Incisor: Ex Ante Cloud Instance Selection for HPC Jobs

TL;DR

Incisor automates cloud instance selection for HPC jobs using program analysis and LLM reasoning, significantly reducing runtime and costs.

Contribution

It introduces a system that automates ex ante cloud instance selection for HPC jobs, combining program analysis and LLMs, outperforming expert-based methods.

Findings

Incisor achieves 100% success in selecting working AWS EC2 instances for first-time runs.

It reduces job runtime by 54% compared to baseline.

It cuts instance costs by 44% relative to expert-based selection.

Abstract

We present Incisor, a cloud HPC job submission system for the ex ante instance selection problem: choosing suitable hardware in the challenging but common setting where only the executable, inputs, and invocation commands are available at submission time. In practice, this task is manual and expertise-intensive, requiring users to combine incomplete knowledge of rapidly evolving cloud offerings with workload-specific intuition, static analysis, and systems reasoning to infer hardware constraints and select an instance type for each job. Incisor automates this process by pairing widely available program analysis tools with LLM-guided reasoning to infer hardware requirements and choose cloud instances. Using submission artifacts alone, Incisor atop frontier coding LLMs selects working AWS EC2 instances ex ante for 100% of first-time runs of source-compiled (C, C++, Fortran) and Python applications. Against a strong baseline combining expert-derived constraints with SkyPilot's instance selection, Incisor cuts job runtime by 54% and instance costs by 44%.