Functions
template<typename... ARGS>
DEVICE auto	accumulate (ARGS &&...args)

template<typename... ARGS>
DEVICE auto	copy (ARGS &&...args)

template<typename... ARGS>
DEVICE void	fill (ARGS &&...args)

template<typename... ARGS>
DEVICE void	iota (ARGS &&...args)

template<typename... ARGS>
DEVICE auto	lower_bound (ARGS &&...args)

template<typename... ARGS>
DEVICE void	partial_sum (ARGS &&...args)

template<typename... ARGS>
DEVICE void	reverse (ARGS &&...args)

template<typename... ARGS>
DEVICE void	sort (ARGS &&...args)

template<typename... ARGS>
DEVICE void	swap (ARGS &&...args)

template<typename... ARGS>
DEVICE auto	upper_bound (ARGS &&...args)

Function Documentation

template<typename... ARGS>

DEVICE auto gpu_enabled::accumulate ( ARGS &&... args )

Definition at line 42 of file gpu_enabled.h.

References run_benchmark_import::args.

Referenced by BoundingBoxIntersectJoinHashTable::approximateTupleCount(), QueryFragmentDescriptor::buildFragmentPerKernelMapForUnion(), anonymous_namespace{RelAlgExecutor.cpp}::check_none_encoded_string_cast_tuple_limit(), StringDictionary::copyStrings(), RelAlgExecutor::createUnionWorkUnit(), PerfectJoinHashTable::genChunkKey(), ColSlotContext::getAlignedPaddedSizeForRange(), ColSlotContext::getAllSlotsPaddedSize(), Executor::getChunkRequestInfo(), getExpressionRange(), ColSlotContext::getTotalBytesOfColumnarBuffers(), Executor::getUniqueThreadSharedResultSets(), hide_sensitive_data_from_query(), ColumnarResults::mergeResults(), QueryExecutionContext::prepareKernelParams(), QueryMemoryInitializer::QueryMemoryInitializer(), ResultSetManager::reduce(), Executor::reduceMultiDeviceResultSets(), PerfectJoinHashTable::reify(), BoundingBoxIntersectJoinHashTable::reifyWithLayout(), BaselineJoinHashTable::reifyWithLayout(), QueryRewriter::rewriteColumnarDelete(), QueryRewriter::rewriteColumnarUpdate(), ExecutionKernel::runImpl(), Data_Namespace::anonymous_namespace{DataMgr.cpp}::BuddyinfoBlocks::sumAvailPages(), and quantile::detail::Centroids< RealType, IndexType >::totalWeight().

                                        {
 #ifdef __CUDACC__
   return thrust::reduce(thrust::device, std::forward<ARGS>(args)...);
 #else
   return std::accumulate(std::forward<ARGS>(args)...);
 #endif
 }

Here is the caller graph for this function:

template<typename... ARGS>

DEVICE auto gpu_enabled::copy ( ARGS &&... args )

Definition at line 51 of file gpu_enabled.h.

References run_benchmark_import::args.

Referenced by RelLeftDeepTreeIdsCollector::aggregateResult(), quantile::detail::Centroids< RealType, IndexType >::appendAndSortCurrent(), StringNoneEncoder::appendData(), anonymous_namespace{ArrowResultSetConverter.cpp}::appendToListColumnBuilder(), anonymous_namespace{WindowContext.cpp}::apply_lag_to_partition(), anonymous_namespace{WindowContext.cpp}::apply_permutation_to_partition(), CodeGenerator::codegenDictRegexp(), CodeGenerator::codegenDictStrCmp(), CodeGenerator::codegenFunctionOper(), WindowFunctionContext::computePartitionBuffer(), ResultSet::copy(), anonymous_namespace{SysCatalog.cpp}::copy_catalog_if_read_only(), StringDictionary::copyStrings(), file_delete(), UdfCompiler::generateAST(), ExtensionFunctionsWhitelist::get_ext_funcs(), DBHandler::get_tables_meta_impl(), StringDictionary::getLikeImpl(), QueryPlanDagExtractor::handleLeftDeepJoinTree(), DBHandler::insert_chunks(), ColumnFetcher::linearizeVarLenArrayColFrags(), ResultSet::parallelTop(), pop_n_rows_from_merged_heaps_gpu(), ArrowForeignStorageBase::replaceNullValuesImpl(), ResultSet::setTargetMetaInfo(), quantile::detail::anonymous_namespace{quantile.h}::Skipped< RealType, IndexType >::shiftRange(), and File_Namespace::FileBuffer::writeHeader().

                                  {
 #ifdef __CUDACC__
   return thrust::copy(thrust::device, std::forward<ARGS>(args)...);
 #else
   return std::copy(std::forward<ARGS>(args)...);
 #endif
 }

Here is the caller graph for this function:

template<typename... ARGS>

DEVICE void gpu_enabled::fill ( ARGS &&... args )

Definition at line 60 of file gpu_enabled.h.

References run_benchmark_import::args.

