WWW: What, When, Where to Compute-in-Memory

Abstract

Matrix multiplication is the dominant computation during Machine Learning (ML) inference. To efficiently perform such multiplication operations, Compute-in-memory (CiM) paradigms have emerged as a highly energy efficient solution. However, integrating compute in memory poses key questions, such as 1) What type of CiM to use: Given a multitude of CiM design characteristics, determining their suitability from architecture perspective is needed. 2) When to use CiM: ML inference includes workloads with a variety of memory and compute requirements, making it difficult to identify when CiM is more beneficial than standard processing cores. 3) Where to integrate CiM: Each memory level has different bandwidth and capacity, creating different data reuse opportunities for CiM integration. To answer such questions regarding on-chip CiM integration for accelerating ML workloads, we use an analytical architecture-evaluation methodology with tailored mapping algorithm. The mapping algorithm aims to achieve highest weight reuse and reduced data movements for a given CiM prototype and workload. Our analysis considers the integration of CiM prototypes into the cache levels of a tensor-core-like architecture, and shows that CiM integrated memory improves energy efficiency by up to 3.4x and throughput by up to 15.6x compared to established baseline with INT-8 precision. We believe the proposed work provides insights into what type of CiM to use, and when and where to optimally integrate it in the cache hierarchy for efficient matrix multiplication.

added supplementary

References in corpus (7)

• Deep Learning Recommendation Model for Personalization and Recommendation Systems
• IMAC: In-memory multi-bit Multiplication andACcumulation in 6T SRAM Array
• LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
• IMPULSE: A 65nm Digital Compute-in-Memory Macro with Fused Weights and Membrane Potential for Spike-based Sequential Learning Tasks
• Full Stack Optimization of Transformer Inference: a Survey
• ZigZag: A Memory-Centric Rapid DNN Accelerator Design Space Exploration Framework
• Benchmarking and modeling of analog and digital SRAM in-memory computing architectures