ops_sse.h

xen虚拟机源代码安装包

    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);
    }
    FORCE_RET();
}

#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)
{
    int i;
    for(i = 0; i < (8 << SHIFT); i++) {
        if (s->B(i) & 0x80)
            stb(A0 + i, d->B(i));
    }
    FORCE_RET();
}

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);
    *d = r;
}

void glue(helper_pshuflw, 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);
    r.Q(1) = s->Q(1);
    *d = r;
}

void glue(helper_pshufhw, SUFFIX) (Reg *d, Reg *s, int order)
{
    Reg r;
    r.Q(0) = s->Q(0);
    r.W(4) = s->W(4 + (order & 3));
    r.W(5) = s->W(4 + ((order >> 2) & 3));
    r.W(6) = s->W(4 + ((order >> 4) & 3));
    r.W(7) = s->W(4 + ((order >> 6) & 3));
    *d = r;
}
#endif

#if SHIFT == 1
/* FPU ops */
/* XXX: not accurate */

#define SSE_HELPER_S(name, F)\
void helper_ ## name ## ps (Reg *d, Reg *s)\
{\
    d->XMM_S(0) = F(32, d->XMM_S(0), s->XMM_S(0));\
    d->XMM_S(1) = F(32, d->XMM_S(1), s->XMM_S(1));\
    d->XMM_S(2) = F(32, d->XMM_S(2), s->XMM_S(2));\
    d->XMM_S(3) = F(32, d->XMM_S(3), s->XMM_S(3));\
}\
\
void helper_ ## name ## ss (Reg *d, Reg *s)\
{\
    d->XMM_S(0) = F(32, d->XMM_S(0), s->XMM_S(0));\
}\
void helper_ ## name ## pd (Reg *d, Reg *s)\
{\
    d->XMM_D(0) = F(64, d->XMM_D(0), s->XMM_D(0));\
    d->XMM_D(1) = F(64, d->XMM_D(1), s->XMM_D(1));\
}\
\
void helper_ ## name ## sd (Reg *d, Reg *s)\
{\
    d->XMM_D(0) = F(64, d->XMM_D(0), s->XMM_D(0));\
}

#define FPU_ADD(size, a, b) float ## size ## _add(a, b, &env->sse_status)
#define FPU_SUB(size, a, b) float ## size ## _sub(a, b, &env->sse_status)
#define FPU_MUL(size, a, b) float ## size ## _mul(a, b, &env->sse_status)
#define FPU_DIV(size, a, b) float ## size ## _div(a, b, &env->sse_status)
#define FPU_MIN(size, a, b) (a) < (b) ? (a) : (b)
#define FPU_MAX(size, a, b) (a) > (b) ? (a) : (b)
#define FPU_SQRT(size, a, b) float ## size ## _sqrt(b, &env->sse_status)

SSE_HELPER_S(add, FPU_ADD)
SSE_HELPER_S(sub, FPU_SUB)
SSE_HELPER_S(mul, FPU_MUL)
SSE_HELPER_S(div, FPU_DIV)
SSE_HELPER_S(min, FPU_MIN)
SSE_HELPER_S(max, FPU_MAX)
SSE_HELPER_S(sqrt, FPU_SQRT)


/* float to float conversions */
void helper_cvtps2pd(Reg *d, Reg *s)
{
    float32 s0, s1;
    s0 = s->XMM_S(0);
    s1 = s->XMM_S(1);
    d->XMM_D(0) = float32_to_float64(s0, &env->sse_status);
    d->XMM_D(1) = float32_to_float64(s1, &env->sse_status);
}

void helper_cvtpd2ps(Reg *d, Reg *s)
{
    d->XMM_S(0) = float64_to_float32(s->XMM_D(0), &env->sse_status);
    d->XMM_S(1) = float64_to_float32(s->XMM_D(1), &env->sse_status);
    d->Q(1) = 0;
}

void helper_cvtss2sd(Reg *d, Reg *s)
{
    d->XMM_D(0) = float32_to_float64(s->XMM_S(0), &env->sse_status);
}

void helper_cvtsd2ss(Reg *d, Reg *s)
{
    d->XMM_S(0) = float64_to_float32(s->XMM_D(0), &env->sse_status);
}

