template<typename _Ts, typename _Td> inline void
cvt_64f( const _Ts* src, size_t sstep, _Td* dst, size_t dstep,
Size size, double a, double b )
{
#if CV_SIMD_64F
v_float64 va = vx_setall_f64(a), vb = vx_setall_f64(b);
const int VECSZ = v_float64::nlanes*2;
#endif
sstep /= sizeof(src[0]);
dstep /= sizeof(dst[0]);
for( int i = 0; i < size.height; i++, src += sstep, dst += dstep )
{
int j = 0;
#if CV_SIMD_64F
for( ; j < size.width; j += VECSZ )
{
if( j > size.width - VECSZ )
{
if( j == 0 || src == (_Ts*)dst )
break;
j = size.width - VECSZ;
}
v_float64 v0, v1;
vx_load_pair_as(src + j, v0, v1);
v0 = v_fma(v0, va, vb);
v1 = v_fma(v1, va, vb);
v_store_pair_as(dst + j, v0, v1);
}
#endif
for( ; j < size.width; j++ )
dst[j] = saturate_cast<_Td>(src[j]*a + b);
}
}
void log64f( const double *x, double *y, int n )
{
CV_INSTRUMENT_REGION();
const double* const logTab = cv::details::getLogTab64f();
const int64 LOGTAB_MASK2_64F = ((int64)1 << (52 - LOGTAB_SCALE)) - 1;
const double
A7 = 1.0,
A6 = -0.5,
A5 = 0.333333333333333314829616256247390992939472198486328125,
A4 = -0.25,
A3 = 0.2,
A2 = -0.1666666666666666574148081281236954964697360992431640625,
A1 = 0.1428571428571428769682682968777953647077083587646484375,
A0 = -0.125;
int i = 0;
#if CV_SIMD_64F
const int VECSZ = v_float64::nlanes;
const v_float64 vln2 = vx_setall_f64(ln_2);
const v_float64
vA0 = vx_setall_f64(A0), vA1 = vx_setall_f64(A1),
vA2 = vx_setall_f64(A2), vA3 = vx_setall_f64(A3),
vA4 = vx_setall_f64(A4), vA5 = vx_setall_f64(A5),
vA6 = vx_setall_f64(A6), vA7 = vx_setall_f64(A7);
for( ; i < n; i += VECSZ )
{
if( i + VECSZ > n )
{
if( i == 0 || x == y )
break;
i = n - VECSZ;
}
v_int64 h0 = vx_load((const int64*)x + i);
v_int32 yi0 = v_pack(v_shr<52>(h0), vx_setzero_s64());
yi0 = (yi0 & vx_setall_s32(0x7ff)) - vx_setall_s32(1023);
v_int64 xi0 = (h0 & vx_setall_s64(LOGTAB_MASK2_64F)) | vx_setall_s64((int64)1023 << 52);
h0 = v_shr<52 - LOGTAB_SCALE - 1>(h0);
v_int32 idx = v_pack(h0, h0) & vx_setall_s32(LOGTAB_MASK*2);
v_float64 xf0, yf0;
v_lut_deinterleave(logTab, idx, yf0, xf0);
yf0 = v_fma(v_cvt_f64(yi0), vln2, yf0);
v_float64 delta = v_cvt_f64(idx == vx_setall_s32(510))*vx_setall_f64(1./512);
xf0 = v_fma(v_reinterpret_as_f64(xi0) - vx_setall_f64(1.), xf0, delta);
v_float64 xq = xf0*xf0;
v_float64 zf0 = v_fma(xq, vA0, vA2);
v_float64 zf1 = v_fma(xq, vA1, vA3);
zf0 = v_fma(zf0, xq, vA4);
zf1 = v_fma(zf1, xq, vA5);
zf0 = v_fma(zf0, xq, vA6);
zf1 = v_fma(zf1, xq, vA7);
zf1 = v_fma(zf1, xf0, yf0);
zf0 = v_fma(zf0, xq, zf1);
v_store(y + i, zf0);
}
#endif
for( ; i < n; i++ )
{
Cv64suf buf;
int64 i0 = ((const int64*)x)[i];
buf.i = (i0 & LOGTAB_MASK2_64F) | ((int64)1023 << 52);
int idx = (int)(i0 >> (52 - LOGTAB_SCALE - 1)) & (LOGTAB_MASK*2);
double y0 = (((int)(i0 >> 52) & 0x7ff) - 1023) * ln_2 + logTab[idx];
double x0 = (buf.f - 1.)*logTab[idx + 1] + (idx == 510 ? -1./512 : 0.);
double xq = x0*x0;
y[i] = (((A0*xq + A2)*xq + A4)*xq + A6)*xq + (((A1*xq + A3)*xq + A5)*xq + A7)*x0 + y0;
}
}
