From: Matt Turner <mattst88@gmail.com>
Date: Wed, 19 Mar 2014 02:19:02 +0000 (-0700)
Subject: i965/vec4: Eliminate dead writes to the flag register.
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=764e25d79dad3096274ab2df04f5aa3ffb232119;p=mesa.git

i965/vec4: Eliminate dead writes to the flag register.

For each write, search previous instructions for unread writes to the
flag register and remove them. Note that this will not eliminate the
last unread write.

total instructions in shared programs: 788074 -> 788004 (-0.01%)
instructions in affected programs:     4930 -> 4860 (-1.42%)

Reviewed-by: Eric Anholt <eric@anholt.net>
---

diff --git a/src/mesa/drivers/dri/i965/brw_vec4.cpp b/src/mesa/drivers/dri/i965/brw_vec4.cpp
index e9219a9aa5e..4ae60208f2c 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4.cpp
@@ -381,35 +381,53 @@ vec4_visitor::dead_code_eliminate()
 
       seen_control_flow = inst->is_control_flow() || seen_control_flow;
 
-      if (inst->dst.file != GRF || inst->has_side_effects())
+      if (inst->has_side_effects())
          continue;
 
-      int write_mask = inst->dst.writemask;
+      bool inst_writes_flag = false;
+      if (inst->dst.file != GRF) {
+         if (inst->dst.is_null() && inst->writes_flag()) {
+            inst_writes_flag = true;
+         } else {
+            continue;
+         }
+      }
 
-      for (int c = 0; c < 4; c++) {
-         if (write_mask & (1 << c)) {
-            assert(this->virtual_grf_end[inst->dst.reg * 4 + c] >= pc);
-            if (this->virtual_grf_end[inst->dst.reg * 4 + c] == pc) {
-               write_mask &= ~(1 << c);
+      if (inst->dst.file == GRF) {
+         int write_mask = inst->dst.writemask;
+
+         for (int c = 0; c < 4; c++) {
+            if (write_mask & (1 << c)) {
+               assert(this->virtual_grf_end[inst->dst.reg * 4 + c] >= pc);
+               if (this->virtual_grf_end[inst->dst.reg * 4 + c] == pc) {
+                  write_mask &= ~(1 << c);
+               }
             }
          }
-      }
 
-      progress = try_eliminate_instruction(inst, write_mask) || progress;
+         progress = try_eliminate_instruction(inst, write_mask) || progress;
+      }
 
       if (seen_control_flow || inst->predicate || inst->prev == NULL)
          continue;
 
-      int dead_channels = inst->dst.writemask;
+      int dead_channels;
+      if (inst_writes_flag) {
+/* Arbitrarily chosen, other than not being an xyzw writemask. */
+#define FLAG_WRITEMASK (1 << 5)
+         dead_channels = inst->reads_flag() ? 0 : FLAG_WRITEMASK;
+      } else {
+         dead_channels = inst->dst.writemask;
 
-      for (int i = 0; i < 3; i++) {
-         if (inst->src[i].file != GRF ||
-             inst->src[i].reg != inst->dst.reg)
-               continue;
+         for (int i = 0; i < 3; i++) {
+            if (inst->src[i].file != GRF ||
+                inst->src[i].reg != inst->dst.reg)
+                  continue;
 
-         for (int j = 0; j < 4; j++) {
-            int swiz = BRW_GET_SWZ(inst->src[i].swizzle, j);
-            dead_channels &= ~(1 << swiz);
+            for (int j = 0; j < 4; j++) {
+               int swiz = BRW_GET_SWZ(inst->src[i].swizzle, j);
+               dead_channels &= ~(1 << swiz);
+            }
          }
       }
 
@@ -418,9 +436,21 @@ vec4_visitor::dead_code_eliminate()
            node = prev, prev = prev->prev) {
          vec4_instruction *scan_inst = (vec4_instruction  *)node;
 
-         if (scan_inst->dst.file != GRF || scan_inst->has_side_effects())
+         if (scan_inst->has_side_effects())
             continue;
 
+         if (inst_writes_flag) {
+            if (scan_inst->dst.is_null() && scan_inst->writes_flag()) {
+               scan_inst->remove();
+               progress = true;
+            } else if (scan_inst->reads_flag()) {
+               dead_channels = 0;
+            }
+            continue;
+         } else if (scan_inst->dst.file != GRF) {
+            continue;
+         }
+
          if (inst->dst.reg == scan_inst->dst.reg) {
             int new_writemask = scan_inst->dst.writemask & ~dead_channels;