/* integer to float */
void helper_cvtdq2ps(Reg *d, Reg *s)
{
    d->XMM_S(0) = int32_to_float32(s->XMM_L(0), &env->sse_status);
    d->XMM_S(1) = int32_to_float32(s->XMM_L(1), &env->sse_status);
    d->XMM_S(2) = int32_to_float32(s->XMM_L(2), &env->sse_status);
    d->XMM_S(3) = int32_to_float32(s->XMM_L(3), &env->sse_status);
}

void helper_cvtdq2pd(Reg *d, Reg *s)
{
    int32_t l0, l1;
    l0 = (int32_t)s->XMM_L(0);
    l1 = (int32_t)s->XMM_L(1);
    d->XMM_D(0) = int32_to_float64(l0, &env->sse_status);
    d->XMM_D(1) = int32_to_float64(l1, &env->sse_status);
}

void helper_cvtpi2ps(XMMReg *d, MMXReg *s)
{
    d->XMM_S(0) = int32_to_float32(s->MMX_L(0), &env->sse_status);
    d->XMM_S(1) = int32_to_float32(s->MMX_L(1), &env->sse_status);
}

void helper_cvtpi2pd(XMMReg *d, MMXReg *s)
{
    d->XMM_D(0) = int32_to_float64(s->MMX_L(0), &env->sse_status);
    d->XMM_D(1) = int32_to_float64(s->MMX_L(1), &env->sse_status);
}

void helper_cvtsi2ss(XMMReg *d, uint32_t val)
{
    d->XMM_S(0) = int32_to_float32(val, &env->sse_status);
}

void helper_cvtsi2sd(XMMReg *d, uint32_t val)
{
    d->XMM_D(0) = int32_to_float64(val, &env->sse_status);
}

#ifdef TARGET_X86_64
void helper_cvtsq2ss(XMMReg *d, uint64_t val)
{
    d->XMM_S(0) = int64_to_float32(val, &env->sse_status);
}

void helper_cvtsq2sd(XMMReg *d, uint64_t val)
{
    d->XMM_D(0) = int64_to_float64(val, &env->sse_status);
}
#endif

/* float to integer */
void helper_cvtps2dq(XMMReg *d, XMMReg *s)
{
    d->XMM_L(0) = float32_to_int32(s->XMM_S(0), &env->sse_status);
    d->XMM_L(1) = float32_to_int32(s->XMM_S(1), &env->sse_status);
    d->XMM_L(2) = float32_to_int32(s->XMM_S(2), &env->sse_status);
    d->XMM_L(3) = float32_to_int32(s->XMM_S(3), &env->sse_status);
}

void helper_cvtpd2dq(XMMReg *d, XMMReg *s)
{
    d->XMM_L(0) = float64_to_int32(s->XMM_D(0), &env->sse_status);
    d->XMM_L(1) = float64_to_int32(s->XMM_D(1), &env->sse_status);
    d->XMM_Q(1) = 0;
}

void helper_cvtps2pi(MMXReg *d, XMMReg *s)
{
    d->MMX_L(0) = float32_to_int32(s->XMM_S(0), &env->sse_status);
    d->MMX_L(1) = float32_to_int32(s->XMM_S(1), &env->sse_status);
}

void helper_cvtpd2pi(MMXReg *d, XMMReg *s)
{
    d->MMX_L(0) = float64_to_int32(s->XMM_D(0), &env->sse_status);
    d->MMX_L(1) = float64_to_int32(s->XMM_D(1), &env->sse_status);
}

int32_t helper_cvtss2si(XMMReg *s)
{
    return float32_to_int32(s->XMM_S(0), &env->sse_status);
}

int32_t helper_cvtsd2si(XMMReg *s)
{
    return float64_to_int32(s->XMM_D(0), &env->sse_status);
}

#ifdef TARGET_X86_64
int64_t helper_cvtss2sq(XMMReg *s)
{
    return float32_to_int64(s->XMM_S(0), &env->sse_status);
}

int64_t helper_cvtsd2sq(XMMReg *s)
{
    return float64_to_int64(s->XMM_D(0), &env->sse_status);
}
#endif

/* float to integer truncated */
void helper_cvttps2dq(XMMReg *d, XMMReg *s)
{
    d->XMM_L(0) = float32_to_int32_round_to_zero(s->XMM_S(0), &env->sse_status);
    d->XMM_L(1) = float32_to_int32_round_to_zero(s->XMM_S(1), &env->sse_status);
    d->XMM_L(2) = float32_to_int32_round_to_zero(s->XMM_S(2), &env->sse_status);
    d->XMM_L(3) = float32_to_int32_round_to_zero(s->XMM_S(3), &env->sse_status);
}

