ops_sse.h

xen虚拟机源代码安装包

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

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

#define FPU_CMPEQ(size, a, b) float ## size ## _eq(a, b, &env->sse_status) ? -1 : 0
#define FPU_CMPLT(size, a, b) float ## size ## _lt(a, b, &env->sse_status) ? -1 : 0
#define FPU_CMPLE(size, a, b) float ## size ## _le(a, b, &env->sse_status) ? -1 : 0
#define FPU_CMPUNORD(size, a, b) float ## size ## _unordered(a, b, &env->sse_status) ? - 1 : 0
#define FPU_CMPNEQ(size, a, b) float ## size ## _eq(a, b, &env->sse_status) ? 0 : -1
#define FPU_CMPNLT(size, a, b) float ## size ## _lt(a, b, &env->sse_status) ? 0 : -1
#define FPU_CMPNLE(size, a, b) float ## size ## _le(a, b, &env->sse_status) ? 0 : -1
#define FPU_CMPORD(size, a, b) float ## size ## _unordered(a, b, &env->sse_status) ? 0 : -1

SSE_HELPER_CMP(cmpeq, FPU_CMPEQ)
SSE_HELPER_CMP(cmplt, FPU_CMPLT)
SSE_HELPER_CMP(cmple, FPU_CMPLE)
SSE_HELPER_CMP(cmpunord, FPU_CMPUNORD)
SSE_HELPER_CMP(cmpneq, FPU_CMPNEQ)
SSE_HELPER_CMP(cmpnlt, FPU_CMPNLT)
SSE_HELPER_CMP(cmpnle, FPU_CMPNLE)
SSE_HELPER_CMP(cmpord, FPU_CMPORD)

const int comis_eflags[4] = {CC_C, CC_Z, 0, CC_Z | CC_P | CC_C};

void helper_ucomiss(Reg *d, Reg *s)
{
    int ret;
    float32 s0, s1;

    s0 = d->XMM_S(0);
    s1 = s->XMM_S(0);
    ret = float32_compare_quiet(s0, s1, &env->sse_status);
    CC_SRC = comis_eflags[ret + 1];
    FORCE_RET();
}

void helper_comiss(Reg *d, Reg *s)
{
    int ret;
    float32 s0, s1;

    s0 = d->XMM_S(0);
    s1 = s->XMM_S(0);
    ret = float32_compare(s0, s1, &env->sse_status);
    CC_SRC = comis_eflags[ret + 1];
    FORCE_RET();
}

void helper_ucomisd(Reg *d, Reg *s)
{
    int ret;
    float64 d0, d1;

    d0 = d->XMM_D(0);
    d1 = s->XMM_D(0);
    ret = float64_compare_quiet(d0, d1, &env->sse_status);
    CC_SRC = comis_eflags[ret + 1];
    FORCE_RET();
}

void helper_comisd(Reg *d, Reg *s)
{
    int ret;
    float64 d0, d1;

    d0 = d->XMM_D(0);
    d1 = s->XMM_D(0);
    ret = float64_compare(d0, d1, &env->sse_status);
    CC_SRC = comis_eflags[ret + 1];
    FORCE_RET();
}

uint32_t helper_movmskps(Reg *s)
{
    int b0, b1, b2, b3;
    b0 = s->XMM_L(0) >> 31;
    b1 = s->XMM_L(1) >> 31;
    b2 = s->XMM_L(2) >> 31;
    b3 = s->XMM_L(3) >> 31;
    return b0 | (b1 << 1) | (b2 << 2) | (b3 << 3);
}

uint32_t helper_movmskpd(Reg *s)
{
    int b0, b1;
    b0 = s->XMM_L(1) >> 31;
    b1 = s->XMM_L(3) >> 31;
    return b0 | (b1 << 1);
}

#endif

uint32_t glue(helper_pmovmskb, SUFFIX)(Reg *s)
{
    uint32_t val;
    val = 0;
    val |= (s->XMM_B(0) >> 7);
    val |= (s->XMM_B(1) >> 6) & 0x02;
    val |= (s->XMM_B(2) >> 5) & 0x04;
    val |= (s->XMM_B(3) >> 4) & 0x08;
    val |= (s->XMM_B(4) >> 3) & 0x10;
    val |= (s->XMM_B(5) >> 2) & 0x20;
    val |= (s->XMM_B(6) >> 1) & 0x40;
    val |= (s->XMM_B(7)) & 0x80;
#if SHIFT == 1
    val |= (s->XMM_B(8) << 1) & 0x0100;
    val |= (s->XMM_B(9) << 2) & 0x0200;
    val |= (s->XMM_B(10) << 3) & 0x0400;
    val |= (s->XMM_B(11) << 4) & 0x0800;
    val |= (s->XMM_B(12) << 5) & 0x1000;
    val |= (s->XMM_B(13) << 6) & 0x2000;
    val |= (s->XMM_B(14) << 7) & 0x4000;
    val |= (s->XMM_B(15) << 8) & 0x8000;
#endif
    return val;
}

