Dataflow Virtual Machine Profiling

In the Dataflow model instructions are executed as soon as their input operands are ready, allowing the natural exploitation of instruction level parallelism (ILP), which makes it extremely useful for increasing applications' performance on multicore machines. However, the lack of accurate info...

Full description

Saved in:
Bibliographic Details
Published in2014 International Symposium on Computer Architecture and High Performance Computing Workshop pp. 66 - 71
Main Authors Lira, Vittor F., Cerreia, Felippe H., Santiago, Leandro, Sena, Alexandre C., De Castro, Maria Clicia S., Marzulo, Leandro A.J.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2014
Subjects
Computational modeling
Data-Flow
High Performance Computing
Multicore processing
Parallel processing
Profiling
Radiation detectors
Runtime
Runtime Environment
Virtual machining
Online AccessGet full text

Cover

More Information
Summary:In the Dataflow model instructions are executed as soon as their input operands are ready, allowing the natural exploitation of instruction level parallelism (ILP), which makes it extremely useful for increasing applications' performance on multicore machines. However, the lack of accurate information on the parallel code can make it more difficult for programmers to perform code analysis and optimization. Thus, the aim of this work is to propose and implement a profiling mechanism for Dataflow runtime environments. To validate the profiling tool implemented, an analysis of the overhead is presented and, also, how the data generated can be used to optimize the code.
DOI:10.1109/SBAC-PADW.2014.24