"Ronald S. Bultje" <[email protected]> writes: > Hi, > > On Thu, Aug 2, 2012 at 7:38 AM, Måns Rullgård <[email protected]> wrote: >> "Ronald S. Bultje " <[email protected]> writes: >> >>> Module: libav >>> Branch: master >>> Commit: b6a3849adb0381a437952a785d39e22cb3b00282 >>> >>> Author: Ronald S. Bultje <[email protected]> >>> Committer: Ronald S. Bultje <[email protected]> >>> Date: Tue Jul 31 20:23:39 2012 -0700 >>> >>> fft: port FFT/IMDCT 3dnow functions to yasm, and disable on x86-64. >>> >>> 64-bit CPUs always have SSE available, thus there is no need to compile >>> in the 3dnow functions. This results in smaller binaries. >>> >>> --- >>> >>> libavcodec/x86/Makefile | 2 - >>> libavcodec/x86/fft.c | 2 + >>> libavcodec/x86/fft_3dn.c | 23 ----- >>> libavcodec/x86/fft_3dn2.c | 173 -------------------------------------- >>> libavcodec/x86/fft_mmx.asm | 196 >>> +++++++++++++++++++++++++++++++++++++------ >>> 5 files changed, 170 insertions(+), 226 deletions(-) >> >> Something in this commit seems to have broken IMDCT on AMD Bulldozer. > > Do we have a fate test that fails using a particular set of cpuflags?
The fate reports are public, you know: http://fate.libav.org/x86_64-bulldozer-linux-gcc-4.7/20120802133135 -- Måns Rullgård [email protected] _______________________________________________ libav-devel mailing list [email protected] https://lists.libav.org/mailman/listinfo/libav-devel
