Global Namespace

// typedefs

typedef ap_uint <8> uintInV_t
typedef ap_uint <8> uintOutV_t
typedef struct unpackerBlockInfo dt_blockInfo
typedef struct unpackerChunkInfo dt_chunkInfo
typedef ap_uint <GMEM_DWIDTH> uint512_t

// structs

struct unpackerBlockInfo
struct unpackerChunkInfo

// global variables

constexpr int c_windowSize
constexpr int c_blockSize
constexpr int c_windowSize
constexpr int c_blockSize
const int c_instreamDWidth
const int c_outstreamDWidth
const int c_windowSize

// macros

#define BLOCKSIZE_IN_KB
#define BLOCKSIZE_IN_KB
#define CORE_NUM
#define DECODER_TYPE
#define DECODER_TYPE
#define DECODER_TYPE
#define DECODER_TYPE
#define DECODER_TYPE
#define DECODER_TYPE
#define DICT_ELE_WIDTH
#define GMEM_BURST_SIZE
#define GMEM_BURST_SIZE
#define GMEM_BURST_SIZE
#define GMEM_BURST_SIZE
#define GMEM_BURST_SIZE
#define GMEM_BURST_SIZE
#define GMEM_BURST_SIZE
#define GMEM_BURST_SIZE
#define GMEM_BURST_SIZE
#define GMEM_BURST_SIZE
#define GMEM_DATAWIDTH
#define GMEM_DWIDTH
#define GMEM_DWIDTH
#define GMEM_DWIDTH
#define GMEM_DWIDTH
#define GMEM_DWIDTH
#define GMEM_DWIDTH
#define GMEM_DWIDTH
#define GMEM_DWIDTH
#define GMEM_DWIDTH
#define GMEM_DWIDTH
#define GMEM_DWIDTH
#define GMEM_IN_DWIDTH
#define GMEM_IN_DWIDTH
#define GMEM_OUT_DWIDTH
#define GMEM_OUT_DWIDTH
#define HISTORY_SIZE
#define HISTORY_SIZE
#define HISTORY_SIZE
#define HISTORY_SIZE
#define HISTORY_SIZE
#define HUFFMAN_TYPE
#define INPUT_BYTES
#define LL_MODEL
#define LL_MODEL
#define LL_MODEL
#define LL_MODEL
#define LL_MODEL
#define LL_MODEL
#define LOW_OFFSET
#define LOW_OFFSET
#define LOW_OFFSET
#define LOW_OFFSET
#define LOW_OFFSET
#define LOW_OFFSET
#define LOW_OFFSET
#define LZ_MAX_OFFSET_LIMIT
#define LZ_MAX_OFFSET_LIMIT
#define LZ_MAX_OFFSET_LIMIT
#define LZ_MAX_OFFSET_LIMIT
#define LZ_MAX_OFFSET_LIMIT
#define LZ_MAX_OFFSET_LIMIT
#define LZ_MAX_OFFSET_LIMIT
#define LZ_MAX_OFFSET_LIMIT
#define LZ_MAX_OFFSET_LIMIT
#define LZ_MAX_OFFSET_LIMIT
#define LZ_MAX_OFFSET_LIMIT
#define LZ_MAX_OFFSET_LIMIT
#define MATCH_LEN
#define MATCH_LEN
#define MATCH_LEN
#define MATCH_LEN
#define MATCH_LEN
#define MATCH_LEVEL
#define MAX_LIT_COUNT
#define MAX_LIT_COUNT
#define MAX_LIT_COUNT
#define MAX_LIT_COUNT
#define MAX_LIT_STREAM_SIZE
#define MAX_LIT_STREAM_SIZE
#define MAX_MATCH_LEN
#define MAX_MATCH_LEN
#define MAX_MATCH_LEN
#define MAX_MATCH_LEN
#define MAX_MATCH_LEN
#define MAX_OFFSET
#define MAX_OFFSET
#define MAX_OFFSET
#define MAX_OFFSET
#define MAX_OFFSET
#define MAX_OFFSET
#define MIN_BLCK_SIZE
#define MIN_BLCK_SIZE
#define MIN_BLCK_SIZE
#define MIN_BLOCK_SIZE
#define MIN_BLOCK_SIZE
#define MIN_MATCH
#define MIN_MATCH
#define MIN_MATCH
#define MIN_MATCH
#define MIN_MATCH
#define MULTIPLE_BYTES
#define MULTIPLE_BYTES
#define MULTIPLE_BYTES
#define MULTIPLE_BYTES
#define MULTIPLE_BYTES
#define MULTIPLE_BYTES
#define MULTIPLE_BYTES
#define NUM_CORE
#define NUM_CORE
#define NUM_CORES
#define NUM_CORES
#define NUM_CORES
#define OFFSET_WINDOW
#define OFFSET_WINDOW
#define OFFSET_WINDOW
#define OFFSET_WINDOW
#define OUTPUT_BYTES
#define OUT_BYTES
#define PARALLEL_BLOCK
#define PARALLEL_BLOCK
#define PARALLEL_BLOCK
#define PARALLEL_BYTES
#define PARALLEL_BYTES
#define PARALLEL_BYTES
#define SEQ_LL_MODEL
#define STRATEGY
#define STREAM_IN_DWIDTH
#define STREAM_IN_DWIDTH
#define STREAM_OUT_DWIDTH
#define STREAM_OUT_DWIDTH
#define STRTGY
#define TUSER_DWIDTH
#define TUSER_WIDTH
#define TUSER_WIDTH
#define URAM_BUFFER
#define ZLIB_BLOCK_SIZE
#define ZLIB_BLOCK_SIZE
#define ZLIB_BLOCK_SIZE
#define ZSTD_BLOCK_SIZE_KB
#define ZSTD_BLOCK_SIZE_KB
#define ZSTD_BLOCK_SIZE_KB

