TileSight: A First-Principles Tile-Centric Analytical GPU Performance Model from Cores to Clusters

TileSight addresses the problem that existing GPU performance tooling relies on coarse roofline bounds, opaque ML predictors, or post-hoc profilers, failing to support tile-centric programming now dominant in AI workloads. The method introduces a first-principles analytical model that uses the tile as a unified abstraction across intra-core compute-memory overlap, inter-core cache hierarchy, and cross-device inter-node communication layers. On A100, H200, B200, and B6000, TileSight predicts single-GPU kernel latency with 12.35% MAPE, L2 cache hit rates within one percentage point, and achieves 16.18% wMAPE on fused distributed kernels up to 32 GPUs. This matters because it provides an interpretable, transferable, and accurate alternative to opaque predictors and post-hoc profilers, enabling tile configuration optimization competitive with vendor and expert baselines.