[Mesa-dev] [PATCH 14/16] i965/fs: Allow flipping cond mod for negated arguments.

[Matt Turner]

This allows us to apply the optimization in cases where the CMP's
argument is negated, by flipping the conditional mod. For example, it
allows us to optimize this:

   add(8)       temp   a      b
   cmp.l.f0(8)  null   -temp  0.0

into

   add.ge.f0(8) temp   a      b

total instructions in shared programs: 5958360 -> 5955701 (-0.04%)
instructions in affected programs:     466880 -> 464221 (-0.57%)
GAINED:                                0
LOST:                                  1
---
 .../drivers/dri/i965/brw_fs_cmod_propagation.cpp   |  9 ++++--
 .../drivers/dri/i965/test_fs_cmod_propagation.cpp  | 33 ++++++++++++++++++++++
 2 files changed, 39 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 4f350c6..b521350 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_cmod_propagation.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_cmod_propagation.cpp
@@ -62,7 +62,6 @@ opt_cmod_propagation_local(fs_visitor *v, bblock_t *block)
           !inst->dst.is_null() ||
           inst->src[0].file != GRF ||
           inst->src[0].abs ||
-          inst->src[0].negate ||
           !inst->src[1].is_zero())
          continue;
 
@@ -73,10 +72,14 @@ 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()) {
+            enum brw_conditional_mod cond =
+               inst->src[0].negate ? brw_invert_cmod(inst->conditional_mod)
+                                   : inst->conditional_mod;
+
             if (scan_inst->can_do_cmod() &&
                 ((!read_flag && scan_inst->conditional_mod == BRW_CONDITIONAL_NONE) ||
-                 scan_inst->conditional_mod == inst->conditional_mod)) {
-               scan_inst->conditional_mod = inst->conditional_mod;
+                 scan_inst->conditional_mod == cond)) {
+               scan_inst->conditional_mod = cond;
                inst->remove(block);
                progress = true;
             }
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 624e0b3..15f685e 100644
--- a/src/mesa/drivers/dri/i965/test_fs_cmod_propagation.cpp
+++ b/src/mesa/drivers/dri/i965/test_fs_cmod_propagation.cpp
@@ -310,3 +310,36 @@ TEST_F(cmod_propagation_test, intervening_flag_read_same_value)
    EXPECT_EQ(BRW_OPCODE_SEL, instruction(block0, 1)->opcode);
    EXPECT_EQ(BRW_PREDICATE_NORMAL, instruction(block0, 1)->predicate);
 }
+
+TEST_F(cmod_propagation_test, negate)
+{
+   fs_reg dest(v, glsl_type::float_type);
+   fs_reg src0(v, glsl_type::float_type);
+   fs_reg src1(v, glsl_type::float_type);
+   fs_reg zero(0.0f);
+   v->emit(BRW_OPCODE_ADD, dest, src0, src1);
+   dest.negate = true;
+   v->emit(BRW_OPCODE_CMP, v->reg_null_f, dest, zero)
+      ->conditional_mod = BRW_CONDITIONAL_GE;
+
+   /* = Before =
+    *
+    * 0: add(8)        dest  src0  src1
+    * 1: cmp.ge.f0(8)  null  -dest 0.0f
+    *
+    * = After =
+    * 0: add.l.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_ADD, instruction(block0, 0)->opcode);
+   EXPECT_EQ(BRW_CONDITIONAL_L, instruction(block0, 0)->conditional_mod);
+}
-- 
2.0.4