Incisor uses program analysis and frontier LLMs to select working AWS EC2 instances ex ante for 100% of first-time HPC runs of C/C++/Fortran and Python codes, cutting runtime 54% and costs 44% versus an expert-constrained SkyPilot baseline.
Do large lan- guage models understand performance optimization?
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
Lean Refactor uses retrieval from a curated multi-objective strategy database to guide frozen LLMs in refactoring Lean proofs, reporting over 70% token compression on benchmarks and improved version transfer.
Empirical study of agentic LLM generation of parallel Julia code finds reliable execution only at small scales with recurring failures in task dependencies and scheduling at larger scales.
KEET uses LLM agents to generate data-grounded natural language explanations of performance issues in GPU kernels from Nsight Compute profiles and shows these improve downstream LLM-based optimization tasks.
Survey mapping LLM applications in software quality assurance to established standards including ISO/IEC 12207, ISO 25010, CMMI, and TMM, with case studies, challenges, and future directions.
citing papers explorer
-
Incisor: Ex Ante Cloud Instance Selection for HPC Jobs
Incisor uses program analysis and frontier LLMs to select working AWS EC2 instances ex ante for 100% of first-time HPC runs of C/C++/Fortran and Python codes, cutting runtime 54% and costs 44% versus an expert-constrained SkyPilot baseline.
-
Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search
Lean Refactor uses retrieval from a curated multi-objective strategy database to guide frozen LLMs in refactoring Lean proofs, reporting over 70% token compression on benchmarks and improved version transfer.
-
Generated, Parallel, Scalable? A Study of Agentic AI-Generated Julia Code on Supercomputers
Empirical study of agentic LLM generation of parallel Julia code finds reliable execution only at small scales with recurring failures in task dependencies and scheduling at larger scales.
-
KEET: Explaining Performance of GPU Kernels Using LLM Agents
KEET uses LLM agents to generate data-grounded natural language explanations of performance issues in GPU kernels from Nsight Compute profiles and shows these improve downstream LLM-based optimization tasks.
-
A Blueprint for AI-Driven Software Quality: Integrating LLMs with Established Standards
Survey mapping LLM applications in software quality assurance to established standards including ISO/IEC 12207, ISO 25010, CMMI, and TMM, with case studies, challenges, and future directions.