On October 06 2023, Science published All for one, one for all: Bringing heterogeneous computing power to more people and posted on its official website, introducing Zhejiang Lab's research achievements in the field of heterogeneous computing.

As Moore's law approaches 60 years old, computer science struggles to keep up with doubling the number of transistors in integrated circuits every 2 years. Now, heterogeneous computing promises a new solution to the need for speed. Instead of gaining performance by packing more elements into computing processors, heterogenous computing creates faster and more efficient processing by combining the powers of different types of computing units: central processing units (CPUs), graphic processing units (GPUs), field programmable gate arrays (FPGAs), AI accelerators, and more.

Please click here to read more.