Related papers: P4DB -- The Case for In-Network OLTP (Extended Tec…
Current high-performance computer systems used for scientific computing typically combine shared memory computational nodes in a distributed memory environment. Extracting high performance from these complex systems requires tailored…
Data loading can dominate deep neural network training time on large-scale systems. We present a comprehensive study on accelerating data loading performance in large-scale distributed training. We first identify performance and scalability…
While traditional RDBMSes offer a lot of advantages, they require significant effort to setup and to use. Because of these challenges, many data scientists and analysts have switched to using alternative data management solutions. These…
Distributed computing frameworks such as MapReduce are often used to process large computational jobs. They operate by partitioning each job into smaller tasks executed on different servers. The servers also need to exchange intermediate…
Near-data processing (NDP) refers to augmenting memory or storage with processing power. Despite its potential for acceleration computing and reducing power requirements, only limited progress has been made in popularizing NDP for various…
In this paper, we introduce a task-data orchestration abstraction that supports a range of distributed applications, including graph processing and key-value stores. Given a batch of lambda tasks each requesting one or more data items,…
Due to the ever increasing importance of the internet, interoperability of heterogeneous data sources is as well of ever increasing importance. Interoperability can be achieved e.g. through data integration and data exchange. Common to both…
In this paper we analyze the problem of optimal task scheduling for data centers. Given the available resources and tasks, we propose a fast distributed iterative algorithm which operates over a large scale network of nodes and allows each…
Power management in multi-server data centers~especially at scale is a vital issue of increasing importance in cloud computing paradigm. Existing studies mostly consider thresholds on the number of idle servers to switch the servers on or…
Persistent or Non Volatile Memory (PMEM or NVM) has recently become commercially available under several configurations with different purposes and goals. Despite the attention to the topic, we are not aware of a comprehensive empirical…
Distributed computing has become a common practice nowadays, where the recent focus has been given to the usage of smart networking devices with in-network computing capabilities. State-of-the-art switches with near-line rate computing and…
Traditionally, when the code of a database management system (DBMS) needs to be updated, the system is restarted and database clients suffer downtime, or the provider instantiates hot-standby instances and rolls over the workload. We…
As real-time analysis of the new data become increasingly compelling, more organizations deploy Hybrid Transactional/Analytical Processing (HTAP) systems to support real-time queries on data recently generated by online transaction…
With the explosive growth of big data, workloads tend to get more complex and computationally demanding. Such applications are processed on distributed interconnected resources that are becoming larger in scale and computational capacity.…
Leadership computing facilities around the world support cutting-edge scientific research across a broad spectrum of disciplines including understanding climate change, combating opioid addiction, or simulating the decay of a neutron. While…
Motivated by the need to extract knowledge and value from interconnected data, graph analytics on big data is a very active area of research in both industry and academia. To support graph analytics efficiently a large number of in memory…
Distributed Complex Event Processing has emerged as a well-established paradigm to detect situations of interest from basic sensor streams, building an operator graph between sensors and applications. In order to detect event patterns that…
Complex scientific experiments from various domains are typically modeled as workflows and executed on large-scale machines using a Parallel Workflow Management System (WMS). Since such executions usually last for hours or days, some WMSs…
Many algorithms for congestion control, scheduling, network measurement, active queue management, security, and load balancing require custom processing of packets as they traverse the data plane of a network switch. To run at line rate,…
Recent increase in energy prices has led researchers to find better ways for capacity provisioning in data centers to reduce energy wastage due to the variation in workload. This paper explores the opportunity for cost saving utilizing the…