Refine
Document Type
- Conference Object (3)
- Part of a Book (1)
Keywords
- Alternatives (1)
- exploration (1)
- generative design (1)
- parallel difference visualization (1)
Improving the Performance of Parallel SpMV Operations on NUMA Systems with Adaptive Load Balancing
(2018)
For a parallel Sparse Matrix Vector Multiply (SpMV) on a multiprocessor, rather simple and efficient work distributions often produce good results. In cases where this is not true, adaptive load balancing can improve the balance and performance. This paper introduces a low overhead framework for adaptive load balancing of parallel SpMV operations. It uses statistical filters to gather relevant runtime performance data and detects an imbalance situation. Three different algorithms were compared that adaptively balance the load with high quality and low overhead. Results show that for sparse matrices, where the adaptive load balancing was enabled, an average speedup of 1.15 (regarding the total execution time) could be achieved with our best algorithm over 4 different matrix formats and two different NUMA systems.
In the conceptual design phase, designers routinely generate dozens of alternatives based on a single idea. This is especially relevant in generative design where an algorithm can generate a large number of viable design options. While solutions for creating and managing a small number of simple alternatives have been proposed, practical applications of these solutions are liMassachusetts Institute of Technologyed. As a result, we present GEM-NI+, an extension to the original GEM-NI system for creating and managing alternatives in generative design. GEM-NI+ is designed to enable editing, managing and comparing up to 24 alternatives simultaneously using a multi-monitor setup. GEM-NI+ also features a new "jamming spaces" technique for assigning individual monitors into different visualization states, which makes organization of a large workspace easier. Finally, GEM-NI+ enables comparison of complex alternatives using recursive group node difference visualization.
We present a new interface for interactive comparisons of more than two alternative documents in the context of a generative design system that uses generative data-flow networks defined via directed acyclic graphs. To better show differences between such networks, we emphasize added, deleted, (un)changed nodes and edges. We emphasize differences in the output as well as parameters using highlighting and enable post-hoc merging of the state of a parameter across a selected set of alternatives. To minimize visual clutter, we introduce new difference visualizations for selected nodes and alternatives using additive and subtractive encodings, which improve readability and keep visual clutter low. We analyzed similarities in networks from a set of alternative designs produced by architecture students and found that the number of similarities outweighs the differences, which motivates use of subtractive encoding. We ran a user study to evaluate the two main proposed difference visualization encodings and found that they are equally effective.
We present GEM-NI -- a graph-based generative-design tool that supports parallel exploration of alternative designs. Producing alternatives is a key feature of creative work, yet it is not strongly supported in most extant tools. GEM-NI enables various forms of exploration with alternatives such as parallel editing, recalling history, branching, merging, comparing, and Cartesian products of and for alternatives. Further, GEM-NI provides a modal graphical user interface and a design gallery, which both allow designers to control and manage their design exploration. We conducted an exploratory user study followed by in-depth one-on-one interviews with moderately and highly skills participants and obtained positive feedback for the system features, showing that GEM-NI supports creative design work well.
