GPUSimBench: Towards Scalable and Reliable GPU-Accelerated Simulators in Embodied AI

• URL: http://arxiv.org/abs/2607.13059v1
• Date: Mon, 06 Jul 2026 15:46:30 GMT
• Title: GPUSimBench: Towards Scalable and Reliable GPU-Accelerated Simulators in Embodied AI
• Abstract summary: We introduce GPUSimBench, which focuses on scalability, physical consistency, and computational determinism.<n>We quantify the inherent non-determinism introduced by GPU-batched execution, characterized by significant run-to-run and inter-environment variability.
• Score: 15.554389634626753
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data-driven embodied AI is rapidly transitioning into a paradigm that scales training through massively parallel simulation, where GPU-accelerated simulators serve as the foundational data infrastructure. However, as computational throughput scales, the underlying trade-offs between parallel efficiency, physical fidelity, and execution determinism remain largely unexamined, hindering the development of reliable robot learning. In this paper, we expose the hidden limits of mainstream GPU-based robotic simulators (e.g., Isaac Lab, Genesis) by introducing GPUSimBench, which focuses on scalability, physical consistency, and computational determinism. First, GPUSimBench establishes a physical grounding evaluation with a controlled inclined-plane task, quantifying the distributional alignment between simulated dynamics and their real-world counterparts. Second, we benchmark parallel scalability by measuring throughput and memory footprints across scaling environment counts. Crucially, beyond standard performance metrics, we unveil and quantify the inherent non-determinism introduced by GPU-batched execution, characterized by significant run-to-run and inter-environment variability even under identical initial conditions. Finally, we identify four empirical regimes of stochasticity within current simulator stacks, highlighting that unbounded scaling can compromise reproducibility without explicit constraints.

Related papers

• GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models [66.77745044586173]
  GAUGE is a real-world-grounded diagnostic benchmark for evaluating how numerical simulators and generative video world models reproduce or deviate from real-world physics.<n>We benchmark Isaac Sim, Genesis, and Newton on 14 task families using generalized trajectory errors, and evaluate 6 image-to-video models on 5 rigid-body tasks.<n>Our results reveal no uniformly faithful physics engine, with the largest discrepancies arising in impulsive contact, rapid textile motion, and volumetric deformation.
  arXiv  Detail & Related papers  (2026-08-06T12:19:38Z)
• NVIDIA Isaac Sim: Enabling Scalable, GPU-Accelerated Simulation for Robotics [16.974627651296498]
  This survey reviews NVIDIA Isaac Sim from system and application perspectives, outlining its architecture and comparing it with widely used simulators.<n>We analyze studies across five major domains and summarize common usage patterns, particularly in data generation and high-fidelity simulation.<n>We also outline key future directions and challenges, including physics open-world learning, simulation-centric training and practical usability constraints.
  arXiv  Detail & Related papers  (2026-06-02T12:12:27Z)
• GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning [55.272458304179025]
  GS-Playground is a multi-modal simulation framework designed to accelerate end-to-end perceptual learning.<n>Our system achieves a breakthrough throughput of 104 FPS at 640x480 resolution, significantly lowering the barrier for large-scale visual RL.
  arXiv  Detail & Related papers  (2026-04-28T10:05:39Z)
• DiffusionHarmonizer: Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion Enhancer [62.18680935878919]
  We introduce DiffusionHarmonizer, an online generative enhancement framework that transforms renderings into temporally consistent outputs.<n>At its core is a single-step temporally-conditioned enhancer capable of running in online simulators on a single GPU.
  arXiv  Detail & Related papers  (2026-02-27T15:35:30Z)
• SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors [58.87134689752605]
  We introduce SimBench, the first large-scale, standardized benchmark for a robust, reproducible science of LLM simulation.<n>We show that even the best LLMs today have limited simulation ability (score: 40.80/100), performance scales log-linearly with model size.<n>We demonstrate that simulation ability correlates most strongly with deep, knowledge-intensive reasoning.
  arXiv  Detail & Related papers  (2025-10-20T13:14:38Z)
• PICT -- A Differentiable, GPU-Accelerated Multi-Block PISO Solver for Simulation-Coupled Learning Tasks in Fluid Dynamics [62.93137406343609]
  We present our fluid simulator PICT, a differentiable pressure-implicit solver coded in PyTorch with Graphics-processing-unit (GPU) support.<n>We first verify the accuracy of both the forward simulation and our derived gradients in various established benchmarks.<n>We show that the gradients provided by our solver can be used to learn complicated turbulence models in 2D and 3D.
  arXiv  Detail & Related papers  (2025-05-22T17:55:10Z)
• GausSim: Foreseeing Reality by Gaussian Simulator for Elastic Objects [55.02281855589641]
  GausSim is a novel neural network-based simulator designed to capture the dynamic behaviors of real-world elastic objects represented through Gaussian kernels.<n>We leverage continuum mechanics and treat each kernel as a Center of Mass System (CMS) that represents continuous piece of matter.<n>In addition, GausSim incorporates explicit physics constraints, such as mass and momentum conservation, ensuring interpretable results and robust, physically plausible simulations.
  arXiv  Detail & Related papers  (2024-12-23T18:58:17Z)
• BeSimulator: A Large Language Model Powered Text-based Behavior Simulator [18.318419980796012]
  We propose BeSimulator as an attempt towards behavior simulation in the context of text-based environments.<n>BeSimulator can generalize across scenarios and achieve long-horizon complex simulation.<n>Our experiments show a significant performance improvement in behavior simulation compared to baselines.
  arXiv  Detail & Related papers  (2024-09-24T08:37:04Z)
• TANQ-Sim: Tensorcore Accelerated Noisy Quantum System Simulation via QIR on Perlmutter HPC [16.27167995786167]
  TANQ-Sim is a full-scale density matrix based simulator designed to simulate practical deep circuits with both coherent and non-coherent noise. To address the significant computational cost associated with such simulations, we propose a new density-matrix simulation approach. To optimize performance, we also propose specific gate fusion techniques for density matrix simulation.
  arXiv  Detail & Related papers  (2024-04-19T21:16:29Z)
• Neural Implicit Surfaces for Efficient and Accurate Collisions in Physically Based Simulations [40.679520739784195]
  Collision detection and solving is a significant bottleneck on physically based simulations. We propose using implicit surface representations learnt through deep learning for collision handling in simulations. Our proposed architecture has a complexity of O(n) -- or O(1) for a single point query -- and has no parallelization issues.
  arXiv  Detail & Related papers  (2021-10-03T09:43:01Z)
• SimNet: Computer Architecture Simulation using Machine Learning [3.7019798164954336]
  This work describes a concerted effort, where machine learning (ML) is used to accelerate discrete-event simulation. A GPU-accelerated parallel simulator is implemented based on the proposed instruction latency predictor. Its simulation accuracy and throughput are validated and evaluated against a state-of-the-art simulator.
  arXiv  Detail & Related papers  (2021-05-12T17:31:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.