cs.DC · 2026-10-15 · No. 144
Distributed, Parallel, and Cluster Computing, 2026-10-15.
4 new papers in cs.DC. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
4 entries-
01
Understanding NVIDIA Grace-Blackwell Unified Memory Through Placement-Controlled Microbenchmarks
Nathan Graddon, Aaron Jarmusch, Sunita Chandrasekaran
cs.DC
NVIDIA Grace--Blackwell systems make CPU--GPU memory increasingly unified at the programming level, but unified addressability does not make the memory system uniform. A CUDA managed allocation on GB200 may be served from GPU-local HBM, accessed through host/system memory, demand-migrated, prefetched, reused after GPU access, or evicted and reloaded under capacity pressure. The problem is that these states share a programming interface while...
-
02
TrimSO(2): Fast and Memory-Efficient Training of Equivariant Interatomic Potentials
Chen Wang, Yuanchang Zhou, Guangming Tan, Mingzhen Li, Weile Jia
cs.DC
Equivariant interatomic potentials enable accurate and efficient simulations of molecules and materials. Among them, models based on SO(2) convolutions reduce the cost of tensor products and achieve state-of-the-art accuracy, but their training remains time-consuming and memory-intensive. Existing training implementations materialize large edge tensors for representation transformations surrounding dense matrix multiplications, increasing...
-
03
JointServe: Serving Multi-Model Agents on Memory-Constrained GPUs
Daijin Hu
cs.DC · cs.LG
LLM agents are evolving from a single model calling tools to planners that orchestrate multiple expert models whose capabilities live in distinct weights. This shift breaks a hidden assumption of today's serving systems: that the working set of models fits in GPU memory. On the memory-constrained GPUs typical of private and edge deployments, naive whole-model swapping serializes weight transfer with computation and, without host-backed KV...
-
04
The Cost of Context: Profiling the Energy Footprint of Input Tokens in Large Language Models
Boris Ruf, Marcin Detyniecki
cs.DC
The rapid adoption of Retrieval-Augmented Generation (RAG) and long-context LLMs has shifted the computational burden toward the prefill phase---the initial stage where the model processes all input tokens in parallel before generating a response---yet its energy impact remains poorly characterised. We investigate the contradiction between massive hardware-level power spikes and the sub-linear marginal cost of input tokens reported in...
This edition is part of The Daily Abstract — cs.DC archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.