Re: [Qemu-ppc] [PATCH RFC v0 3/6] target-ppc: add vcmpnez[b, h, w][.] instructions

[David Gibson]

On Wed, Jul 27, 2016 at 12:56:55AM +0530, Nikunj A Dadhania wrote:
> From: Swapnil Bokade <address@hidden>
> 
> Adds following instructions:
> 
> vcmpnezb[.]: Vector Compare Not Equal or Zero Byte
> vcmpnezh[.]: Vector Compare Not Equal or Zero Halfword
> vcmpnezw[.]: Vector Compare Not Equal or Zero Word
> 
> Signed-off-by: Swapnil Bokade <address@hidden>
> Signed-off-by: Nikunj A Dadhania <address@hidden>
> ---
>  target-ppc/helper.h     |  6 ++++++
>  target-ppc/int_helper.c | 49 
> +++++++++++++++++++++++++++++++++++++++++++++++++
>  target-ppc/translate.c  |  6 ++++++
>  3 files changed, 61 insertions(+)
> 
> diff --git a/target-ppc/helper.h b/target-ppc/helper.h
> index ff6287e..e93b84b 100644
> --- a/target-ppc/helper.h
> +++ b/target-ppc/helper.h
> @@ -144,6 +144,9 @@ DEF_HELPER_4(vcmpequb, void, env, avr, avr, avr)
>  DEF_HELPER_4(vcmpequh, void, env, avr, avr, avr)
>  DEF_HELPER_4(vcmpequw, void, env, avr, avr, avr)
>  DEF_HELPER_4(vcmpequd, void, env, avr, avr, avr)
> +DEF_HELPER_4(vcmpnezb, void, env, avr, avr, avr)
> +DEF_HELPER_4(vcmpnezh, void, env, avr, avr, avr)
> +DEF_HELPER_4(vcmpnezw, void, env, avr, avr, avr)
>  DEF_HELPER_4(vcmpgtub, void, env, avr, avr, avr)
>  DEF_HELPER_4(vcmpgtuh, void, env, avr, avr, avr)
>  DEF_HELPER_4(vcmpgtuw, void, env, avr, avr, avr)
> @@ -160,6 +163,9 @@ DEF_HELPER_4(vcmpequb_dot, void, env, avr, avr, avr)
>  DEF_HELPER_4(vcmpequh_dot, void, env, avr, avr, avr)
>  DEF_HELPER_4(vcmpequw_dot, void, env, avr, avr, avr)
>  DEF_HELPER_4(vcmpequd_dot, void, env, avr, avr, avr)
> +DEF_HELPER_4(vcmpnezb_dot, void, env, avr, avr, avr)
> +DEF_HELPER_4(vcmpnezh_dot, void, env, avr, avr, avr)
> +DEF_HELPER_4(vcmpnezw_dot, void, env, avr, avr, avr)
>  DEF_HELPER_4(vcmpgtub_dot, void, env, avr, avr, avr)
>  DEF_HELPER_4(vcmpgtuh_dot, void, env, avr, avr, avr)
>  DEF_HELPER_4(vcmpgtuw_dot, void, env, avr, avr, avr)
> diff --git a/target-ppc/int_helper.c b/target-ppc/int_helper.c
> index c1b341c..bffe8d6 100644
> --- a/target-ppc/int_helper.c
> +++ b/target-ppc/int_helper.c
> @@ -718,6 +718,55 @@ VCMP(gtsd, >, s64)
>  #undef VCMP_DO
>  #undef VCMP
>  
> +#define VCMPNEZ_DO(suffix, element, record)                         \
> +void helper_vcmpnez##suffix(CPUPPCState *env, ppc_avr_t *r,         \
> +                            ppc_avr_t *a, ppc_avr_t *b)                 \
> +{                                                                       \
> +    uint64_t ones = (uint64_t)-1;                                       \
> +    uint64_t all = ones;                                                \
> +    uint64_t none = 0;                                                  \
> +    int i;                                                              \
> +                                                                        \
> +    for (i = 0; i < ARRAY_SIZE(r->element); i++) {                      \
> +        uint64_t result = ((a->element[i] == 0)                         \
> +                           || (b->element[i] == 0)                      \
> +                           || (a->element[i] != b->element[i]) ?        \
> +                           ones : 0x0);
> \

Couldn't you just use r->element[i] = result instead of the switch?

