IO Utilities

Files
file	parquet_io_utils.hpp
	IO utilities for the Parquet and Hybrid scan readers.

Functions
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::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::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, cudf::host_span< byte_range_info const > byte_ranges, rmm::cuda_stream_view stream, rmm::device_async_resource_ref mr)
	Fetches a list of byte ranges from a datasource into device buffers. More...

Detailed Description

Function Documentation

fetch_byte_ranges_to_device_async()

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,
		cudf::host_span< byte_range_info const >	byte_ranges,
		rmm::cuda_stream_view	stream,
		rmm::device_async_resource_ref	mr
	)

Fetches a list of byte ranges from a datasource into device buffers.

Parameters

datasource	Input datasource
byte_ranges	Byte ranges to fetch
stream	CUDA stream
mr	Device memory resource

Returns

A tuple containing the device buffers, the device spans of the fetched data, and a future to wait on the read tasks

fetch_footer_to_host()

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.

Parameters

datasource

Input data source

Returns

Host buffer containing footer bytes

fetch_page_index_to_host()

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.

Parameters

datasource	Input datasource
page_index_bytes	Byte range of page index

Returns

Host buffer containing page index bytes