i965/gs: Use new NIR intrinsics.

By performing the vertex counting in NIR, we're able to elide a ton of
useless safety checks around every EmitVertex() call:

total instructions in shared programs: 3952 -> 3720 (-5.87%)
instructions in affected programs:     3491 -> 3259 (-6.65%)
helped:                                11
HURT:                                  0

Improves performance in Gl32GSCloth by 0.671742% +/- 0.142202% (n=621)
on Haswell GT3e at 1024x768.

This should also make it easier to implement Broadwell's "Static Vertex
Count" feature someday.

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Jason Ekstrand <jason.ekstrand@intel.com>

1 files changed, 11 insertions, 2 deletions

diff --git a/src/mesa/drivers/dri/i965/brw_vec4_gs_nir.cpp b/src/mesa/drivers/dri/i965/brw_vec4_gs_nir.cpp
index 8a8dd57..4f4e1e1 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4_gs_nir.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_gs_nir.cpp
@@ -92,16 +92,25 @@ vec4_gs_visitor::nir_emit_intrinsic(nir_intrinsic_instr *instr)
    src_reg src;
 
    switch (instr->intrinsic) {
-   case nir_intrinsic_emit_vertex: {
+   case nir_intrinsic_emit_vertex_with_counter: {
+      this->vertex_count =
+         retype(get_nir_src(instr->src[0], 1), BRW_REGISTER_TYPE_UD);
       int stream_id = instr->const_index[0];
       gs_emit_vertex(stream_id);
       break;
    }
 
-   case nir_intrinsic_end_primitive:
+   case nir_intrinsic_end_primitive_with_counter:
+      this->vertex_count =
+         retype(get_nir_src(instr->src[0], 1), BRW_REGISTER_TYPE_UD);
       gs_end_primitive();
       break;
 
+   case nir_intrinsic_set_vertex_count:
+      this->vertex_count =
+         retype(get_nir_src(instr->src[0], 1), BRW_REGISTER_TYPE_UD);
+      break;
+
    case nir_intrinsic_load_invocation_id: {
       src_reg invocation_id =
          src_reg(nir_system_values[SYSTEM_VALUE_INVOCATION_ID]);