-
400G Liquid-Cooled Switch for Edge Computing
The IntellaView 400G EdgeSwitch performs aggregation, filtering, tunneling, Load Balancing, and more for high-demand AI applications and edge computing. Cisco is actively innovating in direct-to-chip liquid cooling for high-performance switches, laying the groundwork for solutions that will enable seamless and scalable AI at unprecedented densities. Edgecore contributed to the Open Compute Project. The 7th generation of NVIDIA® Mellanox® InfiniBand provides AI developers and scientific researchers the fastest networking performance available to take on the world's most challenging problems. It provides ultra-low latency and doubles data throughput with NDR 400Gb/s and adds new NVIDIA. The AS9700-32X switch is a thoughtfully optimized design tailored for Leaf/Spine deployments, catering to 400/100G network requirements. With a total of thirty-two QSFP-DD ports, each port operates at multiple speed modes ranging from 10G to 400G, offering versatile connectivity options (speed. HPE is joining the 400Gbps generation for its Ethernet-based HPC interconnect. The new HPE Slingshot 400 not only increases the switch ASIC speed to 51.
[PDF Version]
-
Indonesia Certified Edge Data Center IP65
Known as EDGE2, the new data center has been under construction since 2022 and is located in Jl. Kuningan Mulia, South Jakarta. Ekagrata Data Gemilang (Edge DC), a subsidiary of PT Indointernet Tbk (Indonet). Jakarta's carrier density is the connectivity gateway to 280 million internet users. Indonesia's first 100% renewable energy data center. Dense ecosystem, scalable up to 300 MW. Colocate with 6 global cloud providers, 80+ telcos, 150+ local, regional and global. EDGE2 becomes the largest data center in the metro with a total IT Load of 23 MW and over 3,400 racks. Our Jakarta data center is designed to offer build-to-suit and multi-tenant purpose-built wholesale capacity, connectivity, and cloud access to this fast-growing, underserved market that serves as a gateway to Southeast Asia for commerce, trade, and technology. 25 PUE, liquid cooling, and 100% dual power circuit availability.
[PDF Version]
-
Dimensions of Server Rack Systems for Intelligent Computing Centers
Common server rack sizes are 19‑inch width, heights like 42U or 48U, and depths from ~24″ to 48″. The right rack dimensions ensure optimal equipment compatibility, airflow efficiency, cable management, and long-term scalability. Regular. Server rack size – also known as cabinet size – refers to the total size of the racks that house servers in a data center or other hosting facility. Rack size is important because it determines how many servers you can fit inside each rack, as well as which types of servers the rack can. As a result, your server rack sizes are a critical piece of ensuring proper airflow, energy consumption, and overall scalability. Most IT environments default to 42U, 19-inch width, and 1000–1200 mm depth unless space constraints or special equipment dictate. A rack unit, abbreviated as “U,” is the standard unit of measurement for the height of devices designed for rack mounting. This standardization allows data center managers to plan their space with precision, knowing exactly how much equipment can fit.
[PDF Version]
-
Applications of Optical Modules in Computing
Optical computing finds applications across various domains, such as parallel processing, high-speed signal processing, energy efficiency, quantum computing, machine learning, secure communication, and signal/image processing. High-Performance Computing (HPC) is no longer confined to elite research labs. It drives breakthroughs in artificial intelligence (AI), climate modeling, drug discovery, and financial analytics. At the heart of every modern HPC cluster lies a critical, often underappreciated component: the optical. This article systematically explains how optical modules build an efficient and stable interconnection system for intelligent computing centers, covering core application scenarios, deployment key points, network adaptation strategies, and implementation processes. Application Scenarios and. Vertical-Cavity Surface-Emitting Lasers (Vertical-Cavity Surface-Emitting Lasers) are compact semiconductor lasers that emit light vertically from the surface of the chip. As the demand for faster and more reliable internet and data services grows, understanding these devices becomes increasingly important.
[PDF Version]
-
Advanced Computing for the Energy Internet
The digital landscape of the Internet of Energy (IoE) is on the brink of a revolutionary transformation with the integration of edge Artificial Intelligence (AI). This comprehensive review elucidates the promise and potential that edge AI holds for reshaping the IoE ecosystem. Dear Colleagues, The Energy Internet represents a transformative paradigm integrating advanced power systems, distributed renewable energy, and digital technologies to achieve efficient, resilient, and sustainable energy. This report is available at no cost from the National Renewable Energy Laboratory (NREL) at www. Biagioni, David, John Farrell, Venu Garikapati, Peter Graf, Nalinrat Guba, Yi Hou, Wesley Jones, Joe Severino, et al. Commencing with a. Artificial intelligence has the potential to transform the energy sector in the coming decade, driving a surge in electricity demand from data centres around the world while also unlocking significant opportunities to cut costs, enhance competitiveness and reduce emissions, according to a major new.
[PDF Version]