Machine Learning Migration for Efficient Near-Data Processing
| Autor: | Aline Santana Cordeiro, Francis B. Moreira, Marco A. Z. Alves, Sairo R. dos Santos, Luigi Carro, Paulo C. Santos |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
010302 applied physics
Data processing business.industry Computer science media_common.quotation_subject Context (language use) 02 engineering and technology Intrinsics Machine learning computer.software_genre 01 natural sciences Field (computer science) 020202 computer hardware & architecture Parallel processing (DSP implementation) Debugging 0103 physical sciences 0202 electrical engineering electronic engineering information engineering x86 Artificial intelligence Graphics business computer media_common |
| Zdroj: | PDP |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|