void helper_cvttpd2dq(XMMReg *d, XMMReg *s)
{
    d->XMM_L(0) = float64_to_int32_round_to_zero(s->XMM_D(0), &env->sse_status);
    d->XMM_L(1) = float64_to_int32_round_to_zero(s->XMM_D(1), &env->sse_status);
    d->XMM_Q(1) = 0;
}

void helper_cvttps2pi(MMXReg *d, XMMReg *s)
{
    d->MMX_L(0) = float32_to_int32_round_to_zero(s->XMM_S(0), &env->sse_status);
    d->MMX_L(1) = float32_to_int32_round_to_zero(s->XMM_S(1), &env->sse_status);
}

void helper_cvttpd2pi(MMXReg *d, XMMReg *s)
{
    d->MMX_L(0) = float64_to_int32_round_to_zero(s->XMM_D(0), &env->sse_status);
    d->MMX_L(1) = float64_to_int32_round_to_zero(s->XMM_D(1), &env->sse_status);
}

int32_t helper_cvttss2si(XMMReg *s)
{
    return float32_to_int32_round_to_zero(s->XMM_S(0), &env->sse_status);
}

int32_t helper_cvttsd2si(XMMReg *s)
{
    return float64_to_int32_round_to_zero(s->XMM_D(0), &env->sse_status);
}

#ifdef TARGET_X86_64
int64_t helper_cvttss2sq(XMMReg *s)
{
    return float32_to_int64_round_to_zero(s->XMM_S(0), &env->sse_status);
}

int64_t helper_cvttsd2sq(XMMReg *s)
{
    return float64_to_int64_round_to_zero(s->XMM_D(0), &env->sse_status);
}
#endif

void helper_rsqrtps(XMMReg *d, XMMReg *s)
{
    d->XMM_S(0) = approx_rsqrt(s->XMM_S(0));
    d->XMM_S(1) = approx_rsqrt(s->XMM_S(1));
    d->XMM_S(2) = approx_rsqrt(s->XMM_S(2));
    d->XMM_S(3) = approx_rsqrt(s->XMM_S(3));
}

void helper_rsqrtss(XMMReg *d, XMMReg *s)
{
    d->XMM_S(0) = approx_rsqrt(s->XMM_S(0));
}

void helper_rcpps(XMMReg *d, XMMReg *s)
{
    d->XMM_S(0) = approx_rcp(s->XMM_S(0));
    d->XMM_S(1) = approx_rcp(s->XMM_S(1));
    d->XMM_S(2) = approx_rcp(s->XMM_S(2));
    d->XMM_S(3) = approx_rcp(s->XMM_S(3));
}

void helper_rcpss(XMMReg *d, XMMReg *s)
{
    d->XMM_S(0) = approx_rcp(s->XMM_S(0));
}

void helper_haddps(XMMReg *d, XMMReg *s)
{
    XMMReg r;
    r.XMM_S(0) = d->XMM_S(0) + d->XMM_S(1);
    r.XMM_S(1) = d->XMM_S(2) + d->XMM_S(3);
    r.XMM_S(2) = s->XMM_S(0) + s->XMM_S(1);
    r.XMM_S(3) = s->XMM_S(2) + s->XMM_S(3);
    *d = r;
}

void helper_haddpd(XMMReg *d, XMMReg *s)
{
    XMMReg r;
    r.XMM_D(0) = d->XMM_D(0) + d->XMM_D(1);
    r.XMM_D(1) = s->XMM_D(0) + s->XMM_D(1);
    *d = r;
}

void helper_hsubps(XMMReg *d, XMMReg *s)
{
    XMMReg r;
    r.XMM_S(0) = d->XMM_S(0) - d->XMM_S(1);
    r.XMM_S(1) = d->XMM_S(2) - d->XMM_S(3);
    r.XMM_S(2) = s->XMM_S(0) - s->XMM_S(1);
    r.XMM_S(3) = s->XMM_S(2) - s->XMM_S(3);
    *d = r;
}

void helper_hsubpd(XMMReg *d, XMMReg *s)
{
    XMMReg r;
    r.XMM_D(0) = d->XMM_D(0) - d->XMM_D(1);
    r.XMM_D(1) = s->XMM_D(0) - s->XMM_D(1);
    *d = r;
}

void helper_addsubps(XMMReg *d, XMMReg *s)
{
    d->XMM_S(0) = d->XMM_S(0) - s->XMM_S(0);
    d->XMM_S(1) = d->XMM_S(1) + s->XMM_S(1);
    d->XMM_S(2) = d->XMM_S(2) - s->XMM_S(2);
    d->XMM_S(3) = d->XMM_S(3) + s->XMM_S(3);
}