DataSys: Data-Intensive Distributed Systems LaboratoryData-Intensive Distributed Systems Laboratory

Illinois Institute of Technology
Department of Computer Science

NSF CAREER: Avoiding Achilles’ Heel in Exascale Computing with Distributed File Systems 

Extreme-scale computers have and will in the foreseeable future enable the unraveling of significant scientific mysteries. There are many scientific domains that have been making revolutionary advancements due to large-scale computing. The state-of-the-art storage in High-End Computing (HEC), in which storage (e.g. parallel file systems) is segregated from compute nodes and connected by a network, will not scale with the expected exponential growth in concurrency; storage has the potential to be the Achilles heel of future extreme-scale systems.

Back in 2010, the PI proposed that future large-scale systems should be designed with non-volatile solid-state memory on every compute node. Every compute node could actively participate in the metadata and data management, leveraging many-core processors and high bisection bandwidth in multi-dimensional networks. Distributed metadata management could be used, implemented in a distributed data-structure, tailored for HEC, supporting constant time operations by emphasizing trustworthy/reliable hardware, fast network interconnects, non-existent node "churn", low latencies, and scientific computing data-access patterns. The data would be partitioned and spread out over many nodes based on the data access patterns. Replication would be used to ensure data availability, cooperative caching would deliver high aggregate throughput, and data would be tracked with provenance information. There would be a variety of data-access semantics, from POSIX-like interfaces for generality and backwards compatibility, to relaxed semantics for increased scalability. This work's contribution lies in the revolutionary new storage architecture making extreme-scale compute systems viable.

This proposal can be summarized in four research and educational activities:

1) Designed, Analyzed, and Implemented a Zero-Hop Distributed Hash Table (ZHT), a light-weight distributed hash table that dynamically allows nodes to join and leave, is fault tolerant through replication, is persistent, scalable, and supports lock-free concurrent key/value modifications.

2) Designed, Analyzed, and Implemented the Fusion Distributed File System (FusionFS), leveraging research from cooperative caching, to scale to millions of nodes and billions of concurrent I/O requests, to address poor scaling workloads from parallel file systems.

3) Evaluated work through both simulations and real systems: 1) explored proposed work on real workloads and applications at thousands of node scales and tens of thousands of core scales; and 2) explored proposed work through simulations at extreme-scale levels with millions of nodes.

4) Integrate research with education spanning high-school, undergrads, and graduate students; the PI has designing three new advanced courses: 1) Introduction to Parallel and Distributed Computing, 2) Data-Intensive Distributed Computing, and 3) Cloud Computing.

The proposed shift in large-scale storage architecture design was seen as controversial back in 2010 when it was originally proposed by the PI as it required storage architectures in HEC to be redefined from their traditional architectures of the past several decades. This new approach was not feasible prior to being proposed due to the unreliable spinning disk technology that had dominated the persistent storage space since the dawn of supercomputing. However, the advancements in solid-state memory (with mean-time-to-failure of over millions of hours) opened up opportunities to rethink storage systems for HEC, distributing storage on every compute node, without sacrificing node reliability or power consumption. The benefits of this new distributed storage architecture enabled some workloads to scale near-linearly with systems scales by leveraging data locality and the full network bisection bandwidth.

This award aimed to address the storage bottleneck in future high-end computing at extreme scales. The intellectual merit of this work is the radical storage architecture departing from traditional parallel file systems. In exploring fundamental research in storage architectures suitable for large-scale computing, the PI touches a diverse set of topics ranging from distributed file systems, distributed key/value storage, distributed relational databases, distributed metadata management, burst buffers, data provenance, erasure coding, cooperative caching, and data compression. The research conducted has shown through both simulations and real systems that distributed file systems are a viable and good solution at extreme scales for a variety of workloads.

