IO utilities for the Parquet and Hybrid scan readers. More...
#include <cudf/io/datasource.hpp>#include <cudf/io/text/byte_range_info.hpp>#include <cudf/utilities/memory_resource.hpp>#include <rmm/device_buffer.hpp>#include <rmm/resource_ref.hpp>#include <cuda/stream>#include <cstddef>#include <cstdint>#include <functional>#include <future>#include <span>#include <tuple>#include <utility>#include <vector>Go to the source code of this file.
Namespaces | |
| cudf | |
| cuDF interfaces | |
| cudf::io | |
| IO interfaces. | |
Enumerations | |
| enum class | cudf::io::parquet::io_submission_policy : int8_t { SERIALIZE , INTERLEAVE } |
| Controls whether I/O submissions are serialized across callers. More... | |
Functions | |
| std::size_t | cudf::io::parquet::metadata_size_hint () |
| Returns the Parquet reader's footer speculative read size in bytes. More... | |
| std::unique_ptr< cudf::io::datasource::buffer > | cudf::io::parquet::fetch_footer_to_host (cudf::io::datasource &datasource) |
| Fetches a host buffer of Parquet footer bytes from the input data source. More... | |
| std::vector< std::unique_ptr< cudf::io::datasource::buffer > > | cudf::io::parquet::fetch_footers_to_host (cudf::host_span< std::reference_wrapper< cudf::io::datasource > const > datasources) |
| Fetches host buffers of Parquet footer bytes from multiple input data sources. More... | |
| std::unique_ptr< cudf::io::datasource::buffer > | cudf::io::parquet::fetch_page_index_to_host (cudf::io::datasource &datasource, byte_range_info const page_index_bytes) |
| Fetches a host buffer of Parquet page index from the input data source. More... | |
| std::vector< std::unique_ptr< cudf::io::datasource::buffer > > | cudf::io::parquet::fetch_page_indexes_to_host (cudf::host_span< std::reference_wrapper< cudf::io::datasource > const > datasources, cudf::host_span< byte_range_info const > page_index_bytes_per_source) |
| Fetches host buffers of Parquet page index bytes from multiple input data sources. More... | |
| std::tuple< std::vector< rmm::device_buffer >, std::vector< cudf::device_span< uint8_t const > >, std::future< void > > | cudf::io::parquet::fetch_byte_ranges_to_device_async (cudf::io::datasource &datasource, std::span< byte_range_info const > byte_ranges, io_submission_policy policy, cuda::stream_ref stream=cudf::get_default_stream(), cudf::memory_resources mr=cudf::get_current_device_resource_ref()) |
| Fetches a list of byte ranges from a datasource into device buffers. More... | |
| std::tuple< std::vector< rmm::device_buffer >, std::vector< std::vector< cudf::device_span< uint8_t const > > >, std::future< void > > | cudf::io::parquet::fetch_byte_ranges_to_device_async (cudf::host_span< std::reference_wrapper< cudf::io::datasource > const > datasources, cudf::host_span< std::vector< byte_range_info > const > byte_ranges_per_source, io_submission_policy policy, cuda::stream_ref stream=cudf::get_default_stream(), cudf::memory_resources mr=cudf::get_current_device_resource_ref()) |
| Fetches lists of byte ranges from multiple datasources into device buffers. More... | |
| std::pair< std::vector< rmm::device_buffer >, std::vector< cudf::device_span< uint8_t const > > > | cudf::io::parquet::fetch_bloom_filters_to_device (cudf::io::datasource &datasource, cudf::host_span< byte_range_info const > bloom_filter_byte_ranges, io_submission_policy policy, cuda::stream_ref stream=cudf::get_default_stream(), cudf::memory_resources mr=cudf::get_current_device_resource_ref()) |
| Fetches Parquet bloom filter bitsets from a datasource into device buffers. More... | |
| std::pair< std::vector< rmm::device_buffer >, std::vector< std::vector< cudf::device_span< uint8_t const > > > > | cudf::io::parquet::fetch_bloom_filters_to_device (cudf::host_span< std::reference_wrapper< cudf::io::datasource > const > datasources, cudf::host_span< std::vector< byte_range_info > const > bloom_filter_byte_ranges_per_source, io_submission_policy policy, cuda::stream_ref stream=cudf::get_default_stream(), cudf::memory_resources mr=cudf::get_current_device_resource_ref()) |
| Fetches Parquet bloom filter bitsets from multiple datasources into device buffers. More... | |
| std::tuple< std::vector< rmm::device_buffer >, std::vector< cudf::device_span< uint8_t const > >, std::future< void > > | cudf::io::parquet::fetch_byte_ranges_to_device_async (cudf::io::datasource &datasource, std::span< byte_range_info const > byte_ranges, cuda::stream_ref stream=cudf::get_default_stream(), cudf::memory_resources mr=cudf::get_current_device_resource_ref()) |
| Fetches a list of byte ranges from a datasource into device buffers. More... | |
| std::tuple< std::vector< rmm::device_buffer >, std::vector< std::vector< cudf::device_span< uint8_t const > > >, std::future< void > > | cudf::io::parquet::fetch_byte_ranges_to_device_async (cudf::host_span< std::reference_wrapper< cudf::io::datasource > const > datasources, cudf::host_span< std::vector< byte_range_info > const > byte_ranges_per_source, cuda::stream_ref stream=cudf::get_default_stream(), cudf::memory_resources mr=cudf::get_current_device_resource_ref()) |
| Fetches lists of byte ranges from multiple datasources into device buffers. More... | |
| std::pair< std::vector< rmm::device_buffer >, std::vector< cudf::device_span< uint8_t const > > > | cudf::io::parquet::fetch_bloom_filters_to_device (cudf::io::datasource &datasource, cudf::host_span< byte_range_info const > bloom_filter_byte_ranges, cuda::stream_ref stream=cudf::get_default_stream(), cudf::memory_resources mr=cudf::get_current_device_resource_ref()) |
| Fetches Parquet bloom filter bitsets from a datasource into device buffers. More... | |
| std::pair< std::vector< rmm::device_buffer >, std::vector< std::vector< cudf::device_span< uint8_t const > > > > | cudf::io::parquet::fetch_bloom_filters_to_device (cudf::host_span< std::reference_wrapper< cudf::io::datasource > const > datasources, cudf::host_span< std::vector< byte_range_info > const > bloom_filter_byte_ranges_per_source, cuda::stream_ref stream=cudf::get_default_stream(), cudf::memory_resources mr=cudf::get_current_device_resource_ref()) |
| Fetches Parquet bloom filter bitsets from multiple datasources into device buffers. More... | |
IO utilities for the Parquet and Hybrid scan readers.
Definition in file parquet_io_utils.hpp.