namespace internal

// namespaces

namespace xf::data_analytics::clustering::internal::kmeansScan

storeCenters2Array

#include "xf_data_analytics/clustering/kmeansTrain.hpp"

template <
    typename DT,
    int Dim,
    int Kcluster,
    int uramDepth,
    int KU,
    int DV
    >
void storeCenters2Array (
    hls::stream <ap_uint <sizeof (DT)*8>> centerStrm [DV],
    hls::stream <bool>& eCenterStrm,
    const int dims,
    ap_uint <sizeof (DT)*8*DV> centers [KU][uramDepth]
    )

storeCenters2Array is used for storing centers to local memory.

Parameters:

DT	data type, supporting float and double
Dim	the maximum number of dimensions, dims<=Dim
Kcluster	the maximum number of cluster,kcluster<=Kcluster
uramDepth	the depth of uram
KU	unroll factor of Kcluster
DV	unroll factor of Dim
centerStrm	input centers streams
ecenterStrm	the end flag of centerStrm
dims	the number of dimensions
centers	local memory for storing centers

scanAndStoreCenters

#include "xf_data_analytics/clustering/kmeansTrain.hpp"

template <
    typename DT,
    int Dim,
    int Kcluster,
    int uramDepth,
    int KU,
    int DV
    >
void scanAndStoreCenters (
    ap_uint <512>* data,
    const ap_uint <32> offset,
    const int dims,
    const int kcluster,
    ap_uint <sizeof (DT)*8*DV> centers [KU][uramDepth]
    )

scanAndStoreCenters is used for scanning initial centers from DDR and storing to local memory.

Parameters:

DT	data type, supporting float and double
Dim	the maximum number of dimensions, dims<=Dim
Kcluster	the maximum number of cluster,kcluster<=Kcluster
uramDepth	the depth of uram
KU	unroll factor of Kcluster
DV	unroll factor of Dim
data	initial centers on DDR
offset	the start position of initial centers in data
dims	the number of dimensions
kcluster	the number of clusters
centers	local memory for storing centers

writeCenters

#include "xf_data_analytics/clustering/kmeansTrain.hpp"

template <
    typename DT,
    int Dim,
    int Kcluster,
    int uramDepth,
    int KU,
    int DV
    >
void writeCenters (
    ap_uint <sizeof (DT)*8*DV> centersArray [KU][uramDepth],
    const int dims,
    const int kcluster,
    const int it,
    ap_uint <512>* kcenters
    )

writeCenters writes best centers to DDR.

Parameters:

DT	data type, supporting float and double
Dim	the maximum number of dimensions, dims<=Dim
Kcluster	the maximum number of cluster,kcluster<=Kcluster
uramDepth	the depth of uram
KU	unroll factor of Kcluster
DV	unroll factor of Dim
centersArray	best centers
dims	the number of dimensions
kcluster	the number of clusters
it	iterations
kcenters	centers in DDR

updateC0

#include "xf_data_analytics/clustering/kmeansTrain.hpp"

template <
    typename DT,
    int Dim,
    int Kcluster,
    int uramDepth,
    int KU,
    int DV
    >
void updateC0 (
    hls::stream <ap_uint <sizeof (DT)*8>> sampleStrm [DV],
    hls::stream <bool>& endSampleStrm,
    hls::stream <ap_uint <32>>& tagStrm,
    hls::stream <bool>& etagStrm,
    const int dims,
    ap_uint <sizeof (DT)*8*DV> betterCenters [KU][uramDepth]
    )

updateC0 is used for updating centers

Parameters:

DT	data type, supporting float and double
Dim	the maximum number of dimensions, dims<=Dim
Kcluster	the maximum number of cluster,kcluster<=Kcluster
uramDepth	the depth of uram
KU	unroll factor of Kcluster
DV	unroll factor of Dim
sampleStrm	input sample streams
endSampleStrm	the end flag of input sample streams
tagStrm	input tag streams,each tag is the id which each sample belongs to cluster.
etagStrm	the end flag of tag streams
dims	the number of dimensions.
betterCenters	updated centers.

convertPort

#include "xf_data_analytics/clustering/kmeansTrain.hpp"

template <
    int sz,
    int sn,
    int Dim,
    int DV
    >
void convertPort (
    hls::stream <ap_uint <sz>> sampleStrm [sn],
    hls::stream <bool>& endSampleStrm,
    hls::stream <ap_uint <sz>> s1Strm [DV],
    hls::stream <bool>& es1Strm,
    hls::stream <ap_uint <sz>> s2Strm [DV],
    hls::stream <bool>& es2Strm
    )

convertPort converts sn streams to DV streams, in which the s1 and s2 are same.

