scholarly journals An Energy-Efficient and Fast Scheme for Hybrid Storage Class Memory in an AIoT Terminal System

Electronics ◽  
2020 ◽  
Vol 9 (6) ◽  
pp. 1013
Author(s):  
Hao Sun ◽  
Lan Chen ◽  
Xiaoran Hao ◽  
Chenji Liu ◽  
Mao Ni
Keyword(s):  
Energy Consumption ◽  
Data Storage ◽  
File System ◽  
Random Access ◽  
Memory System ◽  
Main Memory ◽  
Fast Mode ◽  
Hybrid Storage ◽  
Storage Class Memory ◽  
The Impact

Conventional main memory can no longer meet the requirements of low energy consumption and massive data storage in an artificial intelligence Internet of Things (AIoT) system. Moreover, the efficiency is decreased due to the swapping of data between the main memory and storage. This paper presents a hybrid storage class memory system to reduce the energy consumption and optimize IO performance. Phase change memory (PCM) brings the advantages of low static power and a large capacity to a hybrid memory system. In order to avoid the impact of poor write performance in PCM, a migration scheme implemented in the memory controller is proposed. By counting the write times and row buffer miss times in PCM simultaneously, the write-intensive data can be selected and migrated from PCM to dynamic random-access memory (DRAM) efficiently, which improves the performance of hybrid storage class memory. In addition, a fast mode with a tmpfs-based, in-memory file system is applied to hybrid storage class memory to reduce the number of data movements between memory and external storage. Experimental results show that the proposed system can reduce energy consumption by 46.2% on average compared with the traditional DRAM-only system. The fast mode increases the IO performance of the system by more than 30 times compared with the common ext3 file system.

scholarly journals Q-Selector-Based Prefetching Method for DRAM/NVM Hybrid Main Memory System

Electronics ◽  
2020 ◽  
Vol 9 (12) ◽  
pp. 2158
Author(s):  
Jeong-Geun Kim ◽  
Shin-Dug Kim ◽  
Su-Kyung Yoon
Keyword(s):  
Performance Status ◽  
Random Access ◽  
Memory Systems ◽  
Memory System ◽  
Main Memory ◽  
Learning Method ◽  
Q Learning ◽  
Data Intensive ◽  
Big Data Applications ◽  
Non Volatile Memory

This research is to design a Q-selector-based prefetching method for a dynamic random-access memory (DRAM)/ Phase-change memory (PCM)hybrid main memory system for memory-intensive big data applications generating irregular memory accessing streams. Specifically, the proposed method fully exploits the advantages of two-level hybrid memory systems, constructed as DRAM devices and non-volatile memory (NVM) devices. The Q-selector-based prefetching method is based on the Q-learning method, one of the reinforcement learning algorithms, which determines a near-optimal prefetcher for an application’s current running phase. For this, our model analyzes real-time performance status to set the criteria for the Q-learning method. We evaluate the Q-selector-based prefetching method with workloads from data mining and data-intensive benchmark applications, PARSEC-3.0 and graphBIG. Our evaluation results show that the system achieves approximately 31% performance improvement and increases the hit ratio of the DRAM-cache layer by 46% on average compared to a PCM-only main memory system. In addition, it achieves better performance results compared to the state-of-the-art prefetcher, access map pattern matching (AMPM) prefetcher, by 14.3% reduction of execution time and 12.89% of better CPI enhancement.

scholarly journals A noble approach to develop dynamically scalable namenode in hadoop distributed file system using secondary storage

2019 ◽  
Vol 13 (2) ◽  
pp. 729
Author(s):  
Tumpa Rani Shaha ◽  
Md. Nasim Akhtar ◽  
Fatema Tuj Johora ◽  
Md. Zakir Hossain ◽  
Mostafijur Rahman ◽  
...  
Keyword(s):  
Data Storage ◽  
File System ◽  
Secondary Data ◽  
Threshold Value ◽  
Main Memory ◽  
Distributed File System ◽  
Access Time ◽  
Secondary Memory ◽  
Application Data ◽  
Time Utilization

