Book a demo

Cut patent&paper research from weeks to hours with PatSnap Eureka AI!

Try now

Power Delivery Noise in AI Accelerator Boards — PatSnap Eureka

Power Delivery Noise in AI Accelerator Boards — PatSnap Eureka
Tools Explore in Eureka
Reading9 min
PublishedJun 10, 2025
Coverage1991–2025
PDN Noise · AI Hardware

Power Delivery Noise Reduction in AI Accelerator Boards

As AI workloads exceed 700W per accelerator card, managing power distribution network noise has become a first-order design challenge. This landscape covers patent and literature signals from 1991 to 2025 — spanning active filtering, resonance-aware scheduling, and the emerging frontier of workload-coupled PDN control.

Fig. 01 — Patent Records by Assignee (this dataset)
PDN Noise Patent Records by Assignee: Intel 8, IBM 3, Google 2, Amazon 1, Georgia Tech 2, Microsoft 1, Others multiple Bar chart showing patent record counts per assignee in the PDN noise reduction dataset from PatSnap Eureka, covering filings from 1991 to 2025. 2 4 6 8 10 Intel 8 IBM 3 Google 2 Georgia Tech 2 Amazon 1 Microsoft 1
Published by PatSnap Insights Team · · 9 min read Verified by PatSnap Eureka Data
Technology Overview

Three Core Noise Phenomena Drive PDN Design Complexity

Power delivery noise in AI accelerator boards arises from the interaction between rapidly switching compute loads and the impedance of the power distribution network — a hierarchy spanning voltage regulator modules (VRMs), PCB power planes, package interconnects, and on-die power rails. The core technical problem is consistently framed around three phenomena: voltage droop from sudden current demand spikes (di/dt), PDN resonance at characteristic frequencies where inductive and capacitive elements interact destructively, and simultaneous switching noise (SSN) when multiple lanes or execution units toggle in concert.

As AI workloads grow denser and more power-hungry — often exceeding 700W per accelerator card — managing power distribution network (PDN) noise has become a first-order design challenge. Approaches span from passive filtering and decoupling capacitor placement, to active noise cancellation circuits, to firmware-level workload throttling and resonance-aware scheduling. The most recent filings (2019–2025) show a clear shift toward closed-loop, software-defined PDN management specifically contextualized for accelerator and AI chip architectures.

This landscape draws on patent and literature records from PatSnap’s IP analytics platform, covering filings from 1991 to 2025. It represents a snapshot of innovation signals within this dataset and should not be interpreted as a comprehensive view of the full industry. For authoritative standards context, see IEEE and JEDEC publications on power integrity.

PatSnap Eureka Dataset spans targeted patent and literature searches; filings 1991–2025 across US, EP, WO, CN, GB, MY jurisdictions. Explore the data ↗
700W+
Typical power per AI accelerator card driving PDN noise challenges
3
Core noise phenomena: voltage droop, PDN resonance, SSN
1991
Earliest filing in dataset — Taiwan Semiconductor, power bus noise control
2025
Most recent filing — Amazon’s workload-coupled PDN controller
Innovation Timeline

Three Phases of PDN Noise Innovation: 1991 to 2025

The field has evolved from chip-level I/O driver noise suppression to AI-accelerator-specific closed-loop workload management, with a clear inflection point after 2019.

Phase 1 · 1991–2007
Foundational Mechanisms
Taiwan Semiconductor (1991) — controlling current between I/O power buses
Programmable Output Pads
VLSI Technology (1996) — ground bounce and supply noise reduction
Active Cancellation
Intel (2006) — compensating current waveform injection at I/O switching events
Throttling by Voltage Sense
IBM (2007) — suppress execution units if predicted droop exceeds threshold
Phase 2 · 2008–2018
System-Level PDN Architecture
GlobalFoundries (2013) — voltage compression limits across die, package, PCB
Port-to-Port Delay
Intel (2009–2011) — staggered lane power-on at ~32 unit intervals, ~100 MHz resonance
LDO Bandwidth via PTL
Georgia Tech (2019) — power transmission line creates resonance null at LDO PSR peak
On-Die Anti-Resonance
Micron (2007) — on-die decoupling caps tuned to parasitic interconnect inductance
🔒
Unlock the AI-Accelerator Phase (2019–2025)
See how Amazon, Google, Microsoft, and Axis AB are defining the frontier of workload-coupled PDN control.
Amazon 2025 PDN controllerAxis AB per-layer meteringGoogle resonance scheduling+ more
Generate full report in Eureka →
PatSnap Eureka Patent timeline derived from targeted searches across US, EP, WO, CN, GB, MY jurisdictions. Explore timeline ↗
Key Technology Approaches

Four Technology Clusters Addressing PDN Noise

From active filtering to staggered switching, the patent landscape reveals four distinct engineering strategies — each targeting a different point in the noise generation and propagation chain.

