[kerrmudgeon]

CUTLASS is a collection of CUDA C++ template abstractions for implementing high-performance matrix-multiplication (GEMM) at all levels and scales within CUDA. It incorporates strategies for hierarchical decomposition and data movement similar to those used to implement cuBLAS. CUTLASS decomposes these "moving parts" into reusable, modular software components abstracted by C++ template classes. These thread-wide, warp-wide, block-wide, and device-wide primitives can be specialized and tuned via custom tiling sizes, data types, and other algorithmic policy. The resulting flexibility simplifies their use as building blocks within custom kernels and applications.

[bsprings]

For most formats it achieves >90% of the performance of the hand-tuned assembly implementations in cuBLAS.