diff options
| author | Pauli Nieminen <suokkos@gmail.com> | 2010-02-15 13:45:28 +0200 |
|---|---|---|
| committer | Michel Dänzer <daenzer@vmware.com> | 2010-02-15 16:48:06 +0100 |
| commit | 3ec25e59854b6b03ad763bc374d3475a50f562d8 (patch) | |
| tree | 2ae091fb70ef837162e64f48bd8d6abe02a2eadf /src/radeon_accel.c | |
| parent | 221ef11b31756deb7134801730e76c040e841f5c (diff) | |
Use memcpy instead of memove for RADEONSwapCopy.
memcpy has about 25% better performance than memmove when
destination is GTT (wc caching). Changing memmove to memcpy
in SwapCopy will reduce CPU time spent moving data between
host and GPU.
memcpy will specially help Xv when playing high resolution
videos.
The swap path doesn't support overlapping memory copies either
so extra safety is not worth the performance hit in commonly
used code path.
Signed-off-by: Pauli Nieminen <suokkos@gmail.com>
[ Michel Dänzer: Fixed up whitespace ]
Diffstat (limited to 'src/radeon_accel.c')
| -rw-r--r-- | src/radeon_accel.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/src/radeon_accel.c b/src/radeon_accel.c index 02905dd1..f0d94c30 100644 --- a/src/radeon_accel.c +++ b/src/radeon_accel.c @@ -980,7 +980,7 @@ void RADEONCopySwap(uint8_t *dst, uint8_t *src, unsigned int size, int swap) } } if (src != dst) - memmove(dst, src, size); + memcpy(dst, src, size); } /* Copies a single pass worth of data for a hostdata blit set up by |