i965: Move VUE map computation to once at VS compile time.

With this and the previous patch, 640x480 nexuiz is running 0.169118%
+/- 0.0863696% faster (n=121).  On a VS state change microbenchmark,
performance is increased 8.28645% +/- 0.460478% (n=52).

v2: Fix CACHE_NEW_VS comment.

Reviewed-by: Kenneth Graunke <[email protected]>

1 files changed, 3 insertions, 6 deletions

diff --git a/src/mesa/drivers/dri/i965/gen7_sol_state.c b/src/mesa/drivers/dri/i965/gen7_sol_state.c
index 134153e6703..1a89503d2d5 100644
--- a/src/mesa/drivers/dri/i965/gen7_sol_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_sol_state.c
@@ -239,14 +239,11 @@ upload_sol_state(struct brw_context *brw)
    struct gl_transform_feedback_object *xfb_obj =
       ctx->TransformFeedback.CurrentObject;
    bool active = xfb_obj->Active && !xfb_obj->Paused;
-   struct brw_vue_map vue_map;
-
-   /* CACHE_NEW_VS_PROG */
-   brw_compute_vue_map(&vue_map, intel, brw->vs.prog_data);
 
    if (active) {
       upload_3dstate_so_buffers(brw);
-      upload_3dstate_so_decl_list(brw, &vue_map);
+      /* CACHE_NEW_VS_PROG */
+      upload_3dstate_so_decl_list(brw, &brw->vs.prog_data->vue_map);
 
       intel->batch.needs_sol_reset = true;
    }
@@ -256,7 +253,7 @@ upload_sol_state(struct brw_context *brw)
     * MMIO register updates (current performed by the kernel at each batch
     * emit).
     */
-   upload_3dstate_streamout(brw, active, &vue_map);
+   upload_3dstate_streamout(brw, active, &brw->vs.prog_data->vue_map);
 }
 
 const struct brw_tracked_state gen7_sol_state = {