Global Functions

xilAdler32

#include "adler32_mm.hpp"

void xilAdler32 (
    const ap_uint <PARALLEL_BYTES*8>* in,
    ap_uint <32>* adlerData,
    uint32_t inSize
    )

Adler32 kernel takes the raw data as input and generates the adler32 result.

Parameters:

in	input raw data
adlerData	Adler data
inSize	input size

xilChecksum32

#include "checksum_mm.hpp"

void xilChecksum32 (
    const ap_uint <PARALLEL_BYTES*8>* in,
    ap_uint <32>* initData,
    uint32_t inSize,
    bool checksumType
    )

Checksum kernel takes the raw data as input and generates the checksum result.

Parameters:

in	input raw data
initData	input Initial data
inSize	input size
checksumType	CRC/ADLER

xilCrc32

#include "crc32_mm.hpp"

void xilCrc32 (
    const ap_uint <PARALLEL_BYTES*8>* in,
    ap_uint <32>* crcData,
    uint32_t inSize
    )

Crc32 kernel takes the raw data as input and generates the crc32 result.

Parameters:

in	input raw data
crcData	CRC data
inSize	input size

xilGzipCompressFixedStreaming

#include "gzip_compress_fixed_stream.hpp"

void xilGzipCompressFixedStreaming (
    hls::stream <ap_axiu <GMEM_IN_DWIDTH, 0, 0, 0>>& inStream,
    hls::stream <ap_axiu <GMEM_OUT_DWIDTH, 0, 0, 0>>& outStream,
    hls::stream <ap_axiu <32, 0, 0, 0>>& inSizeStream
    )

GZIP compression kernel takes the raw data as input and compresses the data in block based fashion and writes the output to global memory. This kernel uses fixed huffman encoding for compression.

Parameters:

inStream	input raw data
outStream	output compressed data
inSizeStream	input data size

xilGzipCompBlock

#include "gzip_compress_multicore_mm.hpp"

void xilGzipCompBlock (
    const ap_uint <GMEM_DWIDTH>* in,
    ap_uint <GMEM_DWIDTH>* out,
    uint32_t* compressd_size,
    uint32_t* checksumData,
    uint32_t input_size,
    bool checksumType
    )

GZIP compression kernel takes the raw data as input from DDR and compresses the data using num cores and writes the output to global memory.

Parameters:

in	input raw data
out	output compressed data
compressd_size	compressed output size of each block
checksumData	checksum data
input_size	input data size
checksumTye	checksum type

xilGzipComp

#include "gzip_compress_multicore_stream.hpp"

void xilGzipComp (
    hls::stream <ap_axiu <GMEM_DWIDTH, 0, 0, 0>>& inaxistream,
    hls::stream <ap_axiu <GMEM_DWIDTH, TUSER_DWIDTH, 0, 0>>& outaxistream
    )

GZIP streaming compression kernel takes the raw data as input from axi interface and compresses the data using num cores and writes the output to an axi interface.

