Software Platform for Big Data and Artificial Intelligence

As data is getting bigger and smart, the software platform to handle and analyze data either in real-time or off-line has become a crucial component for big data processing. Two important design challenges for building big data analytics and artificial intelligence are how to design the platforms efficiently and how to scale them with high performance. We are currently evaluating various software platforms for big data analytics and artificial intelligence. We are also investigating algorithms and techniques to improve the performance and to scale the platform.  

        - Big data processing using cloud (Machine Learning cloud), GPUs and multicore CPUs

        - Scheduling framework for machine learning workloads
        - Performance optimization of machine learning clusters
        - Distributed machine learning
        - Scalability analysis and workload characterization of big data analytics engine

        - Evaluation and scalability analysis of in-memory platform such as Spark

        - Real-time and in-stream processing of big data

Cloud/Edge Computing & Software Defined Infrastructure

Software Defined Infrastructure (SDI) is an infrastructure where computing, networking, and storage resources are all virtualized and managed entirely by software. This infrastructure basically combines the concepts of Cloud Computing, Software Defined Networking (SDN), Network Function Virtualization (NFV) and Software Defined Storage (SDS). Virtualization technologies (server virtualization, network virtualization, and storage virtualization) and efficient management of their resources are central to implementing this environment. Followings are the research topics we are currently investigating in our lab:

        - Virtualization techniques (CPU/Network/Storage)
        - Hypervisors (Xen, VMWare, KVM, etc.) and Containers (Docker, etc)
        - Resource provisioning, management, and optimization in cloud computing
        - GPU virtualization and HPC over Cloud
        - Scalable controller architecture and network resource optimization in SDN
        - NFV architecture and service chaining mechanism
        - Data Plane Acceleration using Intel DPDK and SPDK
        - Edge and Fog computing (Scheduling and Load balancing)

Software Supports for Multicore/Manycore Processors

The rapid advance in semiconductor technology has created an opportunity so that the number of cores both in a single chip (multicore) and across the bus (manycore) keeps increasing dramatically. The recent introduction of Intel’s MIC technology (Xeon Phi) has also added a lot of complexity to the software running over these processors. In order to fully utilize this environment, the software (from OS and system software to application software) running over the multicore/manycore processors should be optimized to get the performance benefits provided by this powerful hardware. We are currently investigating the following research issues in our lab:

  - Linux scalability analysis over multicore architecture
  - Improving Linux File System performance over NUMA architecture
  - Performance optimization and parallelization over Xeon Phi and GP-GPU
  - Scalable OS architecture and optimization for multicore/manycore processors
  - Programming model for multicore/manycore processors
  - Memory-based and NVM file system for multicore/manycore processors
  - Storage architecture and OS support for SSD and NVMe
        - Network stack parallelization and optimization

Blockchain Platform and Applications

A blockchain is a distributed ledger technology that stores and manages the blocks in a chain form, which are created based on the transactions over a P2P based distributed environment. The main idea behind the blockchain technology is that anyone who participates in the system can generate/view all transactions, whereas no one can modify or delete the overpassed transactions. This powerful feature creates a great potential for developing many interesting applications such as event recording and identity management etc. that require data integrity and security without a centralized authority. The blockchain basically consists of components such as ledger, p2p layer, execution engine and consensus protocol. We are currently investigating the following research issues in our lab:

- Blockchain Platforms (Bitcoin, Ethereum, Hyperledger, etc.)
- Smart contract and distributed ledger
- Consensus protocol
- Optimization of blockchain p2p network
- Performance analysis and improvement of blockchain execution layer
- Evaluation and scalability analysis of blockchain platform
- Blockchain in IoT and cloud (and edge) computing

        - Network stack parallelization and optimization

In addition to the research areas described above, we are also investigating the following issues.

- Autonomic Computing and Systems
- IoT and Sensor Cloud
- Embedded software and operating systems (Linux)
- Performance optimization of Android Platform
- Communication support for high performance computing systems
- Digital forensics techniques and algorithms

XE Login