GPU-Based Floating-point Adaptive Lossless Compression

Abstract: Domains such as IoT (Internet of Things) and HPC (High Performance Computing) generate a torrential influx of floating-point time-series data. Compressing these data while preserving their absolute fidelity is critical, and leveraging the massive parallelism of modern GPUs offers a path to unprecedented throughput. Nevertheless, designing such a high-performance GPU-based lossless compressor faces three key challenges: 1) heterogeneous data movement bottlenecks, 2) precision-preserving conversion complexity, and 3) anomaly-induced sparsity degradation. To address these challenges, this paper proposes Falcon, a GPU-based Floating-point Adaptive Lossless COmpressioN framework. Specifically, Falcon first introduces a lightweight asynchronous pipeline, which hides the I/O latency during the data transmission between the CPU and GPU. Then, we propose an accurate and fast float-to-integer transformation method with theoretical guarantees, which eliminates the errors caused by floating-point arithmetic. Moreover, we devise an adaptive sparse bit-plane lossless encoding strategy, which reduces the sparsity caused by outliers. Extensive experiments on 12 diverse datasets show that our compression ratio improves by 9.1% over the most advanced CPU-based method, with compression throughput 2.43X higher and decompression throughput 2.4X higher than the fastest GPU-based competitors, respectively.