On Wed, Jan 22, 2014 at 12:42 PM, Ylinen, Mikko <mikko.yli...@intel.com> wrote:
> I verified the numbers and used test/splash.bmp as the source image. > Looks like test/splash.bmp only adds 10ms more compared with BGRX. > > My original BMP is 24bit, no alpha. As far as I can tell this is the same > as test/splash.bmp but without alpha channel. Oh, so if we detect that we do not need to blend, which is probably the most expensive part, we should be in the same area as the original, I guess. What are your relative numbers, do the 10ms matter or is it already good enough? Thanks, Kay _______________________________________________ systemd-devel mailing list systemd-devel@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/systemd-devel