AutoThread uses a physics-informed neural network plus online fine-tuning to set the thread count for discrete-event simulation workloads, delivering up to 83.8% lower runtime than static and adaptive baselines.
Predicting queue wait time probabilities for multi-scale comput- ing.Philosophical Transactions of the Royal Society A, 377(2142):20180151,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Hybrid-Adaptive Thread Tuning to Mitigate Simulation Execution Bottlenecks in High-Performance Reinforcement Learning Inference
AutoThread uses a physics-informed neural network plus online fine-tuning to set the thread count for discrete-event simulation workloads, delivering up to 83.8% lower runtime than static and adaptive baselines.