Related papers: Container Profiler: Profiling Resource Utilization…
Linux containers are gaining increasing traction in both individual and industrial use, and as these containers get integrated into mission-critical systems, real-time detection of malicious cyber attacks becomes a critical operational…
Process Mining is established in research and industry systems to analyze and optimize processes based on event data from information systems. Within this work, we accomodate process mining techniques to Cyber-Physical Systems. To capture…
A bioinformatics platform is introduced aimed at identifying models of disease-specific pathways, as well as a set of network measures that can quantify changes in terms of global structure or single link disruptions.The approach integrates…
This paper proposes TASKPROF, a profiler that identifies parallelism bottlenecks in task parallel programs. It leverages the structure of a task parallel execution to perform fine-grained attribution of work to various parts of the program.…
Very High Resolution satellite and aerial imagery are used to monitor and conduct large scale surveys of ecological systems. Convolutional Neural Networks have successfully been employed to analyze such imagery to detect large animals and…
Many modern applications require real-time processing of large volumes of high-speed data. Such data processing needs can be modeled as a streaming computation. A streaming computation is specified as a dataflow graph that exposes multiple…
Efficient task scheduling is paramount in the Linux kernel, where the Completely Fair Scheduler (CFS) meticulously manages CPU resources to balance high utilization with interactive responsiveness. This research pioneers the use of deep…
System-level resource monitoring with both precision and efficiency is a continuous challenge. We introduce eHashPipe, a lightweight, real-time resource observability system utilizing eBPF and the HashPipe sketching algorithm. eHashPipe…
Analytic performance models are essential for understanding the performance characteristics of loop kernels, which consume a major part of CPU cycles in computational science. Starting from a validated performance model one can infer the…
IOHprofiler is a new tool for analyzing and comparing iterative optimization heuristics. Given as input algorithms and problems written in C or Python, it provides as output a statistical evaluation of the algorithms' performance by means…
Parallel applications can spend a significant amount of time performing I/O on large-scale supercomputers. Fast near-compute storage accelerators called burst buffers can reduce the time a processor spends performing I/O and mitigate I/O…
CellProfiler is a widely used software for creating reproducible, reusable image analysis workflows without needing to code. In addition to the >90 modules that make up the main CellProfiler program, CellProfiler has a plugins system that…
Streaming, big data applications face challenges in creating scalable data flow pipelines, in which multiple data streams must be collected, stored, queried, and analyzed. These data sources are characterized by their volume (in terms of…
A key challenge for supporting elastic behaviour in cloud systems is to achieve a good performance in automated (de-)provisioning and scheduling of computing resources. One of the key aspects that can be significant is the overheads…
Scientists rely on simulations to study natural phenomena. Trusting the simulation results is vital to develop sciences in any field. One approach to build trust is to ensure the reproducibility and traceability of the simulations through…
Linux containers have risen in popularity in the last few years, making their way to commercial IT service offerings (such as PaaS), application deployments, and Continuous Delivery/Integration pipelines within various development teams.…
Many applications in important problem domains such as machine learning and computer vision are streaming applications that take a sequence of inputs over time. It is challenging to find knob settings that optimize the run-time performance…
Recent computational advances enable protein design pipelines to run end-to-end on GPUs, yet their heterogeneous computational behaviors remain undercharacterized at the system level. We implement and profile a representative pipeline at…
Diagnosing performance bottlenecks in modern software is essential yet challenging, particularly as applications become more complex and rely on custom resource management policies. While traditional profilers effectively identify execution…
Pipeline parallelism is a crucial paradigm for large-scale model training. However, imbalances in memory footprint across stages can lead to significant GPU memory wastage, limiting the model sizes that pipeline parallelism can effectively…