Compute Express Link (CXL) 2.0 Controller with AMBA AXI interface
Microsoft Outlines Hardware Architecture for Deep Learning on Intel FPGAs
May 12, 2017 -- At Build, Microsoft’s annual developers conference, taking place this week, Microsoft Azure CTO Mark Russinovich disclosed major advances in Microsoft’s hyperscale deployment of Intel® field programmable gate arrays (FPGAs). These advances have resulted in the industry’s fastest public cloud network, and new technology for acceleration of Deep Neural Networks (DNNs) that replicate “thinking” in a manner that’s conceptually similar to that of the human brain.
The advances offer performance, flexibility and scale, using super low latency networking to leverage the world’s largest cloud investment in FPGAs. The increases in networking speed achieved by this low latency networking will help business, government, healthcare, and universities better process Big Data workloads. Azure’s FPGA-based Accelerated Networking reduces inter-virtual machine latency by up to 10x while freeing the Intel® Xeon® processors for other tasks.
Russinovich also outlined a new cloud acceleration framework that Microsoft calls Hardware Microservices. The infrastructure used to deliver this acceleration is built on Intel® FPGAs. This new technology will enable accelerated computing services, such as Deep Neural Networks, to run in the cloud without any software required, resulting in large advances in speed and efficiency.
“From our early work accelerating Bing search using FPGAs added to the Intel Xeon processor-based servers, to this new Hardware Microservices model that underlies the Deep Neural Networks (DNNs) infrastructure that Mark discussed yesterday afternoon, Microsoft is continuing to invest in novel hardware acceleration infrastructure using Intel® FPGAs,” said Doug Burger, one of Microsoft’s Distinguished Engineers.
“Application and server acceleration requires more processing power today to handle large and diverse workloads, as well as a careful blending of low power and high performance—or performance per Watt, which FPGAs are known for,” said Dan McNamara, corporate vice president and general manager, Programmable Solutions Group, Intel. “Whether used to solve an important business problem, or decode a genomics sequence to help cure a disease, this kind of computing in the cloud, enabled by Microsoft with help from Intel FPGAs, provides a large benefit.”
See Microsoft Azure CTO Mark Russinovich’s presentation.
Learn more about Intel’s FPGAs for computing and storage.
|
Intel FPGA Hot IP
Related News
- ZTE Wireless Institute Achieves Performance Breakthrough for Deep Learning with Intel FPGAs
- Intel Delivers Real Time AI in Microsoft's New Accelerated Deep Learning Platform
- Nextera-Adeas ST 2110 IP cores are now available on Intel FPGAs
- Intel Launches Agilex 7 FPGAs with R-Tile, First FPGA with PCIe 5.0 and CXL Capabilities
- Intrinsic ID Announces Embedded SRAM PUF Security IP for Military-Grade IP protection in Intel FPGAs
Breaking News
- Credo at TSMC 2024 North America Technology Symposium
- Cadence Reports First Quarter 2024 Financial Results
- Rambus Advances AI 2.0 with GDDR7 Memory Controller IP
- Faraday Reports First Quarter 2024 Results
- RAAAM Memory Technologies Closes $4M Seed Round to Commercialize Super Cost Effective On-Chip Memory Solutions
Most Popular
- GUC provides 3DIC ASIC total service package to AI/HPC/Networking customers
- Omni Design Technologies Joins Intel Foundry Accelerator IP Alliance
- Faraday Partners with Arm to Innovate AI-driven Vehicle ASICs
- Semiconductor Capacity Is Up, But Mind the Talent Gap
- Efabless Announces the Release of the OpenLane 2 Development Platform, Transforming Custom Silicon Design Flows
E-mail This Article | Printer-Friendly Page |