This work’s broader impact has made extreme-scale computing more tractable, touching virtually all disciplines in high-end computing, fueling scientific discovery. This work has also funded the development and teaching of new coursework in distributed systems where research was intertwined to deliver cutting edge education to over one thousand students over the course of this award. This award has funded multiple female students, as well as domestic students in funded portions of this research; two PhD students were fully supported by this award, and seven additional PhD students were partially supported by this award. Nearly 100 students (from high-school, undergraduate, master, and PhD students) were engaged in research related activities of this award with peer reviewed publications co-authorship. These students together, collaborators (from UChicago, Northwestern, DePaul, and many DOE laboratories ANL, FNAL, LANL, ORNL, LBL, and PNNL), together with the PI collectively wrote over 100 technical articles, including 4 PhD dissertations, 27 peer reviewed full-paper publications in conferences and journals, 24 peer reviewed short-paper publications in workshops and conferences, and 39 technical reports. 

This work concludes that distributed storage archtiectures are one of the key enablers for extreme-scale computing for high-performance computing, scientific computing, and cloud computing. The results of this work has outlined a blueprint of how these storage systems should be architected including clearly defining the tradeoffs on design decisions in performance, scalability, and resilience. Different storage models are investigated, such as file systems, key/value stores, and relational data-bases, each with their own strengths and weaknesses towards solving a certain sub-set of storage problems for high-end computing. Results are presented for real systems being implemented and evaluated on clusters, clouds, and supercomputers up to 8192-nodes and 32768-cores. Furthermore, extensive evaluation was conducted in simulations at up to millions of node scales. These results lay a solid foundation for future storage research and development in academia, national laboratories, and industry as computing moves towards exascale computing with an ever increasing amount of concurency. 

  

Award: $734K, 01/2011 - 06/2018; for more details, see the NSF description

Collaborators:

PhD Students (* denotes partial funding, ** denotes full funding):

 

PhD Dissertations:

  1. Iman Sadooghi, Ioan Raicu. "Scalable Resource Management in Cloud Computing", Illinois Institute of Technology, Computer Science Department, Doctorate Dissertation, September 2016

  2. Tonglin Li, Ioan Raicu. "Distributed NoSQL Storage for Extreme-SCale System Services in Supercomputers and Clouds", Illinois Institute of Technology, Computer Science Department, PhD Dissertation, 2015

  3. Dongfang Zhao, Ioan Raicu. Big Data System Infrastructure at Extreme Scales, Illinois Institute of Technology, Computer Science Department, PhD Dissertation, 2015

  4. Ke Wang, Ioan Raicu. Scalable Resource Management System Software for Extreme-Scale Distributed Systems, Illinois Institute of Technology, Computer Science Department, PhD Dissertation, 2015

 

Peer Reviewed Publications:

  1. Jason Arnold, Boris Glavic, Ioan Raicu. "A High-Performance Distributed Relational Database System for Scalable OLAP Processing", IEEE International Parallel and Distributed Processing Symposium (IPDPS) 2019

  2. Alex Ballmer, Brendan Batliner, Anna Benson, Blake Ehrenbeck, Zhen Huang, Parker Joncus, Travis Koehring, Alexandru Orhean, William Scullin, Ben Allen, Ioan Raicu. “Reaching for 100TFlops at 3KW Power with Intel Scalable Processors and NVIDIA V100 NVLINK GPUs”, Student Cluster Competition (SCC), IEEE/ACM Supercomputing/SC 2018

  3. Ioan Raicu, William Scullin, Ben Allen, Kyle Hale, Kyle Chard, Alexandru Iulian Orhean. "Breaking 100TFlops at 3KW Power with IBM Power9 and NVIDIA V100 GPUs over NVLink and 200GbE Mesh Interconnect”, Student Cluster Competition (SCC), IEEE/ACM Supercomputing/SC 2018

  4. Anna Blue Keleher, Kyle Chard, Ian Foster, Alexandru Iulian Orhean, Ioan Raicu. “Finding a Needle in a Field of Haystacks: Metadata Search for Distributed Research Repositories”, IEEE/ACM Supercomputing/SC 2017

  5. Alexandru Iulian Orhean, Itua Ijagbone, Dongfang Zhao, Kyle Chard, Ioan Raicu. “Toward Scalable Indexing and Search on Distributed and Unstructured Data”, IEEE Big Data Congress 2017

  6. Alex Ballmer, David Ghiurco, Ryan Mitchell, Ryan Prendergast, Hasan Rizvi, Iva Veseli, William Scullin, Ben Allen, Ioan Raicu. “Application Profiling and Power Management for the Student Cluster Competition”, Student Cluster Competition (SCC), IEEE/ACM Supercomputing/SC 2017

