Related papers: Tolerating Correlated Failures in Massively Parall…

Solving multiscale diffusion problems is often computationally expensive due to the spatial and temporal discretization challenges arising from high-contrast coefficients. To address this issue, a partially explicit temporal splitting…

As inference workloads for large language models (LLMs) scale to meet growing user demand, pipeline parallelism (PP) has become a widely adopted strategy for multi-GPU deployment, particularly in cross-node setups, to improve key-value (KV)…

Mixture-of-Experts is a promising approach for edge AI with low-batch inference. Yet, on-device deployments often face limited on-chip memory and severe workload imbalance; the prevalent use of offloading further incurs off-chip memory…

Flow-Updating (FU) is a fault-tolerant technique that has proved to be efficient in practice for the distributed computation of aggregate functions in communication networks where individual processors do not have access to global…

Stream processing in the last decade has seen broad adoption in both commercial and research settings. One key element for this success is the ability of modern stream processors to handle failures while ensuring exactly-once processing…

Traditional heterogeneous parallel algorithms, designed for heterogeneous clusters of workstations, are based on the assumption that the absolute speed of the processors does not depend on the size of the computational task. This assumption…

In a cloud computing job with many parallel tasks, the tasks on the slowest machines (straggling tasks) become the bottleneck in the job completion. Computing frameworks such as MapReduce and Spark tackle this by replicating the straggling…

Region proposal is critical for object detection while it usually poses a bottleneck in improving the computation efficiency on traditional control-flow architectures. We have observed region proposal tasks are potentially suitable for…

Pipeline Parallelism (PP) serves as a crucial technique for training Large Language Models (LLMs), owing to its capability to alleviate memory pressure from model states with relatively low communication overhead. However, in long-context…

A new technique is proposed for fault-tolerant linear, sesquilinear and bijective (LSB) operations on $M$ integer data streams ($M\geq3$), such as: scaling, additions/subtractions, inner or outer vector products, permutations and…

Monte Carlo simulations employed for the analysis of portfolios of catastrophic risk process large volumes of data. Often times these simulations are not performed in real-time scenarios as they are slow and consume large data. Such…

Security analysis is an essential activity in security engineering to identify potential system vulnerabilities and achieve security requirements in the early design phases. Due to the increasing complexity of modern systems, traditional…

Stream processing is extensively used in the IoT-to-Cloud spectrum to distill information from continuous streams of data. Streaming applications usually run in dedicated Stream Processing Engines (SPEs) that adopt the DataFlow model, which…

Achieving high availability and robust security in Kubernetes requires more than reactive scaling and standard perimeter firewalls. Traditional autoscalers, such as HPA, often fail to react quickly to traffic spikes and cannot distinguish…

The asymmetric exclusion process (ASEP) has attracted a lot of interest not only because its many applications, e.g. in the context of the kinetics of biopolymerization and traffic flow theory, but also because it is a paradigmatic model…

Mixed-Criticality (MC) systems have recently been devised to address the requirements of real-time systems in industrial applications, where the system runs tasks with different criticality levels on a single platform. In some workloads, a…

One of the hardest challenges of the current Big Data landscape is the lack of ability to process huge volumes of information in an acceptable time. The goal of this work, is to ascertain if it is useful to use typical Big Data tools to…

We present a framework for bridging the gap between sensor attack detection and recovery in cyber-physical systems. The proposed framework models modern-day, complex perception pipelines as bipartite graphs, which combined with anomaly…

An active approach to fault tolerance is essential for robot swarms to achieve long-term autonomy. Previous efforts have focused on responding to spontaneous electro-mechanical faults and failures. However, many faults occur gradually over…

To cope with the ever increasing threats of dynamic and adaptive persistent attacks, Fault and Intrusion Tolerance (FIT) is being studied at the hardware level to increase critical systems resilience. Based on state-machine replication, FIT…