i965/fs: Allow flipping cond mod for negated arguments.

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.g.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

Reviewed-by: Jason Ekstrand <jason.ekstrand@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>

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 c8eb3a4f8bec378e322b4fe2e0bdc5ead154a3af..8a03315bc4c4071c45e620428b2eff36279f863e 100644 (file)
--- 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;
 
@@ -74,10 +73,14 @@ opt_cmod_propagation_local(fs_visitor *v, bblock_t *block)
                 scan_inst->dst.reg_offset != inst->src[0].reg_offset)
                break;
 
+            enum brw_conditional_mod cond =
+               inst->src[0].negate ? brw_swap_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 95d335d9543cd80456d49bf19d65f925153affee..fefe515a216378960cb898c9486b0017bb229ec2 100644 (file)
--- a/src/mesa/drivers/dri/i965/test_fs_cmod_propagation.cpp
+++ b/src/mesa/drivers/dri/i965/test_fs_cmod_propagation.cpp
@@ -350,3 +350,36 @@ 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->vgrf(glsl_type::float_type);
+   fs_reg src0 = v->vgrf(glsl_type::float_type);
+   fs_reg src1 = v->vgrf(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.le.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_LE, instruction(block0, 0)->conditional_mod);
+}