Adaptive GPU execution planning for memory-limited Hamiltonian applications
APL Computational Physics · 01.12.2026 · 2 (4)
DOI: 10.1063/5.0351591 ↗Kurz gefasst
Fachartikel in der Zeitschrift APL Computational Physics, online erschienen am 19.11.2026. Verfasst von Uriel Shafir und 1 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hebrew University of Jerusalem.
Abstract (Originalsprache)
Many quantum-simulation workflows, including propagation, filtering, Krylov, stochastic sampling, and observable measurement, are dominated by applications of Hamiltonians or other large operators, either to one state vector, ϕ=Ĥψ, or to several right-hand sides, Y=ĤX. These applications may be repeated many times, as in propagation and filtering, or may occur as one-shot observable, measurement, projection, or post-processing operations. The numerical algorithms used for these tasks are well established. The contribution of this work is an execution layer for these existing algorithms and operator evaluations when dense or effectively dense operator data exceed the memory of a single accelerator. The implementation first inspects the allocated hardware, including the number of GPUs (graphics processing units), available accelerator memory, and supported execution modes. It then enumerates candidate ways to apply the same mathematical operator: direct analytic action, seed-based generation, fused implicit kernels, on-demand block generation, parallel block execution, partial caching, full GPU caching, row-distributed caching across several GPUs, task parallelism, and hybrid row/task parallel execution. These candidates are ranked analytically using memory estimates, arithmetic-work estimates, cache requirements, and GPU-grouping constraints. The best analytically ranked candidates are then tested by a measured autotuner on the allocated hardware. Candidate comparisons use the same operator and input vectors and distinguish steady application time from calibration, compilation, cache construction, and tuning overhead. Plan selection minimizes expected total time for the declared number of operator uses. Validation against a fixed full-cache policy, direct GPU dense linear algebra, and a broader measured candidate search is used to quantify the benefit and overhead of adaptive planning. Logged trials may support learned ranking in future work, but no neural surrogate is used in the reported results.
Förderung
- Hebrew University of Jerusalem
Zitieren
APA
Shafir, U., & Kosloff, R. (2026). Adaptive GPU execution planning for memory-limited Hamiltonian applications. APL Computational Physics, 2(4). https://doi.org/10.1063/5.0351591
Vancouver
Shafir U, Kosloff R. Adaptive GPU execution planning for memory-limited Hamiltonian applications. APL Computational Physics. 2026;2(4). doi:10.1063/5.0351591
BibTeX
@article{Shafir2026,
author = {Shafir, Uriel and Kosloff, Ronnie},
title = {Adaptive GPU execution planning for memory-limited Hamiltonian applications},
journal = {APL Computational Physics},
year = {2026},
volume = {2},
number = {4},
doi = {10.1063/5.0351591}
}
EUVIMED