Cover Image

Empirically-Calibrated H100 Node Power Models for Reducing Uncertainty in AI Training Energy Estimation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Newkirk, Alex C., Fernandez, Jared, Koomey, Jonathan, Latif, Imran, Strubell, Emma, Shehabi, Arman, Samaras, Constantine
Format:	Preprint
Published:	2025
Subjects:	Hardware Architecture
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Empirical Measurements of AI Training Power Demand on a GPU-Accelerated Node
by: Latif, Imran, et al.
Published: (2024)

Accelerating Mini-batch HGNN Training by Reducing CUDA Kernels
by: Wu, Meng, et al.
Published: (2024)

An Analytical and Empirical Investigation of Tag Partitioning for Energy-Efficient Reliable Cache
by: Cheshmikhani, Elham, et al.
Published: (2025)

Energy-Oriented Computing Architecture Simulator for SNN Training
by: Ma, Yunhao, et al.
Published: (2025)

16 Years of SPEC Power: An Analysis of x86 Energy Efficiency Trends
by: Tröpgen, Hannes, et al.
Published: (2024)

EnergAIzer: Fast and Accurate GPU Power Estimation Framework for AI Workloads
by: Lee, Kyungmi, et al.
Published: (2026)

Symbolic Timing Analysis of Digital Circuits Using Analytic Delay Functions
by: Thaqi, Era, et al.
Published: (2025)

A Hybrid Delay Model for Interconnected Multi-Input Gates
by: Ferdowsi, Arman, et al.
Published: (2024)

Fine-Grained Power and Energy Attribution on AMD GPU/APU-Based Exascale Nodes
by: McDaniel, Adam, et al.
Published: (2026)

Scalable and RISC-V Programmable Near-Memory Computing Architectures for Edge Nodes
by: Caon, Michele, et al.
Published: (2024)

A Node-Based Polar List Decoder with Frame Interleaving and Ensemble Decoding Support
by: Ren, Yuqing, et al.
Published: (2024)

Physical Design Exploration of a Wire-Friendly Domain-Specific Processor for Angstrom-Era Nodes
by: Ruotolo, Lorenzo, et al.
Published: (2025)

Quantum Computing -- A new scientific revolution in the making
by: Bertels, Koen, et al.
Published: (2021)

Guac: Energy-Aware and SSA-Based Generation of Coarse-Grained Merged Accelerators from LLVM-IR
by: Brumar, Iulian, et al.
Published: (2024)

M100: An Orchestrated Dataflow Architecture Powering General AI Computing
by: Xie, Yan, et al.
Published: (2026)

AutoPower: Automated Few-Shot Architecture-Level Power Modeling by Power Group Decoupling
by: Zhang, Qijun, et al.
Published: (2025)

DX100: A Programmable Data Access Accelerator for Indirection
by: Khadem, Alireza, et al.
Published: (2025)

Branch Prediction in Hardcaml for a RISC-V 32im CPU
by: Saveau, Alex
Published: (2023)

Calibrating DRAMPower Model for HPC: A Runtime Perspective from Real-Time Measurements
by: Shi, Xinyu, et al.
Published: (2024)

VCO-CARE: VCO-based Calibration-free Analog Readout for Electrodermal activity sensing
by: Alvero-Gonzalez, Leidy Mabel, et al.
Published: (2025)

FirePower: Towards a Foundation with Generalizable Knowledge for Architecture-Level Power Modeling
by: Zhang, Qijun, et al.
Published: (2024)

Soft GPGPU versus IP cores: Quantifying and Reducing the Performance Gap
by: Langhammer, Martin, et al.
Published: (2024)

Generic and ML Workloads in an HPC Datacenter: Node Energy, Job Failures, and Node-Job Analysis
by: Chu, Xiaoyu, et al.
Published: (2024)

Workload-Aware Early-Stage Power Delivery Network Optimization via Architectural Power Traces
by: Hayes, Oran, et al.
Published: (2026)

ReadyPower: A Reliable, Interpretable, and Handy Architectural Power Model Based on Analytical Framework
by: Zhang, Qijun, et al.
Published: (2025)

CarbonClarity: Understanding and Addressing Uncertainty in Embodied Carbon for Sustainable Computing
by: Chen, Xuesi, et al.
Published: (2025)

Cohet: A CXL-Driven Coherent Heterogeneous Computing Framework with Hardware-Calibrated Full-System Simulation
by: Wang, Yanjing, et al.
Published: (2025)

BARD: Reducing Write Latency of DDR5 Memory by Exploiting Bank-Parallelism
by: Vittal, Suhas, et al.
Published: (2025)

Accelerating MRI Uncertainty Estimation with Mask-based Bayesian Neural Network
by: Zhang, Zehuan, et al.
Published: (2024)

Algorithm and Hardware Co-Design for Efficient Complex-Valued Uncertainty Estimation
by: Zhang, Zehuan, et al.
Published: (2026)

PowerFlow-DNN: Compiler-Directed Fine-Grained Power Orchestration for End-to-End Edge AI Inference
by: Chen, Paul, et al.
Published: (2026)

Uncertainty-Guided Live Measurement Sequencing for Fast SAR ADC Linearity Testing
by: Schey, Thorben, et al.
Published: (2025)

PEARL: Power- and Energy-Aware Multicore Intermittent Computing
by: Akhunov, Khakim, et al.
Published: (2025)

ATLAS: A Self-Supervised and Cross-Stage Netlist Power Model for Fine-Grained Time-Based Layout Power Analysis
by: Li, Wenkai, et al.
Published: (2025)

Performance and Energy Benefits of MRDIMMs
by: Díaz, Pau, et al.
Published: (2026)

LIMCA: LLM for Automating Analog In-Memory Computing Architecture Design Exploration
by: Vungarala, Deepak, et al.
Published: (2025)

BinSparX: Sparsified Binary Neural Networks for Reduced Hardware Non-Idealities in Xbar Arrays
by: Malhotra, Akul, et al.
Published: (2024)

A Power-Efficient Hardware Implementation of L-Mul
by: Chen, Ruiqi, et al.
Published: (2024)

Combining Power and Arithmetic Optimization via Datapath Rewriting
by: Coward, Samuel, et al.
Published: (2024)

Register Dispersion: Reducing the Footprint of the Vector Register File in Vector Engines of Low-Cost RISC-V CPUs
by: Titopoulos, Vasileios, et al.
Published: (2025)