i965/fs: Propagate conditional modifiers from not instructions

Skylake
total instructions in shared programs: 14399081 -> 14399010 (<.01%)
instructions in affected programs: 26961 -> 26890 (-0.26%)
helped: 57
HURT: 0
helped stats (abs) min: 1 max: 6 x̄: 1.25 x̃: 1
helped stats (rel) min: 0.16% max: 0.80% x̄: 0.30% x̃: 0.18%
95% mean confidence interval for instructions value: -1.50 -0.99
95% mean confidence interval for instructions %-change: -0.35% -0.25%
Instructions are helped.

total cycles in shared programs: 532978307 -> 532976050 (<.01%)
cycles in affected programs: 468629 -> 466372 (-0.48%)
helped: 33
HURT: 20
helped stats (abs) min: 3 max: 360 x̄: 116.52 x̃: 98
helped stats (rel) min: 0.06% max: 3.63% x̄: 1.66% x̃: 1.27%
HURT stats (abs)   min: 2 max: 172 x̄: 79.40 x̃: 43
HURT stats (rel)   min: 0.04% max: 3.02% x̄: 1.48% x̃: 0.44%
95% mean confidence interval for cycles value: -81.29 -3.88
95% mean confidence interval for cycles %-change: -1.07% 0.12%
Inconclusive result (%-change mean confidence interval includes 0).

All Gen6+ platforms, except Ivy Bridge, had similar results. (Haswell shown)
total instructions in shared programs: 12973897 -> 12973838 (<.01%)
instructions in affected programs: 25970 -> 25911 (-0.23%)
helped: 55
HURT: 0
helped stats (abs) min: 1 max: 2 x̄: 1.07 x̃: 1
helped stats (rel) min: 0.16% max: 0.62% x̄: 0.28% x̃: 0.18%
95% mean confidence interval for instructions value: -1.14 -1.00
95% mean confidence interval for instructions %-change: -0.32% -0.24%
Instructions are helped.

total cycles in shared programs: 410355841 -> 410352067 (<.01%)
cycles in affected programs: 578454 -> 574680 (-0.65%)
helped: 47
HURT: 5
helped stats (abs) min: 3 max: 360 x̄: 85.74 x̃: 18
helped stats (rel) min: 0.05% max: 3.68% x̄: 1.18% x̃: 0.38%
HURT stats (abs)   min: 2 max: 242 x̄: 51.20 x̃: 4
HURT stats (rel)   min: <.01% max: 0.45% x̄: 0.15% x̃: 0.11%
95% mean confidence interval for cycles value: -104.89 -40.27
95% mean confidence interval for cycles %-change: -1.45% -0.66%
Cycles are helped.

Ivy Bridge
total instructions in shared programs: 11679351 -> 11679301 (<.01%)
instructions in affected programs: 28208 -> 28158 (-0.18%)
helped: 50
HURT: 0
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 0.12% max: 0.54% x̄: 0.23% x̃: 0.16%
95% mean confidence interval for instructions value: -1.00 -1.00
95% mean confidence interval for instructions %-change: -0.27% -0.19%
Instructions are helped.

total cycles in shared programs: 257445362 -> 257444662 (<.01%)
cycles in affected programs: 419338 -> 418638 (-0.17%)
helped: 40
HURT: 3
helped stats (abs) min: 1 max: 170 x̄: 65.05 x̃: 24
helped stats (rel) min: 0.02% max: 3.51% x̄: 1.26% x̃: 0.41%
HURT stats (abs)   min: 2 max: 1588 x̄: 634.00 x̃: 312
HURT stats (rel)   min: 0.05% max: 2.97% x̄: 1.21% x̃: 0.62%
95% mean confidence interval for cycles value: -97.96 65.41
95% mean confidence interval for cycles %-change: -1.56% -0.62%
Inconclusive result (value mean confidence interval includes 0).

No changes on Iron Lake or GM45.

v2: Move 'if (cond != BRW_CONDITIONAL_Z && cond != BRW_CONDITIONAL_NZ)'
check outside the loop.  Suggested by Iago.

Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>

diff --git a/src/intel/compiler/brw_fs_cmod_propagation.cpp b/src/intel/compiler/brw_fs_cmod_propagation.cpp
index b4f05613e985f0dff900c74134ea0e6c1125519a..5b74f267359a96fd9ecb2356d893a8a05b119756 100644 (file)
--- a/src/intel/compiler/brw_fs_cmod_propagation.cpp
+++ b/src/intel/compiler/brw_fs_cmod_propagation.cpp
@@ -111,6 +111,60 @@ cmod_propagate_cmp_to_add(const gen_device_info *devinfo, bblock_t *block,
    return false;
 }
 
+/**
+ * Propagate conditional modifiers from NOT instructions
+ *
+ * Attempt to convert sequences like
+ *
+ *    or(8)           g78<8,8,1>      g76<8,8,1>UD    g77<8,8,1>UD
+ *    ...
+ *    not.nz.f0(8)    null            g78<8,8,1>UD
+ *
+ * into
+ *
+ *    or.z.f0(8)      g78<8,8,1>      g76<8,8,1>UD    g77<8,8,1>UD
+ */
+static bool
+cmod_propagate_not(const gen_device_info *devinfo, bblock_t *block,
+                   fs_inst *inst)
+{
+   const enum brw_conditional_mod cond = brw_negate_cmod(inst->conditional_mod);
+   bool read_flag = false;
+
+   if (cond != BRW_CONDITIONAL_Z && cond != BRW_CONDITIONAL_NZ)
+      return false;
+
+   foreach_inst_in_block_reverse_starting_from(fs_inst, scan_inst, inst) {
+      if (regions_overlap(scan_inst->dst, scan_inst->size_written,
+                          inst->src[0], inst->size_read(0))) {
+         if (scan_inst->opcode != BRW_OPCODE_OR &&
+             scan_inst->opcode != BRW_OPCODE_AND)
+            break;
+
+         if (scan_inst->is_partial_write() ||
+             scan_inst->dst.offset != inst->src[0].offset ||
+             scan_inst->exec_size != inst->exec_size)
+            break;
+
+         if (scan_inst->can_do_cmod() &&
+             ((!read_flag && scan_inst->conditional_mod == BRW_CONDITIONAL_NONE) ||
+              scan_inst->conditional_mod == cond)) {
+            scan_inst->conditional_mod = cond;
+            inst->remove(block);
+            return true;
+         }
+         break;
+      }
+
+      if (scan_inst->flags_written())
+         break;
+
+      read_flag = read_flag || scan_inst->flags_read(devinfo);
+   }
+
+   return false;
+}
+
 static bool
 opt_cmod_propagation_local(const gen_device_info *devinfo, bblock_t *block)
 {
@@ -122,7 +176,8 @@ opt_cmod_propagation_local(const gen_device_info *devinfo, bblock_t *block)
 
       if ((inst->opcode != BRW_OPCODE_AND &&
            inst->opcode != BRW_OPCODE_CMP &&
-           inst->opcode != BRW_OPCODE_MOV) ||
+           inst->opcode != BRW_OPCODE_MOV &&
+           inst->opcode != BRW_OPCODE_NOT) ||
           inst->predicate != BRW_PREDICATE_NONE ||
           !inst->dst.is_null() ||
           (inst->src[0].file != VGRF && inst->src[0].file != ATTR &&
@@ -162,6 +217,11 @@ opt_cmod_propagation_local(const gen_device_info *devinfo, bblock_t *block)
          continue;
       }
 
+      if (inst->opcode == BRW_OPCODE_NOT) {
+         progress = cmod_propagate_not(devinfo, block, inst) || progress;
+         continue;
+      }
+
       bool read_flag = false;
       foreach_inst_in_block_reverse_starting_from(fs_inst, scan_inst, inst) {
          if (regions_overlap(scan_inst->dst, scan_inst->size_written,