CudaMon: An R Package to Monitor NVIDIA GPUs, Showcased by Monitoring a GPU-accelerated Single-cell Analysis Workflow in R

2026/05/13 by Mohammad Amin Zadenoori, Riccardo Ceccaroni, Gabriele Sales +1 · 1 voice
Mathematics · #stat.CO

paper · pdf

Abstract

NVIDIA GPUs have recently started to be used in computational biology, yet R users lack integrated GPU monitoring tools, forcing reliance on external utilities like nvidia-smi. We introduce CudaMon, an R package providing real-time monitoring of GPU utilization, memory, temperature, and power draw via NVML, along with data export and visualization utilities. Monitoring a GPU-accelerated single-cell RNA-seq pipeline (1M brain cells, RAPIDS workflow) shows that compute-intensive steps (PCA, UMAP, t-SNE) exceed 90% GPU utilization, while data management phases reveal bottlenecks. CudaMon facilitates resource optimization, performance debugging, and reproducibility for GPU-accelerated R workflows.

Citations

• GPU-accelerated single-cell analysis at scale with rapids-singlecell

Discussions

• Zadenoori, Ceccaroni, Sales, Risso: CudaMon: An R Package to Monitor NVIDIA GPUs, Showcased by Monitoring a GPU-accelerated Single-cell Analysis Workflow in R https://arxiv.org/abs/2605.13928 https:// [bsky, 0 points, 0 comments]

Related

• Analyzing Machine Learning Workloads Using a Detailed GPU Simulator
• CRIUgpu: Transparent Checkpointing of GPU-Accelerated Workloads
• GPU-accelerated single-cell analysis at scale with rapids-singlecell
• Engineering Supercomputing Platforms for Biomolecular Applications
• gpu tracker: Python Package for Tracking and Profiling GPU and Other Hardware Utilization in Both Desktop and High-Performance Computing Environments