tcg/optimize: optimize temps tracking

The tcg_temp_info structure uses 24 bytes per temp. Now that we emulate
vector registers on most guests, it's not uncommon to have more than 100
used temps. This means we have initialize more than 2kB at least twice
per TB, often more when there is a few goto_tb.

Instead used a TCGTempSet bit array to track which temps are in used in
the current basic block. This means there are only around 16 bytes to
initialize.

This improves the boot time of a MIPS guest on an x86-64 host by around
7% and moves out tcg_optimize from the the top of the profiler list.

[rth: Handle TCG_CALL_DUMMY_ARG]

Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Signed-off-by: Richard Henderson <rth@twiddle.net>

1 files changed, 32 insertions, 11 deletions

diff --git a/tcg/optimize.c b/tcg/optimize.c
index cd0e793a9d..413920f261 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -50,6 +50,7 @@ struct tcg_temp_info {
 };
 
 static struct tcg_temp_info temps[TCG_MAX_TEMPS];
+static TCGTempSet temps_used;
 
 /* Reset TEMP's state to TCG_TEMP_UNDEF.  If TEMP only had one copy, remove
    the copy flag from the left temp.  */
@@ -67,6 +68,22 @@ static void reset_temp(TCGArg temp)
     temps[temp].mask = -1;
 }
 
+/* Reset all temporaries, given that there are NB_TEMPS of them.  */
+static void reset_all_temps(int nb_temps)
+{
+    bitmap_zero(temps_used.l, nb_temps);
+}
+
+/* Initialize and activate a temporary.  */
+static void init_temp_info(TCGArg temp)
+{
+    if (!test_bit(temp, temps_used.l)) {
+        temps[temp].state = TCG_TEMP_UNDEF;
+        temps[temp].mask = -1;
+        set_bit(temp, temps_used.l);
+    }
+}
+
 static TCGOp *insert_op_before(TCGContext *s, TCGOp *old_op,
                                 TCGOpcode opc, int nargs)
 {
@@ -98,16 +115,6 @@ static TCGOp *insert_op_before(TCGContext *s, TCGOp *old_op,
     return new_op;
 }
 
-/* Reset all temporaries, given that there are NB_TEMPS of them.  */
-static void reset_all_temps(int nb_temps)
-{
-    int i;
-    for (i = 0; i < nb_temps; i++) {
-        temps[i].state = TCG_TEMP_UNDEF;
-        temps[i].mask = -1;
-    }
-}
-
 static int op_bits(TCGOpcode op)
 {
     const TCGOpDef *def = &tcg_op_defs[op];
@@ -598,12 +605,24 @@ void tcg_optimize(TCGContext *s)
         const TCGOpDef *def = &tcg_op_defs[opc];
 
         oi_next = op->next;
+
+        /* Count the arguments, and initialize the temps that are
+           going to be used */
         if (opc == INDEX_op_call) {
             nb_oargs = op->callo;
             nb_iargs = op->calli;
+            for (i = 0; i < nb_oargs + nb_iargs; i++) {
+                tmp = args[i];
+                if (tmp != TCG_CALL_DUMMY_ARG) {
+                    init_temp_info(tmp);
+                }
+            }
         } else {
             nb_oargs = def->nb_oargs;
             nb_iargs = def->nb_iargs;
+            for (i = 0; i < nb_oargs + nb_iargs; i++) {
+                init_temp_info(args[i]);
+            }
         }
 
         /* Do copy propagation */
@@ -1299,7 +1318,9 @@ void tcg_optimize(TCGContext *s)
             if (!(args[nb_oargs + nb_iargs + 1]
                   & (TCG_CALL_NO_READ_GLOBALS | TCG_CALL_NO_WRITE_GLOBALS))) {
                 for (i = 0; i < nb_globals; i++) {
-                    reset_temp(i);
+                    if (test_bit(i, temps_used.l)) {
+                        reset_temp(i);
+                    }
                 }
             }
             goto do_reset_output;