CUDAHercules benchmark demonstrates that leading LLMs generate functional CUDA code but fail to recover expert-level optimization strategies needed for peak performance on Ampere, Hopper, and Blackwell GPUs.
Mixed citations
Title resolution pending
Mixed citation behavior. Most common role is background (40%).
5
Pith papers citing it
Background
40% of classified citations
citation-role summary
background 2
method 2
other 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5representative citing papers
Causal analysis of water MD simulations shows translational motions drive orientational dynamics in supercooled HDL but remain decoupled at ambient conditions, revealing an emergent arrow of time in fluctuation couplings.
A 1.62-trillion-atom molecular dynamics simulation achieves ab initio accuracy with 100x speedup over prior machine learning force fields and 86.9% weak scaling to 45,000 GPGPUs.
An extended dual-solute framework predicts co-segregation bounds in multicomponent alloys by machine-learning pairwise segregation energies that include solute-solute interactions and is validated on magnesium systems.
GRACE MLIPs train faster and predict alloy properties more accurately than NEP, but NEP's 60-fold speed advantage enables reliable million-atom simulations of shock propagation when paired with ensemble uncertainty quantification.
citing papers explorer
-
CUDAHercules: Benchmarking Hardware-Aware Expert-level CUDA Optimization for LLMs
CUDAHercules benchmark demonstrates that leading LLMs generate functional CUDA code but fail to recover expert-level optimization strategies needed for peak performance on Ampere, Hopper, and Blackwell GPUs.
-
Causality in Liquid Water as a Hallmark of Emergent Glassy Dynamics
Causal analysis of water MD simulations shows translational motions drive orientational dynamics in supercooled HDL but remain decoupled at ambient conditions, revealing an emergent arrow of time in fluctuation couplings.
-
Trillion-atom molecular dynamics simulations with ab initio accuracy
A 1.62-trillion-atom molecular dynamics simulation achieves ab initio accuracy with 100x speedup over prior machine learning force fields and 86.9% weak scaling to 45,000 GPGPUs.
-
Predicting co-segregation in multicomponent alloys with solute-solute interactions
An extended dual-solute framework predicts co-segregation bounds in multicomponent alloys by machine-learning pairwise segregation energies that include solute-solute interactions and is validated on magnesium systems.
-
Machine Learning Interatomic Potentials for Million-Atom Simulations of Multicomponent Alloys
GRACE MLIPs train faster and predict alloy properties more accurately than NEP, but NEP's 60-fold speed advantage enables reliable million-atom simulations of shock propagation when paired with ensemble uncertainty quantification.