Parallel Design of a GPU-Resident Semi-Lagrangian Drift-Kinetic Solver on Unstructured Extruded Tokamak Meshes

Authors: Adams, Mark F.

Subject Terms: Computational Physics, 65Y05, 65Y10, D.1.3; C.4; G.1.8; J.2

Access URL: https://arxiv.org/abs/2610.12585

The Missing Fourth Term for the Emulation Tensor Memory Equilibrium (TME) Model: The Residue Deconstruction Cost

Authors: Bayraktar, Harun, Gunnels, John, Caday, Peter

Subject Terms: Hardware Architecture, Artificial Intelligence, Performance, 65Y10, 65Y20, C.4; G.1.0; G.4; C.1.2

Access URL: https://arxiv.org/abs/2610.10924

Building Navigable Graphs Without Search in Three Composable Stages

Authors: Chávez, Édgar

Subject Terms: Databases, Information Retrieval, 68P10, 68W10, 68P05, H.3.3; C.4; E.1; F.2.2

Access URL: https://arxiv.org/abs/2610.09041

Persistent Memory in Multi-Agent LLM Inference: What It Costs, What It Buys, and When You Can Tell

Authors: Son, Hochan, Han, Kyungdoe, Koh, Jaehan, Dai, Xiaowu, Xu, Wenlu, Cheng, Guang

Subject Terms: Artificial Intelligence, Computation and Language, Distributed, Parallel, and Cluster Computing, Machine Learning, C.4; I.2.7; I.2.11

Access URL: https://arxiv.org/abs/2610.07782

DIALER: A Case for Improving Rare-Class Accuracy in Retraining-Free Edge Video Analytics

Authors: Ryu, Dongyoon, Jeon, Sungho, Ma, Xinyue, Wang, Di, Choi, Jonghyun, Zhang, Minjia, Jeon, Myeongjae

Subject Terms: Distributed, Parallel, and Cluster Computing, C.4

Access URL: https://arxiv.org/abs/2610.06358

MOIRA: Mass-Oriented Indexing with Ragged Attention for Long-Context Decoding

Authors: Nguyen, Dich Nhat Minh, Nguyen, Tran Dang Duong

Subject Terms: Artificial Intelligence, I.2.7; C.4

Access URL: https://arxiv.org/abs/2610.04313

Quantifying Ethereum Energy Consumption via Network Mapping

Authors: Hackspacher, Yahn Costa, Ihle, Cornelius, Shaw, Vasundhara, Trautwein, Dennis, Hoffmann, Geerd-Dietger, Gipp, Bela, Schubotz, Moritz

Subject Terms: Computers and Society, Cryptography and Security, C.2.4; C.2.3; C.4

Access URL: https://arxiv.org/abs/2610.03440

GPU-Initiated Communication: Dissecting Down to the Bone

Authors: Baydamirli, Javid, Ismayilov, Ismayil, Oktay, Kaan, Unat, Didem

Subject Terms: Distributed, Parallel, and Cluster Computing, Networking and Internet Architecture, Performance, C.4; C.2.4

Access URL: https://arxiv.org/abs/2610.01380

Profiling the Energy Consumption of Serverless Functions with Joule Profiler

Authors: Woirhaye, Jérémy, Gibier, François, Da Silva, Anderson Andrei, Faticanti, Francescomaria, Ledoux, Thomas, Rouvoy, Romain

Subject Terms: Software Engineering, C.4; D.4.8; C.2.4

Access URL: https://arxiv.org/abs/2609.37531

Resource-Efficient Speculative Decoding for Long-Context LLM Serving

Authors: Li, Fei, Liu, Song, Nie, Shiqiang, Wang, Jinyu, Wu, Weiguo

Subject Terms: Hardware Architecture, D.4.2; D.4.1; C.4

Access URL: https://arxiv.org/abs/2609.33184

Packets, Transactions and Queues: Design Principles for HFT Systems from a Measurement Study of CME Market Data

