diff options
| author | Roland Scheidegger <rscheidegger_lists@hispeed.ch> | 2013-09-17 23:58:37 +0100 |
|---|---|---|
| committer | Roland Scheidegger <rscheidegger_lists@hispeed.ch> | 2013-09-17 23:58:37 +0100 |
| commit | b0fa6cab5e64886d3f47156a049c5d1b85dcabd9 (patch) | |
| tree | 77a1c17d3db18e0b107ec1d108493711f5e6da4a | |
| parent | 88adea15db8b5bd937b018f7ddf19c03a02a94f4 (diff) | |
| download | xine-lib-b0fa6cab5e64886d3f47156a049c5d1b85dcabd9.tar.gz xine-lib-b0fa6cab5e64886d3f47156a049c5d1b85dcabd9.tar.bz2 | |
Emit vzeroupper after avx memcpy
Emitting vzeroupper is necessary to avoid avx<->sse transition penalties (when
using avx-256 instructions).
This didn't really matter much in the past, since other code wasn't using avx,
hence there was just a penalty once afterwards when sse code was executed.
However, there's code in ffmpeg which mixes avx-128 and sse a lot, and each
time this happens there's a huge penalty. This causes in particular
ff_deblock_v_luma_8_avx to slow down by a factor of 50 or so which makes the
whole decoding about twice as slow (might be dependent on the h264 stream or
maybe ffmpeg version too, since ffmpeg will also emit vzeroupper when using
avx-256 hence not doing it here might not always be an issue, but in the case
I was seeing nothing else used avx-256).
| -rw-r--r-- | src/xine-utils/memcpy.c | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/src/xine-utils/memcpy.c b/src/xine-utils/memcpy.c index 6eda220ed..a59f4e67a 100644 --- a/src/xine-utils/memcpy.c +++ b/src/xine-utils/memcpy.c @@ -251,6 +251,7 @@ static void * sse_memcpy(void * to, const void * from, size_t len) /* since movntq is weakly-ordered, a "sfence" * is needed to become ordered again. */ __asm__ __volatile__ ("sfence":::"memory"); + __asm__ __volatile__ ("vzeroupper"); } /* * Now do the tail of the block |