Hacktoberfest 2026:維護者為十月標記出來的 issue,仍然開放、適合新手。 瀏覽 Hacktoberfest issue

VORTEXM4: STRMM/DTRMM at about half of Accelerate at n = 1024

未關閉
#6,147 0 則留言 0 個 reaction 已指派 0 人 在 GitHub 檢視

維護者通常 1 天內回覆

還沒有人認領這個 Issue。

評估

難度
4/5
預估耗時
3-5 天
新手友好度
52/100
Issue 類型
缺陷
描述清晰度
基本清楚
活躍度
活躍
技術堆疊
c

研究方向

Start by profiling the STRMM path at n = 1024 to separate kernel time, triangle copy time and driver overhead. The issue points to gemm_kernel_sme2.c, trmm_ncopy_sme2.c, trmm_tcopy_sme2.c and driver/level3/trmm_L.c and trmm_R.c; compare those measurements with the listed Accelerate and SYMM results. Done means identifying which part accounts for the slowdown; the candidate causes have not yet been measured separately.

由索引模型根據 Issue 內容生成。

描述

STRMM and DTRMM on VORTEXM4 (SME2 kernels from #6074) are slower than the other level-3 routines also at large sizes. On an M4 Pro, one thread, n = 1024: all 16 STRMM variants run at 780-888 GFLOPS, Accelerate at 1536-1562 (0.52x); DTRMM is at 0.61x. At n = 4096 STRMM is at 0.78-0.86x. SYMM, which uses the same GEMM kernel through the level-3 driver, reaches 0.93x at n = 1024.

The difference is therefore specific to the TRMM path. Candidates, not yet measured separately:

  • the TRMM kernel (gemm_kernel_sme2.c with TRMMKERNEL) zeroes ZA and stores C = alpha * ZA with a per-row scale-only store (s2_c_store_alpha), not the four-row fast path of the GEMM case;
  • the triangle copies (trmm_ncopy_sme2.c, trmm_tcopy_sme2.c, ~43 GB/s, see #6146);
  • driver/level3/trmm_L.c / trmm_R.c call the kernel on chunks of at most 3 x GEMM_UNROLL_N = 48 columns.

A first step is a profile that separates kernel time, copy time and driver overhead at n = 1024.

主要語言
C
星號
7.6k
分支
1.7k
平均合併
1 天 18 小時
30 天內合併 PR
46

環境準備

這個專案沒有提供開發容器、Dockerfile 或貢獻指南,環境需要你自己搭建:先看它的 README,通用步驟見我們的新手貢獻指南。

從這裡開始

  1. 先讀完整個 Issue,再讀專案的貢獻指南。
  2. 在 Issue 下留言說明你要接手 —— 這能避免兩個人做同樣的事。
  3. Fork 儲存庫,在一個分支上完成修改。
  4. 送出 Pull Request,並在描述裡引用這個 Issue 編號。

OpenMathLib/OpenBLAS 的其他 Issue

查看 OpenMathLib/OpenBLAS 的全部 Issue

相似的 Issue

更多 C Issue

把新 issue 寄到你的電子郵件信箱

精選適合新手參與的 GitHub issue 摘要。