Proceedings of the 2nd International Workshop on Extreme Heterogeneity Solutions最新文献

Tiling Framework for Heterogeneous Computing of Matrix based Tiled Algorithms 基于矩阵的平铺算法异构计算的平铺框架

Proceedings of the 2nd International Workshop on Extreme Heterogeneity Solutions Pub Date : 2023-02-25 DOI: 10.1145/3587278.3595642

Narasinga Rao Miniskar, Mohammad Alaul Haque Monil, Pedro Valero-Lara, Frank Liu, J. Vetter

{"title":"Tiling Framework for Heterogeneous Computing of Matrix based Tiled Algorithms","authors":"Narasinga Rao Miniskar, Mohammad Alaul Haque Monil, Pedro Valero-Lara, Frank Liu, J. Vetter","doi":"10.1145/3587278.3595642","DOIUrl":"https://doi.org/10.1145/3587278.3595642","url":null,"abstract":"Tiling matrix operations can improve the load balancing and performance of applications on heterogeneous computing resources. Writing a tile-based algorithm for each operation with a traditional, hand-tuned tiling approach that uses for loops in C/C++ is cumbersome and error prone. Moreover, it must enable and support the heterogeneous memory management of data objects and also explore architecture-supported, native, tiled-data transfer APIs instead of copying the tiled data to continuous memory before the data transfer. The tiling framework provides a tiled data structure for heterogeneous memory mapping and parameterization to a heterogeneous task specification API. We have integrated our tiled framework into MatRIS (Math kernels library using IRIS). IRIS is a heterogeneous run-time framework with a heterogeneous programming model, memory model, and task execution model. Experiments reveal that the tiled framework for BLAS operations has improved the programmability of tiled BLAS and improved performance by ~20% when compared against the traditional method that copies the data to continuous memory locations for heterogeneous computing.","PeriodicalId":169613,"journal":{"name":"Proceedings of the 2nd International Workshop on Extreme Heterogeneity Solutions","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125556227","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}

引用次数: 1

Harnessing Extreme Heterogeneity for Ocean Modeling with Tensors 利用张量模拟海洋的极端非均质性

Proceedings of the 2nd International Workshop on Extreme Heterogeneity Solutions Pub Date : 2023-02-25 DOI: 10.1145/3587278.3595645

Li Tang, Philip W. Jones, S. Pakin

引用次数: 0

Transfer Learning Across Heterogeneous Features For Efficient Tensor Program Generation 跨异构特征的高效张量程序生成迁移学习

Proceedings of the 2nd International Workshop on Extreme Heterogeneity Solutions Pub Date : 2023-02-25 DOI: 10.1145/3587278.3595644

Gaurav Verma, Siddhisanket Raskar, Zhenda Xie, A. Malik, M. Emani, Barbara M. Chapman

{"title":"Transfer Learning Across Heterogeneous Features For Efficient Tensor Program Generation","authors":"Gaurav Verma, Siddhisanket Raskar, Zhenda Xie, A. Malik, M. Emani, Barbara M. Chapman","doi":"10.1145/3587278.3595644","DOIUrl":"https://doi.org/10.1145/3587278.3595644","url":null,"abstract":"Tuning tensor program generation involves searching for various possible program transformation combinations for a given program on target hardware to optimize the tensor program execution. It is already a complex process because of the massive search space, and exponential combinations of transformations make auto-tuning tensor program generation more challenging, especially when we have a heterogeneous target. In this research, we attempt to address these problems by learning the joint neural network and hardware features and transferring them to the new target hardware. We extensively study the existing state-of-the-art dataset, TenSet, perform comparative analysis on the test split strategies and propose methodologies to prune the dataset. We adopt an attention-inspired approach for tuning the tensor programs enabling them to embed neural network and hardware-specific features. Our approach could prune the dataset up to 45% of the baseline without compromising the Pairwise Comparison Accuracy (PCA). Further, the proposed methodology can achieve on-par or improved mean inference time with 25%-40% of the baseline tuning time across different networks and target hardware.","PeriodicalId":169613,"journal":{"name":"Proceedings of the 2nd International Workshop on Extreme Heterogeneity Solutions","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126238270","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}

引用次数: 0

Proceedings of the 2nd International Workshop on Extreme Heterogeneity Solutions 第二届极端异质性解决方案国际研讨会论文集

Proceedings of the 2nd International Workshop on Extreme Heterogeneity Solutions Pub Date : 1900-01-01 DOI: 10.1145/3587278

引用次数: 0