#pragma once #include #include namespace fft_stage { // 0x180008440 (kernel 0x18003fa20): IN-PLACE elementwise double multiply // dst[i] *= src[i]. NOT a complex multiply — the complex op is done via separate // re/im passes on the interleaved layout. void cplx_mul_scalar_inplace(double* dst, const double* src, uint32_t n); // complex elementwise multiply (interleaved re,im): out = in1 * in2 void cplx_mul(double* out, const double* in1, const double* in2, uint32_t n); void stage_complex(double* out, const double* in, const double* tw, uint32_t n); void stage_double(double* out, const double* in, const double* tw, uint32_t n); }