i965/fs: Perform CSE on CMP(N) instructions.

Optimizes

      cmp.ge.f0(8)  null     g45<8,8,1>F  0F
(+f0) sel(8)        g50<1>F  g40<8,8,1>F  g10<8,8,1>F
      cmp.ge.f0(8)  null     g45<8,8,1>F  0F
(+f0) sel(8)        g51<1>F  g41<8,8,1>F  g11<8,8,1>F
      cmp.ge.f0(8)  null     g45<8,8,1>F  0F
(+f0) sel(8)        g52<1>F  g42<8,8,1>F  g12<8,8,1>F
      cmp.ge.f0(8)  null     g45<8,8,1>F  0F
(+f0) sel(8)        g53<1>F  g43<8,8,1>F  g13<8,8,1>F

into

      cmp.ge.f0(8)  null     g45<8,8,1>F  0F
(+f0) sel(8)        g50<1>F  g40<8,8,1>F  g10<8,8,1>F
(+f0) sel(8)        g51<1>F  g41<8,8,1>F  g11<8,8,1>F
(+f0) sel(8)        g52<1>F  g42<8,8,1>F  g12<8,8,1>F
(+f0) sel(8)        g53<1>F  g43<8,8,1>F  g13<8,8,1>F

total instructions in shared programs: 1644938 -> 1638181 (-0.41%)
instructions in affected programs:     574955 -> 568198 (-1.18%)

Two more 16-wide programs (in L4D2). Some large (-9%) decreases in
instruction count in some of Valve's Source Engine games. No
regressions.

Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Paul Berry <stereotype441@gmail.com>

diff --git a/src/mesa/drivers/dri/i965/brw_fs_cse.cpp b/src/mesa/drivers/dri/i965/brw_fs_cse.cpp
index 3f59339f716aba8a0775465d6d8f902e6791ce88..47938744cf6e61edadc8b0e1e412b3909e953cc4 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs_cse.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_cse.cpp
@@ -54,6 +54,8 @@ is_expression(const fs_inst *const inst)
    case BRW_OPCODE_SHR:
    case BRW_OPCODE_SHL:
    case BRW_OPCODE_ASR:
+   case BRW_OPCODE_CMP:
+   case BRW_OPCODE_CMPN:
    case BRW_OPCODE_ADD:
    case BRW_OPCODE_MUL:
    case BRW_OPCODE_FRC:
@@ -102,6 +104,18 @@ operands_match(enum opcode op, fs_reg *xs, fs_reg *ys)
    }
 }
 
+static bool
+instructions_match(fs_inst *a, fs_inst *b)
+{
+   return a->opcode == b->opcode &&
+          a->saturate == b->saturate &&
+          a->predicate == b->predicate &&
+          a->predicate_inverse == b->predicate_inverse &&
+          a->conditional_mod == b->conditional_mod &&
+          a->dst.type == b->dst.type &&
+          operands_match(a->opcode, a->src, b->src);
+}
+
 bool
 fs_visitor::opt_cse_local(bblock_t *block, exec_list *aeb)
 {
@@ -115,11 +129,7 @@ fs_visitor::opt_cse_local(bblock_t *block, exec_list *aeb)
        inst = (fs_inst *) inst->next) {
 
       /* Skip some cases. */
-      if (is_expression(inst) &&
-          !inst->predicate &&
-          !inst->is_partial_write() &&
-          !inst->conditional_mod &&
-          inst->dst.file != HW_REG)
+      if (is_expression(inst) && !inst->is_partial_write())
       {
         bool found = false;
 
@@ -128,11 +138,7 @@ fs_visitor::opt_cse_local(bblock_t *block, exec_list *aeb)
            entry = (aeb_entry *) entry_node;
 
            /* Match current instruction's expression against those in AEB. */
-           if (inst->opcode == entry->generator->opcode &&
-               inst->saturate == entry->generator->saturate &&
-                inst->dst.type == entry->generator->dst.type &&
-                operands_match(inst->opcode, entry->generator->src, inst->src)) {
-
+           if (instructions_match(inst, entry->generator)) {
               found = true;
               progress = true;
               break;
@@ -208,6 +214,19 @@ fs_visitor::opt_cse_local(bblock_t *block, exec_list *aeb)
       foreach_list_safe(entry_node, aeb) {
         aeb_entry *entry = (aeb_entry *)entry_node;
 
+         /* Kill all AEB entries that write a different value to or read from
+          * the flag register if we just wrote it.
+          */
+         if (inst->writes_flag()) {
+            if (entry->generator->reads_flag() ||
+                (entry->generator->writes_flag() &&
+                 !instructions_match(inst, entry->generator))) {
+               entry->remove();
+               ralloc_free(entry);
+               continue;
+            }
+         }
+
         for (int i = 0; i < 3; i++) {
             fs_reg *src_reg = &entry->generator->src[i];