Microsoft Details Hardware Architecture for Deep Learning

Microsoft is offering a new cloud acceleration framework that it calls Hardware Microservices. The infrastructure used to deliver this acceleration is built on Intel field programmable gate arrays (FPGAs). This new technology is designed to enable accelerated computing services, such as deep neural networks, to run in the cloud without any software required, to enhance speed and efficiency.

Intel FPGAs can be used to accelerate the performance of large-scale data systems, according to Intel. Intel FPGAs are designed to enable higher speed data processing by providing customized high-bandwidth, low-latency connections to network and storage systems. In addition, Intel FPGAs provide compression, data filtering, and algorithmic acceleration, according to the company.

For more information, visit Microsoft and Intel.

Sources: Press materials received from the company.