[Mesa-dev] [PATCH] i965: Handle CMP.nz ... 0 and MOV.nz similarly in cmod propagation.

[Kenneth Graunke]

"MOV.nz null src" and "CMP.nz null src 0" are equivalent instructions.

Previously, we deleted MOV.nz instructions when the instruction
generating the MOV's source also wrote the flag register (as the flag
register already contains the desired value).  However, we wouldn't
delete CMP.nz instructions that served the same purpose.

We also didn't attempt true cmod propagation on MOV.nz instructions,
while we would for the equivalent CMP.nz form.

This patch fixes both limitations, treating both forms equally.
CMP.nz instructions will now be deleted (helping the NIR backend),
and MOV.nz instructions will have their .nz propagated.

No changes in shader-db without NIR.  With NIR,

total instructions in shared programs: 6006153 -> 5969364 (-0.61%)
instructions in affected programs:     2087139 -> 2050350 (-1.76%)
helped:                                10704
HURT:                                  0
GAINED:                                2
LOST:                                  2

Cc: Matt Turner <mattst88 at gmail.com>
Signed-off-by: Kenneth Graunke <kenneth at whitecape.org>
---
 src/mesa/drivers/dri/i965/brw_fs_cmod_propagation.cpp | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 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 ec9f812..c6384ab 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_cmod_propagation.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_cmod_propagation.cpp
@@ -69,8 +69,7 @@ opt_cmod_propagation_local(fs_visitor *v, bblock_t *block)
          continue;
 
       if (inst->opcode == BRW_OPCODE_MOV &&
-          (inst->conditional_mod != BRW_CONDITIONAL_NZ ||
-           inst->src[0].negate))
+          inst->conditional_mod != BRW_CONDITIONAL_NZ)
          continue;
 
       bool read_flag = false;
@@ -81,15 +80,20 @@ opt_cmod_propagation_local(fs_visitor *v, bblock_t *block)
                 scan_inst->dst.reg_offset != inst->src[0].reg_offset)
                break;
 
-            if (inst->opcode == BRW_OPCODE_MOV) {
-               if (!scan_inst->writes_flag())
-                  break;
-
+            /* If the instruction generating inst's source also wrote the
+             * flag, and inst is doing a simple .nz comparison, then inst
+             * is redundant - the appropriate value is already in the flag
+             * register.  Delete inst.
+             */
+            if (inst->conditional_mod == BRW_CONDITIONAL_NZ &&
+                !inst->src[0].negate &&
+                scan_inst->writes_flag()) {
                inst->remove(block);
                progress = true;
                break;
             }
 
+            /* Otherwise, try propagating the conditional. */
             enum brw_conditional_mod cond =
                inst->src[0].negate ? brw_swap_cmod(inst->conditional_mod)
                                    : inst->conditional_mod;
-- 
2.2.2