  7. Ioan Raicu, William Scullin, Ben Allen, Kyle Hale, Kyle Chard, Simone Campanoni. “Maximizing Computation per Power Ratios in High-Performance Computing: from Aggressive Power Management to Approximate Computing”, Student Cluster Competition (SCC), IEEE/ACM Supercomputing/SC 2017

  8. Jian Peng, Sughosh Divanji, Ioan Raicu, Mike Lang. “Simulating the Burst Buffer Storage Architecture on an IBM BlueGene/Q Supercomputer”, IEEE/ACM SuperComputing/SC 2016

  9. Jonathan Wu, Suraj Chafle, Ioan Raicu, Kyle Chard. “Optimizing Search in Un-Sharded Large-Scale Distributed Systems”, IEEE/ACM SuperComputing/SC 2016

  10. Alex Ballmer, Ioan Raicu. “FemtoGraph: A Pregel Based Shared-memory Graph Processing Library”, IEEE/ACM SuperComputing/SC 2016

  11. Iman Sadooghi, Geet Kumar, Ke Wang, Dongfang Zhao, Tonglin Li, Ioan Raicu. "Albatross: an Efficient Cloud-enabled Task Scheduling and Execution Framework using Distributed Message Queues", eScience 2016

  12. Dongfang Zhao, Akash Mahakode, Sandip Lakshminarasaiah, Ioan Raicu. “High-performance Storage Support for Scientific Big Data Applications on the Cloud”, Springer’s Resource Management for Big-Data Platforms: Algorithms, Modelling, and High-Performance Computing Techniques, 2016

  13. Dongfang Zhao, Ke Wang, Kan Qiao, Tonglin Li, Iman Sadooghi, Ioan Raicu. "Toward High-performance Key-value Stores through GPU Encoding and Locality-aware Encoding", Journal of Parallel and Distributed Computing, 2016 

  14. Dongfang Zhao, Kan Qiao, Zhou Zhou, Tonglin Li, Xiaobing Zhou, Ioan Raicu. “Exploiting Multi-cores for Efficient Interchange of Large Messages in Distributed Systems”, Concurrency and Computation: Practice and Experience (CCPE), 2015 (Impact Factor 1.0)

  15. Thomas Dubucq, Tony Forlini, Virgile Landeiro Dos Reis, Isabelle Santos, Ke Wang, Ioan Raicu. “Benchmarking State-of-the-art Many-Task Computing Runtime Systems”, ACM HPDC 2015

  16. Xiaobing Zhou, Tonglin Li, Ke Wang, Dongfang Zhao, Iman Sadooghi, Ioan Raicu. "MHT: A Light-weight Scalable Zero-hop MPI Enabling Distributed Hash Table", IEEE Big Data 2015

  17. Iman Sadooghi, Ke Wang, Dharmit Patel, Dongfang Zhao, Tonglin Li, Shiva Srivastava, Ioan Raicu. “FaBRiQ: Leveraging Distributed Hash Tables towards Distributed Publish-Subscribe Message Queues”, IEEE/ACM BDC 2015

  18. Tonglin Li, Ke Wang, Shiva Srivastava, Dongfang Zhao, Kan Qiao, Iman Sadooghi, Xiaobing Zhou, Ioan Raicu. "A Flexible QoS Fortified Distributed Key-Value Storage System for the Cloud", IEEE Big Data 2015

  19. Tonglin Li, Ioan Raicu. "Distributed NoSQL Storage for Extreme-Scale System Services", Doctoral Showcase, IEEE/ACM Supercomputing/SC 2015  

  20. Jason Arnold, Boris Glavic, Ioan Raicu. "HRDBMS: A NewSQL Database for Analytics", IEEE Cluster 2015 

  21. Tonglin Li, Chaoqi Ma, Jiabao Li, Xiaobing Zhou, Ke Wang, Dongfang Zhao, Iman Sadooghi, Ioan Raicu. "GRAPH/Z: A Key-Value Store Based Scalable Graph Processing System", IEEE Cluster 2015

  22. Ke Wang, Kan Qiao, Iman Sadooghi, Xiaobing Zhou, Tonglin Li, Michael Lang, Ioan Raicu. "Load-balanced and locality-aware scheduling for data-intensive workloads at extreme scales", Concurrency and Computation: Practice and Experience (CCPE) Journal 2015

