tcg: Optimize mulu2

Like add2, do operand ordering, constant folding, and dead operand
elimination.  The latter happens about 15% of all mulu2 during an
x86_64 bios boot.

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

3 files changed, 47 insertions, 0 deletions

diff --git a/tcg/optimize.c b/tcg/optimize.c
index 05891ef..a06c8eb 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -543,6 +543,9 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
             swap_commutative(args[0], &args[2], &args[4]);
             swap_commutative(args[1], &args[3], &args[5]);
             break;
+        case INDEX_op_mulu2_i32:
+            swap_commutative(args[0], &args[2], &args[3]);
+            break;
         case INDEX_op_brcond2_i32:
             if (swap_commutative2(&args[0], &args[2])) {
                 args[4] = tcg_swap_cond(args[4]);
@@ -831,6 +834,29 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
             }
             goto do_default;
 
+        case INDEX_op_mulu2_i32:
+            if (temps[args[2]].state == TCG_TEMP_CONST
+                && temps[args[3]].state == TCG_TEMP_CONST) {
+                uint32_t a = temps[args[2]].val;
+                uint32_t b = temps[args[3]].val;
+                uint64_t r = (uint64_t)a * b;
+                TCGArg rl, rh;
+
+                /* We emit the extra nop when we emit the mulu2.  */
+                assert(gen_opc_buf[op_index + 1] == INDEX_op_nop);
+
+                rl = args[0];
+                rh = args[1];
+                gen_opc_buf[op_index] = INDEX_op_movi_i32;
+                gen_opc_buf[++op_index] = INDEX_op_movi_i32;
+                tcg_opt_gen_movi(&gen_args[0], rl, (uint32_t)r);
+                tcg_opt_gen_movi(&gen_args[2], rh, (uint32_t)(r >> 32));
+                gen_args += 4;
+                args += 4;
+                break;
+            }
+            goto do_default;
+
         case INDEX_op_brcond2_i32:
             tmp = do_constant_folding_cond2(&args[0], &args[2], args[4]);
             if (tmp != 2) {
diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h
index a580cfe..8100a5a 100644
--- a/tcg/tcg-op.h
+++ b/tcg/tcg-op.h
@@ -1027,6 +1027,8 @@ static inline void tcg_gen_mul_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
 
     tcg_gen_op4_i32(INDEX_op_mulu2_i32, TCGV_LOW(t0), TCGV_HIGH(t0),
                     TCGV_LOW(arg1), TCGV_LOW(arg2));
+    /* Allow the optimizer room to replace mulu2 with two moves.  */
+    tcg_gen_op0(INDEX_op_nop);
 
     tcg_gen_mul_i32(t1, TCGV_LOW(arg1), TCGV_HIGH(arg2));
     tcg_gen_add_i32(TCGV_HIGH(t0), TCGV_HIGH(t0), t1);
diff --git a/tcg/tcg.c b/tcg/tcg.c
index 0eb407b..f0deea2 100644
--- a/tcg/tcg.c
+++ b/tcg/tcg.c
@@ -1338,6 +1338,25 @@ static void tcg_liveness_analysis(TCGContext *s)
             }
             goto do_not_remove;
 
+        case INDEX_op_mulu2_i32:
+            args -= 4;
+            nb_iargs = 2;
+            nb_oargs = 2;
+            /* Likewise, test for the high part of the operation dead.  */
+            if (dead_temps[args[1]]) {
+                if (dead_temps[args[0]]) {
+                    goto do_remove;
+                }
+                gen_opc_buf[op_index] = op = INDEX_op_mul_i32;
+                args[1] = args[2];
+                args[2] = args[3];
+                assert(gen_opc_buf[op_index + 1] == INDEX_op_nop);
+                tcg_set_nop(s, gen_opc_buf + op_index + 1, args + 3, 1);
+                /* Fall through and mark the single-word operation live.  */
+                nb_oargs = 1;
+            }
+            goto do_not_remove;
+
         default:
             /* XXX: optimize by hardcoding common cases (e.g. triadic ops) */
             args -= def->nb_args;