Parameters:

inaxistream	input raw data
outaxistream	output compressed data

xilGzipCompressStreaming

#include "gzip_compress_stream.hpp"

void xilGzipCompressStreaming (
    hls::stream <ap_axiu <GMEM_IN_DWIDTH, 0, 0, 0>>& inStream,
    hls::stream <ap_axiu <GMEM_OUT_DWIDTH, 0, 0, 0>>& outStream,
    hls::stream <ap_axiu <32, 0, 0, 0>>& inSizeStream
    )

GZIP compression kernel takes the raw data as input and compresses the data in block based fashion and writes the output to global memory.

Parameters:

inStream	input raw data
outStream	output compressed data
inSizeStream	input data size

xilLz4Compress

#include "lz4_compress_mm.hpp"

void xilLz4Compress (
    const xf::compression::uintMemWidth_t* in,
    xf::compression::uintMemWidth_t* out,
    uint32_t* compressd_size,
    uint32_t* in_block_size,
    uint32_t block_size_in_kb,
    uint32_t input_size
    )

LZ4 compression kernel takes the raw data as input and compresses the data in block based fashion and writes the output to global memory.

Parameters:

in	input raw data
out	output compressed data
compressd_size	compressed output size of each block
in_block_size	input block size of each block
block_size_in_kb	input block size in bytes
input_size	input data size

xilLz4CompressStream

#include "lz4_compress_stream.hpp"

void xilLz4CompressStream (
    hls::stream <ap_axiu <8, 0, 0, 0>>& inaxistream,
    hls::stream <ap_axiu <8, 0, 0, 0>>& outaxistream,
    uint32_t inputSize
    )

LZ4 compression streaming kernel. It takes input from axi kernel stream and writes compressed data back to output axi kernel stream.

Parameters:

inaxistream	Input axi kernel stream
outaxistream	Output axi kernel stream
inputSize	Input compressed data size

xilLz4Decompress

#include "lz4_multibyte_decompress_mm.hpp"

void xilLz4Decompress (
    const ap_uint <MULTIPLE_BYTES*8>* in,
    ap_uint <MULTIPLE_BYTES*8>* out,
    uint32_t* in_block_size,
    uint32_t* in_compress_size,
    uint32_t block_size_in_kb,
    uint32_t no_blocks
    )

LZ4 decompression kernel takes compressed data as input and process in block based fashion and writes the raw data to global memory.

Parameters:

in	input compressed data
out	output raw data
in_block_size	input block size of each block
in_compress_size	compress size of each block
block_size_in_kb	block size in bytes
no_blocks	number of blocks

xilLz4DecompressStream

#include "lz4_multibyte_decompress_stream.hpp"

void xilLz4DecompressStream (
    hls::stream <ap_axiu <MULTIPLE_BYTES*8, 0, 0, 0>>& inaxistream,
    hls::stream <ap_axiu <MULTIPLE_BYTES*8, 0, 0, 0>>& outaxistream,
    hls::stream <ap_axiu <32, 0, 0, 0>>& outaxistreamsize,
    uint32_t inputSize
    )

Snappy decompression streaming kernel takes compressed data as input from kernel axi stream and process in block based fashion and writes the raw data to global memory.

Parameters:

inaxistream	input kernel axi stream for compressed data
outaxistream	output kernel axi stream for decompressed data
inputSize	input data size

xilLz4Packer

#include "lz4_packer_mm.hpp"

void xilLz4Packer (
    uint512_t* in,
    uint512_t* out,
    uint32_t* compressd_size,
    uint32_t* in_block_size,
    uint32_t* encoded_size,
    uint512_t* orig_input_data,
    uint32_t block_size_in_kb,
    uint32_t no_blocks,
    uint32_t xxhashVal,
    uint32_t input_size
    )

LZ4 packer kernel takes the raw data as input and compresses the data in block based fashion and writes the output to global memory.

Parameters:

in	input raw data
out	output compressed data
compressd_size	compressed output size of each block
in_block_size	input block size of each block
encoded_size	encoded size of each block
orig_input_data	raw input data
block_size_in_kb	input block size in bytes
no_blocks	number of input blocks
xxhashVal	Hash Value
input_size	Total Input File Size

xilSnappyCompress

#include "snappy_compress_mm.hpp"

void xilSnappyCompress (
    const xf::compression::uintMemWidth_t* in,
    xf::compression::uintMemWidth_t* out,
    uint32_t* compressd_size,
    uint32_t* in_block_size,
    uint32_t block_size_in_kb,
    uint32_t input_size
    )

Snappy compression kernel takes the raw data as input and compresses the data in block based fashion and writes the output to global memory.

