[1/2] ARM: add neon helpers for VQSHLU

Add neon helper functions to implement VQSHLU, which is a
signed-to-unsigned version of VQSHL available only as an
immediate form.

Signed-off-by: Juha Riihimäki <juha.riihimaki@nokia.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
---
 target-arm/helpers.h     |    4 +++
 target-arm/neon_helper.c |   47 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 51 insertions(+), 0 deletions(-)

On Mon, Jan 03, 2011 at 04:20:47PM +0000, Peter Maydell wrote:
> Add neon helper functions to implement VQSHLU, which is a
> signed-to-unsigned version of VQSHL available only as an
> immediate form.
> 
> Signed-off-by: Juha Riihimäki <juha.riihimaki@nokia.com>
> Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
> ---
>  target-arm/helpers.h     |    4 +++
>  target-arm/neon_helper.c |   47 ++++++++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 51 insertions(+), 0 deletions(-)
> 
> diff --git a/target-arm/helpers.h b/target-arm/helpers.h
> index 0d1bc47..b88ebae 100644
> --- a/target-arm/helpers.h
> +++ b/target-arm/helpers.h
> @@ -249,6 +249,10 @@ DEF_HELPER_3(neon_qshl_u32, i32, env, i32, i32)
>  DEF_HELPER_3(neon_qshl_s32, i32, env, i32, i32)
>  DEF_HELPER_3(neon_qshl_u64, i64, env, i64, i64)
>  DEF_HELPER_3(neon_qshl_s64, i64, env, i64, i64)
> +DEF_HELPER_3(neon_qshlu_s8, i32, env, i32, i32);
> +DEF_HELPER_3(neon_qshlu_s16, i32, env, i32, i32);
> +DEF_HELPER_3(neon_qshlu_s32, i32, env, i32, i32);
> +DEF_HELPER_3(neon_qshlu_s64, i64, env, i64, i64);
>  DEF_HELPER_3(neon_qrshl_u8, i32, env, i32, i32)
>  DEF_HELPER_3(neon_qrshl_s8, i32, env, i32, i32)
>  DEF_HELPER_3(neon_qrshl_u16, i32, env, i32, i32)
> diff --git a/target-arm/neon_helper.c b/target-arm/neon_helper.c
> index dae063e..20f3c16 100644
> --- a/target-arm/neon_helper.c
> +++ b/target-arm/neon_helper.c
> @@ -632,6 +632,53 @@ uint64_t HELPER(neon_qshl_s64)(CPUState *env, uint64_t valop, uint64_t shiftop)
>      return val;
>  }
>  
> +#define NEON_FN(dest, src1, src2) do { \
> +    if (src1 & (1 << (sizeof(src1) * 8 - 1))) { \
> +        SET_QC(); \
> +        dest = 0; \
> +    } else { \
> +        int8_t tmp; \
> +        tmp = (int8_t)src2; \
> +        if (tmp >= (ssize_t)sizeof(src1) * 8) { \
> +            if (src1) { \
> +                SET_QC(); \
> +                dest = ~0; \
> +            } else { \
> +                dest = 0; \
> +            } \
> +        } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \
> +            dest = 0; \
> +        } else if (tmp < 0) { \
> +            dest = src1 >> -tmp; \
> +        } else { \
> +            dest = src1 << tmp; \
> +            if ((dest >> tmp) != src1) { \
> +                SET_QC(); \
> +                dest = ~0; \
> +            } \
> +        } \
> +    }} while (0)
> +NEON_VOP_ENV(qshlu_s8, neon_u8, 4)
> +NEON_VOP_ENV(qshlu_s16, neon_u16, 2)
> +#undef NEON_FN
> +
> +uint32_t HELPER(neon_qshlu_s32)(CPUState *env, uint32_t valop, uint32_t shiftop)
> +{
> +    if ((int32_t)valop < 0) {
> +        SET_QC();
> +        return 0;
> +    }
> +    return helper_neon_qshl_u32(env, valop, shiftop);
> +}

I guess defining this function using helper_neon_qshl_u32() instead of
using NEON_VOP_ENV(qshlu_s32, neon_u32, 1) is to optimize the generated
code. Note that it only make 48 bytes difference, with one jump.

> +uint64_t HELPER(neon_qshlu_s64)(CPUState *env, uint64_t valop, uint64_t shiftop)
> +{
> +    if ((int64_t)valop < 0) {
> +        SET_QC();
> +        return 0;
> +    }
> +    return helper_neon_qshl_u64(env, valop, shiftop);
> +}
>  
>  /* FIXME: This is wrong.  */
>  #define NEON_FN(dest, src1, src2) do { \

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