Warp-Level CFG Construction for GPU Kernel WCET Analysis - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Warp-Level CFG Construction for GPU Kernel WCET Analysis

Résumé

We present an abstract interpretation technique to automatically build a Control Flow Graph (CFG) representation of the execution of a GPU kernel. GPUs implement an inherently parallel execution model, in which threads are grouped within so-called warps that execute in lockstep. This execution model enables the representation of the execution of the threads of a warp as a single CFG. However, thread divergence may appear within a warp and its effect must be captured explicitly within the CFG. Our method builds the CFG of a warp by applying abstract interpretation on the assembly (Nvidia SASS) code of a kernel, and by maintaining an abstract representation of which threads within the warp agree on which values. This allows the method to detect precisely the points in the program where thread divergence may occur, and avoid spurious reactivation edges in the CFG. We apply our technique on benchmark kernels as a proof-of-concept, and generate IPET systems using the resulting CFGs.
Fichier principal
Vignette du fichier
OASIcs-WCET-2023-1.pdf (656.13 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04171474 , version 1 (26-07-2023)

Licence

Paternité

Identifiants

Citer

Louison Jeanmougin, Thomas Carle, Pascal Sotin, Christine Rochange. Warp-Level CFG Construction for GPU Kernel WCET Analysis. 21st International Workshop on Worst-Case Execution Time Analysis (WCET 2023), Jul 2023, Vienne, Austria. pp.1:1--1:13, ⟨10.4230/OASIcs.WCET.2023.1⟩. ⟨hal-04171474⟩
69 Consultations
51 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More