197516_4849794282_8656_n

Email: gchap002@fiu.edu
Personal Web Page: web.eng.fiu.edu/~gchap002/www.linkedin.com/pub/gustavo-a-chaparro-baquero/25/a96/b42/
Research Name: Memory Oriented Scheduling for Real-Time Embedded Systems based on Multi-core Processing Platforms
Abstract Research: In computing platforms and specially in embedded  systems the performance of the microprocessor has been increasing at a high rate over the last decades.  Such development have not been seen in the memory development as well. So, we have witnessed an increase in the processor-memory performance gap.  The processing of memory-intensity tasks keep increasing also specially in real-time embedded systems where the time constrains are very sensitive to the overall throughput of the system.  Thus, the performance of such kind of systems is highly degraded by the performance the memory can achieve. Specifically it have been seen an increase of 300% in the Worst Case Execution Time (WCET) of real-time running tasks due to memory interference which is a variation unacceptable taking into consideration that many models and schedulers for those tasks are based on the accurate calculation of that WCET.  Therefore, the scheduling method of such tasks has to change in order to preserve the performance, taking into consideration the multiple new factors involving their execution, like the memory assigned to each task at a certain moment as well as the multi-core platform that will be executing them.
Publications:

Petri Net Workflow Modeling For Digital Publishing- Measuring Quantitative Dependability Attributes

VDM Verlag Dr. Mueller e.K. / June 20th of 2007 / ISBN-10: 3836418894. ISBN-13: 978-3836418898.

Author: Gustavo A. Chaparro-Baquero

Power-Efficient Schemes Via Workload Characterization on the Intel’s Single-chip Cloud Computer

The Eighth Workshop on High-Performance, Power-Aware Computing (HPPAC 2012), in conjunction with IPDPS 2012, Shanghai, China, May 21st of 2012

Authors: Gustavo A. Chaparro-Baquero, Qi Zhou, Chen Liu, Jie Tang and Shaoshan Liu

Measuring Quantitative Dependability Attributes in Digital Publishing Using Petri Net Workflow Modeling

Dependable, Autonomic and Secure Computing, 2nd IEEE International Symposium. Indiana University, Purdue University. Indianapolis, Indiana. USA. September 29th of 2006.

Authors: Gustavo A. Chaparro-Baquero, Nayda G. Santiago, Wilson Rivera and  Fernando Vega-Riveros.

Concentration: PhD Student in Electrical Engineering
Graduation date: Summer 2015