Ayar Labs and NVIDIA are collaborating on developing scale-out architectures enabled by high-bandwidth, low-latency, and ultra-low-power optical-based interconnect for future NVIDIA products. Focused on integrating Ayar Labs’ technology, the two companies hope to accelerate the development and adoption of optical I/O technology to support the growth of AI/ML applications and data volumes.
Cisco has announced Cisco+ Hybrid Cloud storage solutions, an endeavor developed in partnership with NetApp and Pure Storage. Cisco believes that the combination of innovations from these two organizations will result in flexible consumption solutions. Ultimately, their goal is to make it easier for customers when they have to quickly adapt to business changes and
SiPearl and NVIDIA announce a strategic collaboration agreement for joint technical and business development to combine SiPearl HPC microprocessors with NVIDIA’s accelerated computing and networking portfolio. NVIDIA and SiPearl will develop a proxy platform for porting activities and Scalable Vector Extension (SVE) workload analysis combining the strengths of SiPearl CPU (such as HBM memory) and
One of the many tutorials offered by NVIDIA during the ISC High Performance HPC Event in Hamburg, Germany, focuses on Quantum computing or, more specifically, hybrid quantum computers. NVIDIA has focused on quantum computing, making several announcements at GTC in March. They continued the trend at ISC, demonstrating cuQuantum.
Open Compute Project (OCP) has announced the additions of the Wiwynn ES200 edge server and NVIDIA HGX-H100 GPU baseboard to their platform.
Steve Poole is among many researchers around the globe tapping into the power of the network. The distinguished senior scientist at Los Alamos National Laboratory (LANL) foresees huge performance gains using accelerated computing that includes data processing units (DPUs) running on NVIDIA Quantum InfiniBand networks.
Viking Enterprise Solutions (VES), a product division of Sanmina Corporation, has announced the launch of Cloud Native Obsidian (CNO), an on-premise storage solution that delivers control of mission-critical and frequently accessed data. CNO delivers easy-to-manage, cloud-based solutions to markets such as media/entertainment, video surveillance, backup and archive, and enterprise file services with a focus on
As global climate change accelerates, finding and securing clean energy is a crucial challenge for many researchers, organizations, and governments.
Answering the call for high-performance, green data centers, NVIDIA announced the liquid-cooled A100 PCIe GPU, the first in a line of liquid-cooled GPUs for mainstream servers. NVIDIA made the announcement during Computex 2022 in Taiwan.
Oak Ridge National Laboratory has announced that their supercomputer powered by AMD EPYC processors and AMD Instinct accelerators is the first system to break the exascale barrier (i.e., calculating at least 1018 FLOPS). Moreover, the Frontier TDS – HPE Cray EX235a supercomputer took the number one spot on the Top500 for June 2022, making it
Amazon