AI Power Chipsets Delivers High Efficiency In Small Solution Size

202
 

Achieve greater than 95 per cent efficiency and support designs from 60A to 800A or more by delivering best-in-class transient performance

Hyperscale datacentre designers need increasing peak power and associated higher thermal levels for boosting computing power required due to rapidly rising demands of AI applications and deep learning.

Now, designers of high-performance, high-power artificial intelligence (AI) systems can achieve high efficiency (with reduced power cost and heat) and small total solution size with the MAX16602 AI cores dual-output voltage regulator and the MAX20790 smart power-stage IC from Maxim Integrated Products, Inc.

By leveraging the ripple cancellation benefit offered by Maxim Integrated’s patented coupled inductor, this AI multi-phase chipset provides a one per cent efficiency improvement compared to competitive solutions, enabling greater than 95 per cent efficiency at 1.8V output voltage and 200A load conditions.

AI systems implemented with the MAX16602 and MAX20790 multi-phase chipset generate less heat compared to competitive solutions. Due to Maxim Integrated’s patented coupled inductor technology and monolithic integrated dual-side cooling power stage ICs, power loss is reduced as a result of a 50 per cent lower switching frequency. The monolithic integrated approach practically eliminates the parasitic resistance and inductance between FETs and drivers to achieve a high efficiency that results in a 16% reduction in wasted power. It also allows 40 per cent less output capacitance compared to competitive solutions, reducing total solution size and capacitor count.

Since space constraints also challenge designers while boosting AI functionality, the chipset enables the smallest total solution size and allows developers to reduce component count and bill-of-materials (BOM) costs. The chipset’s scalable solution fulfils various output current requirements in multiple form factors. Additionally, the chipset enables AI edge computing as well as cloud computing at the data centre.

Furthermore, Maxim Integrated’s low-profile coupled inductor technology supports a higher saturation current per phase compared to a discrete inductor offered by competitive solutions.

Key Advantages

  • Highest Efficiency/Lowest Heat and Power Dissipation: Reduces switching frequency by 50 per cent, allowing for 1 per cent higher efficiency
  • Smallest Total Solution Size: A decrease in solution size is achieved by reducing output capacitance by 40 per cent and providing a solution with a lower phase count compared to competitive solutions
  • Flexible: Solution is scalable from 2 to 16 phases for different output current requirements (thermal design current is typically 60A to 800A or more); Low profile (<4mm) coupled inductor is customizable to support multiple form factors such as peripheral component interconnect express (PCIe) and OCP accelerator modules (OAM)

“The real estate for AI power solutions is becoming limited while the need to provide high power density in a pre-designed small space is more critical. As a result, designers need a scalable solution to customise their design objectives,” said Steven Chen, director of business management for the Cloud and Data Centre Business Unit at Maxim Integrated. “This multi-phase AI power chipset by Maxim Integrated powers AI hardware accelerators such as GPUs, FPGAs, ASICs and xPUs to increase solution efficiency and reduce solution size for different form factors such as PCIe and OAM.”

The MAX16602, MAX20790 and MAX16602CL8EVKIT# are available at Maxim Integrated’s website, as well as authorised distributors. Samples for MAX16602 and MAX20790 and EE-Sim models are also available at Maxim Integrated’s website.


SHARE YOUR THOUGHTS & COMMENTS

Please enter your comment!
Please enter your name here