# FastML Science Benchmarks: Accelerating Real-Time Scientific Edge Machine Learning

arXiv: https://arxiv.org/abs/2207.07958 · HTML: https://mlsanity.com/paper/2207.07958/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 43 references that are in the map.
- First posted on arXiv 16 Jul 2022.

## Builds on (most cited first, 14 of 14)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [Fast inference of deep neural networks in FPGAs for particle physics](https://mlsanity.com/paper/1804.06913/) (2018)
- [MLPerf Tiny Benchmark](https://mlsanity.com/paper/2106.07597/) (2021)
- [Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors](https://mlsanity.com/paper/2006.10159/) (2020)
- [AI Benchmark: All About Deep Learning on Smartphones in 2019](https://mlsanity.com/paper/1910.06663/) (2019)
- [Scientific Machine Learning Benchmarks](https://mlsanity.com/paper/2110.12773/) (2021)
- [Applications and Techniques for Fast Machine Learning in Science](https://mlsanity.com/paper/2110.13041/) (2021)
- [Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference](https://mlsanity.com/paper/2102.11289/) (2021)
- [Fathom: Reference Workloads for Modern Deep Learning Methods](https://mlsanity.com/paper/1608.06581/) (2016)
- [A reconfigurable neural network ASIC for detector front-end data compression at the HL-LHC](https://mlsanity.com/paper/2105.01683/) (2021)
- [MLPerf HPC: A Holistic Benchmark Suite for Scientific Machine Learning on HPC Systems](https://mlsanity.com/paper/2110.11466/) (2021)
- [The Tracking Machine Learning challenge : Throughput phase](https://mlsanity.com/paper/2105.01160/) (2021)
- [BOOSTR: A Dataset for Accelerator Control Systems](https://mlsanity.com/paper/2101.08359/) (2021)

## Built on by (most cited first, 12 of 12)

- [Scaling Laws in Jet Classification](https://mlsanity.com/paper/2312.02264/) (2023)
- [Building Machine Learning Challenges for Anomaly Detection in Science](https://mlsanity.com/paper/2503.02112/) (2025)
- [AI Benchmark Democratization and Carpentry](https://mlsanity.com/paper/2512.11588/) (2025)
- [End-to-end codesign of Hessian-aware quantized neural networks for FPGAs and ASICs](https://mlsanity.com/paper/2304.06745/) (2023)
- [Architectural Implications of Neural Network Inference for High Data-Rate, Low-Latency Scientific Applications](https://mlsanity.com/paper/2403.08980/) (2024)
- [CGRA4ML: A Hardware/Software Framework to Implement Neural Networks for Scientific Edge Computing](https://mlsanity.com/paper/2408.15561/) (2024)
- [An MLCommons Scientific Benchmarks Ontology](https://mlsanity.com/paper/2511.05614/) (2025)
- [wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation](https://mlsanity.com/paper/2511.05615/) (2025)
- [Achieving Trustworthy Real-Time Decision Support Systems with Low-Latency Interpretable AI Models](https://mlsanity.com/paper/2506.20018/) (2025)
- [Neural Architecture Codesign for Fast Bragg Peak Analysis](https://mlsanity.com/paper/2312.05978/) (2023)
- [Learning Before Filtering: Real-Time Hardware Learning at the Detector Level](https://mlsanity.com/paper/2506.11981/) (2025)
- [Design Rules for Extreme-Edge Scientific Computing on AI Engines](https://mlsanity.com/paper/2604.19106/) (2026)

## Abstract (arXiv)

Applications of machine learning (ML) are growing by the day for many unique and challenging scientific applications. However, a crucial challenge facing these applications is their need for ultra low-latency and on-detector ML capabilities. Given the slowdown in Moore's law and Dennard scaling, coupled with the rapid advances in scientific instrumentation that is resulting in growing data rates, there is a need for ultra-fast ML at the extreme edge. Fast ML at the edge is essential for reducing and filtering scientific data in real-time to accelerate science experimentation and enable more profound insights. To accelerate real-time scientific edge ML hardware and software solutions, we need well-constrained benchmark tasks with enough specifications to be generically applicable and accessible. These benchmarks can guide the design of future edge ML hardware for scientific applications capable of meeting the nanosecond and microsecond level latency requirements. To this end, we present an initial set of scientific ML benchmarks, covering a variety of ML and embedded system techniques.