RFR: 8365926: RISC-V: Performance regression in renaissance (chi-square) [v2]

[Robbin Ehn]

On Wed, 3 Sep 2025 08:13:24 GMT, Hamlin Li <mli at openjdk.org> wrote:

> > ```
> > Using trampolines:
> > ##############
> > --- Statistical Analysis ---
> > Average (Mean):     3610.00
> > Median:             3645.09
> > Standard Deviation: 297.11
> > --------------------------
> > 
> > Using load calls:
> > ##############
> > --- Statistical Analysis ---
> > Average (Mean):     3691.09
> > Median:             3793.11
> > Standard Deviation: 403.80
> > --------------------------
> > ```
> 
> Not sure if I understood the data right. Does this mean old trampolines perform better than new implementation related to benchmark chi-square?

As the averages are within one standard deviation from each other, it's not statistical certain.
But it do indicate that, but as I said without also backporting "8340241: RISC-V: Returns mispredicted", it's not so clear to me at least.

-------------

PR Comment: https://git.openjdk.org/jdk/pull/26944#issuecomment-3248205920