Nvidia Launches Flagship ‘Blackwell’ GPU at GTC

Nvidia CEO Jensen Huang took the stage for a two-hour GTC keynote event and victory lap, which was held before a sold-out crowd at the 17,500-seat SAP Center, home of the San Jose Sharks of the National Hockey League. Today’s news begins with Blackwell, which Nvidia said delivers six “revolutionary” technologies that together enable AI training and real-time LLM inference for models scaling up to 10 trillion parameters. Blackwell chips are comprised of 208 billion transistors ….

HPC News Bytes 20240226: Intel Foundry Bash, Nvidia Earnings and AI Inference, HPC in Space, ISC 2024

A happy Monday of Leap Year Week to you! We offer a rapid run-through of the latest in HPC-AI, including: Intel Foundry bash, Gelsinger talks up the “Systems Foundry Era,” Wall Street hangs on Nvidia earnings, AI Training vs Inference, Digitial In-Memory Computing for inference efficiency, HPC in space, ISC 2024.

The Future-Proofed Datacenter: DDC Delivers 85kW Air-Cooled Density for AI and HPC Workloads

At DDC, the global leader in scalable datacenter-to-edge solutions, we are taking an innovative approach to building new and retrofitting legacy datacenters. Today, our patented cabinet technology can be deployed in nearly any environment or facility and….

Exascale and Industry Innovation at GE Aerospace

Aug.  31, 2023 — GE Aerospace is partnering with French aerospace company Safran … on a next-generation technology demonstration program … that aims to reduce fuel consumption and CO2 emissions by 20 percent compared to today’s most efficient engine technologies. The high-fidelity modeling and simulation capabilities provided by exascale computing enable researchers ….

ETH Prof. Torsten Hoefler Joins CSCS as Chief Architect for Machine Learning

August 31, 2023 —  As of Sept. 1, ETH Professor Torsten Hoefler will be chief architect for machine learning of the architecture and technology workgroup at the Swiss National Supercomputing Centre (CSCS).  Hoefler has headed the Scalable Parallel Computing Laboratory (SPCL) at the Department of Computer Science at ETH Zurich since 2012.

Arm Introduces Neoverse Compute Subsystems

At Hot Chips today, Arm introduced the Arm Neoverse Compute Subsystems (CSS) designed to enable Arm users to build specialized silicon at lower cost, with less risk and faster time-to-market compared to discrete IP. Available today, Arm CSS N2 is a pre-integrated, PPA-optimized configuration of the Neoverse N2….

Sept. 8 Registration Deadline for October ALCF Hands-on HPC Workshop

Aug. 31, 2023 — The Argonne Leadership Computing Facility will hold Hands-on HPC Workshop on October 10-12, 2023 at the TCS Conference Center at Argonne National Laboratory. Deadline for registration is Friday, Sept. 8. Registration information can be found here. The workshop will provide hands-on time on Polaris and AI Testbeds focusing on porting applications […]

DOE Announces $29M for Research on ML, AI and Data Resources for Fusion Energy Sciences

Aug. 31, 2023 — Today, the U.S. Department of Energy (DOE) announced $29 million in funding for seven team awards for research in machine learning, artificial intelligence and data resources for fusion energy sciences. The funding is for projects lasting up to three years, with $11 million in Fiscal Year 2023 dollars and outyear funding contingent on […]

HPC News Bytes 20230828: Gartner on Composable; An ABI for MPI; AMD Acquires Mipsology; Google Cloud HPC Clone

A happy Monday morn to you. This week’s HPC News Bytes offers a quick (4:53) run-through of the major news in our sector over the past week. This morning we look at: Gartner predicts accelerated growth for composable computing; Proposed ABI (application binary interface) for MPI to simplify parallel apps; AMD buys AI software company Mipsology – a sign of more AI M&A activity to come?; HPC clone on Google Cloud Platform

Exascale: Pagoda Updates Programming with Scalable Data Structures and Aggressively Asynchronous Communication

The Pagoda Project researches and develops software that programmers use to implement high-performance applications using the Partitioned Global Address Space model. The project is primarily funded by the Exascale Computing Project and interacts with partner projects….