Výsledky vyhledávání - "Balasubramanian, Arjun"

Report

Accelerating Deep Learning Inference via Learned Caches

Autor: Balasubramanian, Arjun, Kumar, Adarsh, Liu, Yuhan, Cao, Han, Venkataraman, Shivaram, Akella, Aditya

Deep Neural Networks (DNNs) are witnessing increased adoption in multiple domains owing to their high accuracy in solving real-world problems. However, this high accuracy has been achieved by building deeper networks, posing a fundamental challenge t

Externí odkaz: http://arxiv.org/abs/2101.07344

Zobrazit plný text záznamu

Report

Accelerating Deep Learning Inference via Freezing

Autor: Kumar, Adarsh, Balasubramanian, Arjun, Venkataraman, Shivaram, Akella, Aditya

Over the last few years, Deep Neural Networks (DNNs) have become ubiquitous owing to their high accuracy on real-world tasks. However, this increase in accuracy comes at the cost of computationally expensive models leading to higher prediction latenc

Externí odkaz: http://arxiv.org/abs/2002.02645

Zobrazit plný text záznamu

Report

Archipelago: A Scalable Low-Latency Serverless Platform

Autor: Singhvi, Arjun, Houck, Kevin, Balasubramanian, Arjun, Shaikh, Mohammed Danish, Venkataraman, Shivaram, Akella, Aditya

The increased use of micro-services to build web applications has spurred the rapid growth of Function-as-a-Service (FaaS) or serverless computing platforms. While FaaS simplifies provisioning and scaling for application developers, it introduces new

Externí odkaz: http://arxiv.org/abs/1911.09849

Zobrazit plný text záznamu

Report

Themis: Fair and Efficient GPU Cluster Scheduling

Autor: Mahajan, Kshiteej, Balasubramanian, Arjun, Singhvi, Arjun, Venkataraman, Shivaram, Akella, Aditya, Phanishayee, Amar, Chawla, Shuchi

Modern distributed machine learning (ML) training workloads benefit significantly from leveraging GPUs. However, significant contention ensues when multiple such workloads are run atop a shared cluster of GPUs. A key question is how to fairly apporti

Externí odkaz: http://arxiv.org/abs/1907.01484

Zobrazit plný text záznamu

Akademický článek

Clinico-Pathological Profile of Adnexal Torsion Cases: A Retrospective Analysis from A Tertiary Care Teaching Hospital

Autor: Kandasamy. Vijayalakshmi, Gopireddy. Murali Mohan Reddy, Vasantha Nagamma Subbiah, Saktivel Sathiya, Balasubramanian. Arjun

Publikováno v: Journal of Clinical and Diagnostic Research, Vol 8, Iss 6, Pp OC04-OC07 (2014)

Introduction: Torsion of the adnexa is a rare condition which can be potentially lethal for the women. The clinical presentation can be varied and can be seen in any age group. Understanding the clinical and pathological profile of patients suffer

Externí odkaz: https://doaj.org/article/2dbc6eb38ee7491c9418ee93077a2391