English
Related papers

Related papers: Equilibria: Fair Multi-Tenant CXL Memory Tiering A…

200 papers

As AI inference becomes mainstream, research has begun to focus on improving the energy consumption of inference servers. Inference kernels commonly underutilize a GPU's compute resources and waste power from idling components. To improve…

Systems and Control · Electrical Eng. & Systems 2025-06-17 Ryan Quach , Yidi Wang , Ali Jahanshahi , Daniel Wong , Hyoseung Kim

As modern LLMs support thousands to millions of tokens, KV caches grow to hundreds of gigabytes, stressing memory capacity and bandwidth. Existing solutions, such as KV cache pruning and offloading, alleviate these but underutilize hardware…

Performance · Computer Science 2026-04-21 Mao Lin , Xi Wang , Guilherme Cox , Dong Li , Hyeran Jeon

Reducing the average memory access time is crucial for improving the performance of applications running on multi-core architectures. With workload consolidation this becomes increasingly challenging due to shared resource contention.…

Hardware Architecture · Computer Science 2021-02-24 Nadja Ramhöj Holtryd , Madhavan Manivannan , Per Stenström , Miquel Pericàs

Efficiently serving Large Language Models (LLMs) requires selecting an optimal parallel execution plan, balancing computation, memory, and communication overhead. However, determining the best strategy is challenging due to varying…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-01 Yi-Chien Lin , Woosuk Kwon , Ronald Pineda , Fanny Nina Paravecino

High-demand LLM inference services (e.g., ChatGPT and BARD) support a wide range of requests from short chat conversations to long document reading. To ensure that all client requests are processed fairly, most major LLM inference services…

Artificial Intelligence · Computer Science 2024-06-06 Ying Sheng , Shiyi Cao , Dacheng Li , Banghua Zhu , Zhuohan Li , Danyang Zhuo , Joseph E. Gonzalez , Ion Stoica

Large language model (LLM) inference systems face a fundamental tension between minimizing Time-to-First-Token (TTFT) latency for new requests and maintaining a high, steady token generation rate (low Time-Per-Output-Token, or TPOT) for…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-17 Hongtao Lyu , Boyue Liu , Mingyu Wu , Haibo Chen

We present a thorough analysis of the use of modern heterogeneous systems interconnected by various cachecoherent links, including CXL, NVLink-C2C, and Infinity Fabric. We studied a wide range of server systems that combined CPUs from…

Memory tiering is the norm to effectively tackle the increasing server memory total cost of ownership (TCO) and the growing data demands of modern data center workloads. However, the host-based state-of-the-art memory tiering solutions can…

Operating Systems · Computer Science 2025-06-09 Chandra Prakash , Aravinda Prasad , Sandeep Kumar , Sreenivas Subramoney

Trusted hardware's freshness guarantee ensures that an adversary cannot replay an old value in response to a memory read request. They rely on maintaining a version number for each cache block and ensuring their integrity using a Merkle…

Hardware Architecture · Computer Science 2024-10-17 Juechu Dong , Jonah Rosenblum , Satish Narayanasamy

Trusted-execution environments (TEE), like Intel SGX, isolate user-space applications into secure enclaves without trusting the OS. Thus, TEEs reduce the trusted computing base, but add one to two orders of magnitude slow-down. The…

Cryptography and Security · Computer Science 2020-10-19 Zhijingcheng Yu , Shweta Shinde , Trevor E. Carlson , Prateek Saxena

This paper proposes a novel splitting (SPLIT) algorithm to achieve fairness in the multiterminal lossless data compression problem. It finds the egalitarian solution in the Slepian-Wolf region and completes in strongly polynomial time. We…

Information Theory · Computer Science 2018-05-07 Ni Ding , David Smith , Parastoo Sadeghi , Thierry Rakotoarivelo

Tensor parallelism (TP) in large-scale LLM inference and training introduces frequent collective operations that dominate inter-GPU communication. While in-switch computing, exemplified by NVLink SHARP (NVLS), accelerates collective…

Hardware Architecture · Computer Science 2026-05-08 Chen Zhang , Qijun Zhang , Zhuoshan Zhou , Yijia Diao , Haibo Wang , Zhe Zhou , Zhipeng Tu , Zhiyao Li , Guangyu Sun , Zhuoran Song , Zhigang Ji , Jingwen Leng , Minyi Guo

The introduction of Intel(R) Xeon Phi(TM) coprocessors opened up new possibilities in development of highly parallel applications. The familiarity and flexibility of the architecture together with compiler support integrated into the Intel…

Distributed, Parallel, and Cluster Computing · Computer Science 2012-11-26 Jiri Dokulil , Enes Bajrovic , Siegfried Benkner , Sabri Pllana , Martin Sandrieser , Beverly Bachmayer

Scalable user- and application-aware resource allocation for heterogeneous applications sharing an enterprise network is still an unresolved problem. The main challenges are: (i) How to define user- and application-aware shares of…

Networking and Internet Architecture · Computer Science 2020-02-27 Christian Sieber , Susanna Schwarzmann , Andreas Blenk , Thomas Zinner , Wolfgang Kellerer

Most work on the verification of concurrent objects for shared memory assumes sequential consistency, but most multicore processors support only weak memory models that do not provide sequential consistency. Furthermore, most verification…

Distributed, Parallel, and Cluster Computing · Computer Science 2016-04-25 Simon Doherty , John Derrick

With a recent trend of using Large Language Models (LLMs) for different applications within smart cities, there is a need for pushing these models toward the edge of network while still preserving their performance. Edge Computing (EC) as a…

Machine Learning · Computer Science 2025-03-04 Minoo Hosseinzadeh , Hana Khamfroush

This paper presents Block, a distributed scheduling framework designed to optimize load balancing and auto-provisioning across instances in large language model serving frameworks by leveraging contextual information from incoming requests.…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-08-14 Wei Da , Evangelia Kalyvianaki

Large Language Model (LLM) training is frequently interrupted by a heterogeneous spectrum of failures, from common GPU crashes to catastrophic cluster-wide outages. Existing checkpointing systems rely on monolithic, single-tier storage…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-19 Shujie Han , Feng Jiang , Patrick P. C. Lee , Xiao Zhang , Zhijie Huang , Nannan Zhao , Xiaonan Zhao , Lichen Pan

LLM agents, which often comprise parallel inference tasks, are commonly adopted to solve real-world problems. When serving such task-parallel LLM agents in shared GPU servers, the scheduler is expected to attain fast agent completion with…

Machine Learning · Computer Science 2026-03-17 Mingyan Yang , Guanjie Wang , Manqi Luo , Yifei Liu , Chen Chen , Han Zhao , Yu Feng , Quan Chen , Minyi Guo

The widening gap between processor speed and storage latency has made data movement a dominant bottleneck in modern systems. Two lines of storage-layer innovation attempted to close this gap: persistent memory shortened the latency…

Operating Systems · Computer Science 2026-04-06 Yiwei Yang , Yanpeng Hu , Yusheng Zheng , Estabon Ramos , Jianchang Su , Andi Quinn , Wei Zhang