Performance

From OLPC
Revision as of 03:23, 16 March 2008 by Mstone (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

To date, many parts of our software stack have implementations which optimized writing time, ease of manipulation, and compatibility with upstream code rather than running time. As a result, there's a lot of performance work that needs to be done. Two areas which are particularly ripe for improvement include the activity launching process (which Tomeu is working on) and the boot process (which Mitch Bradley cares about).

(Note: recognizing that some of the more adventurous "improvements" may introduce noticeable regressions into the stack, we have created a new build branch called faster in order to isolate the effect of dangerous changes. Please make your changes there.)