Stefan Mileschin

Cost a billion to make

Xilinx has revealed its adaptive computer acceleration platform (ACAP), which is a new kind of programmable chip for flexible hardware.

The company spent more than $1 billion to develop the new chip which it claims is as significant as the invention of FPGAs in the 1980s. The outfit believes it can broaden the use of programmable chips across a broad set of applications for the era of big data and artificial intelligence. For deep neural network processing, it could achieve a 20-fold increase in performance.

The ACAP is a dubbed multi-core heterogeneous compute platform which is changed at the hardware level to adapt to the needs of a wide range of applications and workloads. An ACAP can adapt dynamically during operations, and that can make it more efficient in performance and performance-per-watt than central processing units (CPUs) or graphics processing units (GPUs).

Victor Peng, CEO of Xilinx said the ACAP will have 50 billion transistors and will be a significant technology disruption for the industry.

“This revolutionary new architecture is part of a broader strategy that moves the company beyond FPGAs and supporting only hardware developers. The adoption of ACAP products in the data centre, as well as in our broad markets, will accelerate the pervasive use of adaptive computing, making the intelligent, connected, and the adaptable world a reality sooner.”

The ACAP can be used in applications such as video transcoding, database, data compression, search, AI inference, genomics, machine vision, computational storage and network acceleration. Software and hardware developers will be able to design ACAP-based products for the end point, edge and cloud applications.

Talking to Venture Beat, Peng said that it can do very intricate system designs and still have that flexibility in programming.

https://fudzilla.com/news/processors...grammable-chip