Výsledky vyhledávání - "Proceedings / IEEE International Conference on Cluster Computing"

Accelerating Key-Value Data Structures Using AVX-512 SIMD Extensions Autor HoseinyFarahabady, MohammadReza, Taheri, Javid, Zomaya, Albert Y.

“…Advanced Vector Extensions 512 (AVX-512), a modern SIMD instruction set for x86 architectures, enables data-level parallelism through 512-bit wide ZMM…”
Získat plný text

Are We There Yet? Predicting the Queue Wait Times for HPC Jobs Autor Whitton, Christin, Jones, William, Walker, Craig, Job, Vanessa, Senator, Steven, DeBardeleben, Nathan

“…Large high-performance computing systems are commonly shared among users that submit their workflows to a resource manager and scheduling framework such as…”
Získat plný text

A Versatile Simulated Data Transport Layer for in Situ Workflows Performance Evaluation Autor Suter, Frederic

“…In situ processing does not only allow scientific applications to face the explosion in data volume and velocity but also to address the time constraints of…”
Získat plný text

Uniconn: A Uniform High-Level Communication Library for Portable Multi-GPU Programming Autor Sagbili, Dogan, Ekmekcibasi, Sinan, Ibrahim, Khaled Z., Nguyen, Tan, Unat, Didem

“…Modern HPC and AI systems increasingly rely on multi-GPU clusters, where communication libraries such as MPI, NCCL/RCCL, and NVSHMEM enable data movement…”
Získat plný text

SplitQuant: Resource-Efficient LLM Offline Serving on Heterogeneous GPUs via Phase-Aware Model Partition and Adaptive Quantization Autor Zhao, Juntao, Wan, Borui, Peng, Yanghua, Lin, Haibin, Wu, Chuan

“…Modern large language models (LLMs) serving systems address distributed deployment challenges through two key techniques: distributed model partitioning for…”
Získat plný text

Deadline-Aware Resource Allocation and Scheduling of Serverless Workloads on Heterogeneous Clusters Autor Fritz, Matthias, Benkner, Siegfried, Bajrovic, Enes

“…Serverless computing has become widely adopted as a cloud deployment model due to its ease of use and finegrained pay-as-you-go pricing. By hiding…”
Získat plný text

Revisiting Fragmentation for Deduplication in Clustered Primary Storage Systems Autor Wang, Lin, Hu, Yuchong, Mao, Shilong, Li, Mingqi, Duan, Ziling, Huang, Yue, Qin, Leihua, Feng, Dan, Chen, Zehui, Dong, Ruliang

“…To improve storage efficiency in large-scale clustered storage systems, deduplication that removes duplicate chunks has been widely deployed in distributed…”
Získat plný text

Towards High-Performance and Portable Molecular Docking on CPUs Through Vectorization Autor Accordi, Gianmarco, Domke, Jens, Pollinger, Theresa, Gadioli, Davide, Palermo, Gianluca

“…Recent trends in the HPC field have introduced new CPU architectures with improved vectorization capabilities that require optimization to achieve peak…”
Získat plný text

FIFO-MEP: An Efficient Multi-Eviction-Point FIFO Cache with Stable Demotion for Burst-Oriented Access Mitigation Autor Jia, Ranhao, Gu, Yunfei, Wu, Chentao, Li, Jie, Guo, Minyi, Zhang, Liqiang, Zhang, Zaigui, Zhang, Haijun

“…Caching technology is widely used in multiple areas particularly in distributed computing, where its performance is highly dependent on the cache efficiency…”
Získat plný text

NSYS2PRV: Detailed and Quantitative Analysis of Large-Scale GPU Execution Traces with Paraver Autor Clasca, Marc, Labarta, Jesus, Garcia-Gasulla, Marta

“…This work presents a tool, a methodology, a set of metrics, and practical examples for evaluating the performance of large-scale AI and traditional HPC…”
Získat plný text

Parallel Selected Inversion of Block-Tridiagonal with Arrowhead Matrices Autor Maillou, Vincent, Gaedke-Merzhauser, Lisa, Ziogas, Alexandros Nikolaos, Schenk, Olaf, Luisier, Mathieu

“…The inversion of structured sparse matrices is a fundamental yet computationally and memory-intensive task in many scientific applications, such as Bayesian…”
Získat plný text

Towards Dynamic Message Passing Protocols for Stencil-Based Communication Patterns Autor Suresh, Kaushik Kandadi, Ramesh, Bharath, Kuncham, Goutham Kalikrishna Reddy, Subramoni, Hari, Panda, Dhabaleswar K. DK

“…Halo-exchange communication patterns occur in many stencil-based HPC applications such as MiniAMR, MiniGhost, and MILC. In this pattern, each process performs…”
Získat plný text

Multi-agent Independent PPO-based Automatic ECN Tuning for High-Speed Data Center Networks Autor Wang, Ting, Cheng, Kai, Du, Xiao

“…Explicit Congestion Notification (ECN)-based congestion control schemes have been widely adopted in high-speed data center networks (DCNs), where the ECN…”
Získat plný text

PIAR: Path-Improved Adaptive Routing for Dragonfly Networks Autor Wang, Zhenghao, Wang, Qiang, Lai, Mingche, Xu, Jiaqing, Xu, Jinbo, Xie, Min, Chen, Guo

“…For the next-generation exascale supercomputing communication systems, Dragonfly topology offers strong scalability, low latency, and cost efficiency…”
Získat plný text

DaCe AD: Unifying High-Performance Automatic Differentiation for Machine Learning and Scientific Computing Autor Boudaoud, Affi, Calotoiu, Alexandru, Copik, Marcin, Hoefler, Torsten

“…Automatic differentiation (AD) is a set of techniques that systematically applies the chain rule to compute the gradients of functions without requiring human…”
Získat plný text

PRT: An Efficient Pipeline Reuse Technology for Large Models Training Autor Ji, Zeyu, Zhai, Banghao, Zhang, Zhonghao, Chu, Qi, Liu, Bin

“…The rapid evolution of large models and the widespread application of extensive datasets have made the cost of training increasingly prohibitive. While…”
Získat plný text

DDRM: An SLO-aware Deep Dynamic Resource Management Framework for Microservices Autor Tang, Liangping, Wang, Jin, Wang, Wanyou, Shi, Gaotao, Li, Zhijun

“…Loosely coupled microservice architectures have been widely adopted in cloud-native applications due to their inherent advantages in modularity, development…”
Získat plný text

Cascade: a Collaborative Algorithm for Scalable and Efficient Neighborhood Allgather Autor Sharifian, Hamed, Sojoodi, Amirhossein, Afsahi, Ahmad

“…Neighborhood collectives are a critical feature of MPI, enabling efficient communication in applications with sparse communication patterns. This research…”
Získat plný text

TRACE: A Targeted Recommender for VM Assignment in Cloud Environment Autor Dong, Hongji, Cheng, Yunlong, Chan, Tin Ping, Gao, Xiaofeng, Chen, Guihai

“…Multi-tenancy in modern cloud service colocates multiple virtual machines (VMs) into physical machines (PMs) to improve resource efficiency. However,…”
Získat plný text

GreenK8s: Green-aware Scheduling for Sustainable Kubernetes Cluster Management Autor Sun, Yifan, Xu, Minxian, Toosi, Adel N.

“…With the rise of large-scale data centers and increasing demand for energy-efficient operations, there is a growing need to optimize the use of green energy in…”
Získat plný text