On 11/06/14 11:19, Charles Baylis wrote:
> 2014-05-22 Charles Baylis <[email protected]>
>
> * config/arm/bpabi.S (__aeabi_uldivmod): Optimise stack pointer
> manipulation.
OK.
R.
> ---
> libgcc/config/arm/bpabi.S | 54
> +++++++++++++++++++++++++++++++++++++----------
> 1 file changed, 43 insertions(+), 11 deletions(-)
>
> diff --git a/libgcc/config/arm/bpabi.S b/libgcc/config/arm/bpabi.S
> index ae76cd3..67246b0 100644
> --- a/libgcc/config/arm/bpabi.S
> +++ b/libgcc/config/arm/bpabi.S
> @@ -120,6 +120,46 @@ ARM_FUNC_START aeabi_ulcmp
> #endif
> .endm
>
> +/* we can use STRD/LDRD on v5TE and later, and any Thumb-2 architecture. */
> +#if (defined(__ARM_EABI__) \
> + && (defined(__thumb2__) \
> + || (__ARM_ARCH >= 5 && defined(__TARGET_FEATURE_DSP))))
> +#define CAN_USE_LDRD 1
> +#else
> +#define CAN_USE_LDRD 0
> +#endif
> +
> +/* set up stack from for call to __udivmoddi4. At the end of the macro the
> + stack is arranged as follows:
> + sp+12 / space for remainder
> + sp+8 \ (written by __udivmoddi4)
> + sp+4 lr
> + sp+0 sp+8 [rp (remainder pointer) argument for __udivmoddi4]
> +
> + */
> +.macro push_for_divide fname
> +#if defined(__thumb2__) && CAN_USE_LDRD
> + sub ip, sp, #8
> + strd ip, lr, [sp, #-16]!
> +#else
> + sub sp, sp, #8
> + do_push {sp, lr}
> +#endif
> +98: cfi_push 98b - \fname, 0xe, -0xc, 0x10
> +.endm
> +
> +/* restore stack */
> +.macro pop_for_divide
> + ldr lr, [sp, #4]
> +#if CAN_USE_LDRD
> + ldrd r2, r3, [sp, #8]
> + add sp, sp, #16
> +#else
> + add sp, sp, #8
> + do_pop {r2, r3}
> +#endif
> +.endm
> +
> #ifdef L_aeabi_ldivmod
>
> /* Perform 64 bit signed division.
> @@ -165,18 +205,10 @@ ARM_FUNC_START aeabi_uldivmod
> cfi_start __aeabi_uldivmod, LSYM(Lend_aeabi_uldivmod)
> test_div_by_zero unsigned
>
> - sub sp, sp, #8
> -#if defined(__thumb2__)
> - mov ip, sp
> - push {ip, lr}
> -#else
> - do_push {sp, lr}
> -#endif
> -98: cfi_push 98b - __aeabi_uldivmod, 0xe, -0xc, 0x10
> + push_for_divide __aeabi_uldivmod
> + /* arguments in (r0:r1), (r2:r3) and *sp */
> bl SYM(__gnu_uldivmod_helper) __PLT__
> - ldr lr, [sp, #4]
> - add sp, sp, #8
> - do_pop {r2, r3}
> + pop_for_divide
> RET
> cfi_end LSYM(Lend_aeabi_uldivmod)
>
>
