vc4: Skip re-emitting the shader_rec if it's unchanged.

It's a bunch of work for us to emit it (and its uniforms), more work for
the kernel to validate it, and additional work for the CLE to read
it. Improves es2gears framerate by about 50%.

Signed-off-by: Eric Anholt <[email protected]>

1 files changed, 15 insertions, 2 deletions

diff --git a/src/gallium/drivers/vc4/vc4_program.c b/src/gallium/drivers/vc4/vc4_program.c
index 561da1074ce..a35b50cd39b 100644
--- a/src/gallium/drivers/vc4/vc4_program.c
+++ b/src/gallium/drivers/vc4/vc4_program.c
@@ -2205,6 +2205,8 @@ copy_uniform_state_to_shader(struct vc4_compiled_shader *shader,
         memcpy(uinfo->contents, c->uniform_contents,
                count * sizeof(*uinfo->contents));
         uinfo->num_texture_samples = c->num_texture_samples;
+
+        vc4_set_shader_uniform_dirty_flags(shader);
 }
 
 static struct vc4_compiled_shader *
@@ -2440,9 +2442,20 @@ vc4_update_compiled_vs(struct vc4_context *vc4, uint8_t prim_mode)
                 (prim_mode == PIPE_PRIM_POINTS &&
                  vc4->rasterizer->base.point_size_per_vertex);
 
-        vc4->prog.vs = vc4_get_compiled_shader(vc4, QSTAGE_VERT, &key->base);
+        struct vc4_compiled_shader *vs =
+                vc4_get_compiled_shader(vc4, QSTAGE_VERT, &key->base);
+        if (vs != vc4->prog.vs) {
+                vc4->prog.vs = vs;
+                vc4->dirty |= VC4_DIRTY_COMPILED_VS;
+        }
+
         key->is_coord = true;
-        vc4->prog.cs = vc4_get_compiled_shader(vc4, QSTAGE_COORD, &key->base);
+        struct vc4_compiled_shader *cs =
+                vc4_get_compiled_shader(vc4, QSTAGE_COORD, &key->base);
+        if (cs != vc4->prog.cs) {
+                vc4->prog.cs = cs;
+                vc4->dirty |= VC4_DIRTY_COMPILED_CS;
+        }
 }
 
 void