Corpus ID: 235694211

Design and Evaluation of Scalable Representations of Communication in Gantt Charts for Large-scale Execution Traces

  title={Design and Evaluation of Scalable Representations of Communication in Gantt Charts for Large-scale Execution Traces},
  author={Connor Scully-Allison and Katherine E. Isaacs},
Gantt charts are frequently used to explore execution traces of large-scale parallel programs found in high-performance computing (HPC). In these visualizations, each parallel processor is assigned a row showing the computation state of a processor at a particular time. Lines are drawn between rows to show communication between these processors. When drawn to align equivalent calls across rows, structures can emerge reflecting communication patterns employed by the executing code. However… Expand


Visual Analysis of Inter-Process Communication for Large-Scale Parallel Computing
This work proposes a new visualization approach that affords more scalability and then demonstrates it on systems running with up to 16,384 processes. Expand
Combing the Communication Hairball: Visualizing Parallel Execution Traces using Logical Time
A new trace visualization approach based on transforming the event history into logical time inferred directly from happened-before relationships is presented, which emphasizes the code's structural behavior, which is much more familiar to the application developer. Expand
Ordering Traces Logically to Identify Lateness in Message Passing Programs
This work extracts a trace's logical structure, an ordering of trace events derived from happened-before relationships, while taking into account developer intent, and develops metrics to quantify delays and differences among processes. Expand
Visualizing Large‐scale Parallel Communication Traces Using a Particle Animation Technique
This work introduces an animation‐based interactive visualization technique for the analysis of communication patterns occurring in parallel application execution, which has the advantages of illustrating the dynamic communication patterns in the system as well as a static image of MPI (Message Passing Interface) utilization history. Expand
Visualization and Analysis of Parallel Dataflow Execution with Smart Traces
This work investigates the requirements to create visualisations of execution traces of parallel programs modelled as dataflows, and proposes the Smart Trace (ST) concept, to encode the structure of the data, and guide the construction of specialised visualizations. Expand
Analyzing Parallel Program Executions Using Multiple Views
This work presents a framework for describing views of a parallel program's execution, and an analysis methodology that relates a sequence of views to the program development cycle. Expand
DAGViz: a DAG visualization tool for analyzing task-parallel program traces
A toolset that captures and visualizes the trace of an execution of a task parallel program in the form of a directed acyclic graph (DAG) and provides a task-centric view of the program, which is different from other popular visualizations such as thread-centric timeline visualization and code-centric hotspots analysis. Expand
Edge Bundling for Visualizing Communication Behavior
This work employs edge bundling at unprecedented scale to address emerging problems in timeline displays and introduces scalable visualizations for communication profiles, which offer an alternative view on communication patterns. Expand
A spatiotemporal data aggregation technique for performance analysis of large-scale execution traces
The experimental results show that the proposed new visualization technique can help the quick and accurate detection of anomalies in traces containing up to two hundred million events. Expand
Zinsight: a visual and analytic environment for exploring large event traces
A new tool, Zinsight, to visualize event traces from complex systems, enabling user exploration, analysis and understanding of traces containing millions of events with a novel combination of visualizations and pattern extraction techniques. Expand