Parameters:

in	input raw data
out	output compressed data
compressd_size	compressed output size of each block
in_block_size	input block size of each block
block_size_in_kb	input block size in bytes
input_size	input data size

xilSnappyCompressStream

#include "snappy_compress_stream.hpp"

void xilSnappyCompressStream (
    hls::stream <ap_axiu <8, 0, 0, 0>>& inaxistream,
    hls::stream <ap_axiu <8, 0, 0, 0>>& outaxistream,
    uint32_t inputSize
    )

Snappy compression streaming kernel takes the raw data as input from kernel axi stream and compresses the data in block based fashion and writes the output to kernel axi stream.

Parameters:

inaxistream	input kernel axi stream for raw data
outaxistream	output kernel axi stream for compressed data
inputSize	input data size

xilSnappyDecompress

#include "snappy_multibyte_decompress_mm.hpp"

void xilSnappyDecompress (
    const ap_uint <MULTIPLE_BYTES*8>* in,
    ap_uint <MULTIPLE_BYTES*8>* out,
    uint32_t* in_block_size,
    uint32_t* in_compress_size,
    uint32_t block_size_in_kb,
    uint32_t no_blocks
    )

Snappy decompression kernel takes compressed data as input and process in block based fashion and writes the raw data to global memory.

Parameters:

in	input compressed data
out	output raw data
in_block_size	input block size of each block
in_compress_size	compress size of each block
block_size_in_kb	block size in bytes
no_blocks	number of blocks

xilSnappyDecompressStream

xilSnappyDecompressStream overload (1)

#include "snappy_multibyte_decompress_stream.hpp"

void xilSnappyDecompressStream (
    hls::stream <ap_axiu <MULTIPLE_BYTES*8, 0, 0, 0>>& inaxistream,
    hls::stream <ap_axiu <MULTIPLE_BYTES*8, 0, 0, 0>>& outaxistream,
    hls::stream <ap_axiu <32, 0, 0, 0>>& outaxistreamsize,
    uint32_t inputSize
    )

Snappy decompression streaming kernel takes compressed data as input from kernel axi stream and process in block based fashion and writes the raw data to global memory.

Parameters:

inaxistream	input kernel axi stream for compressed data
outaxistream	output kernel axi stream for decompressed data
outaxistreamsize	output stream data size
inputSize	input data size

xilSnappyDecompressStream overload (2)

#include "snappy_multicore_decompress_stream.hpp"

void xilSnappyDecompressStream (
    hls::stream <ap_axiu <MULTIPLE_BYTES*8, 0, 0, 0>>& inaxistream,
    hls::stream <ap_axiu <32, 0, 0, 0>>& inaxistreamsize,
    hls::stream <ap_axiu <MULTIPLE_BYTES*8, 0, 0, 0>>& outaxistream,
    hls::stream <ap_axiu <32, 0, 0, 0>>& outaxistreamsize
    )

Snappy decompression streaming kernel takes compressed data as input from kernel axi stream and process in block based fashion and writes the raw data to global memory.

Parameters:

inaxistream	input kernel axi stream for compressed data
inaxistreamsize	input stream data size
outaxistream	output kernel axi stream for decompressed data
outaxistreamsize	output stream data size

xilZlibCompressFull

#include "zlib_compress_multi_engine_mm.hpp"

void xilZlibCompressFull (
    const ap_uint <GMEM_DWIDTH>* in,
    ap_uint <GMEM_DWIDTH>* out,
    uint32_t* compressd_size,
    uint32_t input_size
    )

ZLIB compression kernel takes the raw data as input and compresses the data in parallel block based fashion and writes the output to global memory.

Parameters:

in	input raw data
out	output compressed data
compressd_size	compressed output size of each block
input_size	input data size

xilHuffmanKernel

#include "zlib_huffman_enc_mm.hpp"

void xilHuffmanKernel (
    xf::compression::uintMemWidth_t* in,
    uint32_t* lit_freq,
    uint32_t* dist_freq,
    xf::compression::uintMemWidth_t* out,
    uint32_t* in_block_size,
    uint32_t* compressd_size,
    uint32_t block_size_in_kb,
    uint32_t input_size
    )

Huffman kernel top function. This is an initial version of Huffman Kernel which does block based bit packing process. It uses dynamic huffman codes and bit lengths to encode the LZ77 (Byte Compressed Data) output. This version operates on 1MB block data per engine as this is suitable for use cases where raw data is over >100MB and compression ratio is over 2.5x in order to achieve best throughput. This can be further optimized to achieve better throughput for smaller file usecase.

