Search papers, labs, and topics across Lattice.
Incisor automates cloud HPC instance selection by using program analysis tools and LLM-guided reasoning to infer hardware requirements from submission artifacts (executable, inputs, commands). This system achieves 100% success in selecting working AWS EC2 instances for first-time runs of source-compiled and Python applications. Compared to a baseline of expert-derived constraints and SkyPilot's instance selection, Incisor reduces job runtime by 54% and instance costs by 44%.
Forget manual cloud HPC instance selection: Incisor uses LLMs to slash runtime and costs by over 40% with zero human intervention.
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%.
