Computer Systems @ Colorado

ASPIRE—Advancing Sustainability through Powered Infrastructure for Roadway Electrification

2020-11-15T00:00:00+00:00

CU Boulder will play a major role in a new center focused on developing infrastructure and systems that facilitate the widespread adoption of electric vehicles.

ASPIRE—Advancing Sustainability through Powered Infrastructure for Roadway Electrification will explore a diverse range of transportation questions, from electrified highways that energize vehicles to the placement of charging stations, data security and workforce development.

“We need to understand the factors that are impacting the development and adoption of this technology so that we’re solving the right problems,” said Qin (Christine) Lv, ASPIRE’s CU Boulder campus director and co-Principal Investigator of the Engineering Research Center.

nder research, ASPIRE will focus on transportation, adoption, power and data. When this proposal was first presented to Lv, she saw great potential for data analytics research and application.

“If you look at all these pieces, there are a lot of data—and data really can play a very important role in terms of connecting the different components together,” said Lv, who will lead the data research thrust within ASPIRE.

Data is important for electrifying transportation not only because it can help plan how much charge is available at which charging stations and when, but where they should be built, based on traffic data, consumer preferences and more.

“We’re looking at various kinds of scenarios where you can get data and leverage data to analyze the patterns, to optimize or plan and also to improve the performance of the system,” said Lv.

Data security is also important to protect charging infrastructures and individual vehicles from malicious attacks.

CU Boulder faculty from multiple departments within the College of Engineering and Applied Science are involved with ASPIRE.

Sequoia paper is accepted to SoCC’20

2020-09-01T00:00:00+00:00

Ali Tariq, Austin Pahl, Sharat Nimmagadda, Eric Rozner, and Siddharth Lanka recently had a paper accepted at the ACM Symposium on Cloud Computing (SoCC) 22020. The paper presents Sequioa, a new quality-of-service function scheduling and allocation framework that allows developers or administrators to easily define how serverless functions and applications should be deployed, capped, prioritized, or altered based on easily configured, flexible policies.

Spectrum Initiative Institute Planning

2020-09-01T00:00:00+00:00

The University of Colorado was awarded a planning grant for the National Spectrum Initiative Institute. The NSF SII will be a multi-year center that focuses on access to spectrum for wireless systems and science uses of that spectrum such as radio-astronomy adn earth observation. The SII-Center will serve as a focal point for sustained spectrum research in the most challenging areas that are expected to create advanced wireless technologies and systems that benefit society, of which 5G and future cellular networks are an example. The SII-Center is also expected to educate and develop an agile workforce needed to support industries of the future which will rely heavily on wireless technologies and will require new advanced and automated spectrum management techniques. NSF’s goal is to promote transformative use and management of the electromagnetic spectrum, with resulting profound benefits for science and engineering, industry, and other national interests.

During the planning process, faculty at CU will be working with the wireless, spectrum and science community to define a research agenda in spectrum coexistance, new radio and antenna devices and management frameworks to allow coexistance with science and space applications.

FluidMem paper is accepted to ICDCS’20

2020-04-01T00:00:00+00:00

Blake Caldwell, Sepideh Goodarzy, Youngbin Im, Sangtae Ha, Richard Han, Eric Keller, and Eric Rozner recently had a paper accepted at the IEEE International Conference on Distributed Computing Systems (ICDCS) 2020. The paper, titled “FluidMem: Full, Flexible, and Fast Memory Disaggregation for the Cloud,” presents a new approach to memory disaggregation that leverages the user-fault mechanism in Linux to achieve full memory disaggregation in software.

Award-winning work at HotMobile’20

2020-03-06T00:00:00+00:00

The CU Systems Lab recently attended HotMobile 2020. Professor Eric Rozner and his student, Shazal Irshad, won the Best Poster Award for their work “Rethinking Wireless Network Management Through Sensor-driven Contextual Analysis.” Shazal presented a paper on the same subject to a lively audience. Eric served on a Junior Faculty/Researcher Panel and also served as a Session Chair. Professor Christine Lv was TPC chair and helped organize the workshop.

Tam Vu Named Sloan Fellow

2020-02-12T00:00:00+00:00

Assitant Professor Tam Vu was named a 2020 Sloan Fellow.

The Sloan Research Fellowships are awarded annually by the Alfred P. Sloan Foundation since 1955 to “provide support and recognition to early-career scientists and scholars”. This program is one of the oldest of its kind in the United States (See more information on Wikipedia).

Paper accepted at USENIX Symp. on Networked Systems Design and Implementation (NSDI’20)

2020-02-11T00:00:00+00:00

The paper “FileMR: Rethinking RDMA Networking for Scalable Persistent Memory” by Jian Yang (UC San Diego) Joseph Izraelevitz (CU Boulder) and Steven Swanson (UC San Diego) has been accepted to the USENIX Symp. on Networked Systems Design and Implementation (NSDI’20). The paper describes extensions to the RDMA network protocol for integration with persistent memory technologies.

Jason Zhang takes 2nd Place in CU’s Three Minute Thesis

2020-02-01T00:00:00+00:00

Jason Zhang, one of our CS PhD students in the finals presented his work on Building Bridges Between Groups and Reducing Polarization at the three minute thesis competition.

He did an excellent job and earned second place in the competition earning a $750 prize that he can apply towards his research. Jason is co-advised by Christine Liu and Chenhao Tan and works closely with Rick Han and Shivakant Mishra.

Paper accepted at ACM Intl. Conf. on Architectural Support for Programming Languages and Operating Systems (ASPLOS’20)

2020-01-06T00:00:00+00:00

The paper “Pronto: Easy and Fast Persistence for Volatile Data Structures” by Amirsaman Memaripour (UC San Diego) Joseph Izraelevitz (CU Boulder) and Steven Swanson (UC San Diego) has been accepted to the 2020 ACM Intl. Conf. on Architectural Support for Programming Languages and Operating Systems (ASPLOS’20). The paper describes methods for migrating existing data structures to use persistent memory.

Paper accepted at USENIX Conf. on File and Storage Technologies (FAST’20)

2019-12-11T00:00:00+00:00

The paper “An Empirical Guide to the Behavior and Use of Scalable Persistent Memory” by Jian Yang (UC San Diego), Juno Kim (UC San Diego), Morteza Hoseinzadeh (UC San Diego), Joseph Izraelevitz (CU Boulder) and Steve Swanson (UC San Diego) has been accepted to the 2020 USENIX Conf. on File and Storage Technologies (FAST’20). The paper describes practical guidelines for gaining optimal performance from Intel’s new Optane Persistent Memory.