# Predict; Do not React for Enabling Efficient Fine Grain DVFS in GPUs

arXiv: https://arxiv.org/abs/2205.00121 · HTML: https://mlsanity.com/paper/2205.00121/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2022.

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

- [Reducing Compute Waste in LLMs through Kernel-Level DVFS](https://mlsanity.com/paper/2601.08539/) (2026)
- [HALO: Hardware-aware quantization with low critical-path-delay weights for LLM acceleration](https://mlsanity.com/paper/2502.19662/) (2025)
- [Enabling Spatially Fine-Grained DVFS in Neural Processing Units for Energy-Efficient LLM Serving](https://mlsanity.com/paper/2607.16473/) (2026)

## Abstract (arXiv)

With the continuous improvement of on-chip integrated voltage regulators (IVRs) and fast, adaptive frequency control, dynamic voltage-frequency scaling (DVFS) transition times have shrunk from the microsecond to the nanosecond regime, providing additional opportunities to improve energy efficiency. The key to unlocking the continued improvement in voltage-frequency circuit technology is the creation of new, smarter DVFS mechanisms that better adapt to rapid fluctuations in workload demand. It is particularly important to optimize fine-grain DVFS mechanisms for graphics processing units (GPUs) as the chips become ever more important workhorses in the datacenter. However, massive amount of thread-level parallelism in GPUs makes it uniquely difficult to determine the optimal voltage-frequency state at run-time. Existing solutions-mostly designed for single-threaded CPUs and longer time scales-fail to consider the seemingly chaotic, highly varying nature of GPU workloads at short time scales. This paper proposes a novel prediction mechanism, PCSTALL, that is tailored for emerging DVFS capabilities in GPUs and achieves near-optimal energy efficiency. Using the insights from our fine-grained workload analysis, we propose a wavefront-level program counter (PC) based DVFS mechanism that improves program behavior prediction accuracy by 32% on average for a wide set of GPU applications at 1 microsecond DVFS time epochs. Compared to the current state-of-art, our PC-based technique achieves 19% average improvement when optimized for Energy-Delay-Squared Product at 50 microsecond time epochs, reaching 32% power efficiencies when operated with 1 microsecond DVFS technologies.