Tootfinder

A Survey of End-to-End Modeling for Distributed DNN Training: Workloads, Simulators, and TCO
Jonas Svedas, Hannah Watson, Nathan Laubeuf, Diksha Moolchandani, Abubakr Nada, Arjun Singh, Dwaipayan Biswas, James Myers, Debjyoti Bhattacharjee
https://arxiv.org/abs/2506.09275

A Survey of End-to-End Modeling for Distributed DNN Training: Workloads, Simulators, and TCO
Distributed deep neural networks (DNNs) have become a cornerstone for scaling machine learning to meet the demands of increasingly complex applications. However, the rapid growth in model complexity far outpaces CMOS technology scaling, making sustainable and efficient system design a critical challenge. Addressing this requires coordinated co-design across software, hardware, and technology layers. Due to the prohibitive cost and complexity of deploying full-scale training systems, simulators …

Filing: OpenAI seeks to block a May 13 court order requiring it to preserve all ChatGPT logs, including deleted chats, arguing it poses a risk to users' privacy (Ashley Belanger/Ars Technica)
https://arstechnica.com/tech-policy/20

OpenAI slams court order to save all ChatGPT logs, including deleted chats
OpenAI defends privacy of hundreds of millions of ChatGPT users.

This https://arxiv.org/abs/2409.15104 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDC_…

PecSched: Preemptive and Efficient Cluster Scheduling for LLM Inference
The scaling of transformer-based Large Language Models (LLMs) has significantly expanded their context lengths, enabling applications where inputs exceed 100K tokens. Our analysis of a recent Azure LLM inference trace reveals a highly skewed long-tail distribution of input lengths, with approximately 80% of inputs shorter than 2K tokens. Long inputs constitute only a small fraction. Existing cluster-level LLM scheduling strategies, including First-In-First-Out (FIFO), reservation-based, and pri…

How urban scaling and resource distribution shape social welfare and migration dynamics
Bryce Morsky
https://arxiv.org/abs/2506.03384 https://

How urban scaling and resource distribution shape social welfare and migration dynamics
Many outputs of cities scale in universal ways, including infrastructure, crime, and economic activity. Through a mathematical model, this study investigates the interplay between such scaling laws in human organization and governmental allocations of resources, focusing on impacts to migration patterns and social welfare. We find that if superlinear scaling resources of cities -- such as economic and social activity -- are the primary drivers of city dwellers' utility, then cities tend to conv…

On the Performance of Cloud-based ARM SVE for Zero-Knowledge Proving Systems
Dumitrel Loghin, Shuang Liang, Shengwei Liu, Xiong Liu, Pingcheng Ruan, Zhigang Ye
https://arxiv.org/abs/2506.09505

On the Performance of Cloud-based ARM SVE for Zero-Knowledge Proving Systems
Zero-knowledge proofs (ZKP) are becoming a gold standard in scaling blockchains and bringing Web3 to life. At the same time, ZKP for transactions running on the Ethereum Virtual Machine require powerful servers with hundreds of CPU cores. The current zkProver implementation from Polygon is optimized for x86-64 CPUs by vectorizing key operations, such as Merkle tree building with Poseidon hashes over the Goldilocks field, with Advanced Vector Extensions (AVX and AVX512). With these optimizations…

TTrace: Lightweight Error Checking and Diagnosis for Distributed Training
Haitian Jiang, Shaowei Zhu, Zhen Zhang, Zhenyu Song, Xinwei Fu, Zhen Jia, Yida Wang, Jinyang Li
https://arxiv.org/abs/2506.09280

TTrace: Lightweight Error Checking and Diagnosis for Distributed Training
Distributed training is essential for scaling the training of large neural network models, such as large language models (LLMs), across thousands of GPUs. However, the complexity of distributed training programs makes them particularly prone to silent bugs, which do not produce explicit error signal but lead to incorrect training outcome. Effectively detecting and localizing such silent bugs in distributed training is challenging. Common debugging practice using metrics like training loss or gr…

This https://arxiv.org/abs/2505.17155 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling
Large Reasoning Models (LRMs) demonstrate exceptional capability in tackling complex mathematical, logical, and coding tasks by leveraging extended Chain-of-Thought (CoT) reasoning. Test-time scaling methods, such as prolonging CoT with explicit token-level exploration, can push LRMs' accuracy boundaries, but they incur significant decoding overhead. A key inefficiency source is LRMs often generate redundant thinking CoTs, which demonstrate clear structured overthinking and underthinking patter…

Parallel FFTW on RISC-V: A Comparative Study including OpenMP, MPI, and HPX
Alexander Strack, Christopher Taylor, Dirk Pfl\"uger
https://arxiv.org/abs/2506.08653

Parallel FFTW on RISC-V: A Comparative Study including OpenMP, MPI, and HPX
Rapid advancements in RISC-V hardware development shift the focus from low-level optimizations to higher-level parallelization. Recent RISC-V processors, such as the SOPHON SG2042, have 64 cores. RISC-V processors with core counts comparable to the SG2042, make efficient parallelization as crucial for RISC-V as the more established processors such as x86-64. In this work, we evaluate the parallel scaling of the widely used FFTW library on RISC-V for MPI and OpenMP. We compare it to a 64-core AM…

Resilient Auto-Scaling of Microservice Architectures with Efficient Resource Management
Hussain Ahmad, Christoph Treude, Markus Wagner, Claudia Szabo
https://arxiv.org/abs/2506.05693

Resilient Auto-Scaling of Microservice Architectures with Efficient Resource Management
Horizontal Pod Auto-scalers (HPAs) are crucial for managing resource allocation in microservice architectures to handle fluctuating workloads. However, traditional HPAs fail to address resource disruptions caused by faults, cyberattacks, maintenance, and other operational challenges. These disruptions result in resource wastage, service unavailability, and HPA performance degradation. To address these challenges, we extend our prior work on Smart HPA and propose SecureSmart HPA, which offers re…

This https://arxiv.org/abs/2505.16499 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDC_…

Smaller, Smarter, Closer: The Edge of Collaborative Generative AI
The rapid adoption of generative AI (GenAI), particularly Large Language Models (LLMs), has exposed critical limitations of cloud-centric deployments, including latency, cost, and privacy concerns. Meanwhile, Small Language Models (SLMs) are emerging as viable alternatives for resource-constrained edge environments, though they often lack the capabilities of their larger counterparts. This article explores the potential of collaborative inference systems that leverage both edge and cloud resour…