  23. Dongfang Zhao , Kan Qiao , Jian Yin , and Ioan Raicu. "Dynamic Virtual Chunks: On Supporting Efficient Accesses to Compressed Scientific Data", IEEE Transaction on Service Computing (TSC) Journal 2015, Special Issue on Big Data

  24. Dongfang Zhao, Ning Liu, Dries Kimpe, Robert Ross, Xian-He Sun, and Ioan Raicu. "Towards Exploring Data-Intensive Scientific Applications at Extreme Scales through Systems and Simulations", IEEE Transaction on Parallel and Distributed Systems (TPDS) Journal 2015

  25. Tonglin Li, Xiaobing Zhou, Ke Wang, Dongfang Zhao, Iman Sadooghi, Zhao Zhang, Ioan Raicu. "A Convergence of Key-Value Storage Systems from Clouds to Supercomputers", Concurrency and Computation: Practice and Experience (CCPE) Journal 2015

  26. Ke Wang, Ning Liu, Iman Sadooghi, Xi Yang, Xiaobing Zhou, Michael Lang, Xian-He Sun, Ioan Raicu. "Overcoming Hadoop Scaling Limitations through Distributed Task Execution", IEEE Cluster 2015; 24% acceptance rate

  27. Ben Walters, Alex Ballmer, Andrei Dumitru, Adnan Haider, Serapheim Dimitropoulos, Ariel Young, William Scullin, Ben Allen, Ioan Raicu. "15 TFlops Haswell vs. 60 TFlops Knight Landing for HPC Scientific Computing Applications", Student Cluster Competition (SCC), IEEE/ACM Supercomputing/SC 2015

  28. Ke Wang, Abhishek Kulkarni, Michael Lang, Dorian Arnold, and Ioan Raicu. "Exploring the Design Tradeoffs for Extreme-Scale High-Performance Computing System Software", IEEE Transaction on Parallel and Distributed Systems (TPDS) 2015

  29. Dongfang Zhao, Xu Yang, Iman Sadooghi, Gabriele Garzoglio, Steven Timm, Ioan Raicu. "High-Performance Storage Support for Scientific Applications on the Cloud", Invited Paper, ACM ScienceCloud 2015

  30. Tonglin Li, Kate Keahey, Ke Wang, Dongfang Zhao, Ioan Raicu. "A Dynamically Scalable Cloud Data Infrastructure for Sensor Networks", Invited Paper, ACM ScienceCloud 2015

  31. Iman Sadooghi, Jesús Hernández Martin, Tonglin Li, Kevin Brandstatter, Ketan Maheshwari, Tiago Pais Pitta de Lacerda Ruivo, Gabriele Garzoglio, Steven Timm,Yong Zhao, Ioan Raicu. “Understanding the Performance and Potential of Cloud Computing for Scientific Applications”, IEEE Transaction on Cloud Computing (TCC) 2015

  32. Dongfang Zhao, Kan Qiao, Ioan Raicu. "Towards Cost-Effective and High-Performance Caching Middleware for Distributed Systems", International Journal of Big Data Intelligence (IJBDI) 2015, Special Issue on High-Performance Data Intensive Computing

  33. Dongfang Zhao and Ioan Raicu. "Storage Support for Data-Intensive Scientific Applications on the Cloud", NSFCloud Workshop on Experimental Support for Cloud Computing 2014

  34. Dongfang Zhao and Ioan Raicu. "Storage Support for Data-Intensive Applications on Extreme-Scale HPC Systems", Doctoral Showcase, IEEE/ACM Supercomputing/SC 2014

  35. Tonglin Li, Kate Keahey, Rajesh Sankaran, Pete Beckman, Ioan Raicu. “A Cloud-based Interactive Data Infrastructure for Sensor Networks”, IEEE/ACM Supercomputing/SC 2014

  36. Dongfang Zhao, Zhao Zhang, Xiaobing Zhou, Tonglin Li, Ke Wang, Dries Kimpe, Philip Carns, Robert Ross, and Ioan Raicu. "FusionFS: Towards Supporting Data-Intensive Scientific Applications on Extreme-Scale High-Performance Computing Systems", IEEE International Conference on Big Data 2014; 18% acceptance rate

