paper-with-me

홈 › Papers

GPU-Virt-Bench: A Comprehensive Benchmarking Framework for Software-Based GPU Virtualization Systems

2025-11-26 · Jithin VG, Ditto PS arxiv

The proliferation of GPU-accelerated workloads, particularly in artificial intelligence and large language model (LLM) inference, has created unprecedented demand for efficient GPU resource sharing in cloud and container environments. While NVIDIA's Multi-Instance GPU (MIG) technology provides hardware-level isolation, its availability is limited to high-end datacenter GPUs. Software-based virtualization solutions such as HAMi-core and BUD-FCSP offer alternatives for broader GPU families but lack standardized evaluation methodologies. We present GPU-Virt-Bench, a comprehensive benchmarking framework that evaluates GPU virtualization systems across 56 performance metrics organized into 10 categories. Our framework measures overhead, isolation quality, LLM-specific performance, memory bandwidth, cache behavior, PCIe throughput, multi-GPU communication, scheduling efficiency, memory fragmentation, and error recovery. GPU-Virt-Bench enables systematic comparison between software virtualization approaches and ideal MIG behavior, providing actionable insights for practitioners deploying GPU resources in multi-tenant environments. We demonstrate the framework's utility through evaluation of HAMi-core, BUD-FCSP, and simulated MIG baselines, revealing performance characteristics critical for production deployment decisions.

📄 PDF Abstract BibTeX arXiv:2512.22125

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Bencher: Simple and Reproducible Benchmarking for Black-Box Optimization

2025-05-27 · Leonard Papenmeier, Luigi Nardi

We present Bencher, a modular benchmarking framework for black-box optimization that fundamentally decouples benchmark execution from optimization logic. Unlike prior suites that focus on combining many benchmarks in a s…

Benchmarking

SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks

2025-06-13 · Hwiwon Lee, Ziqi Zhang, Hanxiao Lu, Lingming Zhang

Rigorous security-focused evaluation of large language model (LLM) agents is imperative for establishing trust in their safe deployment throughout the software development lifecycle. However, existing benchmarks largely …

BenchmarkingLarge Language Model

Benchmarking Language-agnostic Intent Classification for Virtual Assistant Platforms

2022-07-01 · NAACL (MIA) 2022 7 · Gengyu Wang, Cheng Qian, Lin Pan, Haode Qi 외

Current virtual assistant (VA) platforms are beholden to the limited number of languages they support. Every component, such as the tokenizer and intent classifier, is engineered for specific languages in these intricate…

BenchmarkingClassificationintent-classificationIntent Classification

BENCHIP: Benchmarking Intelligence Processors

2017-10-23 · Jinhua Tao, Zidong Du, Qi Guo, Huiying Lan 외

The increasing attention on deep learning has tremendously spurred the design of intelligence processing hardware. The variety of emerging intelligence processors requires standard benchmarks for fair comparison and syst…

BenchmarkingDiversity

OpenML Benchmarking Suites

2017-08-11 · Bernd Bischl, Giuseppe Casalicchio, Matthias Feurer, Pieter Gijsbers 외

Machine learning research depends on objectively interpretable, comparable, and reproducible algorithm benchmarks. We advocate the use of curated, comprehensive suites of machine learning tasks to standardize the setup, …

BenchmarkingBIG-bench Machine LearningGeneral Classification