Parameters:

sz	the width input/output stream
sn	the number of input streams
Dim	the number of dimensions
DV	the number of output streams
sampleStrm	input streams.
endSampleStrm	the end flag of input streams
s1Strm	duplicate stream.
es1Strm	the end flag of s1Strm.
s2Strm	duplicate stream.
es2Strm	the end flag of s1Strm.

isConverged

#include "xf_data_analytics/clustering/kmeansTrain.hpp"

template <
    typename DT,
    int Dim,
    int Kcluster,
    int uramDepth,
    int KU,
    int DV
    >
bool isConverged (
    ap_uint <sizeof (DT)*8*DV> centers [KU][uramDepth],
    ap_uint <sizeof (DT)*8*DV> betterCenters [KU][uramDepth],
    const int dims,
    const int kcluster,
    const DT eps
    )

isConverged is used for checking whether new centers is close to previous centers and copy betterCenters to centers with clearing betterCenters in order to reduce resource.

Parameters:

DT	data type, supporting float and double
Dim	the maximum number of dimensions,dynamic number of dimension should be not greater than the maximum.
Kcluster	the maximum number of cluster,dynamic number of cluster should be not greater than the maximum.
uramDepth	the depth of uram where centers are stored. uramDepth should be not less than ceiling(Kcluster/KU) ceiling(Dim/DV)
KU	unroll factor of Kcluster, KU centers are took part in calculating distances concurrently with one sample. After Kcluster/KU+1 times at most, ouput the minimum distance of a sample and Kcluster centers.
DV	unroll factor of Dim, DV elements in a center are took part in calculating distances concurrently with one sample.
centers	previous centers.
betterCenters	new centers
dims	the number of dimensions.
kcluster	the number of clusters.
eps	distance thredhold.

kMeansTrainIter

#include "xf_data_analytics/clustering/kmeansTrain.hpp"

template <
    typename DT,
    int Dim,
    int Kcluster,
    int uramDepth,
    int KU,
    int DV
    >
void kMeansTrainIter (
    ap_uint <512>* data,
    ap_uint <sizeof (DT)*8*DV> centers [KU][uramDepth],
    const int nsample,
    const int dims,
    const int kcluster,
    const int offset,
    ap_uint <sizeof (DT)*8*DV> betterCenters [KU][uramDepth]
    )

kMeansTrainIter is used for one iteration of training: scan samples + predict + update centers.

Parameters:

DT	data type, supporting float and double
Dim	the maximum number of dimensions,dynamic number of dimension should be not greater than the maximum.
Kcluster	the maximum number of cluster,dynamic number of cluster should be not greater than the maximum.
uramDepth	the depth of uram where centers are stored. uramDepth should be not less than ceiling(Kcluster/KU) ceiling(Dim/DV)
KU	unroll factor of Kcluster, KU centers are took part in calculating distances concurrently with one sample. After Kcluster/KU+1 times at most, ouput the minimum distance of a sample and Kcluster centers.
DV	unroll factor of Dim, DV elements in a center are took part in calculating distances concurrently with one sample.
centers	input centers used for calculating distance.
nsample	the number of input samples.
dims	the number of dimensions.
kcluster	the number of clusters.
offset	the start position of samples in data, offset = 1 + ceiling(kcluster*dims*8*sizeof(DT)/512).
betterCenters	updated centers as better centers

kMeansTrainImp

#include "xf_data_analytics/clustering/kmeansTrain.hpp"

template <
    typename DT,
    int Dim,
    int Kcluster,
    int KU,
    int DV
    >
void kMeansTrainImp (
    ap_uint <512>* data,
    ap_uint <512>* kcenters
    )

kMeansTrainImp is used for implementation k means training. It parsers all dynamic configures from compressed input data at first, then stores the initial centers to local memory. When iterations is up to maximum number or new centers are very close to previous centers, the last centers as best centers are ouput.

Parameters:

DT	data type, supporting float and double
Dim	the maximum number of dimensions,dynamic number of dimension should be not greater than the maximum.
Kcluster	the maximum number of cluster,dynamic number of cluster should be not greater than the maximum.
KU	unroll factor of Kcluster, KU centers are took part in calculating distances concurrently with one sample. After Kcluster/KU+1 times at most, ouput the minimum distance of a sample and Kcluster centers.
DV	unroll factor of Dim, DV elements in a center are took part in calculating distances concurrently with one sample.
data	input data from host
kcenters	the output best centers