Re: [Qemu-devel] [PATCH 6/7] tcg: Streamline movcond_i64 using 32-bit arithmetic

[Aurelien Jarno]

On Fri, Sep 21, 2012 at 10:13:39AM -0700, Richard Henderson wrote:
> Avoiding 64-bit arithmetic (outside of the compare) reduces the
> generated op count from 15 to 12, and the generated code size on
> i686 from 105 to 88 bytes.
> 
> Signed-off-by: Richard Henderson <address@hidden>
> ---
>  tcg/tcg-op.h | 42 +++++++++++++++++++++++++++++++-----------
>  1 file changed, 31 insertions(+), 11 deletions(-)
> 
> diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h
> index 6d28f82..3e375ea 100644
> --- a/tcg/tcg-op.h
> +++ b/tcg/tcg-op.h
> @@ -2141,18 +2141,38 @@ static inline void tcg_gen_movcond_i64(TCGCond cond, 
> TCGv_i64 ret,
>                                         TCGv_i64 c1, TCGv_i64 c2,
>                                         TCGv_i64 v1, TCGv_i64 v2)
>  {
> -    if (TCG_TARGET_HAS_movcond_i64) {
> -        tcg_gen_op6i_i64(INDEX_op_movcond_i64, ret, c1, c2, v1, v2, cond);
> +    if (TCG_TARGET_REG_BITS == 32) {
> +        TCGv_i32 t0 = tcg_temp_new_i32();
> +        TCGv_i32 t1 = tcg_temp_new_i32();
> +        tcg_gen_op6i_i32(INDEX_op_setcond2_i32, t0,
> +                         TCGV_LOW(c1), TCGV_HIGH(c1),
> +                         TCGV_LOW(c2), TCGV_HIGH(c2), cond);
> +        tcg_gen_neg_i32(t0, t0);
> +
> +        tcg_gen_and_i32(t1, TCGV_LOW(v1), t0);
> +        tcg_gen_andc_i32(TCGV_LOW(ret), TCGV_LOW(v2), t0);
> +        tcg_gen_or_i32(TCGV_LOW(ret), TCGV_LOW(ret), t1);
> +
> +        tcg_gen_and_i32(t1, TCGV_HIGH(v1), t0);
> +        tcg_gen_andc_i32(TCGV_HIGH(ret), TCGV_HIGH(v2), t0);
> +        tcg_gen_or_i32(TCGV_HIGH(ret), TCGV_HIGH(ret), t1);
> +
> +        tcg_temp_free_i32(t0);
> +        tcg_temp_free_i32(t1);
>      } else {
> -        TCGv_i64 t0 = tcg_temp_new_i64();
> -        TCGv_i64 t1 = tcg_temp_new_i64();
> -        tcg_gen_setcond_i64(cond, t0, c1, c2);
> -        tcg_gen_neg_i64(t0, t0);
> -        tcg_gen_and_i64(t1, v1, t0);
> -        tcg_gen_andc_i64(ret, v2, t0);
> -        tcg_gen_or_i64(ret, ret, t1);
> -        tcg_temp_free_i64(t0);
> -        tcg_temp_free_i64(t1);
> +        if (TCG_TARGET_HAS_movcond_i64) {
> +            tcg_gen_op6i_i64(INDEX_op_movcond_i64, ret, c1, c2, v1, v2, 
> cond);
> +        } else {
> +            TCGv_i64 t0 = tcg_temp_new_i64();
> +            TCGv_i64 t1 = tcg_temp_new_i64();
> +            tcg_gen_setcond_i64(cond, t0, c1, c2);
> +            tcg_gen_neg_i64(t0, t0);
> +            tcg_gen_and_i64(t1, v1, t0);
> +            tcg_gen_andc_i64(ret, v2, t0);
> +            tcg_gen_or_i64(ret, ret, t1);
> +            tcg_temp_free_i64(t0);
> +            tcg_temp_free_i64(t1);
> +        }
>      }
>  }
>  

Reviewed-by: Aurelien Jarno <address@hidden>

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