CUDA; reproducibility; API tracing; kernel profiling; binary analysis; HPC; Kokkos
Abstract :
[en] ReProspect is a Python framework for prospecting CUDA code, designed to ensure reproducibility through a fully programmatic approach. Prospecting encompasses three complementary ways of characterizing CUDA-based libraries and software components: how they interact with the CUDA runtime through API tracing, how kernels perform through kernel profiling, and how source constructs translate into machine code through binary analysis.
ReProspect builds on NVIDIA tools: Nsight Systems, Nsight Compute, and the CUDA binary utilities. It streamlines data collection and extraction using these tools, and it complements them with new functionalities for programmatic analysis of these data, thus making it possible to encapsulate the entire prospecting analysis in a single Python script.
Research Center/Unit :
A&M - Aérospatiale et Mécanique - ULiège
Disciplines :
Computer science
Author, co-author :
Tomasetti, Romin ; Université de Liège - ULiège > Aérospatiale et Mécanique (A&M)
Arnst, Maarten ; Université de Liège - ULiège > Département d'aérospatiale et mécanique > Computational and stochastic modeling
Language :
English
Title :
ReProspect - A framework for reproducible prospecting of CUDA applications
