A5014481850- Parallel Computing and Optimization Techniques
- Advanced Data Storage Technologies
- Advanced Memory and Neural Computing
- Caching and Content Delivery
- Advanced Manufacturing and Logistics Optimization
- Manufacturing Process and Optimization
- Advanced Data Compression Techniques
- Assembly Line Balancing Optimization
- Cloud Computing and Resource Management
- Algorithms and Data Compression
- Embedded Systems Design Techniques
- Cloud Data Security Solutions
- Digital Filter Design and Implementation
- Low-power high-performance VLSI design
- IoT and Edge/Fog Computing
- Optimization and Search Problems
- Software System Performance and Reliability
University of California, Merced
2021-2024
The Ohio State University
2020
High capacity persistent memory (PMEM) is finally commercially available in the form of Intel's Optane DC Persistent Memory Module (DCPMM). Researchers have raced to evaluate and understand performance DCPMM itself as well systems applications designed leverage PMEM resulting from over a decade research. Early evaluations show that its behavior more nuanced idiosyncratic than previously thought. Several assumptions made about guided design PMEM-enabled been shown be incorrect. Unfortunately,...
The Data Processing Unit (DPU) (i.e., programmable SmartNICs with System-on-Chip or SoC cores) has emerged as a valuable supplementary resource to the host CPU. DPU architecture been attracting significant attention within High-Performance Computing (HPC) and data center clusters due its advanced capabilities accelerators, which include hardware-based compression engine. This positions prospective tool for accelerating offloading workloads from hosts, can potentially speed up data-intensive...
Applications running inside containers or virtual machines, traditionally use TCP/IP for communication in HPC clouds and data centers. The path usually becomes a major performance bottleneck applications performing NVMe-over-Fabrics (NVMe-oF) based I/O operations disaggregated storage settings. We propose an adaptive channel, called NVMe-over-Adaptive-Fabric (NVMe-oAF), that could leverage to eliminate the high-latency low-bandwidth incurred by remote requests over TCP/IP. NVMe-oAF...
Microservice and serverless computing systems open up massive versatility opportunity to distributed datacenter-scale computing. In the meantime, deployments of modern datacenter resources are moving disaggregated architectures. With flourishing growths from both sides, we believe this is high time write vision paper propose a potential research agenda achieve efficient deployments, management, executions next-generation microservices on top emerging particular, envision critical direction...