Archive of posts tagged: Accelerators
Accelerator-Level Parallelism (ALP)
The demand for computing performance continues to grow exponentially in part due to video and machine learning processing for applications like augmented/virtual reality and self-driving vehicles. However, the underlying advances (Moore’s Law and Dennard...
The First Trillion-Transistor Chip: A New Design Space
There was stunning news at the HotChips-31 conference held at Stanford Memorial Auditorium last week. Cerebras, a startup company working on machine learning accelerators in stealth mode, finally came out and presented a groundbreaking accelerator chip packed with 1.2...
Deep Neural Network Acceleration Beyond Chips
This week Cerebras announced a bold design to accelerate deep neural networks with silicon that is not cut into chips. AI and Moore’s Law: Artificial Intelligence (AI) is much in the news for what it can do today and the promise of what it can do tomorrow (CCC/AAAI...
Academics Should Build Their Own Computers to Advance Systems Research
This is a time of great interest in new hardware. Computers are becoming much more complex. The multicore era has given way to increasingly heterogeneous computing platforms. Modern SoCs contain a tremendous variety of processors, accelerators, and peripheral devices,...Subscribe
