Related papers: Dependency-Aware Rollback and Checkpoint-Restart f…
While the concept of Artificial Intelligent Internet of Things\ (AIoT) is booming, computation and/or communication-intensive tasks accompanied by several sub-tasks are slowly moving from centralized deployment to edge-side deployment. The…
Production MPI codes need checkpoint-restart (CPR) support. Clearly, checkpoint-restart libraries must be fault tolerant lest they open up a window of vulnerability for failures with byzantine outcomes. But, certain popular libraries that…
Deep learning (DL) applications are increasingly being deployed on HPC systems, to leverage the massive parallelism and computing power of those systems for DL model training. While significant effort has been put to facilitate distributed…
Handling faults is a growing concern in HPC. In future exascale systems, it is projected that silent undetected errors will occur several times a day, increasing the occurrence of corrupted results. In this article, we propose SEDAR, which…
In Open Source Software, resources of any project are open for reuse by introducing dependencies or copying the resource itself. In contrast to dependency-based reuse, the infrastructure to systematically support copy-based reuse appears to…
This technical report presents a method for designing a constrained output-feedback model predictive controller (MPC) that behaves in the same way as an existing baseline stabilising linear time invariant output-feedback controller when…
Disaggregated memory architectures provide benefits to applications beyond traditional scale out environments, such as independent scaling of compute and memory resources. They also provide an independent failure model, where computations…
Classical reverse-mode automatic differentiation (AD) imposes only a small constant-factor overhead in operation count over the original computation, but has storage requirements that grow, in the worst case, in proportion to the time…
The rise of transient faults in modern hardware requires system designers to consider errors occurring at runtime. Both hardware- and software-based error handling must be deployed to meet application reliability requirements. The level of…
Consistency properties provided by most key-value stores can be classified into sequential consistency and eventual consistency. The former is easier to program with but suffers from lower performance whereas the latter suffers from…
Training LLMs on decentralized nodes or on-spot instances, lowers the training cost and enables model democratization. The inevitable challenge here is the transient churns of nodes due to failures and the operator's scheduling policies,…
This paper proposes a reversible learning framework to improve the robustness and efficiency of value based Reinforcement Learning agents, addressing vulnerability to value overestimation and instability in partially irreversible…
In this work we consider a generalization of the well-known multivehicle routing problem: given a network, a set of agents occupying a subset of its nodes, and a set of tasks, we seek a minimum cost sequence of movements subject to the…
Limitations of the CAP theorem imply that if availability is desired in the presence of network partitions, one must sacrifice sequential consistency, a consistency model that is more natural for system design. We focus on the problem of…
Exceptions and errors occurring within mission critical applications due to hardware failures have a high cost. With the emerging Next Generation Platforms (NGPs), the rate of hardware failures will likely increase. Therefore, designing our…
Test-Time Scaling enhances the reasoning capabilities of Large Language Models by allocating additional inference compute to broaden the exploration of the solution space. However, existing search strategies typically treat rollouts as…
Machine learning models deployed in non-stationary environments are exposed to temporal distribution shift, which can erode predictive reliability over time. While common mitigation strategies such as periodic retraining and recalibration…
Communication scheduling aims to reduce communication bottlenecks in data parallel training (DP) by maximizing the overlap between computation and communication. However, existing schemes fall short due to three main issues: (1) hard data…
Remote procedure calls are the workhorse of distributed systems. However, as software engineering trends, such as micro-services and serverless computing, push applications towards ever finer-grained decompositions, the overhead of…
Balancing the workload of sophisticated simulations is inherently difficult, since we have to balance both computational workload and memory footprint over meshes that can change any time or yield unpredictable cost per mesh entity, while…