/*

 *  MMX/3DNow!/SSE/SSE2/SSE3/SSSE3/SSE4/PNI support

 *

 *  Copyright (c) 2005 Fabrice Bellard

 *  Copyright (c) 2008 Intel Corporation  <andrew.zaborowski@intel.com>

 *

 * This library is free software; you can redistribute it and/or

 * modify it under the terms of the GNU Lesser General Public

 * License as published by the Free Software Foundation; either

 * version 2 of the License, or (at your option) any later version.

 *

 * This library is distributed in the hope that it will be useful,

 * but WITHOUT ANY WARRANTY; without even the implied warranty of

 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU

 * Lesser General Public License for more details.

 *

 * You should have received a copy of the GNU Lesser General Public

 * License along with this library; if not, write to the Free Software

 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA

 */

#if SHIFT == 0

#define Reg MMXReg

#define XMM_ONLY(x...)

#define B(n) MMX_B(n)

#define W(n) MMX_W(n)

#define L(n) MMX_L(n)

#define Q(n) q

#define SUFFIX _mmx

#else

#define Reg XMMReg

#define XMM_ONLY(x...) x

#define B(n) XMM_B(n)

#define W(n) XMM_W(n)

#define L(n) XMM_L(n)

#define Q(n) XMM_Q(n)

#define SUFFIX _xmm

#endif

void glue(helper_psrlw, SUFFIX)(Reg *d, Reg *s)

{

    int shift;

    if (s->Q(0) > 15) {

        d->Q(0) = 0;

#if SHIFT == 1

        d->Q(1) = 0;

#endif

    } else {

        shift = s->B(0);

        d->W(0) >>= shift;

        d->W(1) >>= shift;

        d->W(2) >>= shift;

        d->W(3) >>= shift;

#if SHIFT == 1

        d->W(4) >>= shift;

        d->W(5) >>= shift;

        d->W(6) >>= shift;

        d->W(7) >>= shift;

#endif

    }

}

void glue(helper_psraw, SUFFIX)(Reg *d, Reg *s)

{

    int shift;

    if (s->Q(0) > 15) {

        shift = 15;

    } else {

        shift = s->B(0);

    }

    d->W(0) = (int16_t)d->W(0) >> shift;

    d->W(1) = (int16_t)d->W(1) >> shift;

    d->W(2) = (int16_t)d->W(2) >> shift;

    d->W(3) = (int16_t)d->W(3) >> shift;

#if SHIFT == 1

    d->W(4) = (int16_t)d->W(4) >> shift;

    d->W(5) = (int16_t)d->W(5) >> shift;

    d->W(6) = (int16_t)d->W(6) >> shift;

    d->W(7) = (int16_t)d->W(7) >> shift;

#endif

}

void glue(helper_psllw, SUFFIX)(Reg *d, Reg *s)

{

    int shift;

    if (s->Q(0) > 15) {

        d->Q(0) = 0;

#if SHIFT == 1

        d->Q(1) = 0;

#endif

    } else {

        shift = s->B(0);

        d->W(0) <<= shift;

        d->W(1) <<= shift;

        d->W(2) <<= shift;

        d->W(3) <<= shift;

#if SHIFT == 1

        d->W(4) <<= shift;

        d->W(5) <<= shift;

        d->W(6) <<= shift;

        d->W(7) <<= shift;

#endif

    }

}

void glue(helper_psrld, SUFFIX)(Reg *d, Reg *s)

{

    int shift;

    if (s->Q(0) > 31) {

        d->Q(0) = 0;

#if SHIFT == 1

        d->Q(1) = 0;

#endif

    } else {

        shift = s->B(0);

        d->L(0) >>= shift;

        d->L(1) >>= shift;

#if SHIFT == 1

        d->L(2) >>= shift;

        d->L(3) >>= shift;

#endif

    }

}

void glue(helper_psrad, SUFFIX)(Reg *d, Reg *s)

{

    int shift;

    if (s->Q(0) > 31) {

        shift = 31;

    } else {

        shift = s->B(0);

    }

    d->L(0) = (int32_t)d->L(0) >> shift;

    d->L(1) = (int32_t)d->L(1) >> shift;

#if SHIFT == 1

    d->L(2) = (int32_t)d->L(2) >> shift;

    d->L(3) = (int32_t)d->L(3) >> shift;

#endif

}

void glue(helper_pslld, SUFFIX)(Reg *d, Reg *s)

{

    int shift;

    if (s->Q(0) > 31) {

        d->Q(0) = 0;

#if SHIFT == 1

        d->Q(1) = 0;

#endif

    } else {

        shift = s->B(0);

        d->L(0) <<= shift;

        d->L(1) <<= shift;

#if SHIFT == 1

        d->L(2) <<= shift;

        d->L(3) <<= shift;

#endif

    }

}

void glue(helper_psrlq, SUFFIX)(Reg *d, Reg *s)

{

    int shift;

    if (s->Q(0) > 63) {

        d->Q(0) = 0;

#if SHIFT == 1

        d->Q(1) = 0;

#endif

    } else {

        shift = s->B(0);

        d->Q(0) >>= shift;

#if SHIFT == 1

        d->Q(1) >>= shift;

#endif

    }

}

void glue(helper_psllq, SUFFIX)(Reg *d, Reg *s)

{

    int shift;

    if (s->Q(0) > 63) {

        d->Q(0) = 0;

#if SHIFT == 1

        d->Q(1) = 0;

#endif

    } else {

        shift = s->B(0);

        d->Q(0) <<= shift;

#if SHIFT == 1

        d->Q(1) <<= shift;

#endif

    }

}

#if SHIFT == 1

void glue(helper_psrldq, SUFFIX)(Reg *d, Reg *s)

{

    int shift, i;

    shift = s->L(0);

    if (shift > 16)

        shift = 16;

    for(i = 0; i < 16 - shift; i++)

        d->B(i) = d->B(i + shift);

    for(i = 16 - shift; i < 16; i++)

        d->B(i) = 0;

}

void glue(helper_pslldq, SUFFIX)(Reg *d, Reg *s)

{

    int shift, i;

    shift = s->L(0);

    if (shift > 16)

        shift = 16;

    for(i = 15; i >= shift; i--)

        d->B(i) = d->B(i - shift);

    for(i = 0; i < shift; i++)

        d->B(i) = 0;

}

#endif

#define SSE_HELPER_B(name, F)\

void glue(name, SUFFIX) (Reg *d, Reg *s)\

{\

    d->B(0) = F(d->B(0), s->B(0));\

    d->B(1) = F(d->B(1), s->B(1));\

    d->B(2) = F(d->B(2), s->B(2));\

    d->B(3) = F(d->B(3), s->B(3));\

    d->B(4) = F(d->B(4), s->B(4));\

    d->B(5) = F(d->B(5), s->B(5));\

    d->B(6) = F(d->B(6), s->B(6));\

    d->B(7) = F(d->B(7), s->B(7));\

    XMM_ONLY(\

    d->B(8) = F(d->B(8), s->B(8));\

    d->B(9) = F(d->B(9), s->B(9));\

    d->B(10) = F(d->B(10), s->B(10));\

    d->B(11) = F(d->B(11), s->B(11));\

    d->B(12) = F(d->B(12), s->B(12));\

    d->B(13) = F(d->B(13), s->B(13));\

    d->B(14) = F(d->B(14), s->B(14));\

    d->B(15) = F(d->B(15), s->B(15));\

    )\

}

#define SSE_HELPER_W(name, F)\

void glue(name, SUFFIX) (Reg *d, Reg *s)\

{\

    d->W(0) = F(d->W(0), s->W(0));\

    d->W(1) = F(d->W(1), s->W(1));\

    d->W(2) = F(d->W(2), s->W(2));\

    d->W(3) = F(d->W(3), s->W(3));\

    XMM_ONLY(\

    d->W(4) = F(d->W(4), s->W(4));\

    d->W(5) = F(d->W(5), s->W(5));\

    d->W(6) = F(d->W(6), s->W(6));\

    d->W(7) = F(d->W(7), s->W(7));\

    )\

}

#define SSE_HELPER_L(name, F)\

void glue(name, SUFFIX) (Reg *d, Reg *s)\

{\

    d->L(0) = F(d->L(0), s->L(0));\

    d->L(1) = F(d->L(1), s->L(1));\

    XMM_ONLY(\

    d->L(2) = F(d->L(2), s->L(2));\

    d->L(3) = F(d->L(3), s->L(3));\

    )\

}

#define SSE_HELPER_Q(name, F)\

void glue(name, SUFFIX) (Reg *d, Reg *s)\

{\

    d->Q(0) = F(d->Q(0), s->Q(0));\

    XMM_ONLY(\

    d->Q(1) = F(d->Q(1), s->Q(1));\

    )\

}

#if SHIFT == 0

static inline int satub(int x)

