Re: [Starpu-devel] Problem with performance model calibration

[Mirko Myllykoski <mirkom@cs.umu.se>]

On 2020-06-09 13:16, Samuel Thibault wrote:
> Mirko Myllykoski, le mar. 09 juin 2020 12:44:00 +0200, a ecrit:
> > In particular, you can see that the "c" parameter is quite small for the
> > CUDA implementation:
>
> Indeed, and also for the CPU case c is bogus, even if to a lesser
> extent. Looking at _starpu_regression_non_linear_power, I see that it
> starts its dichotomy for c in [0, min(averages)]. But with the noisy
> results that you have, taking the minimum is not a good idea: e.g. in
> the CUDA case the minimum average is around 0.004-0.005, but only a few
> of the averages have this value. Taking the minimum was meant to make
> the dichotomy faster, but with noisy data it doesn't seem like a good
> idea. We still need some initial maximum value for the dichotomy, but we
> could use the maximum average, or even a coefficiented average of the
> average.
>
> Could you give a try to converting find_list_min into find_list_max, and
> using that for the initial value of cmax?

That is going to cause problems due to the log(y[i]-c) statement in the 
test_r, compute_b and compute_a functions (negative argument for log).

 - Mirko