SOURCE-LINKED INTELLIGENCE

From 80x to 385x: A Best-Matching-Unit Search at the L2 Roof, Measured Against a Symmetrically Tuned Baseline

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

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 implem

Read original source ↗ Open in workspace

recordType

paper

region

Global