33 C
Monday, August 2, 2021
Home Technology All the key announcements made by Intel at International Supercomputing Conference -...

All the key announcements made by Intel at International Supercomputing Conference – Times of India

At the just lately-held (June 24-July 2) International Supercomputing Conference (ISC), Intel showcased how the firm goals to increase its lead in excessive efficiency computing (HPC) with a spread of expertise disclosures, partnerships and buyer adoptions. The chip big introduced advances in its Xeon processor for HPC and AI in addition to improvements in reminiscence, software program, exascale-class storage, and networking applied sciences for a spread of HPC use instances.
“To maximize HPC performance we must leverage all the computer resources and technology advancements available to us,” mentioned Trish Damkroger, vp and basic supervisor of High Performance Computing at Intel. “Intel is the driving force behind the industry’s move toward exascale computing, and the advancements we’re delivering with our CPUs, XPUs, oneAPI Toolkits, exascale-class DAOS storage, and high-speed networking are pushing us closer toward that realization.”
Earlier this yr, Intel strengthened its place in HPC with the launch of third Gen Intel Xeon Scalable processors. The newest processor delivers as much as 53% larger efficiency throughout a spread of HPC workloads, together with life sciences, monetary companies and manufacturing, as in comparison with the earlier era processor.
Compared to its closest x86 competitor, the third Gen Intel Xeon Scalable processor is claimed to ship higher efficiency throughout a spread of fashionable HPC workloads. Xeon Scalable 8380 processors are additionally claimed to outperform AMD EPYC 7763 processors on key AI workloads, with 50% higher efficiency throughout 20 frequent benchmarks.
HPC labs, supercomputing facilities, universities and unique gear producers who’ve adopted Intel’s newest compute platform embrace Dell Technologies, HPE, Korea Meteorological Administration, Lenovo, Max Planck Computing and Data Facility, Oracle, Osaka University and the University of Tokyo.
The firm claims that its subsequent-era of Xeon Scalable processors (code-named “Sapphire Rapids) will supply built-in High Bandwidth Memory (HBM), offering a dramatic enhance in reminiscence bandwidth and a big efficiency enchancment for HPC functions that function reminiscence bandwidth-delicate workloads. Users can energy by means of workloads utilizing simply High Bandwidth Memory or together with DDR5.
The early main wins for Sapphire Rapids processors with built-in HBM embrace the US Department of Energy’s Aurora supercomputer at Argonne National Laboratory and the Crossroads supercomputer at Los Alamos National Laboratory.
The Sapphire Rapids-based platform will present capabilities to speed up HPC, together with elevated I/O bandwidth with PCI categorical 5.0 (in comparison with PCI categorical 4.0) and Compute Express Link (CXL) 1.1 help, enabling superior use instances throughout compute, networking and storage.
In addition to reminiscence and I/O developments, Sapphire Rapids is optimized for HPC and synthetic intelligence (AI) workloads, with a brand new constructed-in AI acceleration engine referred to as Intel Advanced Matrix Extensions (AMX).
Extending Intel Ethernet for HPC
At ISC 2021, Intel additionally introduced its new High Performance Networking with Ethernet (HPN) answer, which extends Ethernet expertise capabilities for smaller clusters in the HPC section by utilizing customary Intel Ethernet 800 Series Network Adapters and Controllers, switches based mostly on Intel Tofino P4-programmable Ethernet swap ASICs and the Intel Ethernet Fabric suite software program. HPN is alleged to allow software efficiency akin to InfiniBand at a decrease price whereas taking benefit of the ease of use provided by Ethernet.
Commercial help for DAOS
Intel rolled out business help for DAOS (distributed asynchronous object storage), an open-supply software program-outlined object retailer constructed to optimize knowledge alternate throughout Intel HPC architectures. DAOS is at the basis of the Intel Exascale storage stack, beforehand introduced by Argonne National Laboratory, and is getting used by Intel prospects equivalent to LRZ and JINR (Joint Institute for Nuclear Research).
DAOS help is now out there to companions as an L3 help providing, which permits companions to offer a whole turnkey storage answer by combining it with their companies. In addition to Intel’s personal knowledge heart constructing blocks, early companions for this new business help contains HPE, Lenovo, Supermicro, Brightskies, Croit, Nettrix, Quanta, and RSC Group.

Source link

Most Popular