qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Aurelien Jarno <aurelien@aurel32.net>
To: Richard Henderson <rth@twiddle.net>
Cc: qemu-devel@nongnu.org
Subject: Re: [Qemu-devel] [PATCH 07/10] tcg: Do constant folding on double-word comparisons
Date: Wed, 10 Oct 2012 11:45:32 +0200	[thread overview]
Message-ID: <20121010094532.GA25297@ohm.aurel32.net> (raw)
In-Reply-To: <1349202750-16815-8-git-send-email-rth@twiddle.net>

On Tue, Oct 02, 2012 at 11:32:27AM -0700, Richard Henderson wrote:
> Signed-off-by: Richard Henderson <rth@twiddle.net>
> ---
>  tcg/optimize.c | 93 +++++++++++++++++++++++++++++++++++++++++++++-------------
>  1 file changed, 72 insertions(+), 21 deletions(-)
> 
> diff --git a/tcg/optimize.c b/tcg/optimize.c
> index 38027dc..d9251e4 100644
> --- a/tcg/optimize.c
> +++ b/tcg/optimize.c
> @@ -398,6 +398,40 @@ static TCGArg do_constant_folding_cond(TCGOpcode op, TCGArg x,
>      }
>  }
>  
> +/* Return 2 if the condition can't be simplified, and the result
> +   of the condition (0 or 1) if it can */
> +static TCGArg do_constant_folding_cond2(TCGArg *p1, TCGArg *p2, TCGCond c)
> +{
> +    TCGArg al = p1[0], ah = p1[1];
> +    TCGArg bl = p2[0], bh = p2[1];
> +
> +    if (temps[bl].state == TCG_TEMP_CONST
> +        && temps[bh].state == TCG_TEMP_CONST) {
> +        uint64_t b = ((uint64_t)temps[bh].val << 32) | (uint32_t)temps[bl].val;
> +
> +        if (temps[al].state == TCG_TEMP_CONST
> +            && temps[ah].state == TCG_TEMP_CONST) {
> +            uint64_t a;
> +            a = ((uint64_t)temps[ah].val << 32) | (uint32_t)temps[al].val;
> +            return do_constant_folding_cond_64(a, b, c);
> +        }
> +        if (b == 0) {
> +            switch (c) {
> +            case TCG_COND_LTU:
> +                return 0;
> +            case TCG_COND_GEU:
> +                return 1;
> +            default:
> +                break;
> +            }
> +        }
> +    }
> +    if (temps_are_copies(al, bl) && temps_are_copies(ah, bh)) {
> +        return do_constant_folding_cond_eq(c);
> +    }
> +    return 2;
> +}
> +
>  static bool swap_commutative(TCGArg dest, TCGArg *p1, TCGArg *p2)
>  {
>      TCGArg a1 = *p1, a2 = *p2;
> @@ -763,43 +797,60 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
>              goto do_default;
>  
>          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[3]].val == 0) {
> +            tmp = do_constant_folding_cond2(&args[0], &args[2], args[4]);
> +            if (tmp != 2) {
> +                if (tmp) {
> +                    memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
> +                    gen_opc_buf[op_index] = INDEX_op_br;
> +                    gen_args[0] = args[5];
> +                    gen_args += 1;
> +                } else {
> +                    gen_opc_buf[op_index] = INDEX_op_nop;
> +                }
> +            } else 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[3]].val == 0) {
> +                /* Simplify LT/GE comparisons vs zero to a single compare
> +                   vs the high word of the input.  */
> +                memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
>                  gen_opc_buf[op_index] = INDEX_op_brcond_i32;
>                  gen_args[0] = args[1];
>                  gen_args[1] = args[3];
>                  gen_args[2] = args[4];
>                  gen_args[3] = args[5];
>                  gen_args += 4;
> -                args += 6;
> -                memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
> -                break;
> +            } else {
> +                goto do_default;
>              }
> -            goto do_default;
> +            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) {
> +            tmp = do_constant_folding_cond2(&args[1], &args[3], args[5]);
> +            if (tmp != 2) {
> +                gen_opc_buf[op_index] = INDEX_op_movi_i32;
> +                tcg_opt_gen_movi(gen_args, args[0], tmp);
> +                gen_args += 2;
> +            } else 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) {
> +                /* Simplify LT/GE comparisons vs zero to a single compare
> +                   vs the high word of the input.  */
>                  gen_opc_buf[op_index] = INDEX_op_setcond_i32;
>                  gen_args[0] = args[0];
>                  gen_args[1] = args[2];
>                  gen_args[2] = args[4];
>                  gen_args[3] = args[5];
>                  gen_args += 4;
> -                args += 6;
> -                break;
> +            } else {
> +                goto do_default;
>              }
> -            goto do_default;
> +            args += 6;
> +            break;
>  
>          case INDEX_op_call:
>              nb_call_args = (args[0] >> 16) + (args[0] & 0xffff);