void glue(helper_packsswb, SUFFIX) (Reg *d, Reg *s)
{
    Reg r;

    r.B(0) = satsb((int16_t)d->W(0));
    r.B(1) = satsb((int16_t)d->W(1));
    r.B(2) = satsb((int16_t)d->W(2));
    r.B(3) = satsb((int16_t)d->W(3));
#if SHIFT == 1
    r.B(4) = satsb((int16_t)d->W(4));
    r.B(5) = satsb((int16_t)d->W(5));
    r.B(6) = satsb((int16_t)d->W(6));
    r.B(7) = satsb((int16_t)d->W(7));
#endif
    r.B((4 << SHIFT) + 0) = satsb((int16_t)s->W(0));
    r.B((4 << SHIFT) + 1) = satsb((int16_t)s->W(1));
    r.B((4 << SHIFT) + 2) = satsb((int16_t)s->W(2));
    r.B((4 << SHIFT) + 3) = satsb((int16_t)s->W(3));
#if SHIFT == 1
    r.B(12) = satsb((int16_t)s->W(4));
    r.B(13) = satsb((int16_t)s->W(5));
    r.B(14) = satsb((int16_t)s->W(6));
    r.B(15) = satsb((int16_t)s->W(7));
#endif
    *d = r;
}

void glue(helper_packuswb, SUFFIX) (Reg *d, Reg *s)
{
    Reg r;

    r.B(0) = satub((int16_t)d->W(0));
    r.B(1) = satub((int16_t)d->W(1));
    r.B(2) = satub((int16_t)d->W(2));
    r.B(3) = satub((int16_t)d->W(3));
#if SHIFT == 1
    r.B(4) = satub((int16_t)d->W(4));
    r.B(5) = satub((int16_t)d->W(5));
    r.B(6) = satub((int16_t)d->W(6));
    r.B(7) = satub((int16_t)d->W(7));
#endif
    r.B((4 << SHIFT) + 0) = satub((int16_t)s->W(0));
    r.B((4 << SHIFT) + 1) = satub((int16_t)s->W(1));
    r.B((4 << SHIFT) + 2) = satub((int16_t)s->W(2));
    r.B((4 << SHIFT) + 3) = satub((int16_t)s->W(3));
#if SHIFT == 1
    r.B(12) = satub((int16_t)s->W(4));
    r.B(13) = satub((int16_t)s->W(5));
    r.B(14) = satub((int16_t)s->W(6));
    r.B(15) = satub((int16_t)s->W(7));
#endif
    *d = r;
}

void glue(helper_packssdw, SUFFIX) (Reg *d, Reg *s)
{
    Reg r;

    r.W(0) = satsw(d->L(0));
    r.W(1) = satsw(d->L(1));
#if SHIFT == 1
    r.W(2) = satsw(d->L(2));
    r.W(3) = satsw(d->L(3));
#endif
    r.W((2 << SHIFT) + 0) = satsw(s->L(0));
    r.W((2 << SHIFT) + 1) = satsw(s->L(1));
#if SHIFT == 1
    r.W(6) = satsw(s->L(2));
    r.W(7) = satsw(s->L(3));
#endif
    *d = r;
}

