#include "fft_stage.hpp"
#include <cstring>

namespace fft_stage {

void cplx_mul(double* out, const double* in1, const double* in2, uint32_t n) {
    for (uint32_t i = 0; i < n; i += 64) {
        for (uint32_t j = 0; j < 4; j++) {
            double re1 = in1[i + j*2 + 0];
            double im1 = in1[i + j*2 + 1];
            double re2 = in2[i + j*2 + 0];
            double im2 = in2[i + j*2 + 1];
            out[i + j*2 + 0] = re1*re2 - im1*im2;
            out[i + j*2 + 1] = re1*im2 + im1*re2;
        }
    }
}

void stage_complex(double* out, const double* in, const double* tw, uint32_t n) {
    for (uint32_t i = 0; i < n; i += 64) {
        for (uint32_t j = 0; j < 4; j++) {
            double re1 = in[i + j*2 + 0];
            double im1 = in[i + j*2 + 1];
            double re2 = tw[i + j*2 + 0];
            double im2 = tw[i + j*2 + 1];
            out[i + j*2 + 0] = re1*re2 - im1*im2;
            out[i + j*2 + 1] = re1*im2 + im1*re2;
        }
    }
}

void stage_double(double* out, const double* in, const double* tw, uint32_t n) {
    for (uint32_t i = 0; i < n; i += 64) {
        for (uint32_t j = 0; j < 8; j++) {
            out[i + j] = in[i + j] * tw[i + j];
        }
    }
}

}