Repository files navigation

A Huffman decoder for processing raw (i.e. unpartitioned) Huffman encoded data on the GPU. It also includes a basic, sequential encoder.

For further information, please refer to ourconference paper.

• CUDA-enabled GPU with compute capability 3.0 or higher
• GNU/Linux
• GNU compiler version 5.4.0 or higher
• CUDA SDK 8 or higher
• latest proprietary graphics drivers

Please edit the Makefile:

1. SetCUDA_INCLUDE to the include directory of your CUDA installation, e.g.:CUDA_INCLUDE = /usr/local/cuda-9.1/include

2. SetCUDA_LIB to the library directory of your CUDA installation, e.g.:CUDA_LIB = /usr/local/cuda-9.1/lib64

3. SetARCH to the compute capability of your GPU, i.e.ARCH = 35 for compute capability 3.5. If you'd like to compile the decoder for multiple generations of GPUs, please editNVCC_FLAGS accordingly.

The test program will generate a chunk of random, binomially distributed data, encode the data with a specified maximum codeword length and decode the data on the GPU.

To compile the test program, configure the Makefile as described above. Run:

make

./bin/demo <compute device index> <size of input in megabytes>

To compile a static library, run:

make lib