# Library Liberation: Competitive Performance Matmul Through Compiler-composed Nanokernels

arXiv: https://arxiv.org/abs/2511.13764 · HTML: https://mlsanity.com/paper/2511.13764/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Nov 2025.

## Built on by (most cited first, 2 of 2)

- [Space Filling Curves is All You Need: Communication-Avoiding Matrix Multiplication Made Simple](https://mlsanity.com/paper/2601.16294/) (2026)
- [LP-GEMM: Integrating Layout Propagation into GEMM Operations](https://mlsanity.com/paper/2604.04599/) (2026)

## Abstract (arXiv)

The rapidly evolving landscape of AI and machine learning workloads has widened the gap between high-level domain operations and efficient hardware utilization. Achieving near-peak performance still demands deep hardware expertise-experts either handcraft target-specific kernels (e.g., DeepSeek) or rely on specialized libraries (e.g., CUTLASS)-both of which add complexity and limit scalability for most ML practitioners. This paper introduces a compilation scheme that automatically generates scalable, high-performance microkernels by leveraging the MLIR dialects to bridge domain-level operations and processor capabilities. Our approach removes dependence on low-level libraries by enabling the compiler to auto-generate near-optimal code directly. At its core is a mechanism for composing nanokernels from low-level IR constructs with near-optimal register utilization, forming efficient microkernels tailored to each target. We implement this technique in an MLIR-based compiler supporting both vector and tile based CPU instructions. Experiments show that the generated nanokernels are of production-quality, and competitive with state-of-the-art microkernel libraries.