Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Filters

2022 - 20252

Settings

Author: search.filters.author.Rai, S.Subject: search.filters.subject.DRAM

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    SOT-MRAM Based Main Memory: An Alternative to DRAM
    (Institute of Electrical and Electronics Engineers Inc., 2022) Rai, S.; Kallinatha, H.D.; Talawar, B.
    Data is generated enormously today and to process this we need large memories with high speed and optimized power consumption. Conventional DRAM based system which were used as memory in computing systems for several decades are facing challenges in scalability and power consumption. In this regard non-volatile memories with excellent scalability and minimal power consumption are studied extensively. This paper analyzes the impact of introducing SOT-MRAM a non-volatile main memory device as an alternative to DRAM. Experimental results show an average power reduction of 46.09% with an increase in performance up to 30% when DRAM is replaced with SOT-MRAM for embedded system workloads. © 2022 IEEE.
  • No Thumbnail Available
    Item
    Migration and Replacement in Main Memory and Cache in Hybrid Memory Systems
    (Springer Science and Business Media Deutschland GmbH, 2025) Rai, S.; Talawar, B.
    The continuous growth of data-intensive applications like big data analytics, machine learning and AI has led to an increasing demand for high-performance and energy-efficient memory systems. Traditional DRAM technology, while fast, suffers from significant power consumption and scalability issues. Conversely, Non-Volatile Memory (NVM) technologies, offer lower static power consumption and higher density but lag in access speed and endurance. Hybrid memory systems, which combine DRAM and NVM, aim to provide the high-speed capabilities of DRAM with the energy efficiency and non-volatility of NVM. The amalgamation of two technologies requires various modifications for the existing monolithic DRAM-based systems. In this paper, power-performance trade-offs, migration, page replacement and cache replacement for developing energy efficient hybrid memory are explored. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.