Referenced by NoneEncoder< T >::appendValidatedOrNonValidatedData(), anonymous_namespace{WindowContext.cpp}::apply_nth_value_to_partition(), quantile::detail::TDigest< RealType, IndexType >::mergeSorted(), ArrowForeignStorageBase::replaceNullValuesImpl(), and ColSlotContext::setAllSlotsSize().

                                  {
 #ifdef __CUDACC__
   thrust::fill(thrust::device, std::forward<ARGS>(args)...);
 #else
   std::fill(std::forward<ARGS>(args)...);
 #endif
 }

Here is the caller graph for this function:

template<typename... ARGS>

DEVICE void gpu_enabled::iota ( ARGS &&... args )

Definition at line 69 of file gpu_enabled.h.

References run_benchmark_import::args.

Referenced by find_push_down_filters(), import_export::ForeignDataImporter::importGeneralS3(), anonymous_namespace{RelAlgOptimizer.cpp}::mark_live_columns(), foreign_storage::LazyParquetChunkLoader::previewFiles(), Fragmenter_Namespace::SortedOrderFragmenter::sortData(), WindowFunctionContext::sortPartition(), anonymous_namespace{FromTableReordering.cpp}::traverse_join_cost_graph(), and WindowFunctionContext::WindowFunctionContext().

                                  {
 #ifdef __CUDACC__
   thrust::sequence(thrust::device, std::forward<ARGS>(args)...);
 #else
   std::iota(std::forward<ARGS>(args)...);
 #endif
 }

Here is the caller graph for this function:

template<typename... ARGS>

DEVICE auto gpu_enabled::lower_bound ( ARGS &&... args )

Definition at line 78 of file gpu_enabled.h.

References run_benchmark_import::args.

Referenced by Parser::WidthBucketExpr::analyze(), RelRexDagVisitor::castAndVisit(), Analyzer::WidthBucketExpr::compute_bucket(), Parser::WidthBucketExpr::get(), StringDictionary::getCompare(), Analyzer::anonymous_namespace{Analyzer.cpp}::ordered_bucket(), anonymous_namespace{RelAlgDag.cpp}::parse_operator(), heavyai::to_enum(), org.apache.calcite.rel.externalize.HeavyDBRelJson::toJson(), RelAlgTranslator::translateWidthBucket(), RelRexDagVisitor::visit(), anonymous_namespace{RelLeftDeepInnerJoin.cpp}::RebindRexInputsFromLeftDeepJoin::visitInput(), and width_bucket_no_oob_check().

                                         {
 #ifdef __CUDACC__
   return thrust::lower_bound(thrust::device, std::forward<ARGS>(args)...);
 #else
   return std::lower_bound(std::forward<ARGS>(args)...);
 #endif
 }

Here is the caller graph for this function:

template<typename... ARGS>

DEVICE void gpu_enabled::partial_sum ( ARGS &&... args )

Definition at line 87 of file gpu_enabled.h.

References run_benchmark_import::args, and inclusive_scan().

Referenced by ColumnarResults::compactAndCopyEntries(), WindowFunctionContext::fillPartitionEnd(), WindowFunctionContext::fillPartitionStart(), find_push_down_filters(), StringDictionary::getLikeImpl(), inclusive_scan(), quantile::detail::TDigest< RealType, IndexType >::partialSumOfCounts(), anonymous_namespace{RelLeftDeepInnerJoin.cpp}::RebindRexInputsFromLeftDeepJoin::RebindRexInputsFromLeftDeepJoin(), and WindowFunctionContext::WindowFunctionContext().

                                         {
 #ifdef __CUDACC__
   thrust::inclusive_scan(thrust::device, std::forward<ARGS>(args)...);
 #else
   std::partial_sum(std::forward<ARGS>(args)...);
 #endif
 }

Here is the call graph for this function:

Here is the caller graph for this function:

template<typename... ARGS>

DEVICE void gpu_enabled::reverse ( ARGS &&... args )

Definition at line 96 of file gpu_enabled.h.

References run_benchmark_import::args.

Referenced by quantile::detail::Centroids< RealType, IndexType >::appendAndSortCurrent(), and RaExecutionSequence::RaExecutionSequence().

                                     {
 #ifdef __CUDACC__
   thrust::reverse(thrust::device, std::forward<ARGS>(args)...);
 #else
   std::reverse(std::forward<ARGS>(args)...);
 #endif
 }

Here is the caller graph for this function:

template<typename... ARGS>

DEVICE void gpu_enabled::sort ( ARGS &&... args )

Definition at line 105 of file gpu_enabled.h.

References run_benchmark_import::args.

