Presents the first throughput-optimal family of preemptive and non-preemptive scheduling policies for continuous multiresource job models using load-dependent discretization.
arXiv preprint arXiv:2509.08207 (2025)
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
Tensor networks enable tunable, objective compression of 1D fluid data with lossless reconstruction at high bond dimension and efficient in-compressed-space operations like periodic convolution.
StructBioReasoner is a scalable multi-agent system that designs IDP-targeting biologics, with over 50% of 787 candidates for Der f 21 showing better binding free energy than human-designed references.
HPC-vQPU separates a cloud control plane from an HPC execution plane, using topology- and calibration-aware snapshots bound at claim time to export device-faithful virtual QPUs on batch systems.
EnergyLens derives a twelve-parameter closed-form energy model via symbolic regression that achieves 88.2% top-1 configuration accuracy with 50 samples and extrapolates to unseen batch sizes and hardware.
A new high-performance framework combining R-ChFSI, mixed-precision computation, and compressed communication enables exascale fully relativistic pseudopotential DFT calculations for systems up to 100,000 electrons.
Aurora reached 1.01 EF/s FP64 HPL and 11.64 EF/s HPL-MxP through locality-aware mapping, CPU-GPU pipelining, mixed-precision orchestration, and hybrid resilience on a large Intel GPU-based system.
citing papers explorer
-
Throughput-Optimal Multiresource-Job Scheduling with Continuous Requirement Distribution
Presents the first throughput-optimal family of preemptive and non-preemptive scheduling policies for continuous multiresource job models using load-dependent discretization.
-
Tensor network compression using fluid dynamics as a testbed: Analytical foundations in one dimension
Tensor networks enable tunable, objective compression of 1D fluid data with lossless reconstruction at high bond dimension and efficient in-compressed-space operations like periodic convolution.
-
Scalable Agentic Reasoning for Designing Biologics Targeting Intrinsically Disordered Proteins
StructBioReasoner is a scalable multi-agent system that designs IDP-targeting biologics, with over 50% of 787 candidates for Der f 21 showing better binding free energy than human-designed references.
-
HPC-vQPU: A Service-Export Architecture for Virtual QPUs on Batch-Scheduled HPC Systems
HPC-vQPU separates a cloud control plane from an HPC execution plane, using topology- and calibration-aware snapshots bound at claim time to export device-faithful virtual QPUs on batch systems.
-
EnergyLens: Interpretable Closed-Form Energy Models for Multimodal LLM Inference Serving
EnergyLens derives a twelve-parameter closed-form energy model via symbolic regression that achieves 88.2% top-1 configuration accuracy with 50 samples and extrapolates to unseen batch sizes and hardware.
-
Towards exascale fully relativistic pseudopotential density functional theory calculations enabled by mixed-precision computation and compressed-communication using residual based subspace iteration
A new high-performance framework combining R-ChFSI, mixed-precision computation, and compressed communication enables exascale fully relativistic pseudopotential DFT calculations for systems up to 100,000 electrons.
-
Sustaining Exascale Performance: Lessons from HPL and HPL-MxP on Aurora
Aurora reached 1.01 EF/s FP64 HPL and 11.64 EF/s HPL-MxP through locality-aware mapping, CPU-GPU pipelining, mixed-precision orchestration, and hybrid resilience on a large Intel GPU-based system.