Cluster 1

Active and Closed-Loop PDN Filtering

A controller continuously measures voltage noise or a proxy metric such as bit error rate, then actuates variable filter elements to maintain noise within a target envelope. Amazon’s 2025 patent — the most AI-accelerator-specific filing in the dataset — applies workload-specific preset configurations before execution begins, then uses closed-loop monitoring to fine-tune in real time. IBM’s supplemental current supply approach cancels noise at the load by providing additional current from a dedicated second supply path when variation on the primary path is detected. See also PatSnap solutions for cross-domain PDN research.

Amazon 2025 · IBM 2019 · Intel 2006
Cluster 2

Resonance-Aware Workload Scheduling

Rather than filtering noise after it occurs, these approaches predict or detect resonant conditions and alter workload execution to avoid exciting resonant frequencies. Google’s 2022 patent detects when performance management operations such as clock swallowing or zero ops are applied at intervals that excite PDN resonance, then modifies the periodicity or nature of those operations. IBM’s local detection loop architecture deploys per-unit voltage noise sensors within a processor core, enabling fine-grained, spatially resolved throttling. This approach is particularly valuable for accelerator boards where the PDN is fixed in silicon but firmware can modulate execution patterns. For broader context, see IEEE power integrity standards.

Google 2022 · IBM 2021 · IBM 2007
Cluster 3

System-Level PDN Architecture and Impedance Engineering

This cluster focuses on the structural design of the PDN — how package, PCB, and on-die elements are organized and parameterized to suppress noise across the full impedance spectrum. GlobalFoundries’ 2013 patent defines voltage compression limits at each PDN layer (die, package, PCB) and restructures the network if any layer’s compression exceeds its limit. Georgia Tech’s power transmission line approach inserts a one-dimensional PTL between VRM and LDO to create a resonance null precisely in the frequency range where LDO power supply rejection peaks. Micron’s on-die anti-resonance structure uses on-die decoupling capacitors tuned to resonate with parasitic interconnect inductance to flatten the PDN impedance profile. Resources at PatSnap Analytics cover impedance engineering IP landscapes.

GlobalFoundries 2013 · Georgia Tech 2019 · Micron 2007
Cluster 4

Staggered Switching and Port-to-Port Delay

This cluster reduces simultaneous switching noise by introducing controlled temporal offsets between switching events so that their di/dt contributions do not superimpose constructively. Intel’s 2011 patent determines the resonant frequency of the PDN, derives an optimal inter-port delay of approximately 32 unit intervals at ~100 MHz resonance, and staggers lane power-on sequences accordingly. Microsoft’s dynamic power routing patent routes power from idled components specifically to support accelerator burst demands, with predictive pre-staging of power availability before a workload spike arrives. Intel’s multi-criteria pooled accelerator management redirects power between accelerators in a pool based on real-time telemetry. The principle of staggered activation is directly applicable to modern multi-chiplet AI accelerator packages. See JEDEC standards for switching noise specifications.

Intel 2011 · Microsoft 2020 · Intel 2019
PatSnap Eureka Four clusters derived from analysis of patent records in this dataset; cluster boundaries reflect thematic grouping of assignee approaches. Explore all clusters ↗
Data Visualisation

Filing Activity and Jurisdiction Distribution

Patent filing patterns across phases and jurisdictions reveal where PDN noise innovation is concentrated and where coverage is expanding.

Filing Phase Distribution

The AI-accelerator-specific phase (2019–2025) contains the most strategically significant filings, including Amazon’s 2025 workload-coupled PDN controller.

