Using FPGA's and Xeon processors to accelerate cloud workloads
summary
Intel announces a production-ready combination of FPGAs and Xeon CPUs with two form factors: a socket-integrated FPGA package and PCIe accelerator cards that slot into servers. Targets include image‑recognition inference at cloud scale, claiming up to an order-of-magnitude speedup and better TCO via lower power and latency. Work focuses on FPGA-optimized AI frameworks and integrating failover into VM/container orchestration so accelerators behave like first‑class resources.
AI-written summary · about
related talks
22mLisa Spelman | Google Next 2017
16mKeynote: Designing Processors in the Cloud: How Advanced Emulation and AWS Cloud Infrast...
33mReimagining the Modern Data Center
24mFPGAs in the Datacenter
12mMark Hocking | Google Next 2017
42mHow Intel & AWS solve some of the world’s most urgent issues
25mSustainability at the Core with Cloud Native Processors
01h 13mEngineering the Cloud for Tomorrow: Performance, Speed and Scale for AI Workloads