Rekha Singhal

Rekha Singhal
Tata Consultancy Services Limited | TCS · TCS Innovation Labs

Phd, Mtech, BE

About

64
Publications
8,417
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
131
Citations
Introduction
Rekha Singhal currently works as Senior Scientist at the TCS Innovation Labs, Tata Consultancy Services Limited. Rekha does research in Accelerating Software 2.0, High Performance Analytics System, Performance Modelling, analysis and optimization of Big data analytics systems, Databases, Software Engineering and Programming Languages. Their most recent publication is 'SPARK Job Performance Analysis and Prediction Tool'.
Additional affiliations
August 2011 - April 2016
Tata Consultancy Services Limited
Position
  • Senior Researcher
January 2011 - May 2016
Centre for Development of Advanced Computing
Position
  • Senior Researcher
January 2006 - December 2011
Tata Consultancy Services Limited
Position
  • Senior Researcher

Publications

Publications (64)
Conference Paper
Full-text available
This paper proposes a novel merged-accumulation-based approximate MAC unit, MEGA-MAC, for accelerating error-resilient applications. MEGA-MAC utilizes a novel rearrangement and compression strategy in the multiplication stage and a novel approximate ``carry predicting adder'' (CPA) in the accumulation stage. Addition and multiplication operations a...
Preprint
Full-text available
Meta Learning has been in focus in recent years due to the meta-learner model's ability to adapt well and generalize to new tasks, thus, reducing both the time and data requirements for learning. However, a major drawback of meta learner is that, to reach to a state from where learning new tasks becomes feasible with less data, it requires a large...
Preprint
Achieving maximum possible rate of inferencing with minimum hardware resources plays a major role in reducing enterprise operational costs. In this paper we explore use of PCIe streaming on FPGA based platforms to achieve high throughput. PCIe streaming is a unique capability available on FPGA that eliminates the need for memory copy overheads. We...
Chapter
We propose the algorithms for performing multiway joins using a new type of coarse grain reconfigurable hardware accelerator – “Plasticine” – that, compared with other accelerators, emphasizes high compute capability and high on-chip communication bandwidth. Joining three or more relations in a single step, i.e. multiway join, is efficient when the...
Preprint
In this paper, we present iPrescribe, a scalable low-latency architecture for recommending 'next-best-offers' in an online setting. The paper presents the design of iPrescribe and compares its performance for implementations using different real-time streaming technology stacks. iPrescribe uses an ensemble of deep learning and machine learning algo...
Preprint
We propose the algorithms for performing multiway joins using a new type of coarse grain reconfigurable hardware accelerator~-- ``Plasticine''~-- that, compared with other accelerators, emphasizes high compute capability and high on-chip communication bandwidth. Joining three or more relations in a single step, i.e. multiway join, is efficient when...
Preprint
Modern real-time business analytic consist of heterogeneous workloads (e.g, database queries, graph processing, and machine learning). These analytic applications need programming environments that can capture all aspects of the constituent workloads (including data models they work on and movement of data across processing engines). Polystore syst...
Conference Paper
In this paper we present iPrescribe, a scalable low-latency architecture for recommending 'next-best-offers' in an online setting. The paper presents the design of iPrescribe and compares its performance for implementations using different real-time streaming technology stacks. iPrescribe uses ensemble of deep learning and machine learning algorith...
Conference Paper
Full-text available
Distributed big data processing and analytics applications demand a comprehensive end-to-end architecture stack consisting of big data technologies. However, there are many possible architecture patterns (e.g. Lambda, Kappa or Pipeline architectures) to choose from when implementing the application requirements. A big data technology in isolation m...
Conference Paper
Full-text available
Spark is one of most widely deployed in-memory big data technology for parallel data processing across cluster of machines. The availability of these big data platforms on commodity machines has raised the challenge of assuring performance of applications with increase in data size. We have build a tool to assist application developer and tester to...
Conference Paper
Full-text available
The wide availability of open source big data processing frameworks, such as Spark, has increased migration of existing appli- cations and deployment of new applications to these cost-e�ective plat- forms. One of the challenges is assuring performance of an application with increase in data size in production system. We have addressed this problem...
Conference Paper
Typically, applications are tested on small data size for both functional and non functional requirements. However, in production environment, the applications, having SQL queries, may experience performance violations due to increase in data volume. There is need to have tool which could test SQL query performance for large data sizes without elon...
Conference Paper
Application and/or data migration is a result of limitations in existing system architecture to handle new requirements and the availability of newer, more efficient technology. In any big data architecture, technology migration is staggered across multiple levels and poses functional (related to components of the architecture and underlying infras...
Conference Paper
Full-text available
Nowadays applications are migrating from traditional 3-tier architecture to Big data platform which are widely available in open source and can do parallel data processing on cluster of commodity machines. The challenges are to choose the “right” available Big data framework for an application with the available features of the framework. We have p...
