%0 Conference Paper %1 Dees2013-rw %A Dees, J %A Sanders, P %B Data Engineering (ICDE), 2013 IEEE 29th International Conference on %D 2013 %K All CPU_utilization Efficient_query_execution Expose NUMA NUMA-aware_many-core_implementation Query_compilation TPC-H_benchmark aggregation_algorithms automatic_generation block_summary compilation data-parallel data_structures decision_support_query decision_support_systems execution_plan inverted_index_data_structures main_memory_column-store_databases many-core_query_execution memory_column-stores minimal_materialization multiprocessing_systems query_plans query_processing query_set separate_independent_operators single_pass storage_management %P 350--361 %T Efficient many-core query execution in main memory column-stores %X We use the full query set of the TPC-H Benchmark as a case study for the efficient implementation of decision support queries on main memory column-store databases. Instead of splitting a query into separate independent operators, we consider the query as a whole and translate the execution plan into a single function performing the query. This allows highly efficient CPU utilization, minimal materialization, and execution in a single pass over the data for most queries. The single pass is performed in parallel and scales near-linearly with the number of cores. The resulting query plans for most of the 22 queries are remarkably simple and are suited for automatic generation and fast compilation. Using a data-parallel, NUMA-aware many-core implementation with block summaries, inverted index data structures, and efficient aggregation algorithms, we achieve one to two orders of magnitude better performance than the current record holders of the TPC-H Benchmark.

@inproceedings{Dees2013-rw, abstract = {We use the full query set of the TPC-H Benchmark as a case study for the efficient implementation of decision support queries on main memory column-store databases. Instead of splitting a query into separate independent operators, we consider the query as a whole and translate the execution plan into a single function performing the query. This allows highly efficient CPU utilization, minimal materialization, and execution in a single pass over the data for most queries. The single pass is performed in parallel and scales near-linearly with the number of cores. The resulting query plans for most of the 22 queries are remarkably simple and are suited for automatic generation and fast compilation. Using a data-parallel, NUMA-aware many-core implementation with block summaries, inverted index data structures, and efficient aggregation algorithms, we achieve one to two orders of magnitude better performance than the current record holders of the TPC-H Benchmark.}, added-at = {2015-04-10T18:02:47.000+0200}, author = {Dees, J and Sanders, P}, biburl = {https://www.bibsonomy.org/bibtex/230542e9e2d9c76537cdf7d8369d7f7c7/christophv}, booktitle = {Data Engineering ({ICDE)}, 2013 {IEEE} 29th International Conference on}, interhash = {d7313c8a91bec7d330d400c126548390}, intrahash = {30542e9e2d9c76537cdf7d8369d7f7c7}, keywords = {All CPU_utilization Efficient_query_execution Expose NUMA NUMA-aware_many-core_implementation Query_compilation TPC-H_benchmark aggregation_algorithms automatic_generation block_summary compilation data-parallel data_structures decision_support_query decision_support_systems execution_plan inverted_index_data_structures main_memory_column-store_databases many-core_query_execution memory_column-stores minimal_materialization multiprocessing_systems query_plans query_processing query_set separate_independent_operators single_pass storage_management}, month = apr, pages = {350--361}, timestamp = {2016-01-04T14:22:08.000+0100}, title = {Efficient many-core query execution in main memory column-stores}, year = 2013 }