COMPASS: A Compiler Framework for Resource-Constrained Crossbar-Array Based In-Memory Deep Learning Accelerators

TL;DR

COMPASS is a compiler framework that enables resource-constrained crossbar-based in-memory DNN accelerators to efficiently handle larger networks by optimal layer partitioning, improving throughput and energy efficiency.

Contribution

It introduces a novel algorithm for optimal layer partitioning in crossbar-based PIM accelerators, addressing external memory access limitations.

Findings

Achieves 1.78X throughput improvement.

Provides 1.28X energy-delay product savings.

Enables larger networks to be processed with minimal memory footprint.

Abstract

Recently, crossbar array based in-memory accelerators have been gaining interest due to their high throughput and energy efficiency. While software and compiler support for the in-memory accelerators has also been introduced, they are currently limited to the case where all weights are assumed to be on-chip. This limitation becomes apparent with the significantly increasing network sizes compared to the in-memory footprint. Weight replacement schemes are essential to address this issue. We propose COMPASS, a compiler framework for resource-constrained crossbar-based processing-in-memory (PIM) deep neural network (DNN) accelerators. COMPASS is specially targeted for networks that exceed the capacity of PIM crossbar arrays, necessitating access to external memories. We propose an algorithm to determine the optimal partitioning that divides the layers so that each partition can be accelerated on chip. Our scheme takes into account the data dependence between layers, core utilization, and the number of write instructions to minimize latency, memory accesses, and improve energy efficiency. Simulation results demonstrate that COMPASS can accommodate much more networks using a minimal memory footprint, while improving throughput by 1.78X and providing 1.28X savings in energy-delay product (EDP) over baseline partitioning methods.