Archipelago » qemu

/*

 * ARM NEON vector operations.

 *

 * Copyright (c) 2007, 2008 CodeSourcery.

 * Written by Paul Brook

 *

 * This code is licenced under the GNU GPL v2.

 */

#include <stdlib.h>

#include <stdio.h>

#include "cpu.h"

#include "exec-all.h"

#include "helpers.h"

#define SIGNBIT (uint32_t)0x80000000

#define SIGNBIT64 ((uint64_t)1 << 63)

#define SET_QC() env->vfp.xregs[ARM_VFP_FPSCR] = CPSR_Q

static float_status neon_float_status;

#define NFS &neon_float_status

/* Helper routines to perform bitwise copies between float and int.  */

static inline float32 vfp_itos(uint32_t i)

{

    union {

        uint32_t i;

        float32 s;

    } v;

    v.i = i;

    return v.s;

}

static inline uint32_t vfp_stoi(float32 s)

{

    union {

        uint32_t i;

        float32 s;

    } v;

    v.s = s;

    return v.i;

}

#define NEON_TYPE1(name, type) \

typedef struct \

{ \

    type v1; \

} neon_##name;

#ifdef HOST_WORDS_BIGENDIAN

#define NEON_TYPE2(name, type) \

typedef struct \

{ \

    type v2; \

    type v1; \

} neon_##name;

#define NEON_TYPE4(name, type) \

typedef struct \

{ \

    type v4; \

    type v3; \

    type v2; \

    type v1; \

} neon_##name;

#else

#define NEON_TYPE2(name, type) \

typedef struct \

{ \

    type v1; \

    type v2; \

} neon_##name;

#define NEON_TYPE4(name, type) \

typedef struct \

{ \

    type v1; \

    type v2; \

    type v3; \

    type v4; \

} neon_##name;

#endif

NEON_TYPE4(s8, int8_t)

NEON_TYPE4(u8, uint8_t)

NEON_TYPE2(s16, int16_t)

NEON_TYPE2(u16, uint16_t)

NEON_TYPE1(s32, int32_t)

NEON_TYPE1(u32, uint32_t)

#undef NEON_TYPE4

#undef NEON_TYPE2

#undef NEON_TYPE1

/* Copy from a uint32_t to a vector structure type.  */

#define NEON_UNPACK(vtype, dest, val) do { \

    union { \

        vtype v; \

        uint32_t i; \

    } conv_u; \

    conv_u.i = (val); \

    dest = conv_u.v; \

    } while(0)

/* Copy from a vector structure type to a uint32_t.  */

#define NEON_PACK(vtype, dest, val) do { \

    union { \

        vtype v; \

        uint32_t i; \

    } conv_u; \

    conv_u.v = (val); \

    dest = conv_u.i; \

    } while(0)

#define NEON_DO1 \

    NEON_FN(vdest.v1, vsrc1.v1, vsrc2.v1);

#define NEON_DO2 \

    NEON_FN(vdest.v1, vsrc1.v1, vsrc2.v1); \

    NEON_FN(vdest.v2, vsrc1.v2, vsrc2.v2);

#define NEON_DO4 \

    NEON_FN(vdest.v1, vsrc1.v1, vsrc2.v1); \

    NEON_FN(vdest.v2, vsrc1.v2, vsrc2.v2); \

    NEON_FN(vdest.v3, vsrc1.v3, vsrc2.v3); \

    NEON_FN(vdest.v4, vsrc1.v4, vsrc2.v4);

#define NEON_VOP_BODY(vtype, n) \

{ \

    uint32_t res; \

    vtype vsrc1; \

    vtype vsrc2; \

    vtype vdest; \

    NEON_UNPACK(vtype, vsrc1, arg1); \

    NEON_UNPACK(vtype, vsrc2, arg2); \

    NEON_DO##n; \

    NEON_PACK(vtype, res, vdest); \

    return res; \

}

#define NEON_VOP(name, vtype, n) \

uint32_t HELPER(glue(neon_,name))(uint32_t arg1, uint32_t arg2) \

NEON_VOP_BODY(vtype, n)

