From: Matt Turner <mattst88@gmail.com>
Date: Wed, 29 Oct 2014 03:12:21 +0000 (-0700)
Subject: i965/fs: Dead code eliminate instructions writing the flag.
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=60d507c3c5c7caed57119df0ab4d824ad1ea85dc;p=mesa.git

i965/fs: Dead code eliminate instructions writing the flag.

Most prominently helps Natural Selection 2, which has a surprising
number shaders that do very complicated things before drawing black.

instructions in affected programs:     21052 -> 16978 (-19.35%)

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
---

diff --git a/src/mesa/drivers/dri/i965/brw_fs_dead_code_eliminate.cpp b/src/mesa/drivers/dri/i965/brw_fs_dead_code_eliminate.cpp
index 9cf8d89eef4..fa471829e8e 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_dead_code_eliminate.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_dead_code_eliminate.cpp
@@ -43,15 +43,16 @@ fs_visitor::dead_code_eliminate()
 
    int num_vars = live_intervals->num_vars;
    BITSET_WORD *live = ralloc_array(NULL, BITSET_WORD, BITSET_WORDS(num_vars));
+   BITSET_WORD *flag_live = ralloc_array(NULL, BITSET_WORD, 1);
 
    foreach_block (block, cfg) {
       memcpy(live, live_intervals->block_data[block->num].liveout,
              sizeof(BITSET_WORD) * BITSET_WORDS(num_vars));
+      memcpy(flag_live, live_intervals->block_data[block->num].flag_liveout,
+             sizeof(BITSET_WORD));
 
       foreach_inst_in_block_reverse(fs_inst, inst, block) {
-         if (inst->dst.file == GRF &&
-             !inst->has_side_effects() &&
-             !inst->writes_flag()) {
+         if (inst->dst.file == GRF && !inst->has_side_effects()) {
             bool result_live = false;
 
             if (inst->regs_written == 1) {
@@ -67,7 +68,7 @@ fs_visitor::dead_code_eliminate()
             if (!result_live) {
                progress = true;
 
-               if (inst->writes_accumulator) {
+               if (inst->writes_accumulator || inst->writes_flag()) {
                   inst->dst = fs_reg(retype(brw_null_reg(), inst->dst.type));
                } else {
                   inst->opcode = BRW_OPCODE_NOP;
@@ -76,6 +77,14 @@ fs_visitor::dead_code_eliminate()
             }
          }
 
+         if (inst->dst.is_null() && inst->writes_flag()) {
+            if (!BITSET_TEST(flag_live, inst->flag_subreg)) {
+               inst->opcode = BRW_OPCODE_NOP;
+               progress = true;
+               continue;
+            }
+         }
+
          if (inst->dst.file == GRF) {
             if (!inst->is_partial_write()) {
                int var = live_intervals->var_from_reg(&inst->dst);
@@ -85,6 +94,10 @@ fs_visitor::dead_code_eliminate()
             }
          }
 
+         if (inst->writes_flag()) {
+            BITSET_CLEAR(flag_live, inst->flag_subreg);
+         }
+
          for (int i = 0; i < inst->sources; i++) {
             if (inst->src[i].file == GRF) {
                int var = live_intervals->var_from_reg(&inst->src[i]);
@@ -94,10 +107,15 @@ fs_visitor::dead_code_eliminate()
                }
             }
          }
+
+         if (inst->reads_flag()) {
+            BITSET_SET(flag_live, inst->flag_subreg);
+         }
       }
    }
 
    ralloc_free(live);
+   ralloc_free(flag_live);
 
    if (progress) {
       foreach_block_and_inst_safe (block, backend_instruction, inst, cfg) {