{

    if (x < 0)

        return 0;

    else if (x > 255)

        return 255;

    else

        return x;

}

static inline int satuw(int x)

{

    if (x < 0)

        return 0;

    else if (x > 65535)

        return 65535;

    else

        return x;

}

static inline int satsb(int x)

{

    if (x < -128)

        return -128;

    else if (x > 127)

        return 127;

    else

        return x;

}

static inline int satsw(int x)

{

    if (x < -32768)

        return -32768;

    else if (x > 32767)

        return 32767;

    else

        return x;

}

#define FADD(a, b) ((a) + (b))

#define FADDUB(a, b) satub((a) + (b))

#define FADDUW(a, b) satuw((a) + (b))

#define FADDSB(a, b) satsb((int8_t)(a) + (int8_t)(b))

#define FADDSW(a, b) satsw((int16_t)(a) + (int16_t)(b))

#define FSUB(a, b) ((a) - (b))

#define FSUBUB(a, b) satub((a) - (b))

#define FSUBUW(a, b) satuw((a) - (b))

#define FSUBSB(a, b) satsb((int8_t)(a) - (int8_t)(b))

#define FSUBSW(a, b) satsw((int16_t)(a) - (int16_t)(b))

#define FMINUB(a, b) ((a) < (b)) ? (a) : (b)

#define FMINSW(a, b) ((int16_t)(a) < (int16_t)(b)) ? (a) : (b)

#define FMAXUB(a, b) ((a) > (b)) ? (a) : (b)

#define FMAXSW(a, b) ((int16_t)(a) > (int16_t)(b)) ? (a) : (b)

#define FAND(a, b) (a) & (b)

#define FANDN(a, b) ((~(a)) & (b))

#define FOR(a, b) (a) | (b)

#define FXOR(a, b) (a) ^ (b)

#define FCMPGTB(a, b) (int8_t)(a) > (int8_t)(b) ? -1 : 0

#define FCMPGTW(a, b) (int16_t)(a) > (int16_t)(b) ? -1 : 0

#define FCMPGTL(a, b) (int32_t)(a) > (int32_t)(b) ? -1 : 0

#define FCMPEQ(a, b) (a) == (b) ? -1 : 0

#define FMULLW(a, b) (a) * (b)

#define FMULHRW(a, b) ((int16_t)(a) * (int16_t)(b) + 0x8000) >> 16

#define FMULHUW(a, b) (a) * (b) >> 16

#define FMULHW(a, b) (int16_t)(a) * (int16_t)(b) >> 16

#define FAVG(a, b) ((a) + (b) + 1) >> 1

#endif

SSE_HELPER_B(helper_paddb, FADD)

SSE_HELPER_W(helper_paddw, FADD)

SSE_HELPER_L(helper_paddl, FADD)

SSE_HELPER_Q(helper_paddq, FADD)

SSE_HELPER_B(helper_psubb, FSUB)

SSE_HELPER_W(helper_psubw, FSUB)

SSE_HELPER_L(helper_psubl, FSUB)

SSE_HELPER_Q(helper_psubq, FSUB)

SSE_HELPER_B(helper_paddusb, FADDUB)

SSE_HELPER_B(helper_paddsb, FADDSB)

SSE_HELPER_B(helper_psubusb, FSUBUB)

SSE_HELPER_B(helper_psubsb, FSUBSB)

SSE_HELPER_W(helper_paddusw, FADDUW)

SSE_HELPER_W(helper_paddsw, FADDSW)

SSE_HELPER_W(helper_psubusw, FSUBUW)

SSE_HELPER_W(helper_psubsw, FSUBSW)

SSE_HELPER_B(helper_pminub, FMINUB)

SSE_HELPER_B(helper_pmaxub, FMAXUB)

SSE_HELPER_W(helper_pminsw, FMINSW)

SSE_HELPER_W(helper_pmaxsw, FMAXSW)

SSE_HELPER_Q(helper_pand, FAND)

SSE_HELPER_Q(helper_pandn, FANDN)

SSE_HELPER_Q(helper_por, FOR)

SSE_HELPER_Q(helper_pxor, FXOR)

SSE_HELPER_B(helper_pcmpgtb, FCMPGTB)

SSE_HELPER_W(helper_pcmpgtw, FCMPGTW)

SSE_HELPER_L(helper_pcmpgtl, FCMPGTL)

SSE_HELPER_B(helper_pcmpeqb, FCMPEQ)

SSE_HELPER_W(helper_pcmpeqw, FCMPEQ)

