2024/04/15 by Golin, Renato, Chelini, Lorenzo, Siemieniuk, Adam +5 · 2 citations
#Artificial Intelligence (cs.AI) #Distributed #FOS: Computer and information sciences #Hardware Architecture (cs.AR) #Machine Learning (cs.LG) #Parallel #Programming Languages (cs.PL) #and Cluster Computing (cs.DC)
paper · doi:10.48550/arxiv.2404.15204
This work proposes a compilation flow using open-source compiler passes to build a framework to achieve ninja performance from a generic linear algebra high-level abstraction. We demonstrate this flow with a proof-of-concept MLIR project that uses input IR in Linalg-on-Tensor from TensorFlow and PyTorch, performs cache-level optimizations and lowering to micro-kernels for efficient vectorization, achieving over 90% of the performance of ninja-written equivalent programs. The contributions of this work include: (1) Packing primitives on the tensor dialect and passes for cache-aware distribution of tensors (single and multi-core) and type-aware instructions (VNNI, BFDOT, BFMMLA), including propagation of shapes across the entire function; (2) A linear algebra pipeline, including tile, fuse and bufferization strategies to get model-level IR into hardware friendly tile calls; (3) A mechanism for micro-kernel lowering to an open source library that supports various CPUs.