The deep learning company, Deci, has announced a broad strategic business and technology collaboration with Intel to optimise deep learning inference on Intel Architecture (IA) CPUs.
Deci and Intel Collaborate to Optimize Deep Learning Inference on Intel’s CPUs.
Deci’s collaboration with Intel marks a significant step towards enabling new applications of deep learning inference on Intel Architecture (IA) CPUs.
Tel Aviv, Israel, March 11, 2021 – Deci, the deep learning company building the next generation of AI, announced today a broad strategic business and technology collaboration with Intel Corporation to optimize deep learning inference on Intel Architecture (IA) CPUs. As one of the first companies to participate in Intel Ignite startup accelerator, Deci will now work with Intel to deploy innovative AI technologies to mutual customers.
The collaboration between Deci and Intel takes a significant step towards enabling deep learning inference at scale on Intel CPUs, reducing costs and latency, and enabling new applications of deep learning inference. New deep learning tasks can be performed in a real-time environment on edge devices and companies that
Share this article
Share this article
TEL AVIV, Israel, March 11, 2021 /PRNewswire/ Deci, the deep learning company building the next generation of AI, announced today a broad strategic business and technology collaboration with Intel Corporation to optimize deep learning inference on Intel Architecture (IA) CPUs. As one of the first companies to participate in Intel Ignite startup accelerator, Deci will now work with Intel to deploy innovative AI technologies to mutual customers.
The collaboration between Deci and Intel takes a significant step towards enabling deep learning inference at scale on Intel CPUs, reducing costs and latency, and enabling new applications of deep learning inference. New deep learning tasks can be performed in a real-time environment on edge devices and companies that use large scale inference scenarios can dramatically cut cloud or datacenter cost, simply by changing the inference hardware from GPU to Intel CPU.
Intel Sapphire Rapids Enterprise CPUs Confirmed With On-Package HBM Memory Support
The end of the year is typically thin on interesting news in the technology sector, as companies opt to wait for the Consumer Electronics Show (CES) in January to make any major announcements or product unveils. There are exceptions, however. Just before we ring in another year, Intel has posted an interesting document that essentially confirms its upcoming Xeon Scalable processors based on Sapphire Rapids will support on-package high bandwidth memory (HBM).
While previously rumored, this is a feature Intel has not explicit stated up to this point. During its Architecture Day 2020 event this past summer, Intel talked a little about Sapphire Rapids (among other things), noting it is based on an 10-nanometer enhanced SuperFin technology, which should yield better performance and power characteristics.