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.
and Churavy, V.: MPI.jl: Julia Bindings for the Message Passing Interface
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.