Hardware-Software Co-Design for Accelerating Transformer Inference Leveraging Compute-in-Memory

TL;DR

This paper introduces HASTILY, a hardware-software co-designed compute-in-memory accelerator that significantly speeds up transformer attention mechanisms, especially softmax, while reducing memory and energy requirements.

Contribution

The paper presents a novel CIM-based architecture with unified compute and lookup modules, enabling efficient softmax acceleration and linearized attention computation in transformers.

Findings

Achieves 4.4x-9.8x throughput improvement over Nvidia A40 GPU.

Provides 16x-36x energy-efficiency gains over GPU.

Reduces memory dependence from quadratic to linear with respect to sequence length.

Abstract

Transformers have become the backbone of neural network architecture for most machine learning applications. Their widespread use has resulted in multiple efforts on accelerating attention, the basic building block of transformers. This paper tackles the challenges associated with accelerating attention through a hardware-software co-design approach while leveraging compute-in-memory(CIM) architecture. In particular, our energy- and area-efficient CIM based accelerator, named HASTILY, aims to accelerate softmax computation, an integral operation in attention, and minimize their high on-chip memory requirements that grows quadratically with input sequence length. Our architecture consists of novel CIM units called unified compute and lookup modules(UCLMs) that integrate both lookup and multiply-accumulate functionality within the same SRAM array, incurring minimal area overhead over standard CIM arrays. Designed in TSMC 65nm, UCLMs can be used to concurrently perform exponential and matrix-vector multiplication operations. Complementing the proposed architecture, HASTILY features a fine-grained pipelining strategy for scheduling both attention and feed-forward layers, to reduce the quadratic dependence on sequence length to linear dependence. Further, for fast softmax computation which involves computing the maxima and sum of exponential values, such operations are parallelized across multiple cores using reduce and gather strategy. We evaluate our proposed architecture using a compiler tailored towards attention computation and a standard cycle-level CIM simulator. Our evaluation shows end-to-end throughput(TOPS) improvement of 4.4x-9.8x and 1.7x-5.9x over Nvidia A40 GPU and baseline CIM hardware, respectively, for BERT models with INT-8 precision. Additionally, it shows gains of 16x-36x in energy-efficiency(TOPS/W) over A40 GPU and similar energy-efficiency as baseline CIM hardware.