#define NEON_VOP_ENV(name, vtype, n) \

uint32_t HELPER(glue(neon_,name))(CPUState *env, uint32_t arg1, uint32_t arg2) \

NEON_VOP_BODY(vtype, n)

/* Pairwise operations.  */

/* For 32-bit elements each segment only contains a single element, so

   the elementwise and pairwise operations are the same.  */

#define NEON_PDO2 \

    NEON_FN(vdest.v1, vsrc1.v1, vsrc1.v2); \

    NEON_FN(vdest.v2, vsrc2.v1, vsrc2.v2);

#define NEON_PDO4 \

    NEON_FN(vdest.v1, vsrc1.v1, vsrc1.v2); \

    NEON_FN(vdest.v2, vsrc1.v3, vsrc1.v4); \

    NEON_FN(vdest.v3, vsrc2.v1, vsrc2.v2); \

    NEON_FN(vdest.v4, vsrc2.v3, vsrc2.v4); \

#define NEON_POP(name, vtype, n) \

uint32_t HELPER(glue(neon_,name))(uint32_t arg1, uint32_t arg2) \

{ \

    uint32_t res; \

    vtype vsrc1; \

    vtype vsrc2; \

    vtype vdest; \

    NEON_UNPACK(vtype, vsrc1, arg1); \

    NEON_UNPACK(vtype, vsrc2, arg2); \

    NEON_PDO##n; \

    NEON_PACK(vtype, res, vdest); \

    return res; \

}

/* Unary operators.  */

#define NEON_VOP1(name, vtype, n) \

uint32_t HELPER(glue(neon_,name))(uint32_t arg) \

{ \

    vtype vsrc1; \

    vtype vdest; \

    NEON_UNPACK(vtype, vsrc1, arg); \

    NEON_DO##n; \

    NEON_PACK(vtype, arg, vdest); \

    return arg; \

}

#define NEON_USAT(dest, src1, src2, type) do { \

    uint32_t tmp = (uint32_t)src1 + (uint32_t)src2; \

    if (tmp != (type)tmp) { \

        SET_QC(); \

        dest = ~0; \

    } else { \

        dest = tmp; \

    }} while(0)

#define NEON_FN(dest, src1, src2) NEON_USAT(dest, src1, src2, uint8_t)

NEON_VOP_ENV(qadd_u8, neon_u8, 4)

#undef NEON_FN

#define NEON_FN(dest, src1, src2) NEON_USAT(dest, src1, src2, uint16_t)

NEON_VOP_ENV(qadd_u16, neon_u16, 2)

#undef NEON_FN

#undef NEON_USAT

uint32_t HELPER(neon_qadd_u32)(CPUState *env, uint32_t a, uint32_t b)

{

    uint32_t res = a + b;

    if (res < a) {

        SET_QC();

        res = ~0;

    }

    return res;

}

uint64_t HELPER(neon_qadd_u64)(CPUState *env, uint64_t src1, uint64_t src2)

{

    uint64_t res;

    res = src1 + src2;

    if (res < src1) {

        SET_QC();

        res = ~(uint64_t)0;

    }

    return res;

}

#define NEON_SSAT(dest, src1, src2, type) do { \

    int32_t tmp = (uint32_t)src1 + (uint32_t)src2; \

    if (tmp != (type)tmp) { \

        SET_QC(); \

        if (src2 > 0) { \

            tmp = (1 << (sizeof(type) * 8 - 1)) - 1; \

        } else { \

            tmp = 1 << (sizeof(type) * 8 - 1); \

        } \

    } \

    dest = tmp; \

    } while(0)

#define NEON_FN(dest, src1, src2) NEON_SSAT(dest, src1, src2, int8_t)

NEON_VOP_ENV(qadd_s8, neon_s8, 4)

#undef NEON_FN

#define NEON_FN(dest, src1, src2) NEON_SSAT(dest, src1, src2, int16_t)

NEON_VOP_ENV(qadd_s16, neon_s16, 2)

#undef NEON_FN

#undef NEON_SSAT

uint32_t HELPER(neon_qadd_s32)(CPUState *env, uint32_t a, uint32_t b)

