End-to-End Throughput Benchmarking of Portable Deterministic CNN-Based Signal Processing Pipelines

TL;DR

This paper introduces a benchmarking methodology for evaluating the end-to-end throughput of deterministic CNN-based signal processing pipelines across different hardware platforms, focusing on ultrasound imaging workloads.

Contribution

It provides a comprehensive benchmarking framework for CNN-compatible signal processing pipelines, enabling performance comparison across heterogeneous AI accelerators without hardware-specific modifications.

Findings

Performance varies significantly with different operator formulations.

The methodology effectively measures throughput, energy, and memory usage.

Portability and performance are influenced by operator choice and hardware architecture.

Abstract

This paper presents a benchmarking methodology for evaluating end-to-end performance of deterministic signal-processing pipelines expressed using CNN-compatible primitives. The benchmark targets phased-array workloads such as ultrasound imaging and evaluates complete RF-to-image pipelines under realistic execution conditions. Performance is reported using sustained input throughput (MB/s), effective frame rate (FPS), and, where available, incremental energy per run and peak memory usage. Using this methodology, we benchmark a single deterministic, training-free CNN-based signal-processing pipeline executed unmodified across heterogeneous accelerator platforms, including an NVIDIA RTX 5090 GPU and a Google TPU v5e-1. The results demonstrate how different operator formulations (dynamic indexing, fully CNN-expressed, and sparse-matrix-based) impact performance and portability across architectures. This work is motivated by the need for portable, certifiable signal-processing implementations that avoid hardware-specific refactoring while retaining high performance on modern AI accelerators.