- These results are not validated in SPEC sense not reportable according to SPEC rules. The results are an estimation.
- Some benchmark sources have been changed to compile them
successfully. These changes do not change the results significantly.
- Some tests may not have compiled or executed properly.
- The goal of these runs is to monitor the performance of generated
code with most commonly used optimization flags as the base and
commonly used the most aggressive optimization flags as the peak.
The aggressive optimizations includes LTO.
- From time to time, I may change the compiler flags used to compile the benchmarks. In this case, I will inform about this.
Last modified: 02/15/2019 - vmakarov at redhat dot com
Return to index page.