AMD Ryzen AI NPU: Phase Shifting of Input Signals

OverView

This session demonstrates how to perform a ‘Phase Change’ of a complex input signals in frequency domain in AMD Ryzen AI Phoenix using AIE DIALECTS and AIE API

Requirements

AMD Ryzen AI Phoenix.

Linux® based development environment

Python® (for test automation and result validation)

IRON API and MLIR-based AI Engine Toolchain

Project Brief

The SOC is designed to accelerate the AIE-ML algorithms to deliver a good, exceptional performance. The NPU complex has

1. 16 AI Cores for computation

2. 4 Memory Tiles for fast memory access

3. 4 SHIM DMA to Move data in and out of L3 Memory

Note: This project is customized for Phoenix.

Features covered in this session

“How to change the phase of the input samples in the frequency domain?”

Architecture

The phase of a complex input signal represents the angular argument of its complex representation. When this signal undergoes a change, the phase changes by an angle which directly alters the instantaneous position of the signal's phasor on the complex plane.

How the Phase Change Works

A complex signal is typically composed of a real part (in-phase) and an imaginary part (quadrature). The phase change reflects the angular shift between two states of the signal over time.

Applications of Phase Changes

• Digital Modulation (e.g., QPSK, QAM): Systems encode digital data by intentionally changing the phase of the carrier signal to specific angles in the constellation diagram.
• System Analysis: Passing a signal through a physical circuit (like a filter or amplifier) introduces a frequency-dependent phase delay..
• Signal Processing: Tracking phase shifts over time reveals frequency deviations and is essential for coherent signal demodulation.

Data Flow

How to Build and Run

Input Samples

Output Samples

How to Install and Set Up the Environment?

https://www.hackster.io/541340/amd-ryzen-ai-npu-tool-chain-installation-and-execution-b252fa

Conclusion

This project demonstrates how to use the “IRON API and MLIR-based AI Engine Toolchain” and “AIE API” to perform the Phase Shifting on input samples".