diff options
| author | Pauli Nieminen <suokkos@gmail.com> | 2010-02-15 13:40:37 +0200 |
|---|---|---|
| committer | Michel Dänzer <michel@daenzer.net> | 2010-02-15 17:10:06 +0100 |
| commit | 78e7047c5235b09858b66dd3688d39aaa27d7589 (patch) | |
| tree | 9eebea9c29c1cf4b2b0648a64c220fdc4d2ad63a /src/radeon_legacy_memory.c | |
| parent | 3ec25e59854b6b03ad763bc374d3475a50f562d8 (diff) | |
Allocate Xv buffers to GTT.
KMS doesn't have acceleration for upload to vram. memcpy/memmove to VRAM
directly is very slow (40M/s in benchmark) which causes visible problems
to video.
Allocating video buffer in GTT will give good performance (350-450M/s)
for memmove operation. This is nice performance boost for Xv under KMS.
Signed-off-by: Pauli Nieminen <suokkos@gmail.com>
Diffstat (limited to 'src/radeon_legacy_memory.c')
| -rw-r--r-- | src/radeon_legacy_memory.c | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/src/radeon_legacy_memory.c b/src/radeon_legacy_memory.c index 02b95edc..bdf8ca26 100644 --- a/src/radeon_legacy_memory.c +++ b/src/radeon_legacy_memory.c @@ -15,7 +15,8 @@ uint32_t radeon_legacy_allocate_memory(ScrnInfoPtr pScrn, void **mem_struct, int size, - int align) + int align, + int domain) { ScreenPtr pScreen = screenInfo.screens[pScrn->scrnIndex]; RADEONInfoPtr info = RADEONPTR(pScrn); @@ -25,7 +26,7 @@ radeon_legacy_allocate_memory(ScrnInfoPtr pScrn, if (info->cs) { struct radeon_bo *video_bo; - video_bo = radeon_bo_open(info->bufmgr, 0, size, 4096, 0, 0); + video_bo = radeon_bo_open(info->bufmgr, 0, size, 4096, domain, 0); *mem_struct = video_bo; |