tree ed0d96d90686965d9ab41850716c5d28b84d29ea
parent d1e2e4f9ce4df50564f1244dcea9befc3066faa8
author Martin Jambor <mjambor@suse.cz> 1635338941 +0200
committer Martin Jambor <mjambor@suse.cz> 1635340307 +0200
gpgsig -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEE5elVTFt/d09Vsoczv2PBvD+kNUAFAmF5UBMACgkQv2PBvD+k
 NUBi/hAAs/GB+8zpzmSjog40Qt+YDrb64YCyAcoHgL6Ksmtzej1V4hg7kSbEbVq6
 K+qOEQN/zwE12GnHfijXlfsX+8WKrtOBdudZmU3ipWemk4PBjlYjqHmJsSop3Yid
 iVbO4F1XGHh3LEeXQBM+8nVpcsjtV9tZ79cTzAQBEduQ6l8e8GOxC+1xFag1MS/q
 H+tczwuh7m/in7A6PowRJJanOF7HIw4FqHphYVtJjPK9k9vFG+2tEIvHrh5pZ/N+
 DRLmXwfEMFwEyxZGWvMb4mhuRuPOlKuq7prrSwAdFiZLdz90hcM13BuQwIick9Jk
 WXAkPm3h9OEG/IAM3wgDP+nGQwK7AmFRGaA/llBeieNWywWh665yrGmkSwktEEeS
 a23ycLixzd9Jy0STIihb5BnX2DFd6jAhIm46Q/1KWm6tMJgGHspUf3WfKfp17oI7
 2jMI5gh21y5lmYoUsb9IfTUe17wzBP4OBehJn94zkkTzbqF5ZeRUF4tnLcWT3Vx0
 yj9WK23H0DfEYmwf4fxglkYtQXAuqTfaSoSRRcnEUHkH3PLPYp30z2tS6BL7063n
 iPIs9r/0yYTxDTy2nopwICmZdMSE3gXlVe97W+lawbLMqIe0DsLUlImE68rGF8si
 sJ1/QLtuunsGEOKawSVFEjvqZeDrvnHqyEYkqgxloeSPAZcQbDU=
 =8RI/
 -----END PGP SIGNATURE-----

ipa-cp: Select saner profile count to base heuristics on

When profile feedback is available, IPA-CP takes the count of the
hottest node and then evaluates all call contexts relative to it.
This means that typically almost no clones for specialized contexts
are ever created because the maximum is some special function, called
from everywhere (that is likely to get inlined anyway) and all the
examined edges look cold compared to it.

This patch changes the selection.  It simply sorts counts of all edges
eligible for cloning in a vector and then picks the count in 90th
percentile (the actual number is configurable via a parameter).

I also tried more complex approaches which were summing the counts and
picking the edge which together with all hotter edges accounted for a
given portion of the total sum of all edge counts.  But first it was
not apparently clear to me that they make more logical sense that the
simple method and practically I always also had to ignore a few
percent of the hottest edges with really extreme counts (looking at
bash and python).  And when I had to do that anyway, it seemed simpler
to just "ignore" more and take the first non-ignored count as the
base.

Nevertheless, if people think some more sophisticated method should be
used anyway, I am willing to be persuaded.  But this patch is a clear
improvement over the current situation.

gcc/ChangeLog:

2021-10-26  Martin Jambor  <mjambor@suse.cz>

	* params.opt (param_ipa_cp_profile_count_base): New parameter.
	* doc/invoke.texi (Optimize Options): Add entry for
	ipa-cp-profile-count-base.
	* ipa-cp.c (max_count): Replace with base_count, replace all
	occurrences too, unless otherwise stated.
	(ipcp_cloning_candidate_p): identify mostly-directly called
	functions based on their counts, not max_count.
	(compare_edge_profile_counts): New function.
	(ipcp_propagate_stage): Instead of setting max_count, find the
	appropriate edge count in a sorted vector of counts of eligible
	edges and make it the base_count.