Home   About Us   News   Contact Us
 
LZR2 Core
High-Performance Lossless Compression Core
 

General Description

Lossless data compression is a class of data compression algorithms that allows the exact original data to be reconstructed from the compressed data.

LZR2 implements the lossless compression /decompression algorithm. Typical applications include enterprise data storage.

The design is fully synchronous and available in multiple configurations varying in bus widths and throughput.

LZR2 delivers sustained (gapless) throughput of 8 bits per clock on the decompressed side or about 1-2.5 Gbps of throughput in FPGA and 4-6 Gbps in ASIC implementations. The compression ratio greatly depends on the data and somewhat depends on the frames size; on typical file corpuses varies between 1.5 and 2..

Symbol


Key Features

  • Each frame is compressed and decompressed independently

  • Compatibility with public-domain LZ software implementations allows for interoperability

  • Parameterizable maximum block size

  • Support for compression and decompression in a single core; dedicates compression and decompression versions are available

  • Back-to-back compression with no gaps between the frames

Applications

  • High-performance solid-state storage

  • Disk and tape storage systems

 

 

Pin Description

Name Type Description
CLK Input Core clock signal
abort Input HIGH level synchronously resets the core
rstb Input LOW level asynchronously resets the core
cen Input Clock enable
mode Input LOW level for compression/encryption, HIGH for decryption/decompression operation
CDbypass Input HIGH level indicates a bypass of the compression/decompression function
EDbypass Input HIGH level indicates a bypass of the encryption/decryption function
estimate Input HIGH level indicates suppression of the compressed data (Cout).
Cin[31:0 ] Input Input data bus for compression/encryption
CinValid Input Data on Cin is valid
CinReady Output Core is ready to accept data on Cin
Cout[7:0 ] Output Output data bus for results of compression/encryption
CoutReady Input Core can drive data on Cout
CoutValid Output Data on Cout is valid
Din[7:0 ] Input Input data bus for decryption/decompression
DinValid Input Data on Din is valid
DinReady Output Core is ready to accept data on Din
Dout[31:0 ] Output Output data bus for results of decryption/decompression
DoutReady Input Core can drive data on Dout
DoutValid Output Data on Dout is valid
BlkSize[23:0] Input Input data length in bytes minus 1
CmpSize[24:0] Output Output data length in bytes minus 1
start Input A HIGH pulse starts the new block
done Output A HIGH pulse indicates the completion of the block processing
active Output A HIGH level indicates the core is busy processing the block
K1[255:0] Input 128/256-bit AES key. 128-bit key resides in the MSB of this port.
K2[255:0] Input 128/256-bit tweak key (K2). 128-bit key resides in the MSB of this port.
key256 Input When HIGH, the K1 and K2 are 256-bit wide. When low, the keys are 128-bit wide.
IV[127:0] Input Initial counter value (location)
MEM   Memory interface
 

Function Description

The core implements lossless compression / decompression and encryption / decryption of data blocks from 512 bytes up to 4096 bytes (longer lengths can be configured).

 

Performance

On the Calgary corpus with the 4096-byte block the core exhibits the following performance:

File Compression ratio File Compression ratio
bib
1.56 (64.22%)
paper3
1.49 (66.93%)
book1
1.39 (71.97%)
paper4
1.54 (64.83%)
book2
1.58 (63.10%)
paper5
1.59 (62.97%)
geo
1.13 (88.52%)
paper6
1.64 (60.88%)
news
1.51 (66.05%)
pic
4.08 (24.52%)
obj1
1.60 (62.70%)
progc
1.74 (57.59%)
obj2
1.83 (54.53%)
progl
2.13 (46.84%)
paper1
1.61 (62.02%)
progp
2.13 (47.00%)
paper2
1.54 (65.11%)
trans
1.93 (51.73%)