  37. Ke Wang, Xiaobing Zhou, Tonglin Li, Dongfang Zhao, Michael Lang, Ioan Raicu. "Optimizing Load Balancing and Data-Locality with Data-aware Scheduling", IEEE International Conference on Big Data 2014; 18% acceptance rate

  38. Dongfang Zhao, Jian Yin, Kan Qiao, Ioan Raicu. "Virtual Chunks: On Supporting Random Accesses to Scientific Data in Compressible Storage Systems", IEEE International Conference on Big Data 2014; 18% acceptance rate

  39. Kevin Brandstatter, Jason DiBabbo, Daniel Gordon, Ben Walters, Alex Ballmer, Lauren Ribordy, Ioan Raicu. "Delivering 3.5 Double Precision GFlops/Watt and 200Gb/sec Bi-Section Bandwidth with Intel Xeon Phi-based Cisco Servers", Student Cluster Competition (SCC), IEEE/ACM Supercomputing/SC 2014

  40. Tonglin Li, Ioan Raicu, Lavanya Ramakrishnan. "Scalable State Management for Scientific Applications in the Cloud", IEEE BigData 2014; 19% acceptance rate

  41. Dongfang Zhao, Kan Qiao, Ioan Raicu. “HyCache+: Towards Scalable High-Performance Caching Middleware for Parallel File Systems”, 14th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) 2014; 19% acceptance rate

  42. Dongfang Zhao, Jian Yin, Ioan Raicu. “Improving the I/O Throughput for Data-Intensive Scientific Applications with Efficient Compression Mechanisms”, IEEE/ACM Supercomputing 2013

  43. Dongfang Zhao, Chen Shou, Tanu Malik, Ioan Raicu. “Distributed Data Provenance for Large-Scale Data-Intensive Computing”, IEEE Cluster 2013; 31% acceptance rate

  44. Dongfang Zhao, Kent Burlingame, Corentin Debains, Pedro Alvarez-Tabio, Ioan Raicu. “Towards High-Performance and Cost-Effective Distributed Storage Systems with Information Dispersal Algorithms”, IEEE Cluster 2013; 31% acceptance rate

  45. Tonglin Li, Xiaobing Zhou, Kevin Brandstatter, Dongfang Zhao, Ke Wang, Anupam Rajendran, Zhao Zhang, Ioan Raicu. “ZHT: A Light-weight Reliable Persistent Dynamic Scalable Zero-hop Distributed Hash Table”, IEEE International Parallel & Distributed Processing Symposium (IPDPS) 2013; 21% acceptance rate

  46. Dongfang Zhao, Da Zhang, Ke Wang, Ioan Raicu. “Exploring Reliability of Exascale Systems through Simulations”, ACM HPC 2013

  47. Chen Shou, Dongfang Zhao, Tanu Malik, Ioan Raicu. “Towards a Provenance-Aware a Distributed File System”, USENIX TaPP13

  48. Dongfang Zhao, Ioan Raicu. “HyCache: A User-Level Caching Middleware for Distributed File Systems”, IEEE HPDIC 2013

  49. Dongfang Zhao, Ioan Raicu. “Distributed File Systems for Exascale Computing”, Doctoral Showcase, IEEE/ACM Supercomputing/SC 2012

  50. Tonglin Li, Raman Verma, Xi Duan, Hui Jin, Ioan Raicu. “Exploring Distributed Hash Tables in High-End Computing”, ACM Performance Evaluation Review (PER), 2011

  51. I. Raicu, P. Beckman, I. Foster. “Making a Case for Distributed File Systems at Exascale”, ACM Workshop on Large-scale System and Application Performance (LSAP), 2011

 

Technical Reports:

  1. Alexandru Orhean, Kyle Chard, Ioan Raicu. “XSearch: Distributed Information Retrieval in Large-Scale Storage Systems”, Illinois Institute of Technology, Department of Computer Science, PhD Oral Qualifier, 2017

  2. Jian Peng, Michael Lang, Ioan Raicu. “Burst Buffer Simulation in Dragonfly Network”, Illinois Institute of Technology, Department of Computer Science, PhD Oral Qualifier, 2017

