Machine Learning Migration for Efficient Near-Data Processing

Machine Learning (ML) rises as a highly useful tool to analyze the vast amount of data generated in every field of science nowadays. Simultaneously, data movement inside computer systems gains more focus due to its high impact on time and energy consumption. In this context, the Near-Data Processing (NDP) architectures emerged as a prominent solution to increasing data by drastically reducing the required amount of data movement. For NDP, we see three main approaches, Application-Specific Integrated Circuits (ASICs), full Central Processing Units (CPUs) and Graphics Processing Units (GPUs), or vector units integration. However, previous work considered only ASICs, CPUs and GPUs when executing ML algorithms inside the memory. In this paper, we present an approach to execute ML algorithms near-data, using a general-purpose vector architecture and applying near-data parallelism to kernels from KNN, MLP, and CNN algorithms. To facilitate this process, we also present an NDP intrinsics library to ease the evaluation and debugging tasks. Our results show speedups up to $10\times$ for KNN, $11\times$ for MLP, and $3\times$ for convolution when processing near-data compared to a high-performance x86 baseline.