SSE_HELPER_L(helper_pcmpeql, FCMPEQ)

SSE_HELPER_W(helper_pmullw, FMULLW)

#if SHIFT == 0

SSE_HELPER_W(helper_pmulhrw, FMULHRW)

#endif

SSE_HELPER_W(helper_pmulhuw, FMULHUW)

SSE_HELPER_W(helper_pmulhw, FMULHW)

SSE_HELPER_B(helper_pavgb, FAVG)

SSE_HELPER_W(helper_pavgw, FAVG)

void glue(helper_pmuludq, SUFFIX) (Reg *d, Reg *s)

{

    d->Q(0) = (uint64_t)s->L(0) * (uint64_t)d->L(0);

#if SHIFT == 1

    d->Q(1) = (uint64_t)s->L(2) * (uint64_t)d->L(2);

#endif

}

void glue(helper_pmaddwd, SUFFIX) (Reg *d, Reg *s)

{

    int i;

    for(i = 0; i < (2 << SHIFT); i++) {

        d->L(i) = (int16_t)s->W(2*i) * (int16_t)d->W(2*i) +

            (int16_t)s->W(2*i+1) * (int16_t)d->W(2*i+1);

    }

}

#if SHIFT == 0

static inline int abs1(int a)

{

    if (a < 0)

        return -a;

    else

        return a;

}

#endif

void glue(helper_psadbw, SUFFIX) (Reg *d, Reg *s)

{

    unsigned int val;

    val = 0;

    val += abs1(d->B(0) - s->B(0));

    val += abs1(d->B(1) - s->B(1));

    val += abs1(d->B(2) - s->B(2));

    val += abs1(d->B(3) - s->B(3));

    val += abs1(d->B(4) - s->B(4));

    val += abs1(d->B(5) - s->B(5));

    val += abs1(d->B(6) - s->B(6));

    val += abs1(d->B(7) - s->B(7));

    d->Q(0) = val;

#if SHIFT == 1

    val = 0;

    val += abs1(d->B(8) - s->B(8));

    val += abs1(d->B(9) - s->B(9));

    val += abs1(d->B(10) - s->B(10));

    val += abs1(d->B(11) - s->B(11));

    val += abs1(d->B(12) - s->B(12));

    val += abs1(d->B(13) - s->B(13));

    val += abs1(d->B(14) - s->B(14));

    val += abs1(d->B(15) - s->B(15));

    d->Q(1) = val;

#endif

}

void glue(helper_maskmov, SUFFIX) (Reg *d, Reg *s, target_ulong a0)

{

    int i;

    for(i = 0; i < (8 << SHIFT); i++) {

        if (s->B(i) & 0x80)

            stb(a0 + i, d->B(i));

    }

}

void glue(helper_movl_mm_T0, SUFFIX) (Reg *d, uint32_t val)

{

    d->L(0) = val;

    d->L(1) = 0;

#if SHIFT == 1

    d->Q(1) = 0;

#endif

}

#ifdef TARGET_X86_64

void glue(helper_movq_mm_T0, SUFFIX) (Reg *d, uint64_t val)

{

    d->Q(0) = val;

#if SHIFT == 1

    d->Q(1) = 0;

#endif

}

#endif

#if SHIFT == 0

void glue(helper_pshufw, SUFFIX) (Reg *d, Reg *s, int order)

{

    Reg r;

    r.W(0) = s->W(order & 3);

    r.W(1) = s->W((order >> 2) & 3);

    r.W(2) = s->W((order >> 4) & 3);

    r.W(3) = s->W((order >> 6) & 3);

    *d = r;

}

#else

void helper_shufps(Reg *d, Reg *s, int order)

{

    Reg r;

    r.L(0) = d->L(order & 3);

    r.L(1) = d->L((order >> 2) & 3);

    r.L(2) = s->L((order >> 4) & 3);

    r.L(3) = s->L((order >> 6) & 3);

    *d = r;

}

void helper_shufpd(Reg *d, Reg *s, int order)

{

    Reg r;

    r.Q(0) = d->Q(order & 1);

    r.Q(1) = s->Q((order >> 1) & 1);

    *d = r;

}

void glue(helper_pshufd, SUFFIX) (Reg *d, Reg *s, int order)

{

    Reg r;

    r.L(0) = s->L(order & 3);

    r.L(1) = s->L((order >> 2) & 3);

    r.L(2) = s->L((order >> 4) & 3);

    r.L(3) = s->L((order >> 6) & 3);