Overview - 2024.2 English

mixed_radix_fft is a single-channel, decimation-in-time, FFT including radix3 or radix5 *stages.

These are the templates to configure the single-channel decimation-in-time class.

Parameters:

TT_DATA	describes the type of individual data samples input to and output from the transform function. This is a typename and must be one of the following: cint16, cint32, cfloat.
TT_TWIDDLE	describes the type of twiddle factors of the transform. It must be one of the following: cint16, cint32, cfloat and must also satisfy the following rules: TT_TWIDDLE must be an integer type if TT_DATA is an integer type TT_TWIDDLE must be cfloat type if TT_DATA is a cfloat type.
TP_POINT_SIZE	is an unsigned integer which describes the number of samples in the transform. This values must factorize to powers of 2, 3 and 5. When TP_DYN_PT_SIZE is set, TP_POINT_SIZE describes the maximum point size possible.
TP_FFT_NIFFT	selects whether the transform to perform is an FFT (1) or IFFT (0).
TP_SHIFT	selects the power of 2 to scale the result by prior to output.
TP_RND	selects the rounding mode. rnd_pos_inf = Round halfway towards positive infinity. rnd_neg_inf = Round halfway towards negative infinity. rnd_sym_inf = Round halfway towards infinity (away from zero). rnd_sym_zero = Round halfway towards zero (away from infinity). rnd_conv_even = Round halfway towards nearest even number. rnd_conv_odd = Round halfway towards nearest odd number. Ceil and floor mode variants are not supported. Other modes round to the nearest integer. They differ only in how they round for values of 0.5.
TP_SAT	describes the selection of saturation to be applied during the shift down stage of processing. TP_SAT accepts unsigned integer values, where: 0: none = No saturation is performed and the value is truncated on the MSB side. 1: saturate = Default. Saturation rounds an n-bit signed value in the range [- ( 2^(n-1) ) : +2^(n-1) - 1 ]. 3: symmetric = Controls symmetric saturation. Symmetric saturation rounds an n-bit signed value in the range [- ( 2^(n-1) -1 ) : +2^(n-1) - 1 ].
TP_WINDOW_VSIZE	is an unsigned integer which describes the number of samples to be processed in each call to the function. By default, TP_WINDOW_SIZE is set to match TP_POINT_SIZE. TP_WINDOW_SIZE may be set to be an integer multiple of the TP_POINT_SIZE, in which case multiple FFT operations will be performed on a given input window, one calculation per frame of data in the iobuffer, resulting in multiple output frames. This feature of packing multiple frames of data into a single call of the function reduces the number of kernel calls and as a result, reduces the losses due to overheads in the kernel call mechanism. As a result, overall performance is increased.
TP_CASC_LEN	selects the number of kernels the FFT will be divided over in series to improve throughput
TP_API	is an unsigned integer to select window (0) or stream (1) interfaces. When stream I/O is selected, one sample is taken from, or output to, a stream and the next sample from or two the next stream. Two streams minimum are used. In this example, even samples are read from input stream[0] and odd samples from input stream[1].
TP_DYN_PT_SIZE	is an unsigned int to select static point size (0) or dynamic (1) point size. With TP_DYN_PT_SIZE set to 1, there are two input ports. For the first, the user must provide a header input that indicates the point size of frame(s) to be processed in this iteration. The header is a 256 bit size, which is considered to be 8 fields each of int32 type. The first field selects the direction of the transform to perform (1= forward, 0 = inverse). The third field determines the power of 2 factor of the point size. e.g. 1536 decomposes to 3 2^9 so in this case the value would be 9. The fourth field describes the power of 3 of the point size The fifth field describes the power of 5 of the point size. For example, a point size of 240 is 2^4 * 3^1 * 5^1 so the values for the power of 2, 3 and 5 would be 4, 1 and 1 respectively. The last (8th) field is an error indication. This is ignored on input, but set for the output header if the input header is determined to be invalid (e.g. because the point size described is too large or too small. The second (data) input, contains one or more frames of data to be processed. Each frame will start at index nTP_POINT_SIZE in this iobuffer Similarly, when using the dynamic point size feature there will be two output ports. The first holds the output header which is a copy of the input header, but with the error field set to 0 (valid point size) or 1 (invalid point size). The second output port will contain the processed data arranged in the same manner as the input data port. That is, there may be one or more frames of data, as determined by TP_WINDOW_VSIZE/TP_POINT_SIZE. The first frame will begin at index 0. The second will begin at index TP_POINT_VSIZE, the third at 2TP_POINT_SIZE and so on. Note that TP_WINDOW_SIZE still describes the number of samples to be processed and does not include the header.

template <
    typename TT_DATA,
    typename TT_TWIDDLE,
    unsigned int TP_POINT_SIZE,
    unsigned int TP_FFT_NIFFT,
    unsigned int TP_SHIFT,
    unsigned int TP_RND = 4,
    unsigned int TP_SAT = 1,
    unsigned int TP_WINDOW_VSIZE = TP_POINT_SIZE,
    unsigned int TP_CASC_LEN = 1,
    unsigned int TP_API = 0,
    unsigned int TP_DYN_PT_SIZE = 0
    >
class mixed_radix_fft_graph: public graph

// typedefs

typedef std::conditional <std::is_same <TT_DATA, cint16>::value, cint32_t, TT_DATA>::type T_internalDataType

// fields

kernel m_mixed_radix_fftKernels[TP_CASC_LEN]
port_array <input, m_kNumPorts> in
port_array <output, m_kNumPorts> out
static constexpr int kStreamsPerTile
static constexpr int m_kNumPorts
static constexpr int m_kR5Stages
static constexpr int m_kR3Stages
static constexpr int m_kR4Stages
static constexpr int m_kR2Stages
static constexpr int m_kR5factor
static constexpr int m_kR3factor
static constexpr int m_kR4factor
static constexpr int m_kR2factor
static constexpr int m_kTotalStages
static constexpr int m_ktwiddleTableSize