November 2023
Sara McAllister Named
EECS Rising Star!
PDL PhD student, Sara McAllister (Computer Science), advised by Nathan Beckmann and Greg Ganger was named an EECS Rising Star for her work exploring Efficient and Sustainable Data Retrieval Systems: Zettabytes of data, mostly stored in massive, hyperscale datacenters enable much of today's modern computing. However, datacenters are projected to account for 33% of the global carbon emissions by 2050. While most datacenters are moving to renewable energy, the majority of their emissions are not from energy generation, but rather from embodied emissions, generated from lifecycle events like manufacturing and mining raw materials. One key way to reduce embodied emissions is to increase device lifetime. Unfortunately, extending the lifetime of storage is challenging because storage hardware becomes less reliable with both lifetime and IO accesses. Their research focuses on how to reduce IO to enable longer storage-device lifetimes, thus enabling sustainable datacenter storage.
Rising Stars is an intensive workshop for graduate students and postdocs with historically marginalized or underrepresented genders who are interested in pursuing academic careers in electrical engineering, computer science, and artificial intelligence and decision-making. Launched at MIT in 2012, the annual event has since been hosted at the University of California at Berkeley, Carnegie Mellon University, Stanford University, and the University of Illinois at Urbana-Champaign.
November 2023
Niraj Tolia Receives 2023 Parallel Data Lab Distinguished Alumni Award
Carnegie Mellon University’s Parallel Data Lab (PDL) has recognized Niraj Tolia (BS '02, MS '03, Ph.D. '07), CEO and Co-Founder of Alcion, as the recipient of its 2023 Distinguished Alumni Award. PDL announced the honor at its 29th Annual Workshop and Retreat, held November 6-8 at the Omni Bedford Springs Resort in Bedford, PA. Read more...
-- Michael Cunningham, CyLab New, Nov. 16, 2023
November 2023
MICRO Hall of Famers!
Congratulations to CSD faculty members Todd Mowry and Nathan Beckmann for being inducted into the MICRO Hall of Fame, which recognizes authors who have had eight or more papers published in ACM SIGMICRO.
-- from OpenSource (A Weekly SCS Roundup), Nov 6, 2023
August 2023
PIM-Tree Awarded Best Research Paper Runner-up at VLDB!
Congratulations to Yiwei Zhao, Charles McGuffey, Phil Gibbons and their co-authors on receiving the best paper runner up award at VLDB! Their paper "PIM-tree: A Skew-resistant Index for Processing-in-Memory" discusses
solutions to mitigate the bottleneck induced by the memory latency/bandwidth wall in memory indexing by enabling low-latency memory access whose aggregate memory bandwidth scales with the number of PIM nodes.
August 2023
Juncheng Yang and Mohammad Bakshalipour Among the ML Commons Rising Stars!
Congratulations to Juncheng and Mohammad, who have been listed among a stellar group of 35 current and recently graduated PhD students in the inaugural ML Commons Rising Stars cohort! These students, who work in the intersection of Machine Learning and Systems research have been chosen from among over 100 applicants globally. The students will be able to present their research to industry and academic experts and establish collaboration among their fellows, promoting diversity in the ML/systems research community. Juncheng's and Mohammad's first involvement with the group will be a workshop at Google this month where the students will showcase their work and meet their fellows. Juncheng is advised by Rashmi Vinayak and will be discussing his work on "GL-Cache: Group-level Learning for Efficient and High-performance Caching" at the workshop. Mohammad is advised by Phil Gibbons and is presenting his research on "Bridging Robotics and Architecture." Read more about the ML Commons Rising Star program at https://mlcommons.org/en/news/rising-stars-2023/.
July 2023
Two PDL Faculty Receive NSF CAREER Awards!
Congratulations to Dimitrios Skarlatos and Zhihao Jia on receiving NSF Career Awards!
Zhihao Jia, an assistant professor in the Computer Science Department (CSD), received an NSF CAREER award to explore an automated, end-to-end approach to building efficient, scalable and sustainable machine learning (ML) systems for diverse applications and hardware platforms. Deploying ML models requires significant manual effort to ensure optimal performance. Jia will study methods for replacing manually designed performance optimizations with automated generation, verification and application processes. Jia's work could reduce the energy consumption and financial cost of modern machine learning techniques.
Dimitrios Skarlatos, an assistant professor in CSD, received an NSF CAREER award to design and build a virtual memory abstraction that is scalable, heterogenous and secure to meet the current breadth of data center computing. Virtual memory is a cornerstone abstraction of modern computing systems that enables virtualization, programmability and isolation of memory resources. However, existing virtual memory mechanisms were not designed for the current era of data center computing and its ample memory capacity, plethora of heterogeneous hardware resources, and abstraction-breaking security vulnerabilities. Skarlatos' research will address these challenges to create more efficient, sustainable and secure data centers.
