I hope you have your seatbelt low and tight across your waist my friends, because we are flying high into cloud-based design in this week’s episode of Fish Fry! With templates, code, tools, fabs and processes in the cloud cargo hold, Naveed Sherwani (CEO – SiFive), Yunsup Lee (CTO/Founder – SiFive), and I are headed straight into the next generation of silicon design. Also this week, … Read More → "Moore’s Law Only Ends Once"
A big chunk of the vast, imagined IoT (Internet of Things) includes the industrial IoT (IIoT), which is responsible for controlling and monitoring energy-consuming processes based on large motors, pumps, fans, generators, heavy-duty actuators, heaters, and other high-power equipment. Such IIoT applications aren’t as concerned with low-power design compared to the medical and consumer side of the IoT—wearables and the like. Medical and consumer … Read More → "0.6V, and Still the Memory Persisted"
Aaaaand… it’s memory time again. I don’t keep up with every release of memory (who could keep up with that without dedicating their lives to nothing but that?), but here and there we have either technology or application angles to new-memory stories. So, in that vein, we address memory in automotive and AI. Yes, two critical keywords in any tech article these days.Read More → "High Bandwidth, Modest Capacity"
They say that on a clear day you can see forever. When you look into the clouds, do you see System Verilog? In this week’s episode of Fish Fry, you will! Doug Letcher (CEO and President – Metrics Technologies) joins us to chat about details of the Metrics cloud platform, verification 3.0 and why EDA cannot ignore the Cloud any longer. Also this week, we check out a new robotic … Read More → "Infinitely Parallel"
Convolutional Neural Networks (CNNs) have been dominating the discussion on AI advancement for the past couple of years. But CNNs have one glaring weakness – a heavy reliance on massive amounts of multiplication. This huge arithmetic obstacle has led to a plethora of initiatives to accelerate both the training and inference phases of deep learning with CNNs, and a wide variety of hardware and software architectures designed … Read More → "Brainchip Debuts Neuromorphic Chip"
There’s nothing new about the need to cool silicon. It’s just that it used to be easy. Relatively.
To be fair, for your average, run-of-the-mill chip, you can still put it in a package with decent thermal resistance and run air over it if you must. Although more and more gadgets are resisting air cooling because fans are … Read More → "Spray-On Cooling"
