Currently, the cost model uses formulas with predefined relative weights for alternative containers or container implementations. For instance, iterating through a vector is X times faster than iterating through a list.
(Under development.) We are working on customizing this to a particular machine by providing an automated way to compute the actual relative weights for operations on the given machine.
(Under development.) We plan to provide a performance parameter database format that can be filled in either by hand or by an automated training mechanism. The analysis module will then use this database instead of the built in. generic parameters.
@ 1.1.1.1.28.1 log @Sync with HEAD, resolve a couple of conflicts @ text @d2 1 a2 1
@ 1.1.1.2 log @import GCC 6.5.0. this is largely a maint release with no particularly features listed here: http://gcc.gnu.org/gcc-6/changes.html this fixes over 250 PRs in the GCC bugzilla: https://gcc.gnu.org/bugzilla/buglist.cgi?bug_status=RESOLVED&resolution=FIXED&target_milestone=6.5 @ text @d2 1 a2 1
@ 1.1.1.1.8.1 log @file profile_mode_cost_model.html was added on branch tls-maxphys on 2014-08-19 23:54:46 +0000 @ text @d1 17 @ 1.1.1.1.8.2 log @Rebase to HEAD as of a few days ago. @ text @a0 17
Currently, the cost model uses formulas with predefined relative weights for alternative containers or container implementations. For instance, iterating through a vector is X times faster than iterating through a list.
(Under development.) We are working on customizing this to a particular machine by providing an automated way to compute the actual relative weights for operations on the given machine.
(Under development.) We plan to provide a performance parameter database format that can be filled in either by hand or by an automated training mechanism. The analysis module will then use this database instead of the built in. generic parameters.
Currently, the cost model uses formulas with predefined relative weights for alternative containers or container implementations. For instance, iterating through a vector is X times faster than iterating through a list.
(Under development.) We are working on customizing this to a particular machine by providing an automated way to compute the actual relative weights for operations on the given machine.
(Under development.) We plan to provide a performance parameter database format that can be filled in either by hand or by an automated training mechanism. The analysis module will then use this database instead of the built in. generic parameters.