diff options
| author | Chris Wilson <[email protected]> | 2011-02-10 20:25:51 +0000 |
|---|---|---|
| committer | Chris Wilson <[email protected]> | 2011-02-21 12:59:35 +0000 |
| commit | 8d68a90e225d831a395ba788e425cb717eec1f9a (patch) | |
| tree | 1c46eb19125ebbb205625783dd184e0489231d01 /src/mesa/drivers/dri/i965/brw_queryobj.c | |
| parent | 3f55683927278e57f3ef8a151d15f4cffdc060dc (diff) | |
intel: use pwrite for batch
It's faster. Not only is the memcpy more efficiently performed in the
kernel (making up for the system call overhead), but by not using mmap
we remove the greater overhead of tracking the vma of every batch.
And it means we can read back from the batch buffer without incurring
the cost of a uncached read through the GTT.
Signed-off-by: Chris Wilson <[email protected]>
Diffstat (limited to 'src/mesa/drivers/dri/i965/brw_queryobj.c')
| -rw-r--r-- | src/mesa/drivers/dri/i965/brw_queryobj.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/src/mesa/drivers/dri/i965/brw_queryobj.c b/src/mesa/drivers/dri/i965/brw_queryobj.c index 656aad630a1..b41d05dd438 100644 --- a/src/mesa/drivers/dri/i965/brw_queryobj.c +++ b/src/mesa/drivers/dri/i965/brw_queryobj.c @@ -177,7 +177,7 @@ brw_end_query(struct gl_context *ctx, struct gl_query_object *q) ADVANCE_BATCH(); } - intel_batchbuffer_flush(intel->batch); + intel_batchbuffer_flush(intel); } else { /* Flush the batchbuffer in case it has writes to our query BO. * Have later queries write to a new query BO so that further rendering @@ -185,7 +185,7 @@ brw_end_query(struct gl_context *ctx, struct gl_query_object *q) */ if (query->bo) { brw_emit_query_end(brw); - intel_batchbuffer_flush(intel->batch); + intel_batchbuffer_flush(intel); drm_intel_bo_unreference(brw->query.bo); brw->query.bo = NULL; |