{"ID":2860639,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.03872","arxiv_id":"2510.03872","title":"Datacenter Energy Optimized Power Profiles","abstract":"This paper presents datacenter power profiles, a new NVIDIA software feature released with Blackwell B200, aimed at improving energy efficiency and/or performance. The initial feature provides coarse-grain user control for HPC and AI workloads leveraging hardware and software innovations for intelligent power management and domain knowledge of HPC and AI workloads. The resulting workload-aware optimization recipes maximize computational throughput while operating within strict facility power constraints. The phase-1 Blackwell implementation achieves up to 15% energy savings while maintaining performance levels above 97% for critical applications, enabling an overall throughput increase of up to 13% in a power-constrained facility. KEYWORDS GPU power management, energy efficiency, power profile, HPC optimization, Max-Q, Blackwell architecture","short_abstract":"This paper presents datacenter power profiles, a new NVIDIA software feature released with Blackwell B200, aimed at improving energy efficiency and/or performance. The initial feature provides coarse-grain user control for HPC and AI workloads leveraging hardware and software innovations for intelligent power managemen...","url_abs":"https://arxiv.org/abs/2510.03872","url_pdf":"https://arxiv.org/pdf/2510.03872v2","authors":"[\"Sreedhar Narayanaswamy\",\"Pratikkumar Dilipkumar Patel\",\"Ian Karlin\",\"Apoorv Gupta\",\"Sudhir Saripalli\",\"Janey Guo\"]","published":"2025-10-04T16:49:19Z","proceeding":"cs.DC","tasks":"[\"cs.DC\"]","methods":"[]","has_code":false}