University of Arizona Reconfigurable Computing Lab (UA-RCL)
We build open-source ecosystems towards making emerging computing systems accessible for the users. We research ways to bridge the gap between application engineers, hardware architects, and system software developers with a vertically integrated infrastructure that crosses all domains of computing system research. Our research program focuses on high performance computing systems and non-traditional computing architectures with themes that cover: a) development of resource management strategies from multi-processor system-on-chip to cloud computing scale; b) design and development of reconfigurable hardware architectures for reusable systems; c) modeling and simulation of neuromorphic computing architectures; and d) restructuring computationally challenging algorithms for achieving high performance on field programmable gate array (FPGA) and graphics processing unit (GPU) hardware architectures.
News
- Our paper titled PyTorch and CEDR: Enabling Deployment of Machine Learning Models on Heterogeneous Computing Systems (IEEE Xplore) was published in 2023 20th ACS/IEEE International Conference on Computer Systems and Applications (AICCSA).
- Mustafa Ghanim won Best Demonstration Award in ECE Graduate Student Research Poster & Demo Symposium held by ECE department. Congrats Mustafa! (Check out our blog post)
- Our paper titled A Runtime Manager Integrated Emulation Environment for Heterogeneous SoC Design with RISC-V Cores will be presented at the Heterogeneity in Computing Workshop (HCW’24) in May.
- Our paper titled GPU-RANC: A Cuda Accelerated Simulation Framework for Neuromorphic Architectures will be presented at the Neuro-Inspired Computational Elements (NICE’24) in April.
- Joshua Mack and Serhan Gener held a Tutorial Session CEDR: A Holistic Software and Hardware Design Environment for FPGA-Integrated Heterogeneous Systems in FPGA’24. (Check out our blog post)
- Joshua Mack has defended his PhD dissertation successfully. Congrats Dr. Mack! (Check out our blog post)
- Our paper titled Value-Based Resource Management at SoC Scale (ACM) was published in 3rd Workshop on Redefining Scalability for Diversely Heterogeneous Architectures (RSDHA)
- Joshua Mack held an Education Class CEDR: A Novel Runtime Environment for Accelerator-Rich Heterogeneous Architectures (YouTube) in ESWEEK’23.
- Our paper Contention-aware Performance Modeling for Heterogeneous Edge and Cloud Systems (ACM) was published in the Proceedings of the 3rd Workshop on Flexible Resource and Application Management on the Edge.
- Our paper FALCON: An FPGA Emulation Platform for Domain-Specific Systems-on-Chip (DSSoCs) (IEEE Xplore) was published in the IEEE Design & Test.
- Our paper GPU-based and Streaming-enabled Implementation of Pre-processing Flow towards Enhancing Optical Character Recognition Accuracy and Efficiency was accepted to Springer Cluster Computing journal.
- Our article A Novel Implementation Methodology for Error Correction Codes on a Neuromorphic Architecture (arxiv, IEEE Xplore) was published in the IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.
- Our paper CEDR-API: Productive, Performant Programming of Domain-Specific Embedded Systems (arXiv, IEEE Xplore) was published in the 2023 IPDPS Heterogeneity in Computing Workshop.
- Our paper CEDR: A Compiler-Integrated, Extensible, DSSoC Runtime (arXiv, ACM) was published in the ACM Transactions on Embedded Computing Systems.