Related papers: LARK -- Linearizability Algorithms for Replicated …
In large-scale LLM pre-training systems with 100k+ GPUs, failures become the norm rather than the exception, and restart costs can dominate wall-clock training time. However, existing fault-tolerance mechanisms are largely unprepared for…
Data replication is crucial in modern distributed systems as a means to provide high availability. Many techniques have been proposed to utilize replicas to improve a system's performance, often requiring expensive coordination or…
Availability is crucial to the security of distributed systems, but guaranteeing availability is hard, especially when participants in the system may act maliciously. Quorum replication protocols provide both integrity and availability:…
Finding a fixed point to a nonexpansive operator, i.e., $x^*=Tx^*$, abstracts many problems in numerical linear algebra, optimization, and other areas of scientific computing. To solve fixed-point problems, we propose ARock, an algorithmic…
This paper studies the lattice agreement problem in asynchronous systems and explores its application to building linearizable replicated state machines (RSM). First, we propose an algorithm to solve the lattice agreement problem in $O(\log…
Emerging wireless control applications demand for extremely high closed-loop reliability under strict latency constraints, which the conventional Automatic Repeat reQuest (ARQ) solutions with static schedules fail to provide. To overcome…
Raft is a leading consensus algorithm for replicating writes in distributed databases. However, distributed databases also require consistent reads. To guarantee read consistency, a Raft-based system must either accept the high…
Serverless computing is increasingly adopted for its ability to manage complex, event-driven workloads without the need for infrastructure provisioning. However, traditional resource allocation in serverless platforms couples CPU and…
Adaptive Replacement Cache (ARC) and CLOCK with Adaptive Replacement (CAR) are state-of-the- art "adaptive" cache replacement algorithms invented to improve on the shortcomings of classical cache replacement policies such as LRU, LFU and…
Classical state-machine replication protocols, such as Paxos, rely on a distinguished leader process to order commands. Unfortunately, this approach makes the leader a single point of failure and increases the latency for clients that are…
In this paper we introduce Creek, a low-latency, eventually consistent replication scheme that also enables execution of strongly consistent operations (akin to ACID transactions). Operations can have arbitrary complex (but deterministic)…
To exploit both memory locality and the full performance potential of highly tuned kernels, dense linear algebra libraries such as LAPACK commonly implement operations as blocked algorithms. However, to achieve next-to-optimal performance…
The randomized Kaczmarz ($\RK$) algorithm is a simple but powerful approach for solving consistent linear systems $Ax=b$. This paper proposes an accelerated randomized Kaczmarz ($\ARK$) algorithm with better convergence than the standard…
The scaling of Large Language Model (LLM) services faces significant cost and latency challenges, making effective caching under tight capacity crucial. Existing cache replacement policies, from heuristics to learning-based methods,…
Designing a rate limiter that is simultaneously accurate, available, and scalable presents a fundamental challenge in distributed systems, primarily due to the trade-offs between algorithmic precision, availability, consistency, and…
General solutions of state machine replication have to ensure that all replicas apply the same commands in the same order, even in the presence of failures. Such strict ordering incurs high synchronization costs caused by distributed…
In distributed transaction processing, atomic commit protocol (ACP) is used to ensure database consistency. With the use of commodity compute nodes and networks, failures such as system crashes and network partitioning are common. It is…
We present Robust Agent Compensation (RAC), a log-based recovery paradigm (providing a safety net) implemented through an architectural extension that can be applied to most Agent frameworks to support reliable executions (avoiding…
This paper develops a new family of locally recoverable codes for distributed storage systems, Sequential Locally Recoverable Codes (SLRCs) constructed to handle multiple erasures in a sequential recovery approach. We propose a new…
End-to-end communication over the network layer (or data link in overlay networks) is one of the most important communication tasks in every communication network, including legacy communication networks as well as mobile ad hoc networks,…