Parameters:

in	input stream
out	output stream
in_block_size	input block size
compressd_size	output compressed size
dyn_litmtree_codes	input literal and match length codes
dyn_distree_codes	input distance codes
dyn_bitlentree_codes	input bit-length codes
dyn_litmtree_blen	input literal and match length bit length data
dyn_dtree_blen	input distance bit length data
dyn_bitlentree_blen	input bit-length of bit length data
dyn_max_codes	input maximum codes
block_size_in_kb	input block size in bytes
input_size	input data size

xilLz77Compress

#include "zlib_lz77_compress_mm.hpp"

void xilLz77Compress (
    const xf::compression::uintMemWidth_t* in,
    xf::compression::uintMemWidth_t* out,
    uint32_t* compressd_size,
    uint32_t* in_block_size,
    uint32_t* dyn_ltree_freq,
    uint32_t* dyn_dtree_freq,
    uint32_t block_size_in_kb,
    uint32_t input_size
    )

LZ77 compression kernel takes the raw data as input and compresses the data in block based fashion and writes the output to global memory. LZ77 is a byte based compression scheme. The resulting output from this kernel is represented in packet form of 32bit length <Literal, Match Length, Distance>. It also generates output of literal and distance frequencies for dynamic huffman tree generation. The output generated by this kernel is referred by TreeGen and Huffman Kernels.

Parameters:

in	input stream
out	output stream
compressd_size	compressed output size of each block
in_block_size	input block size of each block
dyn_ltree_freq	literal frequency data
dyn_dtree_freq	distance frequency data
block_size_in_kb	input block size in bytes
input_size	input data size

xilTreegenKernel

#include "zlib_treegen_mm.hpp"

void xilTreegenKernel (
    uint32_t* dyn_ltree_freq,
    uint32_t* dyn_dtree_freq,
    uint32_t* dyn_bltree_freq,
    uint32_t* dyn_ltree_codes,
    uint32_t* dyn_dtree_codes,
    uint32_t* dyn_bltree_codes,
    uint32_t* dyn_ltree_blen,
    uint32_t* dyn_dtree_blen,
    uint32_t* dyn_bltree_blen,
    uint32_t* max_codes,
    uint32_t block_size_in_kb,
    uint32_t input_size,
    uint32_t blocks_per_chunk
    )

This is a resource optimized version of huffman treegen kernel. It takes literal and distance frequency data as input through single input stream and generates dynamic huffman codes and bit length data which is output through a single output stream. This kernel does not use DDR in any way and is optimised for both speed and low resource usage.

Parameters:

freqStream	24-bit input stream for getting frequency data
codeStream	20-bit output stream sending huffman codes and bit-lengths data

xilZstdCompress

xilZstdCompress overload (1)

#include "zstd_compress_multicore_stream.hpp"

void xilZstdCompress (
    hls::stream <ap_axiu <STREAM_IN_DWIDTH, 0, 0, 0>>& axiInStream,
    hls::stream <ap_axiu <STREAM_OUT_DWIDTH, 0, 0, 0>>& axiOutStream
    )

ZSTD compression kernel takes input data from axi stream and compresses it into multiple frames having 1 block each and writes the compressed data to output axi stream.

Parameters:

inStream	input raw data
outStream	output compressed data

xilZstdCompress overload (2)

#include "zstd_compress_stream.hpp"

void xilZstdCompress (
    hls::stream <ap_axiu <STREAM_IN_DWIDTH, 0, 0, 0>>& axiInStream,
    hls::stream <ap_axiu <STREAM_OUT_DWIDTH, 0, 0, 0>>& axiOutStream
    )

ZSTD compression kernel takes input data from axi stream and compresses it into multiple frames having 1 block each and writes the compressed data to output axi stream.

Parameters:

inStream	input raw data
outStream	output compressed data

xilZstdDecompressStream

#include "zstd_decompress_stream.hpp"

void xilZstdDecompressStream (
    hls::stream <ap_axiu <c_instreamDWidth, 0, 0, 0>>& inaxistreamd,
    hls::stream <ap_axiu <c_outstreamDWidth, 0, 0, 0>>& outaxistreamd
    )

This is full ZStandard decompression streaming kernel function. It supports all block sizes and supports window size upto 128KB. It takes entire ZStd compressed file as input and produces decompressed file at the kernel output stream. This kernel does not use DDR memory, it uses streams instead. Intermediate data is stored in internal BRAMs and stream FIFOs, which helps to attain better decompression throughput.

Parameters:

inaxistreamd	input kernel axi stream
outaxistreamd	output kernel axi stream