Conference Paper
In a production system, increase in data size will increase the execution time of the application's SQL queries and degrade its performance. Tuning SQL queries in production requires additional efforts and cost. Time constraints during application development do not permit testing SQL queries with high data volumes. Having the capability to predict...
Conference Paper
Digitization of user services and cheap access to the internet has led to two critical problems- quick response to end-user queries and faster analysis of large accumulated data to serve users better. This has also led to the advent of various big data processing technologies, each of them has architecture specific parameters to tune for optimal ex...
Article
Performance model solvers and simulation engines have been around for more than two decades. Yet, performance modeling has not received wide acceptance in the software industry, unlike pervasion of modeling and simulation tools in other industries. This paper explores underlying causes and looks at challenges that eed to be overcome to increase uti...
Conference Paper
The paradigm of big data demands either extension of existing benchmarks or building new benchmarks to capture the diversity of data and impact of change in data size and/or system size. This has led to increase in cycle time of benchmarking an application which includes multiple workloads executions on different data sizes. This paper addresses th...
Conference Paper
The first ACM international workshop on performance analysis of big data system is held in Austin, Texas, USA on February 1, 2015 and co-located with the ACM fifth International Conference on Performance Engineering (ICPE). The main objective of the workshop is to discuss the performance challenges imposed by big data systems and the different stat...
Article
In a typical database application environment, database queries have a major share in contributing to application's response time. A database query elapsed response time (ERT) primarily consists of time spent on the input/output (IO) access including storage subsystem and network transfer, and CPU processing, which changes with change in size of th...
Conference Paper
In a typical database application development, requirement is to optimize SQL queries to meet service level agreements (SLA); the optimized queries are tested on the application development database which is some fraction of the production database. As time progresses the database grows and the earlier optimized queries may not hold SLA anymore. On...
Article
Full-text available
Health is of major concern among people. There are various factors which could affect human health. In this paper we propose a framework to analyze various environmental parameters like air and water pollutants and to understand their impact on human health. The study is confined to understand the diseases which may be caused by these parameters. T...
Conference Paper
In a typical OLTP environment, emphasis has been given on promising Service level Agreements (SLAs) for perceived query elapsed response time; the SQL queries are tested on the small size of database which may be a fraction of the production database. As time progresses the database grows and the earlier optimized queries may not hold SLA anymore....
Article
Information Technology (IT) has touched and changed the lives of the younger generation in India in many ways but IT still has its role to play in making a significant impact to the quality of lives of the senior citizens of our country. This study is undertaken to address the objective of using technology to provide affordable health care and othe...
Article
This paper focuses on implementation of cascaded configuration of initiator-target pair in NetBSD environment. The use of existing independent initiator and target for cascading has some drawbacks, which can be handled by combining pair of target and initiator as proposed in this paper. We also show the performance comparisons between proposed and...
Conference Paper
This paper presents a solution for optimal business continuity, with storage architecture for enterprise applications, which shall ensure negligible data loss and quick recovery. The solution makes use of IP SAN, which are used for data management without burdening the application server, as well as replication techniques to replicate data to remot...
Conference Paper
This paper presents a framework for public healthcare by making a grid over public infrastructure such as Internet. It clearly illustrates the need and viability of such grids. The paper gives in details the technology required behind building such global health grid and the issues to overcome for building public health care grid.
Article
Full-text available
In this paper we propose a design and implementation for efficient semi-synchronous replication solution using iSCSI for disaster recovery. We replicate the data at block level to bring in efficiency. Further we use features of database application which helps in reducing the complexity and improving the performance of the disaster recovery solutio...
Article
We present a design of intelligent storage controllers in IP SAN environment to overcome the performance issues of IP SAN. The controllers are designed with clustering features to introduce parallelism thus increasing the performance of IP SAN. Also implementing the virtualization entity in controller hides the physical storage complexity. The perf...
Conference Paper
Full-text available
iSCSI [1,2], is an emerging communication protocol enabling block data transport over TCP/IP network. The iSCSI protocol is perceived as a low cost alternative to the FC protocol for networked storages [8, 9, 10, and 11]. This paper uses a storage architecture allowing parallel processing of iSCSI commands and presents two novel techniques for impr...

Network

Cited By