This repository presents DecodeX, a unified benchmarking framework for evaluating low-density parity-check (LDPC) decoding acceleration across different hardware platforms. DecodeX integrates a comprehensive suite of LDPC decoder implementations, including kernels, APIs, and test vectors for CPUs (FlexRAN), GPUs (Aerial and Sionna-RK), and ASIC (ACC100), and can be readily extended to additional architectures and configurations.
Current supported benchmarking frameworks consists of the following:
| Hardware | Implementation | Platform |
|---|---|---|
| CPU | FlexRAN | Intel Xeon |
| CPU | OAI | Intel Xeon |
| ASIC | DPDK-BBDev | ACC100 |
| GPU | OAI | RTX 6000 Ada |
| GPU | Sionna-rk | Jetson AGX Orin |
| GPU | Aerial | H200 |
| GPU | Aerial | RTX 3090 |
| GPU | Aerial | RTX 6000 Ada |
If you find DecodeX useful for your research, please consider citing this paper:
@misc{qi2025decodexexploringbenchmarkingldpc,
title={DecodeX: Exploring and Benchmarking of LDPC Decoding across CPU, GPU, and ASIC Platforms},
author={Zhenzhou Qi and Yuncheng Yao and Yiming Li and Chung-Hsuan Tung and Junyao Zheng and Danyang Zhuo and Tingjun Chen},
year={2025},
eprint={2511.02952},
archivePrefix={arXiv},
primaryClass={cs.NI},
url={https://arxiv.org/abs/2511.02952},
}