ACM Home Page
Please provide us with feedback. Feedback
CProf: customizable calling context cross-profiling for embedded java processors
Full text PdfPdf (396 KB)
Source
ACM/SIGPLAN Workshop Partial Evaluation and Semantics-Based Program Manipulation archive
Proceedings of the 2009 ACM SIGPLAN workshop on Partial evaluation and program manipulation table of contents
Savannah, GA, USA
SESSION: Slicing and profiling table of contents
Pages 161-164  
Year of Publication: 2009
ISBN:978-1-60558-327-3
Authors
Philippe Moret  University of Lugano, Lugano, Switzerland
Walter Binder  University of Lugano, Lugano, Switzerland
Alex Villazon  University of Lugano, Lugano, Switzerland
Sponsors
SIGPLAN: ACM Special Interest Group on Programming Languages
ACM: Association for Computing Machinery
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 9,   Downloads (12 Months): 37,   Citation Count: 0
Additional Information:

abstract   references   index terms   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/1480945.1480968
What is a DOI?

ABSTRACT

Performance evaluation of embedded software is essential in an early development phase so as to ensure that the software will run on the embedded device's limited computing resources. Prevailing approaches either require the deployment of the software on the embedded target, which can be tedious and may be impossible in an early development phase, or rely on simulation, which can be very slow. In this paper we present CProf, a customizable cross-profiler for embedded Java processors. It allows the developer to profile the embedded software in the host environment, completely decoupled from the target system, in a standard Java Virtual Machine, but the generated profiles represent the execution time metric of the target system. CProf enables calling context cross-profiling and customizable online processing of profiling data. Furthermore, it supports pluggable CPU cycle estimation and cache simulation strategies, easing the reconfiguration for different target processors. Using the Java Optimized Processor JOP as target, CProf's cross-profiles have only a small percent error below 3.3%.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

1
2
 
3
4
 
5

Collaborative Colleagues:
Philippe Moret: colleagues
Walter Binder: colleagues
Alex Villazon: colleagues