-- from CMU News, July 19, 2023
July 2023
Rashmi Vinayak Named Goldsmith Lecturer
Congratulations to Rashmi, a professor of computer science and faculty member of the PDL, who was named the 2023 Goldsmith Lecturer by the IEEE Information Theory Society for her professional and technical achievements in data systems. The Goldsmith Lecturer Program highlights the technical achievements of early-career researchers and helps build their professional career and recognition. The program contributes to the public visibility of the chosen lecturer and seeks to increase the diversity of IEEE. Vinayak, an assistant professor in the Computer Science Department, studies information and coding theory, computer and networked systems, and where these fields intersect. She currently focuses on robustness and resource efficiency in data systems, including storage and caching systems, systems for machine learning, and live-streaming communication. Vinayak will deliver a lecture at one of the IEEE Information Theory Society’s Schools of Information Theory. These short workshops introduce students to new research frontiers in information theory. More information is available in the IEEE Information Theory Society’s newsletter.
-- info from The Piper, by Aaron Aupperlee, July 25, 2023
June 2023
Best Paper Award at ISCA '23!
Congratulations to Kaiyang Zhao, Dimitrios Skarlatos, and alum Ziqi Wang on winning the Best Paper Award at ISCA '23 this June in Orlando, Florida! Their paper "Contiguitas: The Pursuit of Physical Memory Contiguity in Datacenters" explores Contiguitas, a novel redesign of memory management in the operating system and hardware that provides ample physical memory contiguity. To boost physical memory contiguity Contiguitas first separates regular movable allocations from unmovable ones by placing them into two different continuous regions in physical memory and dynamically adjusts the boundary of the two regions based on memory demand.
June 2023
Sara Mahdizadeh Shahri Awarded K & L Gates Presidential Fellowship
Congratulations to Sara Mahdizadeh Shahri, a PDL and CMU doctoral student on being selected to receive a 2023-24 K & L Gates Presidential Fellowship. Sara is a Ph.D. student in electrical and computer engineering and her research, which bridges computer architecture and software systems, aims to introduce equity in the context of data center systems. The fellowship provides financial support to four doctoral students, enabling them to further their studies on ethical and policy issues surrounding artificial intelligence.
Sara notes: “Existing data center systems are fundamentally inequitable in several ways. So, it is critical to systematically analyze when such prioritization-based solutions can cause biases, compromising equity. I am excited about my research as I believe it can provide a basis of such analysis in the context of data centers, and consequently enable a data center design paradigm that prevents discrimination against users from under-resourced communities.”
-- info from Carnegie Mellon University News, June 16, 2023 by Kelly Saavedra.
May 2023
Kuchnik, Smith, and Amvrosiadis Receive Outstanding Paper at MLSys 2023!
Congratulations to Micheal, Virginia and George on receiving the award for Outstanding Paper at MLSys, held this year in Miami Beach, FL, for their paper "Validating Large Language Models with ReLM." The paper introduces ReLM, a system for validating and querying LLMs using standard regular expressions. ReLM formalizes and enables a broad range of language model evaluations, reducing complex evaluation rules to simple regular expression queries.
May 2023
Akshitha Sriraman is Rethinking Datacenters
Today’s technology would not exist without datacenters. Six in 10 people use modern web services such as social media, web search, video streaming, online banking, and online healthcare that require datacenters that scale to hundreds of thousands of high-end computers or servers. Akshitha Sriraman, assistant professor of electrical and computer engineering, is rethinking datacenter computing across hardware and software systems to enable efficient, sustainable, and equitable large-scale web systems.
Current datacenters house thousands of servers that hold information and route signals for billions of users. With the surge of devices and users coming online daily and the growing amount of data being exchanged, the demand for faster, more efficient cloud services is drastically increasing. With this increase in demand, the logical answer is to keep building larger and more datacenters. However, this is not sustainable in the long-term. Not only are these colossal datacenters extremely expensive to build and maintain, but their carbon footprint is massive. Akshitha and her colleagues are "redesigning datacenters from first principles, thinking about what these servers should look like at the hardware level in a way that they can be cost- and energy-efficient. To enable sustainable datacenters, we must carbon-efficiently architect and manufacture hardware and make the most out of existing hardware. Datacenters must adopt the mindset of reducing, reusing, and recycling hardware.”
