i965/cs: Setup surface binding for gl_NumWorkGroups

This will only be setup when the prog_data uses_num_work_groups
boolean is set.

At this point nothing will set uses_num_work_groups, but soon code
will set it when emitting code for the intrinsic that loads
gl_NumWorkGroups.

We can't emit this surface information earlier at the start of the
DispatchCompute* call because we may not have generated the program
yet. Until we generate the program, we don't know if the
gl_NumWorkGroups variable is accessed.

We also can't emit the surface as part of the brw_cs_state atom,
because we might not need the surface if gl_NumWorkGroups is not used
by the program.

Lastly, we cannot emit the surface later (after state upload) in the
DispatchCompute* call, because it needs to be run before the
brw_cs_state atom is emitted, since it changes the surface state.

Signed-off-by: Jordan Justen <[email protected]>
Reviewed-by: Kristian Høgsberg <[email protected]>

1 files changed, 4 insertions, 1 deletions

diff --git a/src/mesa/drivers/dri/i965/brw_context.h b/src/mesa/drivers/dri/i965/brw_context.h
index e407dec8eab..8b790fe0bca 100644
--- a/src/mesa/drivers/dri/i965/brw_context.h
+++ b/src/mesa/drivers/dri/i965/brw_context.h
@@ -213,6 +213,7 @@ enum brw_state_id {
    BRW_STATE_SAMPLER_STATE_TABLE,
    BRW_STATE_VS_ATTRIB_WORKAROUNDS,
    BRW_STATE_COMPUTE_PROGRAM,
+   BRW_STATE_CS_WORK_GROUPS,
    BRW_NUM_STATE_BITS
 };
 
@@ -294,6 +295,7 @@ enum brw_state_id {
 #define BRW_NEW_SAMPLER_STATE_TABLE     (1ull << BRW_STATE_SAMPLER_STATE_TABLE)
 #define BRW_NEW_VS_ATTRIB_WORKAROUNDS   (1ull << BRW_STATE_VS_ATTRIB_WORKAROUNDS)
 #define BRW_NEW_COMPUTE_PROGRAM         (1ull << BRW_STATE_COMPUTE_PROGRAM)
+#define BRW_NEW_CS_WORK_GROUPS          (1ull << BRW_STATE_CS_WORK_GROUPS)
 
 struct brw_state_flags {
    /** State update flags signalled by mesa internals */
@@ -497,6 +499,7 @@ struct brw_cs_prog_data {
    unsigned local_size[3];
    unsigned simd_size;
    bool uses_barrier;
+   bool uses_num_work_groups;
 
    struct {
       /** @{
@@ -1545,7 +1548,7 @@ struct brw_context
 
    int num_atoms[BRW_NUM_PIPELINES];
    const struct brw_tracked_state render_atoms[60];
-   const struct brw_tracked_state compute_atoms[6];
+   const struct brw_tracked_state compute_atoms[7];
 
    /* If (INTEL_DEBUG & DEBUG_BATCH) */
    struct {