Helping Power Solutions Keep Up with Moore’s Law

When evaluating any system (or collection of systems) in terms of power solutions, power supplies, and other analyses related to power consumption, energy efficiency, or overall energy storage, it helps to separate the sources from the loads. In the simplest form, that means separating the power supplies from the end loads consuming the power these sources provide. Think of the sources and loads as independent black boxes that “talk” to each other. The figure below shows an arbitrary breakdown of a system in block diagram form, in this case, a computing or server-like architecture, highlighting the difference between the typical sources and loads.


This distinction is particularly important when trying to understand the pace of technology in complex systems with numerous system components affected by engineering, manufacturing, and supply chain variables. The trends of exponential improvement, whether transistor count, power density, or energy efficiency, tend to be far more associated with the load side rather than the source side. The source-side components tend to be dominated by magnetics, power transistors, and energy storage, which evolve at a slower rate compared to low-voltage semiconductors.

The consideration of the pace of development for electronics and electrical equipment often converges around Moore’s Law [2], which is more of an economic trend rather than a technical scaling rule. Even without tracking these advancements, there is a perception in the electronics industry that all system components, supply chains, and engineering efforts adhere to this doubling performance trend every 18-24 months.

Aside from Moore’s Law’s impact on transistor density, another trend drives major system power budget reductions. [Moore’s Law keeps logic shrinking exponentially, while microelectromechanical systems (MEMS) [3] shrink sensors to nearly invisible sizes].

However, the impact differs:

• Moore’s Law increases load power, as more transistors increase power density
• MEMS decreases load power, as applications do not require exponentially more sensors

With a reduction in transistor feature size comes a reduction in threshold voltage, allowing ICs to operate with lower bias voltages. This shift has led to power rails decreasing from ~2.5/3.3V to ~1.2/1.5V, and now even <1.0V power rails. However, as more transistors are packed into smaller spaces, power density continues to increase, leading to higher input currents and greater transient demands for power supplies.

As highlighted in many power management resources, key Figures of Merit (FOMs) for a system are size, weight, and power (SWaP). When combined with cost considerations, this expands into SWaP-C factors [4]. Shrinking loads drive SWaP improvements, but the same level of miniaturization does not necessarily apply to power solutions.

Since load power budgets are reducing faster than source power availability is increasing, keeping up with Moore’s Law requires focusing on power budget reductions rather than just designing larger power supplies.

Intelligent Power Management (IPM) techniques optimize power distribution and usage in computer systems and data centers [7].
This mindset shift includes:

• Transitioning from always-on to always-available power architectures
• Peak shaving, using energy storage to handle high-power peaks while optimizing steady-state power
• Load shedding/consolidation, turning off unused subsystems to improve power efficiency
• Power allocation optimization, avoiding over-engineering power supplies for worst-case scenarios

No one expects power solutions to fully match the pace of Moore’s Law or MEMS advancements. However, the gap between source power and load demand is not insurmountable. Through intelligent power management, energy storage, and advanced packaging, engineers can bridge this gap and sustain Moore’s Law-driven improvements.

3D Power Packaging (3DPP^®) and other advanced techniques play a pivotal role in enhancing power density and system efficiency, ensuring power solutions remain viable as load demands evolve. The integration of IPM strategies, MEMS, and power switches continues to push power solutions forward, enabling the next generation of high-performance electronics.

[1] B. Zahnstecher, “Best Practices for Low-Power (IoT/IIoT) Designs: SEPARATING THE SOURCE-SIDE & LOAD-SIDE ANALYSES,” ECCE 2022 Tutorial, Detroit, MI, October 9, 2022.
[2] Wikipedia contributors, "Moore's law," Wikipedia, The Free Encyclopedia, https://en.wikipedia.org/w/index.php?title=Moore%27s_law&oldid=1139518707 (accessed February 24, 2023).
[3] Wikipedia contributors, "Microelectromechanical systems," Wikipedia, The Free Encyclopedia, https://en.wikipedia.org/w/index.php?title=Microelectromechanical_systems&oldid=1139870714 (accessed February 24, 2023).
[4] “Power Supply Design for maximum Performance,” RECOM Blog, Oct 21, 2022, https://recom-power.com/rec-n-power-supply-design-for-maximum-performance-229.html (accessed February 15, 2023).
[5] E. Shelton, P. Palmer, A. Mantooth, B. Zahnstecher, G. Haynes, “WBG Devices, Circuits and Applications,” APEC 2018 Short Course, San Antonio, TX, March 4, 2018.
[6] “DC/DC for GaN,” RECOM Blog, Sep 16, 2022, https://recom-power.com/rec-n-dc!sdc-for-gan-225.html (accessed January 23, 2023).
[7] Data Center Facilities Definitions, "Intelligent Power Management (IPM)," TechTarget, https://www.techtarget.com/searchdatacenter/definitions/Data-center-design-and-facilities (accessed February 24, 2023).