DeMM: A Decoupled Matrix Multiplication Engine Supporting Relaxed Structured Sparsity

Abstract

Deep Learning (DL) has achieved unprecedented success in various application domains. Meanwhile, model pruning has emerged as a viable solution to reduce the footprint of DL models in mobile applications, without compromising their accuracy. To enable the matrix engines built for dense DL models to also handle their pruned counterparts, pruned DL models follow a fine-grained structured sparsity pattern of 1:4, or 2:4, whereby in each group of four contiguous values, at least one, or two, respectively, must be non-zero. Structured sparsity has recently also moved to coarser (relaxed) cases of $N$N:128, or $N$N:256, for small values of $N$N, targeting a wider range of sparsity (10%-90%) for the DL models. In this work, we design an accelerator that operates, by construction, on wide blocks with relaxed structured sparsity. In contrast to the conventional systolic array archetype, the new engine decouples the memory part of the systolic array from the multiply-add units. The memory block comprises 1 write and $N$N read ports, with the number of read ports being equal to the number of non-zero elements per row. The multiply-add units connect directly to each read port and complete the multiplication in a row-wise product-first order. More importantly, simple reconfiguration facilitates more dense patterns. The experimental evaluation demonstrates substantial latency improvements over current state-of-the-art systolic array engines built for fine-grained and relaxed structured sparsity.