Intel has unveiled the 3rd generation of its Xeon Scalable processors which will enable customers to accelerate the development and use of AI and analytics workloads.
The chip giant's new Xeon CPU is the first mainstream server processor with built-in bfloat16 support and this makes AI inference and training more widely deployable on general-purpose CPUs for applications that include image classification, recommendation engines, speech recognition and language modeling.
Vice president and general manager of the Xeon and Memory Group at Intel, Lisa Spelman explained in a press release how the company's 3rd gen Xeon CPUs will enable businesses to rapidly deploy AI and data analytics, saying:
- Intel Lakefield is here, powering the future of computing
- Intel reveals first AI chips
- Microsoft and Intel are turning malware into images
“The ability to rapidly deploy AI and data analytics is essential for today’s businesses. We remain committed to enhancing built-in AI acceleration and software optimizations within the processor that powers the world’s data center and edge solutions, as well as delivering an unmatched silicon foundation to unleash insight from data.”
Cooper Lake processors
With the new 3rd Gen Intel Xeon Scalable processors, Intel is boosting built-in AI acceleration through the integration of bfloat16 support into the processor's unique Intel DL Boost technology.
Bfloat16 is a compact numeric format which uses half the bits of today's FP32 format while achieving comparable model accuracy with minimal software changes. By adding bfloat16 support, the company has accelerated both AI training and inference performance in its Xeon CPUs.
Intel has also upgraded the socket-to-socket interconnect in its Cooper Lake processors. The company's Xeon processors use Ultra Path Interconnect (UPI) to connect multiple CPUs together to act as one system. In Cooper Lake, each CPU-to-CPU connection now involves two UPI links each running at 10.4 GT/s to reach a total of 20.8 GT/s.
As part of the 3rd Gen Intel Xeon Scalable platform, the company has announced the Intel Optane persistent memory 200 series which will provide customers with up to 4.5TB of memory per socket to better handle data intensive workloads.
Both Intel's 3rd Gen Xeon Scalable processors and Optane persistent memory 200 series are available now and have already begun shipping out to customers.
- Also check out the best laptops for business
Via AnandTech
from TechRadar: computing components news https://ift.tt/30Uhvsz
via IFTTT
No comments:
Post a Comment