-from Carnegie Mellon Engineering News, May 16, 2023 - Krista Burns
May 2023
CyLab Faculty and PDL Alumni Earn ‘Test of Time’ Awards at IEEE Symposium on Security and Privacy
At its 44th Symposium on Security and Privacy, the IEEE recognized a paper by CMU/CyLab/PDL faculty and alumni with a 'Test of Time award' for the paper "Guess Again (and Again and Again): Measuring Password Strength by Simulating Password-Cracking Algorithms" (2012). The ‘Test of Time’ award recognizes published papers previously presented at the annual symposium that have had a broad and lasting impact on both research and practice in computer security and privacy.
In the paper, researchers Patrick Gage Kelley, Saranga Komanduri, Michelle L. Mazurek, Richard Shay, Timothy Vidas, Lujo Bauer, Nicolas Christin, Lorrie Faith Cranor, and Julio Lopez analyzed 12,000 passwords collected under seven composition policies and developed an efficient distributed method for calculating how effectively several heuristic password-guessing algorithms guessed passwords. The study advanced the understanding of both password-composition policies and metrics for quantifying password security.
-- from CyLab News, May 23, 2023 - Ryan Noone
April 2023
Lorrie Cranor Named University Professor
School of Computer Science faculty member Lorrie Faith Cranor has been elevated to the rank of University Professor, the highest distinction a faculty member can receive at Carnegie Mellon University. Distinguished by international recognition and for their contributions to education, artistic creativity and/or research, University Professors exemplify a high level of achievement and commitment to the university and the broader academic communities.
Cranor is the director and Bosch Distinguished Professor in Security and Privacy Technologies of CyLab and the FORE Systems Professor of Computer Science and of Engineering and Public Policy. She co-founded and co-directs the world's first privacy engineering master's program and was a founding co-director of the Collaboratory Against Hate: Research and Action Center. Her research focuses on usable privacy and security with contributions in a variety of areas, including antiphishing technologies, usable and secure password policies, privacy "nutrition" labels, and tools to make it easier for people to protect their privacy and security. She founded the Symposium on Usable Privacy and Security and co-founded the Conference on Privacy Engineering Practice and Respect.
-- from School of Computer Science News, April 28, 2023 - Christa Cardone and Kristen Bayley
March 2023
Distinguished Paper Award at ASPLOS '23!
Congratulations to PDL Alums Huaicheng Li and Daniel Berger on being awarded the Distinguished Paper Award for their research on "Pond: CXL-Based Memory Pooling Systems for Cloud Platforms" at ASPLOS '23, held in March in Vancouver, BC, Canada. The paper discusses memory pooling to improve DRAM utilization and thereby reduce costs. Pond is the first memory pooling system that both meets cloud performance goals and significantly reduces DRAM cost.
February 2023
Rashmi Vinayak Earns 2023 Sloan Research Fellowship
Congratulations to Rashmi Vinayak, who has earned a 2023 Sloan Research Fellowship in recognition of her research accomplishments. She is among 125 early career researchers from 54 institutions to receive the award from the Alfred P. Sloan Foundation.
"Sloan Research Fellows are shining examples of innovative and impactful research," said Adam F. Falk, president of the Alfred P. Sloan Foundation. "We are thrilled to support their groundbreaking work and we look forward to following their continued success."
Rashmi Vinayak is an assistant professor in the Computer Science Department (CSD). Her current work focuses on increasing reliability and efficiency in robust data systems by combining information and coding theory. Phillip Gibbons, a professor in CSD and the Department of Electrical and Computer Engineering, nominated Vinayak for the fellowship. Vinayak will receive a two-year, $75,000 fellowship that can be used flexibly to advance her research. To read more about the 2023 Sloan Research Fellows, visit the foundation's website.
-- from SCS News, Feb. 17, 2023. Aaron Aupperlee
November 2022
CMU Professors Awarded NSF Future of Work Grant
An NSF Future of Work grant is designed to increase opportunities for U.S. workers and generate positive societal and economic impacts both locally and nationally, will fund a project that will investigate how AI-augmented learning can help accelerate student progress in community college information technology (IT) courses. This will in turn provide pathways to family-sustaining careers by making more comprehensive technical education accessible to students. The project team of "A New Bridge to the Digital Economy: Integrated AI-Augmented Learning and Collaboration" includes SCS faculty members Carolyn Rose, Majd Sakr, Lauren Herckis and Bruce McLaren. The SCS team, working in conjunction with The Community College of Allegheny County, will use not only decades of research into computer- and technology-assisted learning science but also the latest developments in the field to enhance lessons.
-- from School of Computer Science News Nov 21, 2022 - Aaron Aupperlee and Heinz College
More PDL News here.