%0 Conference Paper %1 Psaroudakis:2018:ASA %A Psaroudakis, Iraklis %A Kaestle, Stefan %A Grimmer, Matthias %A Goodman, Daniel %A Lozi, Jean-Pierre %A Harris, Tim %B Proceedings of the Thirteenth EuroSys Conference %D 2018 %I ACM %K Adaptation Arrays BigData Collections JITData JustInTime NUMA Optimization Placement Replication %P 17:1--17:15 %R 10.1145/3190508.3190514 %T Analytics with Smart Arrays: Adaptive and Efficient Language-independent Data %X This paper introduces smart arrays, an abstraction for providing adaptive and efficient language-independent data storage. Their smart functionalities include NUMA-aware data placement across sockets and bit compression. We show how our single C++ implementation can be used efficiently from both native C++ and compiled Java code. We experimentally evaluate smart arrays on a diverse set of C++ and Java analytics workloads. Further, we show how their smart functionalities affect performance and lead to differences in hardware resource demands on multicore machines, motivating the need for adaptivity. We observe that smart arrays can significantly decrease the memory space requirements of analytics workloads, and improve their performance by up to 4x. Smart arrays are the first step towards general smart collections with various smart functionalities that enable the consumption of hardware resources to be traded-off against one another. %@ 978-1-4503-5584-1

@inproceedings{Psaroudakis:2018:ASA, abstract = {This paper introduces smart arrays, an abstraction for providing adaptive and efficient language-independent data storage. Their smart functionalities include NUMA-aware data placement across sockets and bit compression. We show how our single C++ implementation can be used efficiently from both native C++ and compiled Java code. We experimentally evaluate smart arrays on a diverse set of C++ and Java analytics workloads. Further, we show how their smart functionalities affect performance and lead to differences in hardware resource demands on multicore machines, motivating the need for adaptivity. We observe that smart arrays can significantly decrease the memory space requirements of analytics workloads, and improve their performance by up to 4x. Smart arrays are the first step towards general smart collections with various smart functionalities that enable the consumption of hardware resources to be traded-off against one another.}, acmid = {3190514}, added-at = {2018-04-26T11:17:54.000+0200}, articleno = {17}, author = {Psaroudakis, Iraklis and Kaestle, Stefan and Grimmer, Matthias and Goodman, Daniel and Lozi, Jean-Pierre and Harris, Tim}, biburl = {https://www.bibsonomy.org/bibtex/2798a327d4a1e305e6a75ebe11d248931/gron}, booktitle = {Proceedings of the Thirteenth EuroSys Conference}, description = {Analytics with smart arrays}, doi = {10.1145/3190508.3190514}, interhash = {b39ddb43febb960c0710b56507c27744}, intrahash = {798a327d4a1e305e6a75ebe11d248931}, isbn = {978-1-4503-5584-1}, keywords = {Adaptation Arrays BigData Collections JITData JustInTime NUMA Optimization Placement Replication}, location = {Porto, Portugal}, numpages = {15}, pages = {17:1--17:15}, publisher = {ACM}, series = {EuroSys '18}, timestamp = {2018-04-26T11:17:54.000+0200}, title = {{Analytics with Smart Arrays: Adaptive and Efficient Language-independent Data}}, year = 2018 }