예제 #1
0
    TheTest & test_float_math()
    {
        typedef typename V_RegTrait128<LaneType>::int_reg Ri;
        Data<R> data1, data2, data3;
        data1 *= 1.1;
        data2 += 10;
        R a1 = data1, a2 = data2, a3 = data3;

        Data<Ri> resB = v_round(a1),
                 resC = v_trunc(a1),
                 resD = v_floor(a1),
                 resE = v_ceil(a1);

        Data<R> resF = v_magnitude(a1, a2),
                resG = v_sqr_magnitude(a1, a2),
                resH = v_muladd(a1, a2, a3);

        for (int i = 0; i < R::nlanes; ++i)
        {
            EXPECT_EQ(cvRound(data1[i]), resB[i]);
            EXPECT_EQ((typename Ri::lane_type)data1[i], resC[i]);
            EXPECT_EQ(cvFloor(data1[i]), resD[i]);
            EXPECT_EQ(cvCeil(data1[i]), resE[i]);

            EXPECT_COMPARE_EQ(std::sqrt(data1[i]*data1[i] + data2[i]*data2[i]), resF[i]);
            EXPECT_COMPARE_EQ(data1[i]*data1[i] + data2[i]*data2[i], resG[i]);
            EXPECT_COMPARE_EQ(data1[i]*data2[i] + data3[i], resH[i]);
        }

        return *this;
    }
예제 #2
0
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);
    }
}
예제 #3
0
void exp32f( const float *_x, float *y, int n )
{
    CV_INSTRUMENT_REGION();

    const float* const expTab_f = cv::details::getExpTab32f();

    const float
    A4 = (float)(1.000000000000002438532970795181890933776 / EXPPOLY_32F_A0),
    A3 = (float)(.6931471805521448196800669615864773144641 / EXPPOLY_32F_A0),
    A2 = (float)(.2402265109513301490103372422686535526573 / EXPPOLY_32F_A0),
    A1 = (float)(.5550339366753125211915322047004666939128e-1 / EXPPOLY_32F_A0);

    int i = 0;
    const Cv32suf* x = (const Cv32suf*)_x;
    float minval = (float)(-exp_max_val/exp_prescale);
    float maxval = (float)(exp_max_val/exp_prescale);
    float postscale = (float)exp_postscale;

#if CV_SIMD
    const int VECSZ = v_float32::nlanes;
    const v_float32 vprescale = vx_setall_f32((float)exp_prescale);
    const v_float32 vpostscale = vx_setall_f32((float)exp_postscale);
    const v_float32 vminval = vx_setall_f32(minval);
    const v_float32 vmaxval = vx_setall_f32(maxval);

    const v_float32 vA1 = vx_setall_f32((float)A1);
    const v_float32 vA2 = vx_setall_f32((float)A2);
    const v_float32 vA3 = vx_setall_f32((float)A3);
    const v_float32 vA4 = vx_setall_f32((float)A4);

    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_float32 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_f32(xi0))*vpostscale;
        xf1 = (xf1 - v_cvt_f32(xi1))*vpostscale;

        v_float32 yf0 = v_lut(expTab_f, xi0 & vidxmask);
        v_float32 yf1 = v_lut(expTab_f, xi1 & vidxmask);

        v_int32 v0 = vx_setzero_s32(), v127 = vx_setall_s32(127), v255 = vx_setall_s32(255);
        xi0 = v_min(v_max(v_shr<EXPTAB_SCALE>(xi0) + v127, v0), v255);
        xi1 = v_min(v_max(v_shr<EXPTAB_SCALE>(xi1) + v127, v0), v255);

        yf0 *= v_reinterpret_as_f32(v_shl<23>(xi0));
        yf1 *= v_reinterpret_as_f32(v_shl<23>(xi1));

        v_float32 zf0 = xf0 + vA1;
        v_float32 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 *= 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++ )
    {
        float x0 = x[i].f;
        x0 = std::min(std::max(x0, minval), maxval);
        x0 *= (float)exp_prescale;
        Cv32suf buf;

        int xi = saturate_cast<int>(x0);
        x0 = (x0 - xi)*postscale;

        int t = (xi >> EXPTAB_SCALE) + 127;
        t = !(t & ~255) ? t : t < 0 ? 0 : 255;
        buf.i = t << 23;

        y[i] = buf.f * expTab_f[xi & EXPTAB_MASK] * ((((x0 + A1)*x0 + A2)*x0 + A3)*x0 + A4);
    }
}