Related papers: Improving scalability and reliability of MPI-agnos…

A non-invasive, cloud-agnostic approach is demonstrated for extending existing cloud platforms to include checkpoint-restart capability. Most cloud platforms currently rely on each application to provide its own fault tolerance. A uniform…

Checkpoint/Restart (C/R) saves the running state of the programs periodically, which consumes considerable system resources. We observe that not every piece of data is involved in the computation in typical HPC applications; such unused…

Deep learning training at scale is resource-intensive and time-consuming, often running across hundreds or thousands of GPUs for weeks or months. Efficient checkpointing is crucial for running these workloads, especially in multi-tenant…

Autonomous agents act through sandboxed containers and microVMs whose state spans filesystems, processes, and runtime artifacts. Checkpoint and restore (C/R) of this state is needed for fault tolerance, spot execution, RL rollout branching,…

Distributed applications running on a large cluster environment, such as the cloud instances will have shorter execution time. However, the application might suffer from sudden termination due to unpredicted computing node failures, thus…

With the increasing size of HPC computations, faults are becoming more and more relevant in the HPC field. The MPI standard does not define the application behaviour after a fault, leaving the burden of fault management to the user, who…

The SPAdes assembler for metagenome assembly is a long-running application commonly used at the NERSC supercomputing site. However, NERSC, like many other sites, has a 48-hour limit on resource allocations. The solution is to chain together…

Process checkpoint-restart is a technology with great potential for use in HEP workflows. Use cases include debugging, reducing the startup time of applications both in offline batch jobs and the High Level Trigger, permitting job…

Dynamic Resource Management (DRM) techniques can be leveraged to maximize throughput and resource utilization in computational clusters. Although DRM has been extensively studied through analytical workloads and simulations, skepticism…

DMTCP (Distributed MultiThreaded CheckPointing) is a transparent user-level checkpointing package for distributed applications. Checkpointing and restart is demonstrated for a wide range of over 20 well known applications, including MATLAB,…

Static program analysis today takes an analytical approach which is quite suitable for a well-scoped system. Data- and control-flow is taken into account. Special cases such as pointers, procedures, and undefined behavior must be handled. A…

Common resource management methods in supercomputing systems usually include hard divisions, capping, and quota allotment. Those methods, despite their 'advantages', have some known serious disadvantages including unoptimized utilization of…

Spot instances offer a cost-effective solution for applications running in the cloud computing environment. However, it is challenging to run long-running jobs on spot instances because they are subject to unpredictable evictions. Here, we…

Pre-training & fine-tuning can enhance the transferring efficiency and performance in visual tasks. Recent delta-tuning methods provide more options for visual classification tasks. Despite their success, existing visual delta-tuning art…

High-performance computing continues to increase its computing power and energy efficiency. However, energy consumption continues to rise and finding ways to limit and/or decrease it is a crucial point in current research. For…

Snapshot Compressive Imaging (SCI) enables fast spectral imaging but requires effective decoding algorithms for hyperspectral image (HSI) reconstruction from compressed measurements. Current CNN-based methods are limited in modeling…

The fault tolerance method currently used in High Performance Computing (HPC) is the rollback-recovery method by using checkpoints. This, like any other fault tolerance method, adds an additional energy consumption to that of the execution…

The reliability of concurrent and distributed systems often depends on some well-known techniques for fault tolerance. One such technique is based on checkpointing and rollback recovery. Checkpointing involves processes to take snapshots of…

Scaling supercomputers comes with an increase in failure rates due to the increasing number of hardware components. In standard practice, applications are made resilient through checkpointing data and restarting execution after a failure…

NFV management and orchestration (MANO) systems are being developed to meet the agile and flexible management requirements of virtualized network services in the 5G era and beyond. In this regard, ETSI ISG NFV has specified a standard NFV…