#define UNPCK_OP(base_name, base)                               \
                                                                \
void glue(helper_punpck ## base_name ## bw, SUFFIX) (Reg *d, Reg *s)   \
{                                                               \
    Reg r;                                              \
                                                                \
    r.B(0) = d->B((base << (SHIFT + 2)) + 0);                   \
    r.B(1) = s->B((base << (SHIFT + 2)) + 0);                   \
    r.B(2) = d->B((base << (SHIFT + 2)) + 1);                   \
    r.B(3) = s->B((base << (SHIFT + 2)) + 1);                   \
    r.B(4) = d->B((base << (SHIFT + 2)) + 2);                   \
    r.B(5) = s->B((base << (SHIFT + 2)) + 2);                   \
    r.B(6) = d->B((base << (SHIFT + 2)) + 3);                   \
    r.B(7) = s->B((base << (SHIFT + 2)) + 3);                   \
XMM_ONLY(                                                       \
    r.B(8) = d->B((base << (SHIFT + 2)) + 4);                   \
    r.B(9) = s->B((base << (SHIFT + 2)) + 4);                   \
    r.B(10) = d->B((base << (SHIFT + 2)) + 5);                  \
    r.B(11) = s->B((base << (SHIFT + 2)) + 5);                  \
    r.B(12) = d->B((base << (SHIFT + 2)) + 6);                  \
    r.B(13) = s->B((base << (SHIFT + 2)) + 6);                  \
    r.B(14) = d->B((base << (SHIFT + 2)) + 7);                  \
    r.B(15) = s->B((base << (SHIFT + 2)) + 7);                  \
)                                                               \
    *d = r;                                                     \
}                                                               \
                                                                \
void glue(helper_punpck ## base_name ## wd, SUFFIX) (Reg *d, Reg *s)   \
{                                                               \
    Reg r;                                              \
                                                                \
    r.W(0) = d->W((base << (SHIFT + 1)) + 0);                   \
    r.W(1) = s->W((base << (SHIFT + 1)) + 0);                   \
    r.W(2) = d->W((base << (SHIFT + 1)) + 1);                   \
    r.W(3) = s->W((base << (SHIFT + 1)) + 1);                   \
XMM_ONLY(                                                       \
    r.W(4) = d->W((base << (SHIFT + 1)) + 2);                   \
    r.W(5) = s->W((base << (SHIFT + 1)) + 2);                   \
    r.W(6) = d->W((base << (SHIFT + 1)) + 3);                   \
    r.W(7) = s->W((base << (SHIFT + 1)) + 3);                   \
)                                                               \
    *d = r;                                                     \
}                                                               \
                                                                \
void glue(helper_punpck ## base_name ## dq, SUFFIX) (Reg *d, Reg *s)   \
{                                                               \
    Reg r;                                              \
                                                                \
    r.L(0) = d->L((base << SHIFT) + 0);                         \
    r.L(1) = s->L((base << SHIFT) + 0);                         \
XMM_ONLY(                                                       \
    r.L(2) = d->L((base << SHIFT) + 1);                         \
    r.L(3) = s->L((base << SHIFT) + 1);                         \
)                                                               \
    *d = r;                                                     \
}                                                               \
                                                                \
XMM_ONLY(                                                       \
void glue(helper_punpck ## base_name ## qdq, SUFFIX) (Reg *d, Reg *s)  \
{                                                               \
    Reg r;                                              \
                                                                \
    r.Q(0) = d->Q(base);                                        \
    r.Q(1) = s->Q(base);                                        \
    *d = r;                                                     \
}                                                               \
)

UNPCK_OP(l, 0)
UNPCK_OP(h, 1)

/* 3DNow! float ops */
#if SHIFT == 0
void helper_pi2fd(MMXReg *d, MMXReg *s)
{
    d->MMX_S(0) = int32_to_float32(s->MMX_L(0), &env->mmx_status);
    d->MMX_S(1) = int32_to_float32(s->MMX_L(1), &env->mmx_status);
}

void helper_pi2fw(MMXReg *d, MMXReg *s)
{
    d->MMX_S(0) = int32_to_float32((int16_t)s->MMX_W(0), &env->mmx_status);
    d->MMX_S(1) = int32_to_float32((int16_t)s->MMX_W(2), &env->mmx_status);
}

void helper_pf2id(MMXReg *d, MMXReg *s)
{
    d->MMX_L(0) = float32_to_int32_round_to_zero(s->MMX_S(0), &env->mmx_status);
    d->MMX_L(1) = float32_to_int32_round_to_zero(s->MMX_S(1), &env->mmx_status);
}

void helper_pf2iw(MMXReg *d, MMXReg *s)
{
    d->MMX_L(0) = satsw(float32_to_int32_round_to_zero(s->MMX_S(0), &env->mmx_status));
    d->MMX_L(1) = satsw(float32_to_int32_round_to_zero(s->MMX_S(1), &env->mmx_status));
}

void helper_pfacc(MMXReg *d, MMXReg *s)
{
    MMXReg r;
    r.MMX_S(0) = float32_add(d->MMX_S(0), d->MMX_S(1), &env->mmx_status);
    r.MMX_S(1) = float32_add(s->MMX_S(0), s->MMX_S(1), &env->mmx_status);
    *d = r;
}

void helper_pfadd(MMXReg *d, MMXReg *s)
{
    d->MMX_S(0) = float32_add(d->MMX_S(0), s->MMX_S(0), &env->mmx_status);
    d->MMX_S(1) = float32_add(d->MMX_S(1), s->MMX_S(1), &env->mmx_status);
}

