כתבה
arXiv cs.LG ·
חיפוש יחידות תואמות ב-L2
From 80x to 385x: A Best-Matching-Unit Search at the L2 Roof, Measured Against a Symmetrically Tuned Baseline
תוכנית לטיוב יחידות תואמות ב-L2 השיגה שיפור בביצועים. התוכנית כללה התאמה של אלגוריתם SOM ואלגוריתם cuSPARSE. השיפור היה 5.6-10.1x לעומת הקונפיגורציה הקודמת.
תקציר מקורי באנגליתarXiv:2609.05138v1 Announce Type: new Abstract: 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
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית