R
Ricardo Quislant
Researcher at University of Málaga
Publications - 30
Citations - 180
Ricardo Quislant is an academic researcher from University of Málaga. The author has contributed to research in topics: Transactional memory & Bloom filter. The author has an hindex of 6, co-authored 25 publications receiving 127 citations.
Papers
More filters
Posted Content
NATSA: A Near-Data Processing Accelerator for Time Series Analysis
Iván López Fernández,Ricardo Quislant,Christina Giannoula,Mohammed Alser,Juan Gómez-Luna,Eladio Gutierrez,Oscar Plata,Onur Mutlu +7 more
TL;DR: NATHSA is presented, the first Near-Data Processing accelerator for time series analysis to exploit modern 3D-stacked High Bandwidth Memory (HBM) to enable efficient and fast specialized matrix profile computation near memory, where time series data resides.
Proceedings ArticleDOI
Improving Signatures by Locality Exploitation for Transactional Memory
TL;DR: A novel signature design that exploit locality is proposed to reduce the number of false conflicts and it is shown how that reduction translates into a performance improvement in the execution of concurrent transactions.
Proceedings ArticleDOI
NATSA: A Near-Data Processing Accelerator for Time Series Analysis
Iván López Fernández,Ricardo Quislant,Eladio Gutierrez,Oscar Plata,Christina Giannoula,Mohammed Alser,Juan Gómez-Luna,Onur Mutlu +7 more
TL;DR: NATSA as mentioned in this paper is the first near-data processing accelerator for time series analysis, which exploits modern 3D-stacked High Bandwidth Memory (HBM) to enable efficient and fast specialized matrix profile computation near memory.
Journal ArticleDOI
Hardware Signature Designs to Deal with Asymmetry in Transactional Data Sets
TL;DR: A thorough study of two classes of new signatures, called multiset and reconfigurable asymmetric signatures, which are alternatives to the common scheme to deal with the asymmetry in transactional data sets in an effective way are presented.
Proceedings ArticleDOI
Multiset signatures for transactional memory
TL;DR: Experimental results show that the multiset approach is able to reduce the false positive rate and improve the execution performance in most of the tested codes, without increasing the required hardware area in a noticeable amount.