24 months? Janac: There are segments of the semiconductor market that are shrinking, such as DTV and simple IoT. Others are going ... » read more

Autonomous Drive Requires Smart Sensor Systems


While exotic technology for autonomous drive cars draw wonder all around the world, individual smart sensor systems with “simple” jobs to do are equally important. LiDAR sensors with specialized AI chips for object identification are fascinating. But “simple” smart sensor systems, like passenger airbag deployment systems, are also key to autonomous drive vehicles. A typical trait of a s... » read more

Mine Cryptocurrencies Sooner, Faster, and Cheaper with Achronix Speedcore Embedded FPGAs


New cryptocurrencies such as Monero introduce ASIC-resistance and memory-hardness to prevent ASICs from being built that give some operators a competitive mining advantage over others who do not have access to the same technology. This white paper discusses the relevant background and presents a solution based on Achronix Speedcore embedded FPGAs (eFPGAs), enabling users to regain a highly prof... » read more

Open Source in M&A Due Diligence


Most companies involved with technology M&A understand the danger of open source risks in software. Today’s software contains significant amounts of open source—on average more than 50%, according to a 2018 Synopsys report. There are several ways to assess and manage open source risk in a transaction, with some more effective than others. Similarly, there are several approaches to open s... » read more

← Older posts Newer posts →