Efficient many-core query execution in main memory column-stores
J. Dees, и P. Sanders. Data Engineering (ICDE), 2013 IEEE 29th International
Conference on, стр. 350--361. (апреля 2013)
Аннотация
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.
%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
}