Skip to Main content Skip to Navigation
New interface
Conference papers

Profile-Guided Scope-Based Data Allocation Method

Abstract : The complexity of High Performance Computing nodes memory system increases in order to tackle application growing memory usage and increasing gap between computation and memory access speeds. As these technologies are just being introduced in HPC supercomputers no one knows if it is better to manage them with hardware or software solutions. Thus both are being studied in parallel. For both solutions, the problem consists in choosing what data to store on which memory at any time. In this paper we present a linear formulation of the data allocation problem. Moreover, we propose a new profile-guided scope-based approach which reduces the data allocation problem complexity, thus enhancing the precision of state of the art analyzes. Finally we have implemented our method in a framework made of GCC plugins, dynamic libraries and python scripts, allowing to test the method on several benchmarks. We have evaluated our method on an INTEL Knight's Landing processor. To this aim we have run LULESH, HydroMM, two hydrodynamic codes, and MiniFE, a finite element mini application. We have compared our framework performance over these codes to several straightforward solutions: MCDRAM as a cache, in hybrid mode, in flat mode using numactl command and existing AutoHBW dynamic library.
Complete list of metadata

Cited literature [34 references]  Display  Hide  Download
Contributor : Hugo BRUNIE Connect in order to contact the contributor
Submitted on : Wednesday, October 17, 2018 - 5:16:31 PM
Last modification on : Saturday, June 25, 2022 - 10:38:40 AM
Long-term archiving on: : Friday, January 18, 2019 - 3:34:57 PM


Files produced by the author(s)


  • HAL Id : hal-01897917, version 1




Hugo Brunie, Julien Jaeger, Patrick Carribault, Denis Barthou. Profile-Guided Scope-Based Data Allocation Method. MEMSYS 2018 - International Symposium on Memory Systems, Oct 2018, Alexandria, United States. ⟨hal-01897917⟩



Record views


Files downloads