rapidsai/cudf

Use grid stride in CSV reader kernels

Open

#14,066 建立於 2023年9月8日

在 GitHub 查看
 (1 留言) (0 反應) (1 負責人)C++ (6,000 star) (735 fork)batch import
PerformancecuIOgood first issue

描述

Currently, the CSV reader parses data using a thread per row, and a separate thread is used for each row, regardless of the file size. Using a grid stride loop would allow kernels to launch with preset number of blocks even with large input.

This applies both to the parser and the data inference kernels.

貢獻者指南

技術棧
cpp
領域
backenddataperformance
議題類型
performance
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
4
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
half day
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
blocked
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
clear
前置要求
CUDA programminggrid stride loopsC++
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
20
研究方向
Investigate the current CSV reader kernel implementations in the cudf repository, specifically the parser and data inference kernels. Look for where threads are assigned per row and refactor to use a grid stride loop. This will involve modifying CUDA kernel launches and loop structures in files such as csv reader.cu or similar. Refer to existing CUDA grid stride examples in the codebase for pattern consistency.