Authors: Maciejewski, Vincent

Subject Terms: Trading and Market Microstructure, Distributed, Parallel, and Cluster Computing, Performance, Statistical Finance, 60K25, 60G55, 90B22, C.4; D.4.8; C.2.4

Access URL: https://arxiv.org/abs/2609.32848

WLCG Mini-Capability Challenge: Host Tuning to Im- prove WAN Data Transfers

Authors: Melo, Andrew Malone, Gamboa, Carlos Fernando, Foyo, Diego Devila, Bach, Eduardo, Dart, Eli, McKee, Shawn, Attebury, Garhan, Laurens, Philippe, Wu, Wendy, Shaw, Syed Asif, Ito, Hiro

Subject Terms: Instrumentation and Detectors, High Energy Physics - Experiment, 68M20, 68M10, 68M14, C.4; C.2.3; C.2.4; J.2

Access URL: https://arxiv.org/abs/2609.35859

KCensus: Synthesizing Latency-Optimal Consensus Fast Paths (Extended Version)

Authors: Burgelin, Clément, Murat, Antoine, Sela, Gal, Aguilera, Marcos K., Guerraoui, Rachid

Subject Terms: Distributed, Parallel, and Cluster Computing, C.2.4; C.4

Access URL: https://arxiv.org/abs/2609.31302

Large language models underestimate and partly misrepresent cultural variation in everyday norms

Authors: Eriksson, Kimmo, Vartanova, Irina, Strimling, Pontus

Subject Terms: Computers and Society, J.4; K.4.m; C.4

Access URL: https://arxiv.org/abs/2609.30896

The KV Cache Is the New Memory Wall

Authors: Singh, Tejinder

Subject Terms: Distributed, Parallel, and Cluster Computing, Machine Learning, Performance, C.4; B.3.2; C.1.4

Access URL: https://arxiv.org/abs/2609.30854

Job Class Thermal Intent Aware Liquid Cooling Allocation for AI Data Centers

Authors: Sunkara, Krishna Chaitanya

Subject Terms: Distributed, Parallel, and Cluster Computing, Performance, Systems and Control, C.4; D.4.1; I.6.8

Access URL: https://arxiv.org/abs/2609.30785

Managing Iterative Hybrid Quantum-Classical Optimization as a First-Class Scientific Workflow

Authors: Moreau, Giuliana Siddi, Clemente, Maria Laura, Pisani, Lorenzo, Profir, Manuela, Pinna, Marco, Moro, Marco, Leoni, Lidia

Subject Terms: Distributed, Parallel, and Cluster Computing, 68M14 (Primary) 68M15, 68M20, 81P68, 90C27 (Secondary), C.2.4; C.4; D.4.5; C.1.3; H.4.1

Access URL: https://arxiv.org/abs/2609.30532

Batched Feedback and the Random-Access Wall in Search-Based Graph Construction

Authors: Chávez, Édgar

Subject Terms: Databases, H.3.3; C.4; E.1; F.2.2

Access URL: https://arxiv.org/abs/2609.30493

Xtrace: High-Fidelity GPU Intra-Kernel Tracing via Binary-Level Instruction Splicing

Authors: Huang, Zhuobin, Zhang, Kai, Cui, Weihao, Tan, Hongshi, Luo, Liang, Dewan, Christopher, Li, Shen, He, Bingsheng

Subject Terms: Hardware Architecture, D.2.5; C.4; D.3.4; C.1.2

Access URL: https://arxiv.org/abs/2609.28769

Accurate Distributed Tracing for Large-Scale AI Infrastructure: Time Synchronization as a Foundation for Reliable Observability

Authors: Elbakoury, Hesham, Sharma, Ankur

Subject Terms: Distributed, Parallel, and Cluster Computing, C.2.4; C.2.1; C.4; D.4.8; F.2.2; G.3; I.2.6

Access URL: https://arxiv.org/abs/2609.23301