Skip to Main content Skip to Navigation
Reports

Memory Organisation Cartography & Analysis

David Beniamine 1 Youenn Corre 1 Damien Dosimont 1 Guillaume Huard 1
1 MOAIS - PrograMming and scheduling design fOr Applications in Interactive Simulation
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
Abstract : Although performance analysis is one of the most important phase of High Perfor- mance Computing application development, analysis tools are complex to use. Most of the time, they rely on performance counters which are hard to understand for the final user. Therefore only few advanced users are able to do an efficient and precise analysis. Moreover these counters focus on the processor while most of the performance issues are due to a bad memory usage. In this report, we present MOCA a new kind of analysis tool which provides an overview of the memory access over time. We present MOCA's trace visualization through Ocelotl, a tool designed to provided an aggregated view of data while loosing as few information as possible. Finally, we explain how using these tools, the user can identify memory usage patterns, execution phases and how to interpret them.
Complete list of metadata

Cited literature [17 references]  Display  Hide  Download

https://hal.inria.fr/hal-01130478
Contributor : David Beniamine <>
Submitted on : Wednesday, March 11, 2015 - 6:49:03 PM
Last modification on : Tuesday, February 9, 2021 - 3:24:24 PM
Long-term archiving on: : Monday, April 17, 2017 - 9:11:00 AM

File

RR-8694.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01130478, version 1

Collections

Citation

David Beniamine, Youenn Corre, Damien Dosimont, Guillaume Huard. Memory Organisation Cartography & Analysis. [Research Report] RR-8694, INRIA Grenoble; INRIA. 2015. ⟨hal-01130478⟩

Share

Metrics

Record views

360

Files downloads

228