{

    uint32_t res = a + b;

    if (((res ^ a) & SIGNBIT) && !((a ^ b) & SIGNBIT)) {

        SET_QC();

        res = ~(((int32_t)a >> 31) ^ SIGNBIT);

    }

    return res;

}

uint64_t HELPER(neon_qadd_s64)(CPUState *env, uint64_t src1, uint64_t src2)

{

    uint64_t res;

    res = src1 + src2;

    if (((res ^ src1) & SIGNBIT64) && !((src1 ^ src2) & SIGNBIT64)) {

        SET_QC();

        res = ((int64_t)src1 >> 63) ^ ~SIGNBIT64;

    }

    return res;

}

#define NEON_USAT(dest, src1, src2, type) do { \

    uint32_t tmp = (uint32_t)src1 - (uint32_t)src2; \

    if (tmp != (type)tmp) { \

        SET_QC(); \

        dest = 0; \

    } else { \

        dest = tmp; \

    }} while(0)

#define NEON_FN(dest, src1, src2) NEON_USAT(dest, src1, src2, uint8_t)

NEON_VOP_ENV(qsub_u8, neon_u8, 4)

#undef NEON_FN

#define NEON_FN(dest, src1, src2) NEON_USAT(dest, src1, src2, uint16_t)

NEON_VOP_ENV(qsub_u16, neon_u16, 2)

#undef NEON_FN

#undef NEON_USAT

uint32_t HELPER(neon_qsub_u32)(CPUState *env, uint32_t a, uint32_t b)

{

    uint32_t res = a - b;

    if (res > a) {

        SET_QC();

        res = 0;

    }

    return res;

}

uint64_t HELPER(neon_qsub_u64)(CPUState *env, uint64_t src1, uint64_t src2)

{

    uint64_t res;

    if (src1 < src2) {

        SET_QC();

        res = 0;

    } else {

        res = src1 - src2;

    }

    return res;

}

#define NEON_SSAT(dest, src1, src2, type) do { \

    int32_t tmp = (uint32_t)src1 - (uint32_t)src2; \

    if (tmp != (type)tmp) { \

        SET_QC(); \

        if (src2 < 0) { \

            tmp = (1 << (sizeof(type) * 8 - 1)) - 1; \

        } else { \

            tmp = 1 << (sizeof(type) * 8 - 1); \

        } \

    } \

    dest = tmp; \

    } while(0)

#define NEON_FN(dest, src1, src2) NEON_SSAT(dest, src1, src2, int8_t)

NEON_VOP_ENV(qsub_s8, neon_s8, 4)

#undef NEON_FN

#define NEON_FN(dest, src1, src2) NEON_SSAT(dest, src1, src2, int16_t)

NEON_VOP_ENV(qsub_s16, neon_s16, 2)

#undef NEON_FN

#undef NEON_SSAT

uint32_t HELPER(neon_qsub_s32)(CPUState *env, uint32_t a, uint32_t b)

{

    uint32_t res = a - b;

    if (((res ^ a) & SIGNBIT) && ((a ^ b) & SIGNBIT)) {

        SET_QC();

        res = ~(((int32_t)a >> 31) ^ SIGNBIT);

    }

    return res;

}

uint64_t HELPER(neon_qsub_s64)(CPUState *env, uint64_t src1, uint64_t src2)

{

    uint64_t res;

    res = src1 - src2;

    if (((res ^ src1) & SIGNBIT64) && ((src1 ^ src2) & SIGNBIT64)) {

        SET_QC();

        res = ((int64_t)src1 >> 63) ^ ~SIGNBIT64;

    }

    return res;

}

#define NEON_FN(dest, src1, src2) dest = (src1 + src2) >> 1

NEON_VOP(hadd_s8, neon_s8, 4)

NEON_VOP(hadd_u8, neon_u8, 4)

NEON_VOP(hadd_s16, neon_s16, 2)

NEON_VOP(hadd_u16, neon_u16, 2)

#undef NEON_FN

int32_t HELPER(neon_hadd_s32)(int32_t src1, int32_t src2)

{

    int32_t dest;

    dest = (src1 >> 1) + (src2 >> 1);

    if (src1 & src2 & 1)

        dest++;

    return dest;