PDN Noise Filing Phases: Foundational 1991–2007, System-Level 2008–2018, AI-Accelerator-Specific 2019–2025 Horizontal bar chart showing the three innovation phases for PDN noise reduction patents, from PatSnap Eureka dataset analysis. FOUNDATIONAL 1991–2007 I/O drivers, output pads, basic cancellation SYSTEM-LEVEL 2008–2018 Package, PCB, on-die hierarchy AI-ACCELERATOR-SPECIFIC 2019–2025 Workload-coupled, per-layer, resonance-aware

Jurisdiction Coverage

US jurisdiction dominates the dataset; EP and WO filings appear predominantly for Intel, while CN shows growing engagement from both multinationals and domestic assignees.

PDN Noise Patent Jurisdiction Distribution: US dominant, EP and WO for Intel, CN growing, GB and MY recent diversification Donut-style chart showing relative jurisdiction coverage of PDN noise reduction patents in the PatSnap Eureka dataset. US dominant US — Majority of records EP — Intel international WO — Intel & IBM CN — Growing engagement GB / MY — Recent diversification Source: PatSnap Eureka dataset
PatSnap Eureka Jurisdiction data from targeted patent searches; proportions are indicative of dataset composition, not full industry filing volumes. Explore the data ↗
Emerging Directions

Five Converging Trajectories Shaping PDN Noise in 2025

The most recent filings (2019–2025) reveal a convergence toward predictive, software-defined, and AI-workload-aware PDN management strategies.

Workload-Coupled PDN Control (2025)

Amazon’s 2025 patent introduces applying a workload-specific preset configuration before execution begins, then using closed-loop monitoring to fine-tune in real time. This “predictive + reactive” two-phase model is directly tailored to AI inference workloads with known computation graphs and represents the leading edge of the dataset.

Per-Layer Neural Network Power Metering (2023–2024)

Axis AB’s filings capture per-layer power measurements in multi-layer networks, enabling the power management system to anticipate which network layers will create high di/dt events and pre-emptively reduce clock frequency. This granularity — below the chip level, at the neural network layer level — is described in the dataset as a significant architectural advance.

Resonance-Aware Scheduling as a Software Primitive (2019–2022)

Google’s resonance-aware performance management patents establish that PDN resonance avoidance can be implemented as a software/firmware primitive rather than requiring hardware redesign. This is particularly valuable for accelerator boards where the PDN is fixed in silicon but firmware can modulate execution patterns.

🔒
Unlock 2 More Emerging Directions
See Microsoft’s predictive power pre-staging and Georgia Tech’s LDO-PTL architecture — both directly applicable to AI accelerator PCB design.
Microsoft pre-staging 2020Georgia Tech LDO-PTL+ strategic implications
Unlock in Eureka →
PatSnap Eureka Emerging direction signals derived from filings dated 2019–2025 in this dataset. Explore emerging signals ↗
Application Domains & Strategic Implications

Where PDN Noise Patents Apply and What They Mean for R&D Teams

Domain Key Assignees Core Mechanism Strategic Signal
AI Accelerators & Neural Network Hardware Amazon, Axis AB Workload-specific PDN preset; per-layer clock frequency reduction Hyperscalers building proprietary PDN intelligence into custom silicon — assess FTO exposure
Cloud & Data Center Compute Microsoft, Intel Dynamic power routing; multi-criteria pooled accelerator management Rack-level and data-center-scale accelerator deployments sharing a common power budget
High-Speed I/O & Interconnects Intel, Georgia Tech Port-to-port delay ~32 unit intervals at ~100 MHz resonance; LDO-PTL bandwidth enhancement PCI-E, CSI, FBD interfaces on AI accelerator boards connecting GPU/TPU dies to host CPUs
🔒
Unlock Full Domain & Strategy Table
See GPU core applications, scientific instrumentation design philosophy, and full strategic implications for IP teams.
IBM/Google GPU coresATLAS instrumentationIP white spaces
See full table in Eureka →
PatSnap Eureka Domain mapping derived from patent application field descriptions and claims in this dataset. See PatSnap customer case studies for applied IP strategy examples. Explore applications ↗
Frequently asked questions

Power Delivery Noise in AI Accelerators — key questions answered

Still have questions? PatSnap Eureka can answer them instantly from patent and research data. Ask Eureka ↗
PatSnap Eureka

Generate Your Own PDN Noise Landscape for Any Technology Area

Join 18,000+ innovators using PatSnap Eureka to generate reports like this one for any technology area.

Ask anything about PDN noise in AI accelerator boards.
PatSnap Eureka searches patents and research literature to answer instantly.
Powered by PatSnap Eureka
Link copied to clipboard