Dr. Daniel A. Jiménez, a professor in the Department of Computer Science and Engineering at Texas A&M University, has been inducted into the International Symposium on Computer Architecture (ISCA) Hall of Fame for publishing eight papers in the conference. This year, only nine members of the ISCA community were given the distinction. ISCA is the premier forum for new ideas and research results in computer architecture.
"ISCA is our top conference and very competitive,” he said. “Many doctoral students graduate without publishing in ISCA, like me when I was in grad school. I'm happy to have had many graduate student co-authors on these ISCA papers, including eight students from Texas A&M.”
Jiménez has been a Texas A&M faculty member since 2013. He received his doctorate in computer sciences from The University of Texas at Austin, and his master’s in computer science and bachelor’s degree in computer science and systems design from The University of Texas at San Antonio.
Listed below are three papers that he has recently published with several other Texas A&M researchers:
- “Exploring Predictive Replacement Policies for Instruction Cache and Branch Target Buffer,” ISCA 2018, co-authored with Samira Mirbagher-Ajorpaz, Elba Garza and Sangam Jindal. This paper gives a novel policy that can manage replacement for both the instruction cache and branch target buffer using a predictor specially designed to track the behavior of these structures.
- “Perceptron-based Prefetch Filtering,” ISCA 2019, co-authored with Eshan Bhatia, Gino Chacon, Seth Pugsley, Elvira Teran and Paul V. Gratz. This paper shows how to use a machine-learning technique to improve the accuracy of data cache prefetchers, improving processor performance.
- “Bit-level Perceptron Prediction for Indirect Branches,” ISCA 2019, co-authored with Elba Garza, Samira Mirbagher-Ajorpaz and Tahsin Ahmad Khan. This paper shows how to use a machine-learning technique to develop a novel indirect branch predictor whose accuracy exceeds the previous state-of-the-art.