radeonsi/gfx10: implement streamout-related queries

The NGG hardware pipeline doesn't track these statistics automatically,
and in fact *cannot* track them automatically when API geometry shaders
are involved, so we accumulate statistics in the shader using atomic
adds.

This implementation accumulates statistics via the memory system and
the RW buffer descriptor setup. We could use GDS, but since these
atomics aren't latency-sensitive, that basically just trades off
L2$ bandwidth vs. export bus bandwidth. One single memory transaction
per shader workgroup doesn't seem too bad. The result ring buffer in
memory is needed either way to avoid pipeline stalls.

The shader code contains the atomic unconditionally, though the
GFX10_GS_QUERY_BUF is a null buffer when no queries are active. The
atomic is simply discarded by the shader hardware in that case.

Acked-by: Bas Nieuwenhuizen <[email protected]>

1 files changed, 3 insertions, 0 deletions

diff --git a/src/gallium/drivers/radeonsi/si_state.h b/src/gallium/drivers/radeonsi/si_state.h
index 678f87cd73d..757dd1bf5cd 100644
--- a/src/gallium/drivers/radeonsi/si_state.h
+++ b/src/gallium/drivers/radeonsi/si_state.h
@@ -228,6 +228,7 @@ union si_state_atoms {
 		struct si_atom spi_map;
 		struct si_atom scratch_state;
 		struct si_atom window_rectangles;
+		struct si_atom shader_query;
 	} s;
 	struct si_atom array[0];
 };
@@ -370,6 +371,8 @@ enum {
 	SI_PS_IMAGE_COLORBUF0_FMASK,
 	SI_PS_IMAGE_COLORBUF0_FMASK_HI,
 
+	GFX10_GS_QUERY_BUF,
+
 	SI_NUM_RW_BUFFERS,
 };