优化自组织映射搜索，性能提升至385倍，突破内存带宽瓶颈。
From 80x to 385x: A Best-Matching-Unit Search at the L2 Roof, Measured Against a Symmetrically Tuned Baseline
- 通过四重优化提升搜索效率，覆盖块大小、聚类等关键参数
- 在32×32至512×512地图上实现5.6–10.1倍加速，总性能达385倍
- 首次对齐对比基线，揭示内存带宽为最终性能上限
GPU实现的比较通常不对称：一方由作者调优，另一方直接使用。本文对新型SOM算法SparseBin与对比基线cuSPARSE均进行了系统调优。主导自组织映射训练的最优匹配单元搜索，通过块大小、块成员聚类、神经元轴分块和向量化加载四个杠杆进行优化，在32×32至512×512的地图规模下，每轮训练相比此前发表配置提升5.6–10.1倍，并将与早期MEDLINE图谱所用CUDA实现的差距从约80倍扩大至约385倍。cuSPARSE也同步应用对应优化，速度提升2–3倍。调优后的内核在所有其他单元保持40–65%利用率时，达到L2带宽峰值的77%，任何未测试杠杆均被该上限制约或证实无效，标志着性能终局而非中继点。
原文摘要 · Abstract (English)
Comparisons between GPU implementations are usually asymmetric: one side is tuned by its author, the other is run as found. I report a programme that tuned both a novel SOM algorithm (SparseBin) and the baseline algorithm it was being compared to (cuSPARSE). The best-matching-unit search that dominates self-organizing map training was tuned through four levers - tile size, tile-membership clustering, neuron-axis chunking and vectorised loads - reaching 5.6-10.1x per epoch over the previously published configuration at map sizes from 32x32 to 512x512, and lifting the margin over the CUDA implementation behind our earlier MEDLINE atlases from ~80x to ~385x. cuSPARSE, the implementation SparseBin is compared against, received every lever with an analogue on its side, and became 2-3x faster in the process. The tuned kernel pressed the L2 bandwidth roof at 77% of peak with every other unit at 40-65%, bounding any further lever at ~1.3x - a terminal result rather than a waypoint, and every untested lever was either capped by that bound by construction or measured null.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。