For scalable data storage, Hadoop is widely used nowadays. It provides a distributed file system that stores data on the compute nodes. Basically, it represents a master/slave architecture that consists of a NameNode and copious Data Nodes. Data Nodes contain application data and metadata of application data resides in the Main Memory of NameNode. In cached approach, they fragment the metadata depending on the last access time and move the least frequently used data to secondary memory. If the requested data is not found in main memory then the secondary data will be loaded again on the RAM. So when the secondary data reloads to the primary memory then the NameNode main memory limitation arises again. The focus of this research is to reduce the namespace problem of main memory and to make the system dynamically scalable. A new Metadata Fragmentation Algorithm is proposed that separates the metadata list of NameNode dynamically. The NameNode creates Secondary Memory File in perspective of the threshold value and allocates secondary memory location based on the requirement. According to the proposed algorithm the maximum third, out of fourth of main memory is used at the secondary file caching time. The free space aids in faster operation by Dynamically Scalable NameNode approach. This proposed algorithm shows that the space utilization is increased to 17% and time utilization is increased to 0.0005% with the comparison of the existing fragmentation algorithm.For scalable data storage, Hadoop is widely used nowadays. It provides a distributed file system that stores data on the compute nodes. Basically, it represents a master/slave architecture that consists of a NameNode and copious Data Nodes. Data Nodes contain application data and metadata of application data resides in the Main Memory of NameNode. In cached approach, they fragment the metadata depending on the last access time and move the least frequently used data to secondary memory. If the requested data is not found in main memory then the secondary data will be loaded again on the RAM. So when the secondary data reloads to the primary memory then the NameNode main memory limitation arises again. The focus of this research is to reduce the namespace problem of main memory and to make the system dynamically scalable. A new Metadata Fragmentation Algorithm is proposed that separates the metadata list of NameNode dynamically. The NameNode creates Secondary Memory File in perspective of the threshold value and allocates secondary memory location based on the requirement. According to the proposed algorithm the maximum third, out of fourth of main memory is used at the secondary file caching time. The free space aids in faster operation by Dynamically Scalable NameNode approach. This proposed algorithm shows that the space utilization is increased to 17% and time utilization is increased to 0.0005% with the comparison of the existing fragmentation algorithm.For scalable data storage, Hadoop is widely used nowadays. It provides a distributed file system that stores data on the compute nodes. Basically, it represents a master/slave architecture that consists of a NameNode and copious Data Nodes. Data Nodes contain application data and metadata of application data resides in the Main Memory of NameNode. In cached approach, they fragment the metadata depending on the last access time and move the least frequently used data to secondary memory. If the requested data is not found in main memory then the secondary data will be loaded again on the RAM. So when the secondary data reloads to the primary memory then the NameNode main memory limitation arises again. The focus of this research is to reduce the namespace problem of main memory and to make the system dynamically scalable. A new Metadata Fragmentation Algorithm is proposed that separates the metadata list of NameNode dynamically. The NameNode creates Secondary Memory File in perspective of the threshold value and allocates secondary memory location based on the requirement. According to the proposed algorithm the maximum third, out of fourth of main memory is used at the secondary file caching time. The free space aids in faster operation by Dynamically Scalable NameNode approach. This proposed algorithm shows that the space utilization is increased to 17% and time utilization is increased to 0.0005% with the comparison of the existing fragmentation algorithm.

A New Hybrid Storage System Base on Openstack

2014 ◽  
Vol 556-562 ◽  
pp. 5371-5376
Author(s):  
Ding Wei Wu ◽  
Qiang Wu ◽  
Xi Cheng Fu ◽  
Zhi Zhong Ye ◽  
Jia Lun Lin
Keyword(s):  
Big Data ◽  
Data Storage ◽  
High Performance ◽  
File System ◽  
Storage Systems ◽  
Low Cost ◽  
Storage System ◽  
Small Data ◽  
Hybrid Storage ◽  
Hybrid Storage System

In recent years, hybrid storage has gradually become a hotspot in the research of data storage owing to its high-performance and low cost. An OpenStack-based hybrid storage system is presented in this paper. According to the characteristics, the data is divided into small data, big data and temporary data in this hybrid storage system; meanwhile a storage strategy, combining database storage system, the virtual file system and servers file system, is designed. In the application of iCampus project, this proposed hybrid storage system shows better performance and higher efficiency than the traditional single storage systems.

Impact of roof shading on building energy performance in warm & humid climatic places of India

2020 ◽  
pp. 50-64
Author(s):  
Kuladeep Kumar Sadevi ◽  
Avlokita Agrawal
Keyword(s):  
Energy Consumption ◽  
Energy Conservation ◽  
Energy Performance ◽  
General Assumption ◽  
Climatic Conditions ◽  
Building Envelope ◽  
Passive Cooling ◽  
Base Case ◽  
U Value ◽  
The Impact

With the rise in awareness of energy efficient buildings and adoption of mandatory energy conservation codes across the globe, significant change is being observed in the way the buildings are designed. With the launch of Energy Conservation Building Code (ECBC) in India, climate responsive designs and passive cooling techniques are being explored increasingly in building designs. Of all the building envelope components, roof surface has been identified as the most significant with respect to the heat gain due to the incident solar radiation on buildings, especially in tropical climatic conditions. Since ECBC specifies stringent U-Values for roof assembly, use of insulating materials is becoming popular. Along with insulation, the shading of the roof is also observed to be an important strategy for improving thermal performance of the building, especially in Warm and humid climatic conditions. This study intends to assess the impact of roof shading on building’s energy performance in comparison to that of exposed roof with insulation. A typical office building with specific geometry and schedules has been identified as base case model for this study. This building is simulated using energy modelling software ‘Design Builder’ with base case parameters as prescribed in ECBC. Further, the same building has been simulated parametrically adjusting the amount of roof insulation and roof shading simultaneously. The overall energy consumption and the envelope performance of the top floor are extracted for analysis. The results indicate that the roof shading is an effective passive cooling strategy for both naturally ventilated and air conditioned buildings in Warm and humid climates of India. It is also observed that a fully shaded roof outperforms the insulated roof as per ECBC prescription. Provision of shading over roof reduces the annual energy consumption of building in case of both insulated and uninsulated roofs. However, the impact is higher for uninsulated roofs (U-Value of 3.933 W/m2K), being 4.18% as compared to 0.59% for insulated roofs (U-Value of 0.33 W/m2K).While the general assumption is that roof insulation helps in reducing the energy consumption in tropical buildings, it is observed to be the other way when insulation is provided with roof shading. It is due to restricted heat loss during night.

ANALISIS DETERMINAN KUALITAS LINGKUNGAN PERIODE 1999-2013

2016 ◽  
Vol 21 (1) ◽  
pp. 9-20
Author(s):  
Ersalina Tang
Keyword(s):  
Foreign Direct Investment ◽  
Energy Consumption ◽  
Gross Domestic Product ◽  
Co2 Emissions ◽  
Direct Investment ◽  
Meat Consumption ◽  
Domestic Product ◽  
World Data ◽  
The World ◽  
The Impact

The purpose of this study is to analyze the impact of Foreign Direct Investment, Gross Domestic Product, Energy Consumption, Electric Consumption, and Meat Consumption on CO2 emissions of 41 countries in the world using panel data from 1999 to 2013. After analyzing 41 countries in the world data, furthermore 17 countries in Asia was analyzed with the same period. This study utilized quantitative approach with Ordinary Least Square (OLS) regression method. The results of 41 countries in the world data indicates that Foreign Direct Investment, Gross Domestic Product, Energy Consumption, and Meat Consumption significantlyaffect Environmental Qualities which measured by CO2 emissions. Whilst the results of 17 countries in Asia data implies that Foreign Direct Investment, Energy Consumption, and Electric Consumption significantlyaffect Environmental Qualities. However, Gross Domestic Product and Meat Consumption does not affect Environmental Qualities.

