cs.DC · 2026-07-27 · No. 66

Distributed, Parallel, and Cluster Computing, 2026-07-27.

8 new papers in cs.DC. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

8 entries

01

TileSight: A First-Principles Tile-Centric Analytical GPU Performance Model from Cores to Clusters

Zhiwen Mo, Yu Cheng, Lei Wang, Zhengju Tang, Lei Xu, Guoyu Li, Yuqi Dong, Lingxiao Ma, Yuqing Xia, Jilong Xue, Fan...

cs.DC · cs.PF

Recent GPU programming frameworks such as Triton, TileLang, and CUDA Tile adopt tiles as first-class primitives, making tile-centric programming the prevailing approach for high-performance GPU kernels. Performance-analysis tooling has not followed: programmers still rely on coarse roofline bounds, opaque ML predictors, or post-hoc profilers to understand kernel execution. This gap is acute for modern AI workloads, where kernel fusion and...

arxiv.org/abs/2607.22432 · PDF
02

NUMA balancing hampering performance of spiking network simulations

Melissa Lober, Alp Inangu, Gorka Peraza Coppola, Dennis Terhorst, Sebastian Gillessen, Jan Vogelsang, Hans Ekkehard...

cs.DC · q-bio.NC

Computing centers today mostly operate conventional CPU- and GPU-based systems, where the direct way of decreasing energy consumption is a reduction in the applications' runtime. Neuromorphic computing promises an alternative architecture with improved energy efficiency for artificial intelligence. In this endeavor, code for the simulation of large-scale spiking networks on conventional supercomputers is the reference. We show that turning...

arxiv.org/abs/2607.22275 · PDF
03

Agentic CPU-GPU Scheduling for Heterogeneous AI Workloads

Tianxi Lu, Sherief Reda

cs.DC

Agentic AI systems compose heterogeneous tool workloads on shared GPU/CPU infrastructure, yet existing frameworks assign all GPU-capable tools to the GPU by default. We profile 19 AI tools across GPU and CPU and find that 11 are GPU-preferred, 4 are ambiguous, 1 is CPU-preferred due to PCIe transfer dominance, and 3 are device-neutral, establishing that blanket GPU-first scheduling is suboptimal. We formulate device scheduling as assigning...

arxiv.org/abs/2607.22242 · PDF
04

Duet: Co-Optimizing P2P Message Propagation and Rotating-Leader Consensus

Yifeng Ye, Rongji Huang, Gerui Wang, Mingchao Wan, Yuxing Duan, Jingjing Zhang, Shengyun Liu

cs.DC

In blockchain systems, peer-to-peer (P2P) overlay networks play a crucial role in providing reliable, scalable and efficient message-delivery services to upper layers. However, the consensus layer and the underlying P2P network remain mutually opaque in existing blockchains, waiving the opportunity for further improvement. In contrast to other P2P applications, blockchain can naturally be abstracted as a state machine. We therefore leverage...

arxiv.org/abs/2607.22209 · PDF
05

Accountable Transaction Inclusion Lists: Enhancing Ethereum's Censorship Resistance

Patrick Spiesberger, Hannes Hartenstein

cs.DC

In Ethereum, transaction inclusion is rarely in question; what matters is the delay until inclusion. Currently, block builders could exercise censorship across consecutive blocks, threatening time-critical applications, such as on-chain auctions. To mitigate this risk, existing proposals such as FOCIL, scheduled for deployment in late 2026, assign a committee to list transactions for mandatory inclusion. However, no committee member is held...

arxiv.org/abs/2607.22040 · PDF
06

Smart Contract Tells: Aircraft Maintenance Records Are Now Trustworthy

Woosuk Choi, Seungmo Kim

cs.DC

Aircraft maintenance records are critical to airworthiness and asset valuation, yet they are often fragmented across stakeholders, creating verification bottlenecks and information asymmetry that may suppress aircraft residual value. This paper proposes a blockchain-anchored decentralized application (dApp) based on a dual-layer architecture that combines InterPlanetary File System (IPFS)-based off-chain storage with on-chain anchoring of...

arxiv.org/abs/2607.21989 · PDF
07

Unified Static-Dynamic Pruning for Efficient LLM Inference

Jinhyeok Kim, Yejoon Lee, Jaeyoung Do

cs.DC · cs.AI · cs.AR · cs.LG

The increasing deployment of large language models (LLMs) has magnified the computational and memory bottlenecks of autoregressive decoding, where low compute intensity and bandwidth-bound kernels dominate inference cost. Weight pruning offers a promising remedy, but existing methods remain confined to either static pruning (SP), which permanently removes redundant weights but lacks adaptivity, or dynamic pruning (DP), which adapts to input...

arxiv.org/abs/2607.21985 · PDF
08

PRISM: Evaluating POSIX Storage Systems for AI Research Workflows

Adithya Kumar, Aditya Basu, Jacob Kahn, Parth Malani, Leo Huang, Kalyan Saladi

cs.DC · cs.PF

The rapid advancement of AI research is driven by massive investments in GPU clusters, yet the critical role of storage systems in enabling efficient research workflows is often overlooked. Unlike traditional HPC workloads, AI research prioritizes researcher productivity and ease of iteration. Practitioners rely on POSIX compliant file systems for seamless prototyping, debugging, and experimentation before scaling to specialized storage...

arxiv.org/abs/2607.21746 · PDF

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.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.