Reviewed-by: Aurelien Jarno <aurelien@aurel32.net>

-- 
Aurelien Jarno                          GPG: 1024D/F1BCDB73
aurelien@aurel32.net                 http://www.aurel32.net

  reply	other threads:[~2012-10-10  9:45 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-10-02 18:32 [Qemu-devel] [PATCH v2 00/10] Double-word tcg/optimize improvements Richard Henderson
2012-10-02 18:32 ` [Qemu-devel] [PATCH 01/10] tcg: Split out swap_commutative as a subroutine Richard Henderson
2012-10-09 15:13   ` Aurelien Jarno
2012-10-09 15:23     ` Richard Henderson
2012-10-09 15:31       ` Aurelien Jarno
2012-10-09 16:40         ` Richard Henderson
2012-10-02 18:32 ` [Qemu-devel] [PATCH 02/10] tcg: Canonicalize add2 operand ordering Richard Henderson
2012-10-09 15:14   ` Aurelien Jarno
2012-10-02 18:32 ` [Qemu-devel] [PATCH 03/10] tcg: Swap commutative double-word comparisons Richard Henderson
2012-10-09 15:16   ` Aurelien Jarno
2012-10-09 15:31     ` Richard Henderson
2012-10-09 15:48       ` Aurelien Jarno
2012-10-02 18:32 ` [Qemu-devel] [PATCH 04/10] tcg: Use common code when failing to optimize Richard Henderson
2012-10-09 15:25   ` Aurelien Jarno
2012-10-09 15:33     ` Richard Henderson
2012-10-02 18:32 ` [Qemu-devel] [PATCH 05/10] tcg: Optimize double-word comparisons against zero Richard Henderson
2012-10-09 16:32   ` Aurelien Jarno
2012-10-02 18:32 ` [Qemu-devel] [PATCH 06/10] tcg: Split out subroutines from do_constant_folding_cond Richard Henderson
2012-10-09 16:33   ` Aurelien Jarno
2012-10-02 18:32 ` [Qemu-devel] [PATCH 07/10] tcg: Do constant folding on double-word comparisons Richard Henderson
2012-10-10  9:45   ` Aurelien Jarno [this message]
2012-10-02 18:32 ` [Qemu-devel] [PATCH 08/10] tcg: Constant fold add2 and sub2 Richard Henderson
2012-10-10  9:52   ` Aurelien Jarno
2012-10-02 18:32 ` [Qemu-devel] [PATCH 09/10] tcg: Optimize half-dead add2/sub2 Richard Henderson
2012-10-16 23:25   ` Aurelien Jarno
2012-10-02 18:32 ` [Qemu-devel] [PATCH 10/10] tcg: Optimize mulu2 Richard Henderson
2012-10-16 23:25   ` Aurelien Jarno
2012-10-17  1:09     ` Richard Henderson
2012-10-17 10:58       ` Avi Kivity
2012-10-17 16:41 ` [Qemu-devel] [PATCH v2 00/10] Double-word tcg/optimize improvements Aurelien Jarno

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20121010094532.GA25297@ohm.aurel32.net \
    --to=aurelien@aurel32.net \
    --cc=qemu-devel@nongnu.org \
    --cc=rth@twiddle.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).