F41 Change Proposal - Python built with gcc -03 (self-contained)

[churchyard (Miro Hrončok)]

aarch64

• 1.05x faster
• 1.05x faster
• 1.05x faster
• 1.04x faster
• 1.07x faster
• 1.06x faster
• 1.06x faster
• 1.05x faster

i686

• 1.08x faster
• 1.08x faster
• 1.12x faster
• 1.07x faster
• 1.07x faster
• 1.08x faster
• 1.08x faster
• 1.12x faster

ppc64le

• 1.05x faster
• 1.05x faster
• 1.10x faster
• 1.13x faster
• 1.09x faster
• 1.04x faster
• 1.09x faster
• 1.10x faster

s390x

• 1.06x slower
• 1.19x faster
• 1.15x faster
• 1.14x faster
• 1.16x faster
• 1.15x faster
• 1.16x faster
• 1.19x faster

x86_64

• 1.05x faster
• 1.05x faster
• 1.05x faster
• 1.05x faster
• 1.09x faster
• 1.09x faster
• 1.07x faster
• 1.10x faster

Three builds still running, but you get the idea.

Take this with a grain of salt, the logs are full of:

WARNING: the benchmark result may be unstable
* the standard deviation (17.4 ns) is 24% of the mean (72.1 ns)
* the maximum (113 ns) is 57% greater than the mean (72.1 ns)
Try to rerun the benchmark with more runs, values and/or loops.
Run 'python -m pyperf system tune' command to reduce the system jitter.
Use pyperf stats, pyperf dump and pyperf hist