Efficient Implementation of an Adaptive Transformer Accelerator for Massive MIMO Outdoor Localization

2026-05-13

AI Summary

This work addresses the challenge of balancing real-time performance and accuracy in 5G massive MIMO outdoor localization by proposing a Transformer-based adaptive localization hardware acceleration architecture. The design incorporates propagation-aware row-level sparse skipping, a static hybrid input/output dataflow, and a lightweight runtime model switching strategy to efficiently execute matrix operations on a heterogeneous vector processing engine. Experimental results on a Xilinx Zynq UltraScale+ FPGA demonstrate that the system achieves inference latencies of 0.51–2.11 ms and a throughput of 1961 positions per second, while maintaining localization accuracy better than 1.15 meters (with less than 10% accuracy degradation). The architecture supports up to 65% row sparsity, yielding approximately a 2× speedup in computation.

Abstract

We present the implementation of an adaptive Transformer-based localization system for 5G massive MIMO targeting sub-10ms real-time positioning. The design exploits propagation characteristics, where beam-delay channel representations exhibit sparsity, enabling a row-wise skipping mechanism that removes low-energy beam components with minimal control overhead. The contribution is focused on hardware realization of the model using a mixed dataflow architecture, combining input- and output-stationary execution, mapped onto a heterogeneous vector processing engine with parallel processing elements and adder trees for efficient matrix computation. Environment-dependent processing is supported through a lightweight runtime model-switching mechanism, where temporally filtered outputs of a single-layer perceptron router enable stable selection between specialized models with reduced latency. Implemented on a Xilinx Zynq UltraScale+ FPGA and evaluated on real-world massive MIMO measurements, the design achieves up to 65% row sparsity, yielding peak computational speedups of approximately 2x while limiting the average localization accuracy degradation to below 10%, relative to the floating-point baseline model. The accelerator attains below 1.15m localization accuracy across scenarios, with inference latency of 0.51-2.11ms and throughput of up to 1961 positions/s. These results demonstrate that propagation-aware sparsity, mixed dataflow execution, and efficient runtime model switching enable a scalable and low-latency hardware realization of adaptive Transformer-based localization for real-time 5G systems.

Problem

• massive MIMO
• outdoor localization
• real-time positioning
• adaptive Transformer
• 5G

Innovation

• adaptive Transformer
• massive MIMO localization
• propagation-aware sparsity
• mixed dataflow architecture
• runtime model switching