Pub Date : 2021-10-01DOI: 10.1109/LDAV53230.2021.00012
Riley Lipinski, K. Moreland, M. Papka, T. Marrinan
Visualizations of large-scale data sets are often created on graphics clusters that distribute the rendering task amongst many processes. When using real-time GPU-based graphics algorithms, the most time-consuming aspect of distributed rendering is typically the com-positing phase - combining all partial images from each rendering process into the final visualization. Compo siting requires image data to be copied off the GPU and sent over a network to other processes. While compression has been utilized in existing distributed rendering compositors to reduce the data being sent over the network, this compression tends to occur after the raw images are transferred from the GPU to main memory. In this paper, we present work that leverages OpenGL / CUDA interoperability to compress raw images on the GPU prior to transferring the data to main memory. This approach can significantly reduce the device-to-host data transfer time, thus enabling more efficient compositing of images generated by distributed rendering applications.
{"title":"GPU-based Image Compression for Efficient Compositing in Distributed Rendering Applications","authors":"Riley Lipinski, K. Moreland, M. Papka, T. Marrinan","doi":"10.1109/LDAV53230.2021.00012","DOIUrl":"https://doi.org/10.1109/LDAV53230.2021.00012","url":null,"abstract":"Visualizations of large-scale data sets are often created on graphics clusters that distribute the rendering task amongst many processes. When using real-time GPU-based graphics algorithms, the most time-consuming aspect of distributed rendering is typically the com-positing phase - combining all partial images from each rendering process into the final visualization. Compo siting requires image data to be copied off the GPU and sent over a network to other processes. While compression has been utilized in existing distributed rendering compositors to reduce the data being sent over the network, this compression tends to occur after the raw images are transferred from the GPU to main memory. In this paper, we present work that leverages OpenGL / CUDA interoperability to compress raw images on the GPU prior to transferring the data to main memory. This approach can significantly reduce the device-to-host data transfer time, thus enabling more efficient compositing of images generated by distributed rendering applications.","PeriodicalId":441438,"journal":{"name":"2021 IEEE 11th Symposium on Large Data Analysis and Visualization (LDAV)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132238322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-01DOI: 10.1109/LDAV53230.2021.00013
Florian Friess, M. Becher, G. Reina, T. Ertl
Both visual detail and a low-latency transfer of image data are required for collaborative exploration of scientific data sets across large high-resolution displays. In this work, we present an approach that reduces the resolution before the encoding and uses temporal upscaling to reconstruct the full resolution image, reducing the overall latency and the required bandwidth without significantly impacting the details perceived by observers. Our approach takes advantage of the fact that humans do not perceive the full details of moving objects by providing a perfect reconstruction for static parts of the image, while non-static parts are reconstructed with a lower quality. This strategy enables a substantial reduction of the encoding latency and the required bandwidth with barely noticeable changes in visual quality, which is crucial for collaborative analysis across display walls at different locations. Additionally, our approach can be combined with other techniques aiming to reduce the required bandwidth while keeping the quality as high as possible, such as foveated encoding. We demonstrate the reduced overall latency, the required bandwidth, as well as the high image quality using different visualisations.
{"title":"Amortised Encoding for Large High-Resolution Displays","authors":"Florian Friess, M. Becher, G. Reina, T. Ertl","doi":"10.1109/LDAV53230.2021.00013","DOIUrl":"https://doi.org/10.1109/LDAV53230.2021.00013","url":null,"abstract":"Both visual detail and a low-latency transfer of image data are required for collaborative exploration of scientific data sets across large high-resolution displays. In this work, we present an approach that reduces the resolution before the encoding and uses temporal upscaling to reconstruct the full resolution image, reducing the overall latency and the required bandwidth without significantly impacting the details perceived by observers. Our approach takes advantage of the fact that humans do not perceive the full details of moving objects by providing a perfect reconstruction for static parts of the image, while non-static parts are reconstructed with a lower quality. This strategy enables a substantial reduction of the encoding latency and the required bandwidth with barely noticeable changes in visual quality, which is crucial for collaborative analysis across display walls at different locations. Additionally, our approach can be combined with other techniques aiming to reduce the required bandwidth while keeping the quality as high as possible, such as foveated encoding. We demonstrate the reduced overall latency, the required bandwidth, as well as the high image quality using different visualisations.","PeriodicalId":441438,"journal":{"name":"2021 IEEE 11th Symposium on Large Data Analysis and Visualization (LDAV)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122129752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-12DOI: 10.1109/LDAV53230.2021.00008
Jules Vidal, Julien Tierny
This paper presents an algorithm for the efficient approximation of the saddle-extremum persistence diagram of a scalar field. Vidal et al. introduced recently a fast algorithm for such an approximation (by interrupting a progressive computation framework [78]). However, no theoretical guarantee was provided regarding its approximation quality. In this work, we revisit the progressive framework of Vidal et al. [78] and we introduce in contrast a novel approximation algorithm, with a user controlled approximation error, specifically, on the Bottleneck distance to the exact solution. Our approach is based on a hierarchical representation of the input data, and relies on local simplifications of the scalar field to accelerate the computation, while maintaining a controlled bound on the output error. The locality of our approach enables further speedups thanks to shared memory parallelism. Experiments conducted on real life datasets show that for a mild error tolerance (5% relative Bottleneck distance), our approach improves runtime performance by 18 % on average (and up to 48 % on large, noisy datasets) in comparison to standard, exact, publicly available implementations. In addition to the strong guarantees on its approximation error, we show that our algorithm also provides in practice outputs which are on average 5 times more accurate (in terms of the L2- Wasserstein distance) than a naive approximation baseline. We illustrate the utility of our approach for interactive data exploration and we document visualization strategies for conveying the uncertainty related to our approximations.
{"title":"Fast Approximation of Persistence Diagrams with Guarantees","authors":"Jules Vidal, Julien Tierny","doi":"10.1109/LDAV53230.2021.00008","DOIUrl":"https://doi.org/10.1109/LDAV53230.2021.00008","url":null,"abstract":"This paper presents an algorithm for the efficient approximation of the saddle-extremum persistence diagram of a scalar field. Vidal et al. introduced recently a fast algorithm for such an approximation (by interrupting a progressive computation framework [78]). However, no theoretical guarantee was provided regarding its approximation quality. In this work, we revisit the progressive framework of Vidal et al. [78] and we introduce in contrast a novel approximation algorithm, with a user controlled approximation error, specifically, on the Bottleneck distance to the exact solution. Our approach is based on a hierarchical representation of the input data, and relies on local simplifications of the scalar field to accelerate the computation, while maintaining a controlled bound on the output error. The locality of our approach enables further speedups thanks to shared memory parallelism. Experiments conducted on real life datasets show that for a mild error tolerance (5% relative Bottleneck distance), our approach improves runtime performance by 18 % on average (and up to 48 % on large, noisy datasets) in comparison to standard, exact, publicly available implementations. In addition to the strong guarantees on its approximation error, we show that our algorithm also provides in practice outputs which are on average 5 times more accurate (in terms of the L2- Wasserstein distance) than a naive approximation baseline. We illustrate the utility of our approach for interactive data exploration and we document visualization strategies for conveying the uncertainty related to our approximations.","PeriodicalId":441438,"journal":{"name":"2021 IEEE 11th Symposium on Large Data Analysis and Visualization (LDAV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132294346","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：