LUT AM-AM is the amplitude-to-amplitude correction function stored in a look-up table that compensates for a power amplifier's nonlinear gain compression by mapping instantaneous input envelope values to gain expansion factors. This component directly counteracts the AM-AM distortion where output amplitude deviates from the ideal linear relationship with input amplitude, particularly as the amplifier approaches saturation.
Glossary
LUT AM-AM
The amplitude-to-amplitude correction component stored in a look-up table that compensates for the power amplifier's nonlinear gain compression curve.
AMPLITUDE-TO-AMPLITUDE CORRECTION
What is LUT AM-AM?
The amplitude-to-amplitude correction component stored in a look-up table that compensates for the power amplifier's nonlinear gain compression curve.
The AM-AM LUT is typically indexed by the quantized input signal magnitude and stores real-valued gain correction coefficients. As the input envelope increases into the compression region, the LUT outputs progressively larger gain values to linearize the amplifier's transfer characteristic. When combined with its companion LUT AM-PM component, the AM-AM correction forms the complete complex-gain predistortion function essential for meeting stringent ACLR and EVM requirements in modern wideband transmitters.
AMPLITUDE CORRECTION FUNDAMENTALS
Key Characteristics of LUT AM-AM
The AM-AM LUT is the core memory structure that maps instantaneous input envelope power to a complex gain correction factor, directly counteracting the power amplifier's gain compression curve.
01
Gain Expansion Counteraction
The AM-AM LUT stores inverse gain values that expand as the input power increases, precisely mirroring the amplifier's compression. At low power, entries are near unity; at saturation, the stored gain may be 2-3× the linear gain to push the output back to the ideal linear trajectory. This creates a pre-distorted envelope that, after passing through the compressing PA, yields a linear output.
02
Indexing by Instantaneous Envelope
Addressing is performed by quantizing the magnitude of the complex baseband signal |x(n)|. The quantizer maps the continuous envelope to a discrete address:
- Uniform quantization: equal step sizes across the dynamic range
- Non-uniform quantization: finer steps in the compression region
- Typical table sizes: 64–1024 entries for narrowband; up to 4096 for wideband signals
03
Complex Gain vs. Scalar Gain
A pure AM-AM LUT stores real-valued gain corrections only, assuming phase distortion is handled separately by an AM-PM LUT. However, many implementations combine both into a complex-gain LUT where each entry is a single complex number G(|x|) = G_I + jG_Q. This simultaneously corrects:
- AM-AM: magnitude of G(|x|) compensates gain compression
- AM-PM: phase of G(|x|) compensates phase shift
04
Interpolation Between Entries
To reduce quantization error without increasing table size, interpolation estimates values between stored entries:
- Linear interpolation: simplest, uses two adjacent entries
- Polynomial interpolation: fits a curve through 3–4 neighboring points
- Cubic spline: smoothest transition, higher compute cost Without interpolation, the discrete steps create spectral regrowth from abrupt gain transitions.
05
Adaptation via LMS Update
The Least Mean Squares (LMS) algorithm iteratively refines each LUT entry. For a given address i, the update rule is:
LUT(i) ← LUT(i) + μ · e(n) · x*(n)
where μ is the step size, e(n) is the error between desired and actual PA output, and x*(n) is the complex conjugate input. Only the entry corresponding to the current envelope magnitude is updated per sample.
06
Compression Region Density
The AM-AM characteristic is most nonlinear in the gain compression region near the 1 dB compression point (P1dB) and saturation (Psat). Non-uniform LUTs allocate 60–70% of entries to the top 20% of the input power range where the gain curve changes most rapidly. This optimizes correction accuracy without wasting memory in the linear region where gain is nearly constant.
Enabling Efficiency, Speed & Accuracy
Intelligent Analysis, Decision & Execution
We build AI systems for teams that need search across company data, workflow automation across tools, or AI features inside products and internal software.
Talk to Us
Search across company data
Give teams answers from docs, tickets, runbooks, and product data with sources and permissions.
Useful when people spend too long searching or get different answers from different systems.
Enterprise searchRAGPermissions
Read more
Automate internal workflows
Use AI to route work, draft outputs, trigger actions, and keep approvals and logs in place.
Useful when repetitive work moves across multiple tools and teams.
AI agentsWorkflow automationGovernance
Read more
Add AI to products and internal tools
Build assistants, guided actions, or decision support into the software your team or customers already use.
Useful when AI needs to be part of the product, not a separate tool.
AI integrationDecision supportModel routing
Read moreLUT AM-AM CORRECTION
Frequently Asked Questions
Essential questions about the amplitude-to-amplitude correction component in look-up table-based digital predistortion systems.
LUT AM-AM is the amplitude-to-amplitude correction component stored in a look-up table that compensates for a power amplifier's nonlinear gain compression curve. It operates by mapping the instantaneous input signal envelope magnitude to a complex gain correction factor, where the magnitude of this factor counteracts the amplifier's gain deviation from ideal linear behavior. As the input power increases and the amplifier enters compression, the LUT AM-AM function applies progressively larger gain expansion to maintain a constant overall gain. The correction values are typically derived through indirect learning architectures where the error between the desired linear output and the actual amplifier output drives coefficient updates. In a complex-gain LUT implementation, the AM-AM correction is stored as the magnitude component of a single complex-valued entry, while the phase component handles LUT AM-PM correction simultaneously. The indexing mechanism uses the quantized input envelope to address the appropriate memory location, and LUT interpolation between adjacent entries smooths the correction function to minimize quantization artifacts.
About the author
Prasad Kumkar
CEO & MD, Inference Systems
Prasad Kumkar is the CEO & MD of Inference Systems and writes about AI systems architecture, LLM infrastructure, model serving, evaluation, and production deployment. Over 5+ years, he has worked across computer vision models, L5 autonomous vehicle systems, and LLM research, with a focus on taking complex AI ideas into real-world engineering systems.
His work and writing cover AI systems, large language models, AI agents, multimodal systems, autonomous systems, inference optimization, RAG, evaluation, and production AI engineering.
LinkedIn
Limited slotsGet a Free AI Consultation
Partnered with leading AI, data, and software stack.
How We Work
Custom AI workflows for your Business
One-fit-all AI don't work for modern businesses. At Inferensys, we aim to understand your business & custom requirements; which we use to define most efficient agentic workflows, the data, and the tools for your business.
01
Review the use case
We understand the task, the users, and where AI can actually help.
Read more02
Pick the right approach
We define what needs search, automation, or product integration.
Read more03
Build the first useful version
We implement the part that proves the value first.
Read more04
Improve from there
We add the checks and visibility needed to keep it useful.
Read moreThe first call is a practical review of your use case and the right next step.
Talk to Us