void helper_pfcmpeq(MMXReg *d, MMXReg *s)
{
    d->MMX_L(0) = float32_eq(d->MMX_S(0), s->MMX_S(0), &env->mmx_status) ? -1 : 0;
    d->MMX_L(1) = float32_eq(d->MMX_S(1), s->MMX_S(1), &env->mmx_status) ? -1 : 0;
}

void helper_pfcmpge(MMXReg *d, MMXReg *s)
{
    d->MMX_L(0) = float32_le(s->MMX_S(0), d->MMX_S(0), &env->mmx_status) ? -1 : 0;
    d->MMX_L(1) = float32_le(s->MMX_S(1), d->MMX_S(1), &env->mmx_status) ? -1 : 0;
}

void helper_pfcmpgt(MMXReg *d, MMXReg *s)
{
    d->MMX_L(0) = float32_lt(s->MMX_S(0), d->MMX_S(0), &env->mmx_status) ? -1 : 0;
    d->MMX_L(1) = float32_lt(s->MMX_S(1), d->MMX_S(1), &env->mmx_status) ? -1 : 0;
}

void helper_pfmax(MMXReg *d, MMXReg *s)
{
    if (float32_lt(d->MMX_S(0), s->MMX_S(0), &env->mmx_status))
        d->MMX_S(0) = s->MMX_S(0);
    if (float32_lt(d->MMX_S(1), s->MMX_S(1), &env->mmx_status))
        d->MMX_S(1) = s->MMX_S(1);
}

void helper_pfmin(MMXReg *d, MMXReg *s)
{
    if (float32_lt(s->MMX_S(0), d->MMX_S(0), &env->mmx_status))
        d->MMX_S(0) = s->MMX_S(0);
    if (float32_lt(s->MMX_S(1), d->MMX_S(1), &env->mmx_status))
        d->MMX_S(1) = s->MMX_S(1);
}

void helper_pfmul(MMXReg *d, MMXReg *s)
{
    d->MMX_S(0) = float32_mul(d->MMX_S(0), s->MMX_S(0), &env->mmx_status);
    d->MMX_S(1) = float32_mul(d->MMX_S(1), s->MMX_S(1), &env->mmx_status);
}

void helper_pfnacc(MMXReg *d, MMXReg *s)
{
    MMXReg r;
    r.MMX_S(0) = float32_sub(d->MMX_S(0), d->MMX_S(1), &env->mmx_status);
    r.MMX_S(1) = float32_sub(s->MMX_S(0), s->MMX_S(1), &env->mmx_status);
    *d = r;
}

void helper_pfpnacc(MMXReg *d, MMXReg *s)
{
    MMXReg r;
    r.MMX_S(0) = float32_sub(d->MMX_S(0), d->MMX_S(1), &env->mmx_status);
    r.MMX_S(1) = float32_add(s->MMX_S(0), s->MMX_S(1), &env->mmx_status);
    *d = r;
}

void helper_pfrcp(MMXReg *d, MMXReg *s)
{
    d->MMX_S(0) = approx_rcp(s->MMX_S(0));
    d->MMX_S(1) = d->MMX_S(0);
}

void helper_pfrsqrt(MMXReg *d, MMXReg *s)
{
    d->MMX_L(1) = s->MMX_L(0) & 0x7fffffff;
    d->MMX_S(1) = approx_rsqrt(d->MMX_S(1));
    d->MMX_L(1) |= s->MMX_L(0) & 0x80000000;
    d->MMX_L(0) = d->MMX_L(1);
}

void helper_pfsub(MMXReg *d, MMXReg *s)
{
    d->MMX_S(0) = float32_sub(d->MMX_S(0), s->MMX_S(0), &env->mmx_status);
    d->MMX_S(1) = float32_sub(d->MMX_S(1), s->MMX_S(1), &env->mmx_status);
}

void helper_pfsubr(MMXReg *d, MMXReg *s)
{
    d->MMX_S(0) = float32_sub(s->MMX_S(0), d->MMX_S(0), &env->mmx_status);
    d->MMX_S(1) = float32_sub(s->MMX_S(1), d->MMX_S(1), &env->mmx_status);
}

void helper_pswapd(MMXReg *d, MMXReg *s)
{
    MMXReg r;
    r.MMX_L(0) = s->MMX_L(1);
    r.MMX_L(1) = s->MMX_L(0);
    *d = r;
}
#endif

#undef SHIFT
#undef XMM_ONLY
#undef Reg
#undef B
#undef W
#undef L
#undef Q
#undef SUFFIX