}

uint32_t HELPER(neon_hadd_u32)(uint32_t src1, uint32_t src2)

{

    uint32_t dest;

    dest = (src1 >> 1) + (src2 >> 1);

    if (src1 & src2 & 1)

        dest++;

    return dest;

}

#define NEON_FN(dest, src1, src2) dest = (src1 + src2 + 1) >> 1

NEON_VOP(rhadd_s8, neon_s8, 4)

NEON_VOP(rhadd_u8, neon_u8, 4)

NEON_VOP(rhadd_s16, neon_s16, 2)

NEON_VOP(rhadd_u16, neon_u16, 2)

#undef NEON_FN

int32_t HELPER(neon_rhadd_s32)(int32_t src1, int32_t src2)

{

    int32_t dest;

    dest = (src1 >> 1) + (src2 >> 1);

    if ((src1 | src2) & 1)

        dest++;

    return dest;

}

uint32_t HELPER(neon_rhadd_u32)(uint32_t src1, uint32_t src2)

{

    uint32_t dest;

    dest = (src1 >> 1) + (src2 >> 1);

    if ((src1 | src2) & 1)

        dest++;

    return dest;

}

#define NEON_FN(dest, src1, src2) dest = (src1 - src2) >> 1

NEON_VOP(hsub_s8, neon_s8, 4)

NEON_VOP(hsub_u8, neon_u8, 4)

NEON_VOP(hsub_s16, neon_s16, 2)

NEON_VOP(hsub_u16, neon_u16, 2)

#undef NEON_FN

int32_t HELPER(neon_hsub_s32)(int32_t src1, int32_t src2)

{

    int32_t dest;

    dest = (src1 >> 1) - (src2 >> 1);

    if ((~src1) & src2 & 1)

        dest--;

    return dest;

}

uint32_t HELPER(neon_hsub_u32)(uint32_t src1, uint32_t src2)

{

    uint32_t dest;

    dest = (src1 >> 1) - (src2 >> 1);

    if ((~src1) & src2 & 1)

        dest--;

    return dest;

}

#define NEON_FN(dest, src1, src2) dest = (src1 > src2) ? ~0 : 0

NEON_VOP(cgt_s8, neon_s8, 4)

NEON_VOP(cgt_u8, neon_u8, 4)

NEON_VOP(cgt_s16, neon_s16, 2)

NEON_VOP(cgt_u16, neon_u16, 2)

NEON_VOP(cgt_s32, neon_s32, 1)

NEON_VOP(cgt_u32, neon_u32, 1)

#undef NEON_FN

#define NEON_FN(dest, src1, src2) dest = (src1 >= src2) ? ~0 : 0

NEON_VOP(cge_s8, neon_s8, 4)

NEON_VOP(cge_u8, neon_u8, 4)

NEON_VOP(cge_s16, neon_s16, 2)

NEON_VOP(cge_u16, neon_u16, 2)

NEON_VOP(cge_s32, neon_s32, 1)

NEON_VOP(cge_u32, neon_u32, 1)

#undef NEON_FN

#define NEON_FN(dest, src1, src2) dest = (src1 < src2) ? src1 : src2

NEON_VOP(min_s8, neon_s8, 4)

NEON_VOP(min_u8, neon_u8, 4)

NEON_VOP(min_s16, neon_s16, 2)

NEON_VOP(min_u16, neon_u16, 2)

NEON_VOP(min_s32, neon_s32, 1)

NEON_VOP(min_u32, neon_u32, 1)

NEON_POP(pmin_s8, neon_s8, 4)

NEON_POP(pmin_u8, neon_u8, 4)

NEON_POP(pmin_s16, neon_s16, 2)

NEON_POP(pmin_u16, neon_u16, 2)

#undef NEON_FN

#define NEON_FN(dest, src1, src2) dest = (src1 > src2) ? src1 : src2

NEON_VOP(max_s8, neon_s8, 4)

NEON_VOP(max_u8, neon_u8, 4)

NEON_VOP(max_s16, neon_s16, 2)

