Acceleration of Deflate Encoding and Decoding with GPU implementations

Takafuji, Daisuke; Nakano, Koji; Ito, Yasuaki; Kasagi, Akihiko

doi:10.1109/candarw53999.2021.00036

Cited by 1 publication

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) In the preliminary version 23 of this journal paper, we have presented GPU Deflate encoding and decoding. This journal paper improves the GPU implementation of Deflate encoding.…”

Section: Introductionmentioning

confidence: 99%

“…By computing the gap array in the process of Huffman encoding, parallel Huffman decoding can be done very efficiently in a GPU. 22 Moreover, we describe the following four points of the differences between the preliminary version 23 and this journal paper: (1) Improvement of Deflate encoding, (2) Usage of the latest high-end GPU, (3) Implementing a parallel Deflate decoding on CPUs to evaluate the performance of our GPU Deflate decoding, and (4) Enhancement of evaluation by comparing our GPU Deflate encoding/decoding with parallel CPU implementations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

GPU implementations of deflate encoding and decoding

Takafuji

Nakano

Ito

et al. 2022

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Summary Deflate coding is a very popular lossless data compression method used in zlib, gzip (GNU zip), and zip, which performs the LZSS compression algorithm with Huffman coding. Deflate encoding and decoding involve sequential operations and their parallel acceleration using a GPU is quite hard. The main purpose of this paper is to present GPU implementations for encoding and decoding of Deflate coding. For efficient GPU implementations of Deflate coding, we have used multiple small hash tables for finding matching subsequences in the dictionary by multiple threads in parallel and applied the Single Kernel Soft Synchronization (SKSS) technique to fully utilize GPU computing resources. We have also adopted Huffman coding with gap arrays to accelerate parallel Huffman decoding. We have evaluated the performance of our GPU implementations using an NVIDIA A100 GPU and compared them with parallel/sequential Deflate encoding and decoding on the Intel X86 multicore CPUs using multiple threads/a single thread. Our GPU implementation of Deflate decoding is 1.66x–8.33x faster than the multiple thread implementation and 4.13x–36.56x faster than the single thread implementation.

show abstract

“…(1) In the preliminary version 23 of this journal paper, we have presented GPU Deflate encoding and decoding. This journal paper improves the GPU implementation of Deflate encoding.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%