Referenced by anonymous_namespace{RelAlgOptimizer.cpp}::add_new_indices_for(), anonymous_namespace{RelAlgDag.cpp}::add_window_function_pre_project(), Catalog_Namespace::Catalog::addColumnDescriptor(), Catalog_Namespace::Catalog::addTableToMap(), quantile::detail::Centroids< RealType, IndexType >::appendAndSortCurrent(), SpeculativeTopNMap::asRows(), Catalog_Namespace::Catalog::buildColumnsMapUnlocked(), HashJoin::collectFragmentIds(), Parser::AddColumnStmt::execute(), RelAlgExecutor::executeRelAlgQuerySingleStep(), RelAlgExecutor::executeRelAlgStep(), RelAlgExecutor::executeSort(), import_export::fill_missing_columns(), DBHandler::get_completion_hints(), anonymous_namespace{RelAlgExecutor.cpp}::get_input_desc_impl(), anonymous_namespace{RelAlgOptimizer.cpp}::get_live_ins(), Fragmenter_Namespace::InsertOrderFragmenter::getChunkMetadata(), File_Namespace::CachingFileMgr::init(), File_Namespace::FileMgr::init(), ColumnFetcher::linearizeVarLenArrayColFrags(), RelRexDagVisitor::make_handlers(), quantile::detail::TDigest< RealType, IndexType >::mergeBuffer(), RaExecutionSequence::mergeSortWithInput(), DBHandler::parse_to_ra(), anonymous_namespace{RelAlgOptimizer.cpp}::pick_always_live_col_idx(), project_separates_sort(), anonymous_namespace{RelAlgOptimizer.cpp}::propagate_input_renumbering(), Catalog_Namespace::Catalog::removeColumnDescriptor(), Executor::resultsUnion(), sort_column_limit__cpu_template(), File_Namespace::FileMgr::sortAndCopyFilePagesForCompaction(), StringDictionary::sortCache(), DataRecycler< std::optional< HashType >, EMPTY_META_INFO >::sortCacheContainerByQueryMetric(), CacheMetricTracker::sortCacheInfoByQueryMetric(), Fragmenter_Namespace::sortIndexesImpl(), WindowFunctionContext::sortPartition(), RaExecutionSequence::stepsToNextBroadcast(), ResultSet::topPermutation(), QueryPlanDagCache::translateColVarsToInfoHash(), and RelAlgVisitor< std::vector< unsigned > >::visit().

                                  {
 #ifdef __CUDACC__
   thrust::sort(thrust::device, std::forward<ARGS>(args)...);
 #else
   std::sort(std::forward<ARGS>(args)...);
 #endif
 }

Here is the caller graph for this function:

template<typename... ARGS>

DEVICE void gpu_enabled::swap ( ARGS &&... args )

Definition at line 114 of file gpu_enabled.h.

References run_benchmark_import::args.

Referenced by SpeculativeTopNMap::asRows(), StringDictionaryGenerations::clear(), TableGenerations::clear(), AggregatedColRange::clear(), InputTableInfoCache::clear(), anonymous_namespace{RelAlgDag.cpp}::coalesce_nodes(), CodeGenerator::codegenLogicalShortCircuit(), eliminate_identical_copy(), RelAlgExecutor::executeRelAlgSeq(), RelAlgExecutor::executeRelAlgSubSeq(), RelAlgExecutor::getOuterFragmentCount(), import_export::import_thread_delimited(), StringDictionary::invalidateInvertedIndex(), HashJoin::normalizeColumnPair(), foreign_storage::anonymous_namespace{TextFileBufferParser.cpp}::set_coordinates_from_separate_lon_lat_columns(), RaExecutionSequence::skipQuerySteps(), translate_bounding_box_intersect_with_reordering(), and Catalog_Namespace::SysCatalog::updateUserRoleName().

                                  {
 #ifdef __CUDACC__
   thrust::swap(std::forward<ARGS>(args)...);
 #else
   std::swap(std::forward<ARGS>(args)...);
 #endif
 }

Here is the caller graph for this function:

template<typename... ARGS>

DEVICE auto gpu_enabled::upper_bound ( ARGS &&... args )

Definition at line 123 of file gpu_enabled.h.

References run_benchmark_import::args.

Referenced by Parser::WidthBucketExpr::analyze(), Analyzer::WidthBucketExpr::compute_bucket(), eliminate_dead_subqueries(), File_Namespace::FileMgr::freePagesBeforeEpochUnlocked(), anonymous_namespace{JoinLoopTest.cpp}::generate_descriptors(), Parser::WidthBucketExpr::get(), foreign_storage::ForeignTableSchema::getLogicalColumnIdIterator(), foreign_storage::anonymous_namespace{FileReader.cpp}::offset_to_index(), anonymous_namespace{RelAlgDag.cpp}::parse_operator(), quantile::detail::TDigest< RealType, IndexType >::quantile(), org.apache.calcite.rel.externalize.HeavyDBRelJson::toJson(), anonymous_namespace{ResultSetReductionCodegen.cpp}::translate_for(), RelAlgTranslator::translateWidthBucket(), and foreign_storage::anonymous_namespace{LazyParquetChunkLoader.cpp}::within_range().

                                         {
 #ifdef __CUDACC__
   return thrust::upper_bound(thrust::device, std::forward<ARGS>(args)...);
 #else
   return std::upper_bound(std::forward<ARGS>(args)...);
 #endif
 }

Here is the caller graph for this function: