i965/fs: Use a single instance of the pull_constant_loc[] array.

Now that we don't renumber uniform registers, assign_constant_locations
and move_uniform_array_access_to_pull_constants use the same names.
So, they can share a single copy of the pull_constant_loc[] array.

This simplifies the code considerably.  assign_constant_locations()
doesn't need to walk through pull_params[] to rediscover reladdr
demotions; it just has that information in pull_constant_loc[].  We also
only need to rewrite the instruction stream once, instead of twice.

Even better, we now have a single array describing the layout of
all pull parameters, which we can pass to the SIMD16 program.

This actually hurts a few shaders in Serious Sam 3, and one in KWin:
total instructions in shared programs: 1841957 -> 1842035 (0.00%)
instructions in affected programs:     1165 -> 1243 (6.70%)
Comparing dump_instructions() before and after the pull constant
transformations with and without this patch, it appears that there is
a uniform array with variable indexing (reladdr) and constant indexing
(of array element 0).  Previously, we uploaded array element 0 as both
a pull constant (for reladdr) /and/ a push constant.

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Reviewed-by: Eric Anholt <eric@anholt.net>

diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp
index eca5a9b6c1b06603dcc51bf583b7afe5ece7d492..054bed544b6547a6a22d283cc6b6d1b859304966 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs.cpp
@@ -1786,10 +1786,6 @@ fs_visitor::move_uniform_array_access_to_pull_constants()
          }
       }
    }
-   demote_pull_constants(true);
-
-   ralloc_free(pull_constant_loc);
-   pull_constant_loc = NULL;
 }
 
 /**
@@ -1836,9 +1832,6 @@ fs_visitor::assign_constant_locations()
    unsigned int num_push_constants = 0;
 
    push_constant_loc = ralloc_array(mem_ctx, int, uniforms);
-   pull_constant_loc = ralloc_array(mem_ctx, int, uniforms);
-   for (unsigned int i = 0; i < uniforms; i++)
-      pull_constant_loc[i] = -1;
 
    for (unsigned int i = 0; i < uniforms; i++) {
       if (!is_live[i] || pull_constant_loc[i] != -1) {
@@ -1858,20 +1851,9 @@ fs_visitor::assign_constant_locations()
          /* Demote to a pull constant. */
          push_constant_loc[i] = -1;
 
-         /* If our constant is already being uploaded for reladdr purposes,
-          * reuse it.
-          */
-         for (unsigned int j = 0; j < stage_prog_data->nr_pull_params; j++) {
-            if (stage_prog_data->pull_param[j] == stage_prog_data->param[i]) {
-               pull_constant_loc[i] = j;
-               break;
-            }
-         }
-         if (pull_constant_loc[i] == -1) {
-            int pull_index = stage_prog_data->nr_pull_params++;
-            stage_prog_data->pull_param[pull_index] = stage_prog_data->param[i];
-            pull_constant_loc[i] = pull_index;
-         }
+         int pull_index = stage_prog_data->nr_pull_params++;
+         stage_prog_data->pull_param[pull_index] = stage_prog_data->param[i];
+         pull_constant_loc[i] = pull_index;
       }
    }
 
@@ -1890,8 +1872,6 @@ fs_visitor::assign_constant_locations()
       assert(remapped <= i);
       stage_prog_data->param[remapped] = stage_prog_data->param[i];
    }
-
-   demote_pull_constants(false);
 }
 
 /**
@@ -1899,7 +1879,7 @@ fs_visitor::assign_constant_locations()
  * or VARYING_PULL_CONSTANT_LOAD instructions which load values into VGRFs.
  */
 void
-fs_visitor::demote_pull_constants(bool reladdr_only)
+fs_visitor::demote_pull_constants()
 {
    foreach_list(node, &this->instructions) {
       fs_inst *inst = (fs_inst *)node;
@@ -1920,9 +1900,6 @@ fs_visitor::demote_pull_constants(bool reladdr_only)
          fs_reg surf_index(stage_prog_data->binding_table.pull_constants_start);
          fs_reg dst = fs_reg(this, glsl_type::float_type);
 
-         if (reladdr_only != (inst->src[i].reladdr != NULL))
-            continue;
-
          /* Generate a pull load into dst. */
          if (inst->src[i].reladdr) {
             exec_list list = VARYING_PULL_CONSTANT_LOAD(dst,
@@ -3382,6 +3359,7 @@ fs_visitor::run()
 
       move_uniform_array_access_to_pull_constants();
       assign_constant_locations();
+      demote_pull_constants();
 
       opt_drop_redundant_mov_to_flags();
 

diff --git a/src/mesa/drivers/dri/i965/brw_fs.h b/src/mesa/drivers/dri/i965/brw_fs.h
index 5733a497ddb2aea03a2a835c38f8ce1df0099015..9de1f3a0a8a40eeb83458c5740b8dc8337973591 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs.h
+++ b/src/mesa/drivers/dri/i965/brw_fs.h
@@ -358,7 +358,7 @@ public:
    void compact_virtual_grfs();
    void move_uniform_array_access_to_pull_constants();
    void assign_constant_locations();
-   void demote_pull_constants(bool reladdr_only);
+   void demote_pull_constants();
    void invalidate_live_intervals();
    void calculate_live_intervals();
    void calculate_register_pressure();