void exp64f( const double *_x, double *y, int n )
{
CV_INSTRUMENT_REGION();
const double* const expTab = cv::details::getExpTab64f();
const double
A5 = .99999999999999999998285227504999 / EXPPOLY_32F_A0,
A4 = .69314718055994546743029643825322 / EXPPOLY_32F_A0,
A3 = .24022650695886477918181338054308 / EXPPOLY_32F_A0,
A2 = .55504108793649567998466049042729e-1 / EXPPOLY_32F_A0,
A1 = .96180973140732918010002372686186e-2 / EXPPOLY_32F_A0,
A0 = .13369713757180123244806654839424e-2 / EXPPOLY_32F_A0;
int i = 0;
const Cv64suf* x = (const Cv64suf*)_x;
double minval = (-exp_max_val/exp_prescale);
double maxval = (exp_max_val/exp_prescale);
#if CV_SIMD_64F
const int VECSZ = v_float64::nlanes;
const v_float64 vprescale = vx_setall_f64(exp_prescale);
const v_float64 vpostscale = vx_setall_f64(exp_postscale);
const v_float64 vminval = vx_setall_f64(minval);
const v_float64 vmaxval = vx_setall_f64(maxval);
const v_float64 vA1 = vx_setall_f64(A1);
const v_float64 vA2 = vx_setall_f64(A2);
const v_float64 vA3 = vx_setall_f64(A3);
const v_float64 vA4 = vx_setall_f64(A4);
const v_float64 vA5 = vx_setall_f64(A5);
const v_int32 vidxmask = vx_setall_s32(EXPTAB_MASK);
bool y_aligned = (size_t)(void*)y % 32 == 0;
for( ; i < n; i += VECSZ*2 )
{
if( i + VECSZ*2 > n )
{
if( i == 0 || _x == y )
break;
i = n - VECSZ*2;
y_aligned = false;
}
v_float64 xf0 = vx_load(&x[i].f), xf1 = vx_load(&x[i + VECSZ].f);
xf0 = v_min(v_max(xf0, vminval), vmaxval);
xf1 = v_min(v_max(xf1, vminval), vmaxval);
xf0 *= vprescale;
xf1 *= vprescale;
v_int32 xi0 = v_round(xf0);
v_int32 xi1 = v_round(xf1);
xf0 = (xf0 - v_cvt_f64(xi0))*vpostscale;
xf1 = (xf1 - v_cvt_f64(xi1))*vpostscale;
v_float64 yf0 = v_lut(expTab, xi0 & vidxmask);
v_float64 yf1 = v_lut(expTab, xi1 & vidxmask);
v_int32 v0 = vx_setzero_s32(), v1023 = vx_setall_s32(1023), v2047 = vx_setall_s32(2047);
xi0 = v_min(v_max(v_shr<EXPTAB_SCALE>(xi0) + v1023, v0), v2047);
xi1 = v_min(v_max(v_shr<EXPTAB_SCALE>(xi1) + v1023, v0), v2047);
v_int64 xq0, xq1, dummy;
v_expand(xi0, xq0, dummy);
v_expand(xi1, xq1, dummy);
yf0 *= v_reinterpret_as_f64(v_shl<52>(xq0));
yf1 *= v_reinterpret_as_f64(v_shl<52>(xq1));
v_float64 zf0 = xf0 + vA1;
v_float64 zf1 = xf1 + vA1;
zf0 = v_fma(zf0, xf0, vA2);
zf1 = v_fma(zf1, xf1, vA2);
zf0 = v_fma(zf0, xf0, vA3);
zf1 = v_fma(zf1, xf1, vA3);
zf0 = v_fma(zf0, xf0, vA4);
zf1 = v_fma(zf1, xf1, vA4);
zf0 = v_fma(zf0, xf0, vA5);
zf1 = v_fma(zf1, xf1, vA5);
zf0 *= yf0;
zf1 *= yf1;
if( y_aligned )
{
v_store_aligned(y + i, zf0);
v_store_aligned(y + i + VECSZ, zf1);
}
else
{
v_store(y + i, zf0);
v_store(y + i + VECSZ, zf1);
}
}
vx_cleanup();
#endif
for( ; i < n; i++ )
{
double x0 = x[i].f;
x0 = std::min(std::max(x0, minval), maxval);
x0 *= exp_prescale;
Cv64suf buf;
int xi = saturate_cast<int>(x0);
x0 = (x0 - xi)*exp_postscale;
int t = (xi >> EXPTAB_SCALE) + 1023;
t = !(t & ~2047) ? t : t < 0 ? 0 : 2047;
buf.i = (int64)t << 52;
y[i] = buf.f * expTab[xi & EXPTAB_MASK] * (((((A0*x0 + A1)*x0 + A2)*x0 + A3)*x0 + A4)*x0 + A5);
}
}
