We may extend m_scratch to avoid write beyond bound bug, it give us more performance.
btw: I put check code in C model before, but when I merge patch to hg tree, I lost it. At 2015-11-04 22:34:33,[email protected] wrote: ># HG changeset patch ># User Dnyaneshwar G <[email protected]> ># Date 1446645042 -19800 ># Wed Nov 04 19:20:42 2015 +0530 ># Node ID 25bada1bb5494fc12d62e87d1b7b788307dd963f ># Parent c11dd97a8b999414c60dceef8620d3d9055cf4c1 >asm: fix mbtree_propagate_cost asm failure, fixes crash in OpenBSD > >The SSE2 asm code reads and write extra 4 bytes if loop counter is not multiple >of 2 as SSE2 asm code process 2 int values in single iteration > >The AVX asm code reads and write extra 4,8 or 12 bytes if loop counter is not >multiple of 4 as AVX asm code process 4 int values in single iteration >
_______________________________________________ x265-devel mailing list [email protected] https://mailman.videolan.org/listinfo/x265-devel
