# Wattchmen: Watching the Wattchers -- High Fidelity, Flexible GPU Energy Modeling

arXiv: https://arxiv.org/abs/2603.26435 · HTML: https://mlsanity.com/paper/2603.26435/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Mar 2026.

## Built on by (most cited first, 3 of 3)

- [Characterization of Request and Token Energy Costs for LLM Inference Workloads on GPU Platforms](https://mlsanity.com/paper/2608.28044/) (2026)
- [The Model Parking Tax: Quantifying the Hidden Energy Cost of Always-On GPU Model Deployment](https://mlsanity.com/paper/2605.23918/) (2026)
- [Experiments in Agentic AI for Science](https://mlsanity.com/paper/2605.26305/) (2026)

## Abstract (arXiv)

Modern GPU-rich HPC systems are increasingly becoming energy-constrained. Thus, understanding an application's energy consumption becomes essential. Unfortunately, current GPU energy attribution techniques are either inaccurate, inflexible, or outdated. Therefore, we propose Wattchmen, a flexible methodology for measuring, attributing, and predicting GPU energy consumption. We construct a per-instruction energy model using a diverse set of microbenchmarks to systematically quantify the energy consumption of GPU instructions, enabling finer-grain prediction and energy consumption breakdowns for applications. Compared with the state-of-the-art systems like AccelWattch (32%) and Guser (25%), across 16 popular GPGPU, graph analytics, HPC, and ML workloads, Wattchmen reduces the mean absolute percent error (MAPE) to 14% on V100 GPUs. Furthermore, we show that Wattchmen provides similar MAPEs for water-cooled V100s (15%) and extends to later architectures, including air-cooled A100 (11%) and H100 (12%) GPUs. Finally, to further demonstrate Wattchmen's value, we apply it to applications such as Backprop and QMCPACK, where Wattchmen's insights enable energy reductions of up to 35%.