On Thu, Sep 27, 2012 at 10:19:54AM -0700, Richard Henderson wrote:
> Signed-off-by: Richard Henderson <r...@twiddle.net>
> ---
> tcg/optimize.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 51 insertions(+)
>
> diff --git a/tcg/optimize.c b/tcg/optimize.c
> index d39926e..c972e4f 100644
> --- a/tcg/optimize.c
> +++ b/tcg/optimize.c
> @@ -799,6 +799,57 @@ static TCGArg *tcg_constant_folding(TCGContext *s,
> uint16_t *tcg_opc_ptr,
> }
> args += 6;
> break;
> + case INDEX_op_brcond2_i32:
> + /* Simplify LT/GE comparisons vs zero to a single compare
> + vs the high word of the input. */
> + if ((args[4] == TCG_COND_LT || args[4] == TCG_COND_GE)
> + && temps[args[2]].state == TCG_TEMP_CONST
> + && temps[args[3]].state == TCG_TEMP_CONST
> + && temps[args[2]].val == 0
> + && temps[args[2]].val == 0) {
The value comparison there is wrong, probably copy & paste issue. I
wonder how it could work.
> + gen_opc_buf[op_index] = INDEX_op_brcond_i32;
> + args[0] = args[1];
> + args[1] = args[3];
> + args[2] = args[4];
> + args[3] = args[5];
> + gen_args += 4;
> + } else {
> + gen_args[0] = args[0];
> + gen_args[1] = args[1];
> + gen_args[2] = args[2];
> + gen_args[3] = args[3];
> + gen_args[4] = args[4];
> + gen_args[5] = args[5];
> + gen_args += 6;
> + }
> + memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
> + args += 6;
> + break;
> + case INDEX_op_setcond2_i32:
> + /* Simplify LT/GE comparisons vs zero to a single compare
> + vs the high word of the input. */
> + if ((args[5] == TCG_COND_LT || args[5] == TCG_COND_GE)
> + && temps[args[3]].state == TCG_TEMP_CONST
> + && temps[args[4]].state == TCG_TEMP_CONST
> + && temps[args[3]].val == 0
> + && temps[args[4]].val == 0) {
Here it is fine.
> + gen_opc_buf[op_index] = INDEX_op_setcond_i32;
> + args[1] = args[2];
> + args[2] = args[4];
> + args[3] = args[5];
> + gen_args += 4;
> + } else {
> + reset_temp(args[0]);
> + gen_args[0] = args[0];
> + gen_args[1] = args[1];
> + gen_args[2] = args[2];
> + gen_args[3] = args[3];
> + gen_args[4] = args[4];
> + gen_args[5] = args[5];
> + gen_args += 6;
> + }
> + args += 6;
> + break;
> case INDEX_op_call:
> nb_call_args = (args[0] >> 16) + (args[0] & 0xffff);
> if (!(args[nb_call_args + 1] & (TCG_CALL_CONST |
> TCG_CALL_PURE))) {
While it's a nice optimization to have, one that seems to happen a lot
more often is the two high parts being equal. It happens when the guest
is working on (u)int32_t.
--
Aurelien Jarno GPG: 1024D/F1BCDB73
aurel...@aurel32.net http://www.aurel32.net
