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]);
}
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) {
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);
}
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;