i965/fs: Compact the virtual GRF arrays.

During code generation, we create tons of temporary variables, many of
which get immediately killed and are never used.  Later optimization and
analysis passes, such as compute_live_intervals, loop over all the
virtual GRFs.  By compacting them, we can save a lot of overhead.

Reduces compilation time in L4D2's largest fragment shader from 10.2
seconds to 5.2 seconds (50%).  Drops compute_live_variables() from
10-12% of another game's startup time to 8%.

Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>

diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp
index 56cb447fafeab981e0f2948c32fa3215d161198b..777879e1241cf9cc1f93f7a1a70e768cc42f540a 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs.cpp
@@ -1102,6 +1102,64 @@ fs_visitor::split_virtual_grfs()
    this->live_intervals_valid = false;
 }
 
+/**
+ * Remove unused virtual GRFs and compact the virtual_grf_* arrays.
+ *
+ * During code generation, we create tons of temporary variables, many of
+ * which get immediately killed and are never used again.  Yet, in later
+ * optimization and analysis passes, such as compute_live_intervals, we need
+ * to loop over all the virtual GRFs.  Compacting them can save a lot of
+ * overhead.
+ */
+void
+fs_visitor::compact_virtual_grfs()
+{
+   /* Mark which virtual GRFs are used, and count how many. */
+   int remap_table[this->virtual_grf_count];
+   memset(remap_table, -1, sizeof(remap_table));
+
+   foreach_list(node, &this->instructions) {
+      const fs_inst *inst = (const fs_inst *) node;
+
+      if (inst->dst.file == GRF)
+         remap_table[inst->dst.reg] = 0;
+
+      for (int i = 0; i < 3; i++) {
+         if (inst->src[i].file == GRF)
+            remap_table[inst->src[i].reg] = 0;
+      }
+   }
+
+   /* Compact the GRF arrays. */
+   int new_index = 0;
+   for (int i = 0; i < this->virtual_grf_count; i++) {
+      if (remap_table[i] != -1) {
+         remap_table[i] = new_index;
+         virtual_grf_sizes[new_index] = virtual_grf_sizes[i];
+         if (live_intervals_valid) {
+            virtual_grf_use[new_index] = virtual_grf_use[i];
+            virtual_grf_def[new_index] = virtual_grf_def[i];
+         }
+         ++new_index;
+      }
+   }
+
+   this->virtual_grf_count = new_index;
+
+   /* Patch all the instructions to use the newly renumbered registers */
+   foreach_list(node, &this->instructions) {
+      fs_inst *inst = (fs_inst *) node;
+
+      if (inst->dst.file == GRF)
+         inst->dst.reg = remap_table[inst->dst.reg];
+
+      for (int i = 0; i < 3; i++) {
+         if (inst->src[i].file == GRF)
+            inst->src[i].reg = remap_table[inst->src[i].reg];
+      }
+   }
+}
+
 bool
 fs_visitor::remove_dead_constants()
 {
@@ -1860,6 +1918,8 @@ fs_visitor::run()
       do {
         progress = false;
 
+         compact_virtual_grfs();
+
         progress = remove_duplicate_mrf_writes() || progress;
 
         progress = opt_algebraic() || progress;

diff --git a/src/mesa/drivers/dri/i965/brw_fs.h b/src/mesa/drivers/dri/i965/brw_fs.h
index 0b2681d6cdd8de8346f0faa7b0fc5e02b2c4d7de..13662bb8836a19660e35441763364e6eac8759d4 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs.h
+++ b/src/mesa/drivers/dri/i965/brw_fs.h
@@ -240,6 +240,7 @@ public:
    int choose_spill_reg(struct ra_graph *g);
    void spill_reg(int spill_reg);
    void split_virtual_grfs();
+   void compact_virtual_grfs();
    void setup_pull_constants();
    void calculate_live_intervals();
    bool opt_algebraic();