- Browse by Author
Browsing by Author "Papka, Michael E."
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Evaluating Gradient Perception in Color-Coded Scalar Fields(IEEE, 2019-10) Reda, Khairi; Papka, Michael E.; Human-Centered Computing, School of Informatics and ComputingColor mapping is a commonly used technique for visualizing scalar fields. While there exists advice for choosing effective colormaps, it is unclear if current guidelines apply equally across task types. We study the perception of gradients and evaluate the effectiveness of three colormaps at depicting gradient magnitudes. In a crowd-sourced experiment, we determine the just-noticeable differences (JNDs) at which participants can reliably compare and judge variations in gradient between two scalar fields. We find that participants exhibited lower JNDs with a diverging (cool-warm) or a spectral (rainbow) scheme, as compared with a monotonic-luminance colormap (viridis). The results support a hypothesis that apparent discontinuities in the color ramp may help viewers discern subtle structural differences in gradient. We discuss these findings and highlight future research directions for colormap evaluation.Item A visual Analytics System for Optimizing Communications in Massively Parallel Applications(IEEE, 2017) Fujiwara, Takanori; Malakar, Preeti; Reda, Khairi; Vishwanath, Venkatram; Papka, Michael E.; Ma, Kwan-LiuCurrent and future supercomputers have tens of thousands of compute nodes interconnected with high-dimensional networks and complex network topologies for improved performance. Application developers are required to write scalable parallel programs in order to achieve high throughput on these machines. Application performance is largely determined by efficient inter-process communication. A common way to analyze and optimize performance is through profiling parallel codes to identify communication bottlenecks. However, understanding gigabytes of profile data is not a trivial task. In this paper, we present a visual analytics system for identifying the scalability bottlenecks and improving the communication efficiency of massively parallel applications. Visualization methods used in this system are designed to comprehend large-scale and varied communication patterns on thousands of nodes in complex networks such as the 5D torus and the dragonfly. We also present efficient rerouting and remapping algorithms that can be coupled with our interactive visual analytics design for performance optimization. We demonstrate the utility of our system with several case studies using three benchmark applications on two leading supercomputers. The mapping suggestion from our system led to 38% improvement in hop-bytes for MiniAMR application on 4,096 MPI processes.