i965: Convert the binding table to streamed indirect state.

This slightly reduces reduces cairo-gl firefox-talos-gfx runtime on my
Ironlake:
before:
[ # ]  backend                         test   min(s) median(s) stddev. count
[  0]       gl            firefox-talos-gfx   38.236   38.383   0.43%    5/6
after:
[  0]       gl            firefox-talos-gfx   37.799   38.203   0.39%    6/6

It turns out the cost of caching these objects and looking them up in
the cache again is greater than the cost of just computing the object
again, particularly when the overhead of having a separate BO to pin
is removed.

(Those that are paying close attention will note that this is a
reversal of the path I was moving the driver in a couple of years ago.
The major thing that has changed is that back then all state was
recomputed when we wrapped the streaming state buffer, including
recompiling our precious programs.  Now, we're uncaching just the
objects that are cheap to compute, and retaining caching of expensive
objects)

1 files changed, 3 insertions, 1 deletions

diff --git a/src/mesa/drivers/dri/i965/brw_state_upload.c b/src/mesa/drivers/dri/i965/brw_state_upload.c
index 08535bb59c..e345dbcf5b 100644
--- a/src/mesa/drivers/dri/i965/brw_state_upload.c
+++ b/src/mesa/drivers/dri/i965/brw_state_upload.c
@@ -69,6 +69,7 @@ static const struct brw_tracked_state *gen4_atoms[] =
    &brw_vs_surfaces,		/* must do before unit */
    &brw_wm_constant_surface,	/* must do before wm surfaces/bind bo */
    &brw_wm_surfaces,		/* must do before samplers and unit */
+   &brw_wm_binding_table,
    &brw_wm_samplers,
 
    &brw_wm_unit,
@@ -268,6 +269,8 @@ static struct dirty_bit_map brw_bits[] = {
    DEFINE_BIT(BRW_NEW_CONTEXT),
    DEFINE_BIT(BRW_NEW_WM_INPUT_DIMENSIONS),
    DEFINE_BIT(BRW_NEW_PSP),
+   DEFINE_BIT(BRW_NEW_WM_SURFACES),
+   DEFINE_BIT(BRW_NEW_BINDING_TABLE),
    DEFINE_BIT(BRW_NEW_INDICES),
    DEFINE_BIT(BRW_NEW_INDEX_BUFFER),
    DEFINE_BIT(BRW_NEW_VERTICES),
@@ -295,7 +298,6 @@ static struct dirty_bit_map cache_bits[] = {
    DEFINE_BIT(CACHE_NEW_CLIP_UNIT),
    DEFINE_BIT(CACHE_NEW_CLIP_PROG),
    DEFINE_BIT(CACHE_NEW_SURFACE),
-   DEFINE_BIT(CACHE_NEW_SURF_BIND),
    {0, 0, 0}
 };