Did some experiments removing always_inline from blend_pixels to see what performance difference was: https://treeherder.mozilla.org/perfherder/compare?originalProject=try&newProject=try&newRevision=6a176b1e685fa622fb15be32afab1a6c008c211c&framework=1&selectedTimeRange=172800 Looks like there are performance regressions between 9% and 26% (tsvg, tscroll, etc). So pretty much looks like what I remember. Not inlining this function really hurts us.
Bug 1700520 Comment 16 Edit History
Note: The actual edited comment in the bug view page will always show the original commenter’s name and original timestamp.
Did some experiments removing always_inline from blend_pixels to see what performance difference was as of recently: https://treeherder.mozilla.org/perfherder/compare?originalProject=try&newProject=try&newRevision=6a176b1e685fa622fb15be32afab1a6c008c211c&framework=1&selectedTimeRange=172800 Looks like there are performance regressions between 9% and 26% (tsvg, tscroll, etc). So pretty much looks like what I remember. Not inlining this function really hurts us.
Did some experiments removing always_inline from blend_pixels to see what performance difference was as of recently: https://treeherder.mozilla.org/perfherder/compare?originalProject=try&newProject=try&newRevision=6a176b1e685fa622fb15be32afab1a6c008c211c&framework=1&selectedTimeRange=172800 Looks like there are performance regressions between 9% and 26% (tsvg, tscroll, etc), even on the shippable builds. So pretty much looks like what I remember. Not inlining this function really hurts us.