[Mesa-dev] [PATCH 15/16] i965/fs: Add support for removing MOV.NZ instructions.

[Matt Turner]

For some reason, we occasionally write the flag register with a MOV.NZ
instruction:

   add(8)          g25<1>F         -g6<0,1,0>F     g15<8,8,1>F
   cmp.l.f0(8)     g26<1>D         g25<8,8,1>F     0F
   mov.nz.f0(8)    null            g26<8,8,1>D

A MOV.NZ instruction on the result of a CMP is like comparing for
equality with true in C. It's useless. Removing it allows us to
generate:

   add.l.f0(8)     null            -g6<0,1,0>F     g15<8,8,1>F

total instructions in shared programs: 5955701 -> 5951657 (-0.07%)
instructions in affected programs:     302910 -> 298866 (-1.34%)
GAINED:                                1
LOST:                                  0
---
 .../drivers/dri/i965/brw_fs_cmod_propagation.cpp   | 23 ++++++++++++++--
 .../drivers/dri/i965/test_fs_cmod_propagation.cpp  | 32 ++++++++++++++++++++++
 2 files changed, 52 insertions(+), 3 deletions(-)

diff --git a/src/mesa/drivers/dri/i965/brw_fs_cmod_propagation.cpp b/src/mesa/drivers/dri/i965/brw_fs_cmod_propagation.cpp
index b521350..dd89512 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_cmod_propagation.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_cmod_propagation.cpp
@@ -57,12 +57,20 @@ opt_cmod_propagation_local(fs_visitor *v, bblock_t *block)
    foreach_inst_in_block_reverse_safe(fs_inst, inst, block) {
       ip--;
 
-      if (inst->opcode != BRW_OPCODE_CMP ||
+      if ((inst->opcode != BRW_OPCODE_CMP &&
+           inst->opcode != BRW_OPCODE_MOV) ||
           inst->predicate != BRW_PREDICATE_NONE ||
           !inst->dst.is_null() ||
           inst->src[0].file != GRF ||
-          inst->src[0].abs ||
-          !inst->src[1].is_zero())
+          inst->src[0].abs)
+         continue;
+
+      if (inst->opcode == BRW_OPCODE_CMP && !inst->src[1].is_zero())
+         continue;
+
+      if (inst->opcode == BRW_OPCODE_MOV &&
+          (inst->conditional_mod != BRW_CONDITIONAL_NZ ||
+           inst->src[0].negate))
          continue;
 
       bool read_flag = false;
@@ -72,6 +80,15 @@ opt_cmod_propagation_local(fs_visitor *v, bblock_t *block)
              scan_inst->dst.reg == inst->src[0].reg &&
              scan_inst->dst.reg_offset == inst->src[0].reg_offset &&
              !scan_inst->is_partial_write()) {
+            if (inst->opcode == BRW_OPCODE_MOV) {
+               if (!scan_inst->writes_flag())
+                  break;
+
+               inst->remove(block);
+               progress = true;
+               break;
+            }
+
             enum brw_conditional_mod cond =
                inst->src[0].negate ? brw_invert_cmod(inst->conditional_mod)
                                    : inst->conditional_mod;
diff --git a/src/mesa/drivers/dri/i965/test_fs_cmod_propagation.cpp b/src/mesa/drivers/dri/i965/test_fs_cmod_propagation.cpp
index 15f685e..9541597 100644
--- a/src/mesa/drivers/dri/i965/test_fs_cmod_propagation.cpp
+++ b/src/mesa/drivers/dri/i965/test_fs_cmod_propagation.cpp
@@ -343,3 +343,35 @@ TEST_F(cmod_propagation_test, negate)
    EXPECT_EQ(BRW_OPCODE_ADD, instruction(block0, 0)->opcode);
    EXPECT_EQ(BRW_CONDITIONAL_L, instruction(block0, 0)->conditional_mod);
 }
+
+TEST_F(cmod_propagation_test, movnz)
+{
+   fs_reg dest(v, glsl_type::float_type);
+   fs_reg src0(v, glsl_type::float_type);
+   fs_reg src1(v, glsl_type::float_type);
+   v->emit(BRW_OPCODE_CMP, dest, src0, src1)
+      ->conditional_mod = BRW_CONDITIONAL_GE;
+   v->emit(BRW_OPCODE_MOV, v->reg_null_f, dest)
+      ->conditional_mod = BRW_CONDITIONAL_NZ;
+
+   /* = Before =
+    *
+    * 0: cmp.ge.f0(8)  dest  src0  src1
+    * 1: mov.nz.f0(8)  null  dest
+    *
+    * = After =
+    * 0: cmp.ge.f0(8)  dest  src0  src1
+    */
+
+   v->calculate_cfg();
+   bblock_t *block0 = v->cfg->blocks[0];
+
+   EXPECT_EQ(0, block0->start_ip);
+   EXPECT_EQ(1, block0->end_ip);
+
+   EXPECT_TRUE(cmod_propagation(v));
+   EXPECT_EQ(0, block0->start_ip);
+   EXPECT_EQ(0, block0->end_ip);
+   EXPECT_EQ(BRW_OPCODE_CMP, instruction(block0, 0)->opcode);
+   EXPECT_EQ(BRW_CONDITIONAL_GE, instruction(block0, 0)->conditional_mod);
+}
-- 
2.0.4