Machine learning based design space exploration for hybrid main-memory design
Abstract
We develop a machine learning (ML) based design space exploration (DSE) method that builds predictive models for various responses of a hybrid main-memory system. To overcome the challenges associated with latency, capacity, and power of memory systems in future extreme-scale machines, the hybrid memory architectures are being considered in which novel non-volatile memory (NVM) systems augment the traditional DRAM. However, way before their actual design and implementation, these emerging hybrid memory systems need to be simulated and analyzed to fully understand their capabilities and limitations. As the conventional architectural-level memory simulators require significant amounts of computational costs and time, we propose to utilize ML techniques for developing various memory-response models that can instantly provide a predicted response corresponding to any new memory configuration. Specifically, in this work, we apply four supervised ML techniques to build regression models for memory latency, bandwidth, power, and total read/write responses. The training and validation data for the ML methods are generated using NVMain memory simulator for DRAM, NVM, and their hybrid combinations. We demonstrate the results of the ML based memory-DSE method in terms of the learning curve characteristics for hyperparameter tuning and the statistical error analyses of the designed predictive models.
- Publication Date:
- Research Org.:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1606980
- DOE Contract Number:
- AC05-00OR22725
- Resource Type:
- Conference
- Resource Relation:
- Conference: International Symposium on Memory Systems (MEMSYS 2019) - Washington DC, District of Columbia, United States of America - 9/30/2019 12:00:00 PM-10/3/2019 12:00:00 PM
- Country of Publication:
- United States
- Language:
- English
Citation Formats
Sen, Satyabrata, and Imam, Neena. Machine learning based design space exploration for hybrid main-memory design. United States: N. p., 2019.
Web. doi:10.1145/3357526.3357544.
Sen, Satyabrata, & Imam, Neena. Machine learning based design space exploration for hybrid main-memory design. United States. https://doi.org/10.1145/3357526.3357544
Sen, Satyabrata, and Imam, Neena. Sun .
"Machine learning based design space exploration for hybrid main-memory design". United States. https://doi.org/10.1145/3357526.3357544. https://www.osti.gov/servlets/purl/1606980.
@article{osti_1606980,
title = {Machine learning based design space exploration for hybrid main-memory design},
author = {Sen, Satyabrata and Imam, Neena},
abstractNote = {We develop a machine learning (ML) based design space exploration (DSE) method that builds predictive models for various responses of a hybrid main-memory system. To overcome the challenges associated with latency, capacity, and power of memory systems in future extreme-scale machines, the hybrid memory architectures are being considered in which novel non-volatile memory (NVM) systems augment the traditional DRAM. However, way before their actual design and implementation, these emerging hybrid memory systems need to be simulated and analyzed to fully understand their capabilities and limitations. As the conventional architectural-level memory simulators require significant amounts of computational costs and time, we propose to utilize ML techniques for developing various memory-response models that can instantly provide a predicted response corresponding to any new memory configuration. Specifically, in this work, we apply four supervised ML techniques to build regression models for memory latency, bandwidth, power, and total read/write responses. The training and validation data for the ML methods are generated using NVMain memory simulator for DRAM, NVM, and their hybrid combinations. We demonstrate the results of the ML based memory-DSE method in terms of the learning curve characteristics for hyperparameter tuning and the statistical error analyses of the designed predictive models.},
doi = {10.1145/3357526.3357544},
url = {https://www.osti.gov/biblio/1606980},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2019},
month = {9}
}