MARVELL IS HONORED TO RECEIVE THE LEADING EDGE 2025 AWARD

Low-loss liquid-cooled power supply 2025 model

Low-loss liquid-cooled power supply 2025 model

Key features of the showcase include complete power solutions for both 800 VDC and ±400 VDC power architectures, the newly-launched liquid-to-liquid (L2L) CDU with 2,000kW of cooling capacity for new AI data centers, the new 300kW liquid-to-air (L2A) CDU for. , October 6th, 2025 — Delta, a global leader in power management and smart green solutions, will present its next-generation of highly integrated high-voltage DC power distribution, advanced precision cooling, and networking solutions for AI data centers at the OCP Global Summit. The iHP20S Liquid Cooled precision AC-DC configurable power supply is 100% digitally controlled in a 757. 8 mm package and provides eight individual slots that accept intelligent DC-DC converter modules. Its cooling is handled by the PC's custom liquid cooling setup, which means that. The PSU channels coolant through heatsinks that come into contact with the hottest components, such as switching MOSFETs, Schottky diodes, APFC, IGBTs, and more.

Read More
Fiber optic switch does not receive transmitters

Fiber optic switch does not receive transmitters

This simple step resolves many issues with sfp optical transceivers in access switches and core routers. Fiber optic troubleshooting is an essential skill for network administrators, technicians, and engineers responsible for maintaining and repairing fiber optic systems. These high-speed, high-capacity communication networks are increasingly replacing copper cables, offering superior performance and.

Read More
Dimensional parameters of server rack systems for edge computing

Dimensional parameters of server rack systems for edge computing

The three primary dimensions to consider are rack height (measured in rack units or U), rack width (most commonly the industry-standard 19-inch format), and rack depth (typically ranging from 24 inches to 48 inches). Understanding server rack sizes is essential for data centers, enterprise IT teams, and businesses deploying high-performance infrastructure. Most IT environments default to 42U, 19-inch width, and 1000–1200 mm depth unless space constraints or special equipment dictate. Selecting the right rack size ensures not only compatibility with today's hardware but also room for future expansion. The standard width of a mountable server rack is 19 inches, so the server chassis must be less than 17. Basically, we have different 19-inch server cabinet models for edge computing solutions in our product range, which differ, among other things, in the potential cooling capacity. EDGE 5 Micro Data Centre is an air conditioned server rack that facilitates edge computing.

Read More
New optoelectronic fusion technology for edge computing

New optoelectronic fusion technology for edge computing

We have proposed the Fourier domain diffraction neural network, constructed the reconfigurable diffraction computing processor (DPU), developed the all-analog optoelectronic fusion computing chip ACCEL, and the large-scale general-purpose intelligent optoelectronic computing . We present GENIO, a novel platform that integrates edge computing within existing Passive Optical Network (PON) infrastructures. Integrating microelectronics and optoelectronics can harness the mature processes and functions of microelectronics, with the ultra-wideband and low-power benefits of optoelectronics.

Read More
Energy-efficient Raman amplifier for edge computing

Energy-efficient Raman amplifier for edge computing

The RAMAN accelerator is designed to leverage data and weight sparsity to deploy deep neural networks at the edge, ensuring low power consumption, minimal storage requirements, and reduced processing latency. To introduce novel solutions that can be viable for extreme edge cases, hybrid solutions combining conventional. Abstract—The shift from centralized cloud to edge comput-ing demands hardware systems with data processing capability at ultra-low power. Researchers at the Department of Electronic Systems Engineering, IISc, led by Chetan Singh Thakur, have developed an AI co-processor called RAMAN, or Re-configurable And sparse tinyML Accelerator for infereNce. This paper introduces the Modified Dadda Approximate Multiplier (MDAM), an innovative architecture that optimizes hardware economy.

Read More

Get In Touch

Connect With Us

📱

Poland (Sales & Engineering HQ)

+48 22 538 72 19

🇪🇺

Germany (EU Technical Support)

+49 30 983 21 44

📍

Headquarters & Manufacturing

ul. Postępu 14, 02-676 Warszawa, Poland