NEON_VOP(max_u16, neon_u16, 2)

NEON_VOP(max_s32, neon_s32, 1)

NEON_VOP(max_u32, neon_u32, 1)

NEON_POP(pmax_s8, neon_s8, 4)

NEON_POP(pmax_u8, neon_u8, 4)

NEON_POP(pmax_s16, neon_s16, 2)

NEON_POP(pmax_u16, neon_u16, 2)

#undef NEON_FN

#define NEON_FN(dest, src1, src2) \

    dest = (src1 > src2) ? (src1 - src2) : (src2 - src1)

NEON_VOP(abd_s8, neon_s8, 4)

NEON_VOP(abd_u8, neon_u8, 4)

NEON_VOP(abd_s16, neon_s16, 2)

NEON_VOP(abd_u16, neon_u16, 2)

NEON_VOP(abd_s32, neon_s32, 1)

NEON_VOP(abd_u32, neon_u32, 1)

#undef NEON_FN

#define NEON_FN(dest, src1, src2) do { \

    int8_t tmp; \

    tmp = (int8_t)src2; \

    if (tmp >= (ssize_t)sizeof(src1) * 8 || \

        tmp <= -(ssize_t)sizeof(src1) * 8) { \

        dest = 0; \

    } else if (tmp < 0) { \

        dest = src1 >> -tmp; \

    } else { \

        dest = src1 << tmp; \

    }} while (0)

NEON_VOP(shl_u8, neon_u8, 4)

NEON_VOP(shl_u16, neon_u16, 2)

NEON_VOP(shl_u32, neon_u32, 1)

#undef NEON_FN

uint64_t HELPER(neon_shl_u64)(uint64_t val, uint64_t shiftop)

{

    int8_t shift = (int8_t)shiftop;

    if (shift >= 64 || shift <= -64) {

        val = 0;

    } else if (shift < 0) {

        val >>= -shift;

    } else {

        val <<= shift;

    }

    return val;

}

#define NEON_FN(dest, src1, src2) do { \

    int8_t tmp; \

    tmp = (int8_t)src2; \

    if (tmp >= (ssize_t)sizeof(src1) * 8) { \

        dest = 0; \

    } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \

        dest = src1 >> (sizeof(src1) * 8 - 1); \

    } else if (tmp < 0) { \

        dest = src1 >> -tmp; \

    } else { \

        dest = src1 << tmp; \

    }} while (0)

NEON_VOP(shl_s8, neon_s8, 4)

NEON_VOP(shl_s16, neon_s16, 2)

NEON_VOP(shl_s32, neon_s32, 1)

#undef NEON_FN

uint64_t HELPER(neon_shl_s64)(uint64_t valop, uint64_t shiftop)

{

    int8_t shift = (int8_t)shiftop;

    int64_t val = valop;

    if (shift >= 64) {

        val = 0;

    } else if (shift <= -64) {

        val >>= 63;

    } else if (shift < 0) {

        val >>= -shift;

    } else {

        val <<= shift;

    }

    return val;

}

#define NEON_FN(dest, src1, src2) do { \

    int8_t tmp; \

    tmp = (int8_t)src2; \

    if ((tmp >= (ssize_t)sizeof(src1) * 8) \

        || (tmp <= -(ssize_t)sizeof(src1) * 8)) { \

        dest = 0; \

    } else if (tmp < 0) { \

        dest = (src1 + (1 << (-1 - tmp))) >> -tmp; \

    } else { \

        dest = src1 << tmp; \

    }} while (0)

NEON_VOP(rshl_s8, neon_s8, 4)

NEON_VOP(rshl_s16, neon_s16, 2)

#undef NEON_FN

/* The addition of the rounding constant may overflow, so we use an

 * intermediate 64 bits accumulator.  */

uint32_t HELPER(neon_rshl_s32)(uint32_t valop, uint32_t shiftop)

{

    int32_t dest;

    int32_t val = (int32_t)valop;

    int8_t shift = (int8_t)shiftop;

    if ((shift >= 32) || (shift <= -32)) {

        dest = 0;

    } else if (shift < 0) {

        int64_t big_dest = ((int64_t)val + (1 << (-1 - shift)));

        dest = big_dest >> -shift;

