Business technology major Microsoft has selected Intel Stratix 10 FPGAs as a hardware accelerator in its deep learning platform – code-named Project Brainwave.
This FPGA-based deep learning platform is capable of delivering real-time AI, which will allow cloud infrastructure to process and transmit data as fast as it comes in, with ultralow latency. In the cloud, delivering real-time AI is becoming more important as systems are required to process live data streams, including video, sensors or search queries, and rapidly deliver the data back to users.
Microsoft said Project Brainwave will be leveraging Intel FPGAs because it’s capable of handling challenging deep learning models with performance and flexibility. Microsoft demonstrated its FPGA-based deep learning platform at Hot Chips 2017, a symposium that showcases the latest advancements in semiconductor technology.
Intel Stratix 10 FPGAs enable the acceleration of deep neural networks (DNNs) that replicate “thinking” in a manner that is conceptually similar to that of the human brain.
Compared to dedicated deep learning hardware accelerators that are optimized to run a single workload, the flexibility of Intel FPGAs enable users to customize the hardware to meet specific workload requirements, and reconfigure the hardware rapidly as deep learning workloads and use models change.
Project Brainwave demonstrated over 39 Teraflops of achieved performance on a single request, setting a new standard in the cloud for real-time AI computation. Stratix 10 FPGAs sets a new level of cloud performance for real-time AI computation, with record low latency, record performance and batch-free execution of AI requests.
“We exploit the flexibility of Intel FPGAs to incorporate new innovations rapidly, while offering performance comparable to, or greater than, many ASIC-based deep learning processing units,” said Doug Burger, distinguished engineer at Microsoft Research NExT.
Microsoft is working to deploy Project Brainwave in the Azure cloud so that customers eventually can run complex deep learning models at record-setting performance.