> +        switch (sizeof(a->element[0])) {                                \
> +        case 8:                                                         \
> +            r->u64[i] = result;                                         \
> +            break;
> \

Also it doesn't actually look like there is a 64-bit case.

> +        case 4:                                                         \
> +            r->u32[i] = result;                                         \
> +            break;                                                      \
> +        case 2:                                                         \
> +            r->u16[i] = result;                                         \
> +            break;                                                      \
> +        case 1:                                                         \
> +            r->u8[i] = result;                                          \
> +            break;                                                      \
> +        }                                                               \
> +        all &= result;                                                  \
> +        none |= result;                                                 \
> +    }                                                                   \
> +    if (record) {                                                       \
> +        env->crf[6] = ((all != 0) << 3) | ((none == 0) << 1);           \
> +    }                                                                   \
> +}
> +
> +/* VCMPNEZ - Vector compare not equal to zero
> + *   suffix  - instruction mnemonic suffix (b: byte, h: halfword, w: word)
> + *   element - element type to access from vector
> + */
> +#define VCMPNEZ(suffix, element)         \
> +    VCMPNEZ_DO(suffix, element, 0)       \
> +    VCMPNEZ_DO(suffix##_dot, element, 1)
> +VCMPNEZ(b, u8)
> +VCMPNEZ(h, u16)
> +VCMPNEZ(w, u32)
> +#undef VCMPNEZ_DO
> +#undef VCMPNEZ
> +
>  #define VCMPFP_DO(suffix, compare, order, record)                       \
>      void helper_vcmp##suffix(CPUPPCState *env, ppc_avr_t *r,            \
>                               ppc_avr_t *a, ppc_avr_t *b)                \
> diff --git a/target-ppc/translate.c b/target-ppc/translate.c
> index b18e13f..7cf0c8e 100644
> --- a/target-ppc/translate.c
> +++ b/target-ppc/translate.c
> @@ -7565,6 +7565,9 @@ GEN_VXRFORM(vcmpequb, 3, 0)
>  GEN_VXRFORM(vcmpequh, 3, 1)
>  GEN_VXRFORM(vcmpequw, 3, 2)
>  GEN_VXRFORM(vcmpequd, 3, 3)
> +GEN_VXRFORM(vcmpnezb, 3, 4)
> +GEN_VXRFORM(vcmpnezh, 3, 5)
> +GEN_VXRFORM(vcmpnezw, 3, 6)
>  GEN_VXRFORM(vcmpgtsb, 3, 12)
>  GEN_VXRFORM(vcmpgtsh, 3, 13)
>  GEN_VXRFORM(vcmpgtsw, 3, 14)
> @@ -10998,6 +11001,9 @@ GEN_VXFORM(vminfp, 5, 17),
>  GEN_VXRFORM(vcmpequb, 3, 0)
>  GEN_VXRFORM(vcmpequh, 3, 1)
>  GEN_VXRFORM(vcmpequw, 3, 2)
> +GEN_VXRFORM(vcmpnezb, 3, 4)
> +GEN_VXRFORM(vcmpnezh, 3, 5)
> +GEN_VXRFORM(vcmpnezw, 3, 6)
>  GEN_VXRFORM(vcmpgtsb, 3, 12)
>  GEN_VXRFORM(vcmpgtsh, 3, 13)
>  GEN_VXRFORM(vcmpgtsw, 3, 14)

-- 
David Gibson                    | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au  | minimalist, thank you.  NOT _the_ _other_
                                | _way_ _around_!
http://www.ozlabs.org/~dgibson

signature.asc
Description: PGP signature