Evaluation Mappings of Spatial Accelerator Based On Data Placement

TL;DR

PolyAcc is a framework that improves performance evaluation of workload mappings on spatial accelerators by modeling data placement relations, leading to more accurate estimates of latency, energy, and hardware utilization.

Contribution

The paper introduces PolyAcc, a novel data placement-based evaluation framework that enhances accuracy over existing cost-models by capturing customized memory hierarchies.

Findings

PolyAcc achieves 0.82% accuracy in execution time estimation.

PolyAcc reduces energy consumption estimation error by 18.8%.

PolyAcc closely matches ideal execution time and PE utilization for GEMM and Conv workloads.

Abstract

The scheduling strategies of workloads are critical to fully exploiting the performance of spatial accelerators, accurate performance models are required to evaluate the mapping of workloads.Recent works proposed various cost-model to describe the dataflow of the spatial accelerator. However, they are less expressive about customized memory hierarchies and thus lead to inaccurate performance models. In this paper, we propose, PolyAcc, a framework for evaluating the mappings of workload on spatial accelerator based on data placement. The Data placement relation describes the temporal-spatial relation of data at different memory levels, which can accurately capture the runtime behavior of hardware units. Based on data placement relations, polyAcc accurately analyzes the data volume for different reuse patterns and estimate metrics, including data reuse, latency, and energy. Overall, polyAcc closely matches the ideal execution time and PE utilization for GEMM and Conv workloads, respectively achieves 0.82%, 18.8% improvements for execution time and energy consumption estimates in validation against Eyeriss architecture compared to the state-of-the-art framework.