22 papers
FZ-VIS: A Visual Analytics Framework for Quantities-of-Interest-Aware Scientific Lossy Compression
Guoxi Liu, Yuxiao Li, Congrong Ren +6
Modern scientific simulations generate massive volumes of data, making lossy compression essential for efficient storage and transmission. However, preserving critical quantities o…
SPARe: Stacked Parallelism with Adaptive Reordering for Fault-Tolerant LLM Pretraining Systems with 100k+ GPUs
Jin Lee, Zhonghao Chen, Xuhang He +6
In large-scale LLM pre-training systems with 100k+ GPUs, failures become the norm rather than the exception, and restart costs can dominate wall-clock training time. However, exist…
ReCoVer: Resilient LLM Pre-Training System via Fault-Tolerant Collective and Versatile Workload
Ziyue Liu, Zhengyang Wang, Ruijie Zhang +7
Pre-training large language models on massive GPU clusters has made hardware faults routine rather than rare, driving the need for resilient training systems. Yet existing framewor…
Preserving Clusters in Error-Bounded Lossy Compression of Scientific Particle Data
Congrong Ren, Sheng Di, Katrin Heitmann +2
Scientific particle simulations in cosmology, molecular dynamics, and fluid dynamics produce large-scale datasets whose storage, movement, and analysis increasingly rely on lossy c…
Enabling Homomorphic Analytical Operations on Compressed Scientific Data with Multi-stage Decompression
Xuan Wu, Sheng Di, Tripti Agarwal +3
Error-controlled lossy compressors have been widely used in scientific applications to reduce the unprecedented size of scientific data while keeping data distortion within a user-…
Rate-Distortion Bounds for Heterogeneous Random Fields on Finite Lattices
Sujata Sinha, Vishwas Rao, Robert Underwood +4
Since Shannon's foundational work, rate-distortion theory has defined the fundamental limits of lossy compression. Classical results, derived for memoryless and stationary ergodic…