We’ve heard so much about the CXL interconnect – including the recent announcement of CXL v3.0 – and components that are CXL-ready, that it may come as a surprise that CXL v1.1 “hosts” are only just now shipping. It’s a technology that could play a central role in the ever-more heterogenous, more memory-intensive systems of the future. And now, after several years of experimentation and various interconnect consortia, CXL is emerging as the standard for advanced functionality for fabric technologies. Along with CXL we also discuss some of the details of the CHIPS and Science Act….
ALCF to Hold Cerebras AI Testbed Workshop, Aug. 9-10
July 29, 2022 by
The Argonne Leadership Computing Facility (ALCF) will hold a virtual AI testbed training event Aug. 9-10 that will introduce users to the Cerebras hardware and software stack. It will provide hands-on training to get started on the system in the ALCF AI Testbed. Registration is here. Day 1 will focus on Cerebras hardware and software architecture. […]
NVIDIA Announces GA of AI Enterprise 2.1
July 25, 2022 by
NVIDIA today announced the general availability of NVIDIA AI Enterprise 2.1., an updated version of its AI and data analytics software suite designed to help enterprises deploy and scale AI applications across bare metal, virtual, container, and cloud environments. NVIDIA said AI Enterprise 2.1 offers advanced data science with the latest NVIDIA RAPIDS and low […]
@HPCpodcast: US Pressures ASML on Exports to China; US vs China Exascale; HPC Software
July 18, 2022 by
Following recent reports that Dutch chip manufacturing equipment maker ASML is under diplomatic pressure from the U.S. to regulate the export of its fabrication equipment to China, we discuss market data, other suppliers of fab equipment, and a quick view of some of ASML’s own suppliers. ASML, the world’s only maker of extreme ultraviolet lithography systems, does not export to China EUV equipment instrumental to making the world’s most advanced chips used in HPC systems; it is the company’s older equipment, DUV (deep ultraviolet lithography) systems, that the US is trying to block from the China market.
Micron: DDR5 Server DRAM Now Available
July 6, 2022 by
BOISE, Idaho, July 06, 2022 — Memory and storage company Micron Technology, Inc. (Nasdaq: MU), today announced the availability of Micron DDR5 server DRAM in support of industry qualification of next-generation Intel and AMD DDR5 server and workstation platforms. Micron said the move to DDR5 memory enables up to an 85 percent increase in system […]
@HPCpodcast: Horst Simon on DOE’s Post-Exascale HPC Vision – More Flexibility, More Vendor Diversity; the Start of a New Leadership-class Supercomputing Market?
July 6, 2022 by
Following DOE’s next-gen supercomputing Request for Information (RFI) issued last week, we discussed what it all may mean with Dr. Horst Simon, Special Advisor to the Laboratory Director at Lawrence Berkeley National Laboratory and co-editor of the TOP500 list since 2000. He takes us through the current (though fungible) state of DOE’s post-exascale vision, the implications of an Advanced Computing Ecosystem (ACE) outlined in the RFI and the possible emergence of a new, more vendor-diverse leadership-class systems market.
DOE Awards 18M HPC Node Hours to 45 ASCR Projects, Including Access to Perlmutter, Polaris and Frontier
June 29, 2022 by
June 29, 2022 – Today, the U.S. Department of Energy (DOE) announced that 18 million node-hours have been awarded to 45 scientific projects under the Advanced Scientific Computing Research (ASCR) Leadership Computing Challenge (ALCC) program. The projects, with applications ranging from advanced energy systems to climate change to cancer research, will use DOE supercomputers with the goal of uncovering […]
Cerebras Claims Record for Largest AI Models Trained on a Single Device
June 22, 2022 by
SUNNYVALE, Calif., June 22, 2022 — AI computing company Cerebras Systems today announced that a single Cerebras CS-2 system is able to train models with up to 20 billion parameters on – something not possible on any other single device, according to the company. By enabling a single CS-2 to train these models, Cerebras said […]
insideHPC’s Exclusive ISC 2022 Video Interviews
June 13, 2022 by
Check out our exclusive video interviews from the ISC 2022 conference! You can find them on the right side of our home page. They include: AMD – An update on the EPYC CPUs and Instinct GPUs powering the new no. 1 supercomputer, Frontier, which is also the first HPC system to exascale-certified, along with the […]
