The Effects of Toolchain Configuration on the WCET of SCADE Generated Software: Dataset

The Effects of Toolchain Configuration on the WCET of SCADE Generated Software: Dataset

Citation Author(s):
Sean
Kauffman
University of Waterloo
Sebastian
Fischmeister
University of Waterloo
Submitted by:
Sean Kauffman
Last updated:
Fri, 08/30/2019 - 14:27
DOI:
10.21227/ffkx-a427
Data Format:
License:
Creative Commons Attribution
Dataset Views:
60
Rating:
0
0 ratings - Please login to submit your rating.
Share / Embed Cite

CATEGORIES

This dataset uses a newly introduced method for the analysis of the effects on WCET of the toolchain configurations used in real-time systems. It is the result of a full factorial experiment comparing SCADE code generation tools (SCADE 5 and 6), compilers (Wind River, GCC, Code Warrior), optimization settings, and WCET analysis tools (high water mark measurement, Rapita RVS, Otawa, AbsInt aiT). SCADE generated software is targeted due to its prevalence in hard real-time systems that require WCET analysis for scheduling. The Freescale MPC5554, commonly used in the automotive and aerospace domains, is used as the target hardware.

Instructions: 

The dataset is in CSV format with a header row.  The meaning of each column is the following:

  1. model -- the id of the generated SCADE model
  2. scade -- the SCADE major version (5,6)
  3. compiler -- the compiler used for the experiment (CodeWarrior, GCC, WindRiver)
  4. opt -- the optimization setting (1 is on, 0 is off)
  5. real -- the bit width for floating point operations (float for 32 bit, double for 64 bit)
  6. tool -- the WCET tool used (hwm for ad-hoc measurement using NI equipment, rvs for Rapita RVS, abs for AbsInt aiT, ota for Otawa)
  7. stat -- redundant (wcet) used because some tools output other values
  8. value -- the raw WCET number computed from the tool result
  9. ratio -- the normalized WCET number based on the model
  10. range -- the range of results for a model and toolchain (max (measured) - min (measured)) / max (measured) note that this number is the same regardless of tool

Dataset Files

You must login with an IEEE Account to access these files. IEEE Accounts are FREE.

Sign Up now or login.

Embed this dataset on another website

Copy and paste the HTML code below to embed your dataset:

Share via email or social media

Click the buttons below:

facebooktwittermailshare
[1] Sean Kauffman, Sebastian Fischmeister, "The Effects of Toolchain Configuration on the WCET of SCADE Generated Software: Dataset", IEEE Dataport, 2019. [Online]. Available: http://dx.doi.org/10.21227/ffkx-a427. Accessed: Mar. 29, 2020.
@data{ffkx-a427-19,
doi = {10.21227/ffkx-a427},
url = {http://dx.doi.org/10.21227/ffkx-a427},
author = {Sean Kauffman; Sebastian Fischmeister },
publisher = {IEEE Dataport},
title = {The Effects of Toolchain Configuration on the WCET of SCADE Generated Software: Dataset},
year = {2019} }
TY - DATA
T1 - The Effects of Toolchain Configuration on the WCET of SCADE Generated Software: Dataset
AU - Sean Kauffman; Sebastian Fischmeister
PY - 2019
PB - IEEE Dataport
UR - 10.21227/ffkx-a427
ER -
Sean Kauffman, Sebastian Fischmeister. (2019). The Effects of Toolchain Configuration on the WCET of SCADE Generated Software: Dataset. IEEE Dataport. http://dx.doi.org/10.21227/ffkx-a427
Sean Kauffman, Sebastian Fischmeister, 2019. The Effects of Toolchain Configuration on the WCET of SCADE Generated Software: Dataset. Available at: http://dx.doi.org/10.21227/ffkx-a427.
Sean Kauffman, Sebastian Fischmeister. (2019). "The Effects of Toolchain Configuration on the WCET of SCADE Generated Software: Dataset." Web.
1. Sean Kauffman, Sebastian Fischmeister. The Effects of Toolchain Configuration on the WCET of SCADE Generated Software: Dataset [Internet]. IEEE Dataport; 2019. Available from : http://dx.doi.org/10.21227/ffkx-a427
Sean Kauffman, Sebastian Fischmeister. "The Effects of Toolchain Configuration on the WCET of SCADE Generated Software: Dataset." doi: 10.21227/ffkx-a427