The Nexus between Financial Development, Economic Growth and Energy Consumption in India: A VECM Technique

2020 ◽  
pp. 602-612
Keyword(s):  
Economic Growth ◽  
Energy Consumption ◽  
Financial Development ◽  
Consumer Price Index ◽  
Development Economic ◽  
Energy Prices ◽  
Vector Error Correction ◽  
Percent Increase ◽  
Growth Energy ◽  
The Impact

The demand for energy consumption requires efficient financial development in terms of bank credit. Therefore, this study examines the nexus between Financial Development, Economic Growth, Energy Prices and Energy Consumption in India, utilizing Vector Error Correction Model (VECM) technique to determine the nature of short and long term relationships from 2010 to 2019. The estimation of results indicates that a one percent increase in bank credits to private sector results in 0.10 percent increase in energy consumption and 0.28 percent increase in energy consumption responses to 1 percent increase in economic growth. It is also observed that the impact of energy price proxied by consumer price index is statistically significant with a negative sign indicating the consistency with the theory.

Deoxyribonucleic Acid as a Tool for Digital Information Storage: An Overview

2019 ◽  
Vol 15 (01) ◽  
pp. 1-8
Author(s):  
Ashish C Patel ◽  
C G Joshi
Keyword(s):  
Data Storage ◽  
Dna Sequences ◽  
Consensus Sequence ◽  
Random Access ◽  
Information Storage ◽  
Digital Data ◽  
Digital Information ◽  
Multiple Sequence ◽  
Digital World ◽  
Digital File

Current data storage technologies cannot keep pace longer with exponentially growing amounts of data through the extensive use of social networking photos and media, etc. The "digital world” with 4.4 zettabytes in 2013 has predicted it to reach 44 zettabytes by 2020. From the past 30 years, scientists and researchers have been trying to develop a robust way of storing data on a medium which is dense and ever-lasting and found DNA as the most promising storage medium. Unlike existing storage devices, DNA requires no maintenance, except the need to store at a cool and dark place. DNA has a small size with high density; just 1 gram of dry DNA can store about 455 exabytes of data. DNA stores the informations using four bases, viz., A, T, G, and C, while CDs, hard disks and other devices stores the information using 0’s and 1’s on the spiral tracks. In the DNA based storage, after binarization of digital file into the binary codes, encoding and decoding are important steps in DNA based storage system. Once the digital file is encoded, the next step is to synthesize arbitrary single-strand DNA sequences and that can be stored in the deep freeze until use.When there is a need for information to be recovered, it can be done using DNA sequencing. New generation sequencing (NGS) capable of producing sequences with very high throughput at a much lower cost about less than 0.1 USD for one MB of data than the first sequencing technologies. Post-sequencing processing includes alignment of all reads using multiple sequence alignment (MSA) algorithms to obtain different consensus sequences. The consensus sequence is decoded as the reversal of the encoding process. Most prior DNA data storage efforts sequenced and decoded the entire amount of stored digital information with no random access, but nowadays it has become possible to extract selective files (e.g., retrieving only required image from a collection) from a DNA pool using PCR-based random access. Various scientists successfully stored up to 110 zettabytes data in one gram of DNA. In the future, with an efficient encoding, error corrections, cheaper DNA synthesis,and sequencing, DNA based storage will become a practical solution for storage of exponentially growing digital data.

Analysis of 6T SRAM Cell in Different Technologies

2017 ◽  
Vol MCSP2017 (01) ◽  
pp. 7-10 ◽  
Author(s):  
Subhashree Rath ◽  
Siba Kumar Panda
Keyword(s):  
Low Power ◽  
Data Storage ◽  
Low Voltage ◽  
Random Access ◽  
Storage Device ◽  
Cmos Process ◽  
Process Technology ◽  
Digital Devices ◽  
Noise Margin ◽  
Sram Cell

Static random access memory (SRAM) is an important component of embedded cache memory of handheld digital devices. SRAM has become major data storage device due to its large storage density and less time to access. Exponential growth of low power digital devices has raised the demand of low voltage low power SRAM. This paper presents design and implementation of 6T SRAM cell in 180 nm, 90 nm and 45 nm standard CMOS process technology. The simulation has been done in Cadence Virtuoso environment. The performance analysis of SRAM cell has been evaluated in terms of delay, power and static noise margin (SNM).

Sign in / Sign up

Export Citation Format

Share Document