  3. Itua Ijagbone, Ioan Raicu (advisor). "Scalable Indexing and Searching on Distributed File Systems", Department of Computer Science, Illinois Institute of Technology, MS Thesis, 2016

  4. Itua Ijagbone, Shivakumar Vinayagam, David Pisanski, Kevin Brandstatter, Dongfang Zhao, Ioan Raicu. "Towards Scalable Searching of Distributed File Systems", GCASR 2016    

  5. Mermer Dupree, Mike Wilde, Justin Wozniak, Ioan Raicu. "Optimizing Data Locality with Swift/T and FusionFS", GCASR 2016 

  6. Iman Sadooghi, Ioan Raicu. "Scalable Resource Management in Cloud Computing", Illinois Institute of Technology, Computer Science Department, PhD Proposal, 2015

  7. Jason Arnold, Boris Glavic, Ioan Raicu. "HRDBMS: Combining the Best of Modern and Traditional Relational Databases", Illinois Institute of Technology, Department of Computer Science, PhD Oral Qualifier, 2015  

  8. David Pisanski, Kevin Brandstatter, Dongfang Zhao, Calin Segarceanu, Ioan Raicu. "Enabling Distributed Data Indexing and Search in the FusionFS Distributed File System", Illinois Institute of Technology, Department of Computer Science, Technical Report, 2015

  9. Ariel Young, Ioan Raicu. "HPC Power Management on Haswell CPU Architecture", Illinois Institute of Technology, Department of Computer Science, Technical Report, 2015

  10. Mermer Dupree, Justin M. Wozniak, Michael Wilde, Ioan Raicu. "Optimizing Data Locality between the Swift Parallel Programming System and the FusionFS Distributed File System", Illinois Institute of Technology, Department of Computer Science, Technical Report, 2015  

  11. Tonglin Li, Chaoqi Ma, Jiabao Li, Ioan Raicu. "ZHT+: A Graph Database On ZHT", Illinois Institute of Technology, Department of Computer Science, Technical Report, 2015

  12. Sughosh Divanji, Raghav Kapoor, Dongfang Zhao, Ioan Raicu. "PVFS simulation using CODES/ROSS simulator", Illinois Institute of Technology, Department of Computer Science, Technical Report, 2015

  13. Kevin Brandstatter, Ben Walters, Alexander Ballmer, Adnan Haider, Andrei Dumitru, Serapheim Dimitropoulos, Ariel Young, William Scullin, Ben Allen, Ioan Raicu. "Experiences in Optimizing Cluster Performance For Scientific Applications: Controlling Configuration, Utilization, and Power Consumption", GCASR 2015

  14. Tonglin Li, Ioan Raicu. "A Convergence of NoSQL Storage Systems from Clouds to Supercomputers", Illinois Institute of Technology, Computer Science Department, PhD Proposal, 2014 

  15. Dongfang Zhao, Ioan Raicu. "Towards Supporting Data-Intensive Scientific Applications on Extreme-Scale High-Performance Computing Systems," Illinois Institute of Technology, Computer Science Department, PhD Proposal, 2014

    16.

  16. Kiran Ramamurthy, Ioan Raicu. "Exploring Distributed HPC Scheduling with Randomized Resource Stealing", 3rd Greater Chicago Area System Research Workshop (GCASR), 2014 (poster)

  17. Ke Wang, Ioan Raicu. "Achieving Data-Aware Load Balancing through Distributed Queues and Key/Value Stores", 3rd Greater Chicago Area System Research Workshop (GCASR), 2014 (poster)

  18. Ioan Raicu. "Towards Data-Intensive Extreme-Scale Computing", NSF CyberBridges Workshop, 2014 (poster)

  19. Dongfang Zhao, Ioan Raicu. "Exploring Data Compression in Distributed File Systems", Illinois Institute of Technology, Department of Computer Science, Technical Report, 2013

  20. Kun Feng, Tianyang Che, Tonglin Li, Ioan Raicu. "OHT: Hierarchical Distributed Hash Tables", Illinois Institute of Technology, Department of Computer Science, Technical Report, 2013

  21. Shukun Xie, Ran Xin, Tonglin Li, Ioan Raicu. "Exploring Eventual Consistency Support in ZHT", Illinois Institute of Technology, Department of Computer Science, Technical Report, 2013

