nvc0: add compute invocation counter

The strategy is to keep a CPU-side counter of the direct invocations,
and a GPU-side counter of the indirect invocations, and then add them
together for queries.

The specific technique is a macro which multiplies a list of integers
together and accumulates the product into SCRATCH registers held inside
of the context. Another macro will read those values out and add them to
the passed-in cpu-side counter to be stored in a query buffer the same
way that all the other statistics are stored.

Original implementation by Rhys Perry, redone by Ilia Mirkin to use the
SCRATCH temporaries.

Signed-off-by: Ilia Mirkin <[email protected]>

1 files changed, 2 insertions, 0 deletions

diff --git a/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c b/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c
index 216fba49d9e..6a79fd9a903 100644
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c
@@ -1308,6 +1308,8 @@ nvc0_screen_create(struct nouveau_device *dev)
    MK_MACRO(NVC0_3D_MACRO_DRAW_ELEMENTS_INDIRECT_COUNT, mme9097_draw_elts_indirect_count);
    MK_MACRO(NVC0_3D_MACRO_QUERY_BUFFER_WRITE, mme9097_query_buffer_write);
    MK_MACRO(NVC0_3D_MACRO_CONSERVATIVE_RASTER_STATE, mme9097_conservative_raster_state);
+   MK_MACRO(NVC0_3D_MACRO_COMPUTE_COUNTER, mme9097_compute_counter);
+   MK_MACRO(NVC0_3D_MACRO_COMPUTE_COUNTER_TO_QUERY, mme9097_compute_counter_to_query);
    MK_MACRO(NVC0_CP_MACRO_LAUNCH_GRID_INDIRECT, mme90c0_launch_grid_indirect);
 
    BEGIN_NVC0(push, NVC0_3D(RASTERIZE_ENABLE), 1);