    } else {

        dest = val << shift;

    }

    return dest;

}

/* Handling addition overflow with 64 bits inputs values is more

 * tricky than with 32 bits values.  */

uint64_t HELPER(neon_rshl_s64)(uint64_t valop, uint64_t shiftop)

{

    int8_t shift = (int8_t)shiftop;

    int64_t val = valop;

    if ((shift >= 64) || (shift <= -64)) {

        val = 0;

    } else if (shift < 0) {

        val >>= (-shift - 1);

        if (val == INT64_MAX) {

            /* In this case, it means that the rounding constant is 1,

             * and the addition would overflow. Return the actual

             * result directly.  */

            val = 0x4000000000000000LL;

        } else {

            val++;

            val >>= 1;

        }

    } else {

        val <<= shift;

    }

    return val;

}

#define NEON_FN(dest, src1, src2) do { \

    int8_t tmp; \

    tmp = (int8_t)src2; \

    if (tmp >= (ssize_t)sizeof(src1) * 8 || \

        tmp < -(ssize_t)sizeof(src1) * 8) { \

        dest = 0; \

    } else if (tmp == -(ssize_t)sizeof(src1) * 8) { \

        dest = src1 >> (-tmp - 1); \

    } else if (tmp < 0) { \

        dest = (src1 + (1 << (-1 - tmp))) >> -tmp; \

    } else { \

        dest = src1 << tmp; \

    }} while (0)

NEON_VOP(rshl_u8, neon_u8, 4)

NEON_VOP(rshl_u16, neon_u16, 2)

#undef NEON_FN

/* The addition of the rounding constant may overflow, so we use an

 * intermediate 64 bits accumulator.  */

uint32_t HELPER(neon_rshl_u32)(uint32_t val, uint32_t shiftop)

{

    uint32_t dest;

    int8_t shift = (int8_t)shiftop;

    if (shift >= 32 || shift < -32) {

        dest = 0;

    } else if (shift == -32) {

        dest = val >> 31;

    } else if (shift < 0) {

        uint64_t big_dest = ((uint64_t)val + (1 << (-1 - shift)));

        dest = big_dest >> -shift;

    } else {

        dest = val << shift;

    }

    return dest;

}

/* Handling addition overflow with 64 bits inputs values is more

 * tricky than with 32 bits values.  */

uint64_t HELPER(neon_rshl_u64)(uint64_t val, uint64_t shiftop)

{

    int8_t shift = (uint8_t)shiftop;

    if (shift >= 64 || shift < -64) {

        val = 0;

    } else if (shift == -64) {

        /* Rounding a 1-bit result just preserves that bit.  */

        val >>= 63;

    } else if (shift < 0) {

        val >>= (-shift - 1);

        if (val == UINT64_MAX) {

            /* In this case, it means that the rounding constant is 1,

             * and the addition would overflow. Return the actual

             * result directly.  */

            val = 0x8000000000000000ULL;

        } else {

            val++;

            val >>= 1;

        }

    } else {

        val <<= shift;

    }

    return val;

}

#define NEON_FN(dest, src1, src2) do { \

    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(qshl_u8, neon_u8, 4)

NEON_VOP_ENV(qshl_u16, neon_u16, 2)

NEON_VOP_ENV(qshl_u32, neon_u32, 1)

#undef NEON_FN

uint64_t HELPER(neon_qshl_u64)(CPUState *env, uint64_t val, uint64_t shiftop)

{

    int8_t shift = (int8_t)shiftop;

    if (shift >= 64) {

        if (val) {

            val = ~(uint64_t)0;

            SET_QC();

        }

    } else if (shift <= -64) {

        val = 0;

    } else if (shift < 0) {

        val >>= -shift;

    } else {

        uint64_t tmp = val;

        val <<= shift;

        if ((val >> shift) != tmp) {

            SET_QC();

            val = ~(uint64_t)0;

        }

    }

    return val;

