facebook/zstd

IBM Linux on z SIMD optimization

Open

#2,679 建立於 2021年5月21日

在 GitHub 查看
 (7 留言) (4 反應) (0 負責人)C (27,100 star) (2,481 fork)batch import
Announcehelp wanted

描述

Is your feature request related to a problem? Please describe. IBM z architecture provides SIMD capabilities that can be utilized for zstd optimization similar to SSE and Neon SIMD optimizations that have been contributrd to zstd.

Describe the solution you'd like Optimize zstd to utilize IBMz VX SIMD intrinsics in zstd_lazy.c and ztsd_compress.c equivalent to optimization for SSE and Neon.

Describe alternatives you've considered Because zstd has implemented architecture-specific optimizations for other architectures, a hand-coded implementation has been shown to provide unique benefits above auto-vectorization.

Additional context Financial bounty from IBM available for negotiation. Inquiries from interested developers welcome.

貢獻者指南

技術棧
c
領域
performance
議題類型
feature
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。
over 1 week
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。
stale
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
mostly clear
前置要求
C programmingSIMD intrinsics knowledgeIBM z architecture understandingzstd codebase familiarity
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。
15
研究方向
The issue requests implementing IBM z VX SIMD intrinsics optimizations in zstd lazy.c and zstd compress.c, similar to existing SSE and Neon implementations. The contributor should study the existing SSE and Neon code paths, refer to IBM z architecture documentation for VX intrinsics, and propose a design. Maintainer feedback on scope and acceptance criteria is needed.