{"ID":2844668,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.06052","arxiv_id":"2511.06052","title":"Inductive Loop Analysis for Practical HPC Application Optimization","abstract":"Scientific computing applications heavily rely on multi-level loop nests operating on multidimensional arrays. This presents multiple optimization opportunities from exploiting parallelism to reducing data movement through prefetching and improved register usage. HPC frameworks often delegate fine-grained data movement optimization to compilers, but their low-level representations hamper analysis of common patterns, such as strided data accesses and loop-carried dependencies. In this paper, we introduce symbolic, inductive loop optimization (SILO), a novel technique that models data accesses and dependencies as functions of loop nest strides. This abstraction enables the automatic parallelization of sequentially-dependent loops, as well as data movement optimizations including software prefetching and pointer incrementation to reduce register spills. We demonstrate SILO on fundamental kernels from scientific applications with a focus on atmospheric models and numerical solvers, achieving up to 12$\\times$ speedup over the state of the art.","short_abstract":"Scientific computing applications heavily rely on multi-level loop nests operating on multidimensional arrays. This presents multiple optimization opportunities from exploiting parallelism to reducing data movement through prefetching and improved register usage. HPC frameworks often delegate fine-grained data movement...","url_abs":"https://arxiv.org/abs/2511.06052","url_pdf":"https://arxiv.org/pdf/2511.06052v1","authors":"[\"Philipp Schaad\",\"Tal Ben-Nun\",\"Patrick Iff\",\"Torsten Hoefler\"]","published":"2025-11-08T15:47:48Z","proceeding":"cs.DC","tasks":"[\"cs.DC\",\"cs.PF\"]","methods":"[]","has_code":false}