On Mon, Aug 05, 2013 at 08:07:19AM -1000, Richard Henderson wrote:
> Use a 7 byte lea before the ultimate 10 byte movq.
>
> Signed-off-by: Richard Henderson <[email protected]>
> ---
> tcg/i386/tcg-target.c | 19 ++++++++++++++++---
> 1 file changed, 16 insertions(+), 3 deletions(-)
>
> diff --git a/tcg/i386/tcg-target.c b/tcg/i386/tcg-target.c
> index 841bd75..456bd9e 100644
> --- a/tcg/i386/tcg-target.c
> +++ b/tcg/i386/tcg-target.c
> @@ -541,19 +541,32 @@ static inline void tcg_out_mov(TCGContext *s, TCGType
> type,
> static void tcg_out_movi(TCGContext *s, TCGType type,
> TCGReg ret, tcg_target_long arg)
> {
> + tcg_target_long diff;
> +
> if (arg == 0) {
> tgen_arithr(s, ARITH_XOR, ret, ret);
> return;
> } else if (arg == (uint32_t)arg || type == TCG_TYPE_I32) {
> tcg_out_opc(s, OPC_MOVL_Iv + LOWREGMASK(ret), 0, ret, 0);
> tcg_out32(s, arg);
> + return;
> } else if (arg == (int32_t)arg) {
> tcg_out_modrm(s, OPC_MOVL_EvIz + P_REXW, 0, ret);
> tcg_out32(s, arg);
> - } else {
> - tcg_out_opc(s, OPC_MOVL_Iv + P_REXW + LOWREGMASK(ret), 0, ret, 0);
> - tcg_out64(s, arg);
> + return;
> }
Now that all the else parts end up with a return, it would improve
readability to remove them and keep only the ifs.
> +
> + /* Try a 7 byte pc-relative lea before the 10 byte movq. */
> + diff = arg - ((tcg_target_long)s->code_ptr + 7);
> + if (diff == (int32_t)diff) {
> + tcg_out_opc(s, OPC_LEA | P_REXW, ret, 0, 0);
> + tcg_out8(s, (LOWREGMASK(ret) << 3) | 5);
> + tcg_out32(s, diff);
> + return;
> + }
> +
> + tcg_out_opc(s, OPC_MOVL_Iv + P_REXW + LOWREGMASK(ret), 0, ret, 0);
> + tcg_out64(s, arg);
> }
>
> static inline void tcg_out_pushi(TCGContext *s, tcg_target_long val)
Otherwise it looks good.
--
Aurelien Jarno GPG: 1024D/F1BCDB73
[email protected] http://www.aurel32.net
