RAS: A Bit-Exact rANS Accelerator For High-Performance Neural Lossless Compression

TL;DR

RAS is a specialized hardware architecture that accelerates neural lossless compression using rANS, achieving significant speedups and maintaining bit-exactness, thus enabling practical high-performance data center compression.

Contribution

The paper introduces RAS, a hardware accelerator for rANS that integrates probabilistic models, reduces logic and memory costs, and scales throughput for neural lossless compression.

Findings

121.2x encode speedup over Python rANS

70.9x decode speedup over Python rANS

Higher compression ratios with neural models

Abstract

Data centers handle vast volumes of data that require efficient lossless compression, yet emerging probabilistic models based methods are often computationally slow. To address this, we introduce RAS, the Range Asymmetric Numeral System Acceleration System, a hardware architecture that integrates the rANS algorithm into a lossless compression pipeline and eliminates key bottlenecks. RAS couples an rANS core with a probabilistic generator, storing distributions in BF16 format and converting them once into a fixed-point domain shared by a unified division/modulo datapath. A two-stage rANS update with byte-level re-normalization reduces logic cost and memory traffic, while a prediction-guided decoding path speculatively narrows the cumulative distribution function (CDF) search window and safely falls back to maintain bit-exactness. A multi-lane organization scales throughput and enables fine-grained clock gating for efficient scheduling. On image workloads, our RTL-simulated prototype achieves 121.2x encode and 70.9x decode speedups over a Python rANS baseline, reducing average decoder binary-search steps from 7.00 to 3.15 (approximately 55% fewer). When paired with neural probability models, RAS sustains higher compression ratios than classical codecs and outperforms CPU/GPU rANS implementations, offering a practical approach to fast neural lossless compression.