Re: [Qemu-devel] [PATCH for-2.5 01/10] tcg/optimize: optimize temps tracking

[Paolo Bonzini]

On 24/07/2015 18:30, Aurelien Jarno wrote:
> 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.
> 
> Cc: Richard Henderson <address@hidden>
> Signed-off-by: Aurelien Jarno <address@hidden>
> ---
>  tcg/optimize.c | 32 ++++++++++++++++++++++----------
>  1 file changed, 22 insertions(+), 10 deletions(-)
> 
> diff --git a/tcg/optimize.c b/tcg/optimize.c
> index cd0e793..20e24b3 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)
> +{
> +    memset(&temps_used.l, 0, sizeof(long) * BITS_TO_LONGS(nb_temps));

You can use bitmap_zero here.

Paolo

> +}
> +
> +/* 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];
> @@ -606,6 +613,11 @@ void tcg_optimize(TCGContext *s)
>              nb_iargs = def->nb_iargs;
>          }
>  
> +        /* Initialize the temps that are going to be used */
> +        for (i = 0; i < nb_oargs + nb_iargs; i++) {
> +            init_temp_info(args[i]);
> +        }
> +
>          /* Do copy propagation */
>          for (i = nb_oargs; i < nb_oargs + nb_iargs; i++) {
>              if (temps[args[i]].state == TCG_TEMP_COPY) {
>