  22. Dongfang Zhao, Ioan Raicu. Supporting Large Scale Data-Intensive Computing with the FusionFS Distributed File System, Illinois Institute of Technology, Department of Computer Science, Technical Report, 2013

  23. Ioan Raicu. “Distributed Storage Systems for Extreme-Scale Data-Intensive Computing”, NSF CyberBridges Workshop, 2013 (poster)

  24. Tonglin Li, Xiaobing Zhou, Kevin Brandstatter, Ioan Raicu. "Distributed Kev-Value Store on HPC and Cloud Systems", 2nd Greater Chicago Area System Research Workshop (GCASR), 2013 (poster)

  25. Dongfang Zhao, Chen Shou, Zhao Zhang, Iman Sadooghi, Xiaobing Zhou, Tonglin Li, Ioan Raicu. "FusionFS: a distributed file system for large scale data-intensive computing", 2nd Greater Chicago Area System Research Workshop (GCASR), 2013 (poster)

  26. Kevin Brandstatter, Tonglin Li, Xiaobing Zhou, Ioan Raicu. "NoVoHT: a Lightweight Dynamic Persistent NoSQL Key/Value Store", 2nd Greater Chicago Area System Research Workshop (GCASR), 2013 (poster)

  27. Chen Shou, Dongfang Zhao, Tanu Malik, Ioan Raicu. "Towards a Provenance-aware Distributed Filesystem", 2nd Greater Chicago Area System Research Workshop (GCASR), 2013 (poster)

  28. Corentin Debains, Pedro Alvarez-Tabio, Dongfang Zhao, Kent Burlingame, Ioan Raicu. "IStore: Towards High Efficiency, Performance, and Reliability in Distributed Data Storage with Information Dispersal Algorithms", Illinois Institute of Technology, Department of Computer Science, Technical Report, 2013 

  29. Tonglin Li, Ioan Raicu. "ZHT: a Zero-hop DHT for High-End Computing Environment", Illinois Institute of Technology, Department of Computer Science, PhD Oral Qualifier, 2012

  30. Dongfang Zhao, Ioan Raicu. "HyCache: A Hybrid User-Level File System with SSD Caching", Illinois Institute of Technology, Department of Computer Science, PhD Oral Qualifier, 2012

  31. Kevin Brandstatter, Ioan Raicu. “CiteSearcher: A Google Scholar frontend for Mobile Devices", Illinois Institute of Technology Research Day, 2012 (Poster)

  32. Ioan Raicu. “Building Blocks for Scalable Distributed Storage Systems”, NSF CyberBridges Workshop, 2012 (poster)

  33. Tonglin Li, Antonio Perez De Tejada, Kevin Brandstatter, Zhao Zhang, Ioan Raicu. “ZHT: a Zero-hop DHT for High-End Computing Environment”, 1st Greater Chicago Area System Research Workshop, 2012 (poster)

  34. Corentin Debains, Pedro Manuel Alvarez-tabio Togores, Ioan Raicu. “Evaluating Information Dispersal Algorithms”, 1st Greater Chicago Area System Research Workshop, 2012 (poster)

  35. Dongfang Zhao, Ioan Raicu. “HyCache: A Hybrid User-Level File System with SSD Caching”, 1st Greater Chicago Area System Research Workshop, 2012 (poster)

  36. Da Zhang, Ioan Raicu. "SimHEC: Simulator for High-End Computing Systems”, 1st Greater Chicago Area System Research Workshop, 2012 (poster)

  37. Dongfang Zhao, Ioan Raicu. "HyCache: A Hybrid User-Level File System with SSD Caching", Illinois Institute of Technology, Department of Computer Science, PhD Oral Qualifier, 2012

  38. Tonglin Li, Ioan Raicu. "ZHT: a Zero-hop DHT for High-End Computing Environment", Illinois Institute of Technology, Department of Computer Science, PhD Oral Qualifier, 2012

  39. Jesús Hernández Martin, Ioan Raicu. "Performance evaluation of AWS: Exploring storage alternatives in Amazon Web Services", Illinois Institute of Technology, Department of Computer Science, Technical Report, 2012