}

#define NEON_FN(dest, src1, src2) do { \

    int8_t tmp; \

    tmp = (int8_t)src2; \

    if (tmp >= (ssize_t)sizeof(src1) * 8) { \

        if (src1) { \

            SET_QC(); \

            dest = (uint32_t)(1 << (sizeof(src1) * 8 - 1)); \

            if (src1 > 0) { \

                dest--; \

            } \

        } else { \

            dest = src1; \

        } \

    } else if (tmp <= -(ssize_t)sizeof(src1) * 8) { \

        dest = src1 >> 31; \

    } else if (tmp < 0) { \

        dest = src1 >> -tmp; \

    } else { \

        dest = src1 << tmp; \

        if ((dest >> tmp) != src1) { \

            SET_QC(); \

            dest = (uint32_t)(1 << (sizeof(src1) * 8 - 1)); \

            if (src1 > 0) { \

                dest--; \

            } \

        } \

    }} while (0)

NEON_VOP_ENV(qshl_s8, neon_s8, 4)

NEON_VOP_ENV(qshl_s16, neon_s16, 2)

NEON_VOP_ENV(qshl_s32, neon_s32, 1)

#undef NEON_FN

uint64_t HELPER(neon_qshl_s64)(CPUState *env, uint64_t valop, uint64_t shiftop)

{

    int8_t shift = (uint8_t)shiftop;

    int64_t val = valop;

    if (shift >= 64) {

        if (val) {

            SET_QC();

            val = (val >> 63) ^ ~SIGNBIT64;

        }

    } else if (shift <= -64) {

        val >>= 63;

    } else if (shift < 0) {

        val >>= -shift;

    } else {

        int64_t tmp = val;

        val <<= shift;

        if ((val >> shift) != tmp) {

            SET_QC();

            val = (tmp >> 63) ^ ~SIGNBIT64;

        }

    }

    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);

}

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 { \

    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 == -(ssize_t)sizeof(src1) * 8) { \

        dest = src1 >> (sizeof(src1) * 8 - 1); \

    } else if (tmp < 0) { \

        dest = (src1 + (1 << (-1 - tmp))) >> -tmp; \

    } else { \

        dest = src1 << tmp; \

        if ((dest >> tmp) != src1) { \

            SET_QC(); \

            dest = ~0; \

        } \

    }} while (0)

NEON_VOP_ENV(qrshl_u8, neon_u8, 4)

NEON_VOP_ENV(qrshl_u16, neon_u16, 2)

#undef NEON_FN

/* The addition of the rounding constant may overflow, so we use an

 * intermediate 64 bits accumulator.  */

uint32_t HELPER(neon_qrshl_u32)(CPUState *env, uint32_t val, uint32_t shiftop)

{

    uint32_t dest;

    int8_t shift = (int8_t)shiftop;

    if (shift >= 32) {

        if (val) {

            SET_QC();

            dest = ~0;

        } else {

            dest = 0;

        }

    } else if (shift < -32) {

        dest = 0;

    } else if (shift == -32) {

        dest = val >> 31;

    } else if (shift < 0) {

        uint64_t big_dest = ((uint64_t)val + (1 << (-1 - shift)));

        dest = big_dest >> -shift;

    } else {

        dest = val << shift;

        if ((dest >> shift) != val) {

            SET_QC();

            dest = ~0;

        }

    }

    return dest;

}

/* Handling addition overflow with 64 bits inputs values is more

 * tricky than with 32 bits values.  */

uint64_t HELPER(neon_qrshl_u64)(CPUState *env, uint64_t val, uint64_t shiftop)

{

    int8_t shift = (int8_t)shiftop;

    if (shift >= 64) {

        if (val) {

            SET_QC();

            val = ~0;

        }

    } else if (shift < -64) {

        val = 0;

    } else if (shift == -64) {

        val >>= 63;

    } else if (shift < 0) {

        val >>= (-shift - 1);

        if (val == UINT64_MAX) {

            /* In this case, it means that the rounding constant is 1,

             * and the addition would overflow. Return the actual

             * result directly.  */

            val = 0x8000000000000000ULL;

        } else {

            val++;

            val >>= 1;

        }

    } else { \

        uint64_t tmp = val;

        val <<= shift;

        if ((val >> shift) != tmp) {