i965/fs: Take into account lower frequency of conditional blocks in spilling cost...

The individual branches of an if/else/endif construct will be executed
some unknown number of times between 0 and 1 relative to the parent
block.  Use some factor in between as weight while approximating the
cost of spill/fill instructions within a conditional if-else branch.
This favors spilling registers used within conditional branches which
are likely to be executed less frequently than registers used at the
top level.

Improves the framerate of the SynMark2 OglCSDof benchmark by ~1.9x on
my SKL GT4e.  Should have a comparable effect on other platforms.  No
significant regressions.

Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>

diff --git a/src/intel/compiler/brw_fs_reg_allocate.cpp b/src/intel/compiler/brw_fs_reg_allocate.cpp
index 5c6f3d490f01185e94f1aafd9ce39c17c2e89708..c981d72e4f2e664b7cecda4d7072a84c807b2e3c 100644 (file)
--- a/src/intel/compiler/brw_fs_reg_allocate.cpp
+++ b/src/intel/compiler/brw_fs_reg_allocate.cpp
@@ -806,7 +806,7 @@ emit_spill(const fs_builder &bld, fs_reg src,
 int
 fs_visitor::choose_spill_reg(struct ra_graph *g)
 {
-   float loop_scale = 1.0;
+   float block_scale = 1.0;
    float spill_costs[this->alloc.count];
    bool no_spill[this->alloc.count];
 
@@ -822,23 +822,32 @@ fs_visitor::choose_spill_reg(struct ra_graph *g)
    foreach_block_and_inst(block, fs_inst, inst, cfg) {
       for (unsigned int i = 0; i < inst->sources; i++) {
         if (inst->src[i].file == VGRF)
-            spill_costs[inst->src[i].nr] += loop_scale;
+            spill_costs[inst->src[i].nr] += block_scale;
       }
 
       if (inst->dst.file == VGRF)
          spill_costs[inst->dst.nr] += DIV_ROUND_UP(inst->size_written, REG_SIZE)
-                                      * loop_scale;
+                                      * block_scale;
 
       switch (inst->opcode) {
 
       case BRW_OPCODE_DO:
-        loop_scale *= 10;
+        block_scale *= 10;
         break;
 
       case BRW_OPCODE_WHILE:
-        loop_scale /= 10;
+        block_scale /= 10;
         break;
 
+      case BRW_OPCODE_IF:
+      case BRW_OPCODE_IFF:
+         block_scale *= 0.5;
+         break;
+
+      case BRW_OPCODE_ENDIF:
+         block_scale /= 0.5;
+         break;
+
       case SHADER_OPCODE_GEN4_SCRATCH_WRITE:
         if (inst->src[0].file == VGRF)
             no_spill[inst->src[0].nr] = true;