Aviso: Se está a ler esta mensagem, provavelmente, o browser que utiliza não é compatível com os "standards" recomendados pela W3C. Sugerimos vivamente que actualize o seu browser para ter uma melhor experiência de utilização deste "website". Mais informações em webstandards.org.

Warning: If you are reading this message, probably, your browser is not compliant with the standards recommended by the W3C. We suggest that you upgrade your browser to enjoy a better user experience of this website. More informations on webstandards.org.

Sub Menu

Summary (Link)

Overview (Link)

Mauricio Breternitz, Ph.D.

Research Fellow at ISCTE-IUL Instituto Universitario de Lisboa

ISCTE-IUL Instituto Universitario de Lisboa


Mauricio is an energetic and innovative researcher with interest in real-life solutions with practical impact, currently researching end-to-end application of machine learning to enhanced living spaces via digital assistance.
For a previous employer, Mauricio conceived and pushed through deployment innovative algorithmic & microarchitectural ideas that have had significant positive product impact (estimated upwards of $18M).
He holds 48 U.S. patents and has 58 more pending in areas related to compilation, code optimization, binary translation, processor, cache and memory system organization and cryptography. Mauricio's academic service include ACM/IEEE conferences such as IISWC (general chair), HPCA(finance chair),AMAS-BT/ISCA Workshop (organizer & chair), CGO, ISCA, and multiple program committees.
Mauricio received the Electronics Engineer degree with honors at ITA-Instituto Tecnologico de Aeronautica, Brazil, a MSc in Computer Science at UNICAMP, Brazil and the Ph.D. in Computer Engineering at Carnegie-Mellon University. He worked on parallelizing compilers for a research multiprocessor and for VLIW architectures, binary translation of x86 codes, on IP telephony libraries and on parallelizing database server programs. Recently he has worked on novel algorithms utilizing CPU and GPUs accelerating machine learning on Apache Spark, on system-level and architectural-level characterization of cloud workloads and on novel approaches to utilizing CPU and GPU in cloud workloads such as MapReduce and GraphLab. He is interested in scale-up and scale-out frameworks for Deep Neural Networks using CPUs and GPUs. He worked at IBM (TJWatson and Austin), Motorola, Intel Labs and TimesN Systems, an Austin startup.
Specialties: compiler research and development, multicore programming systems, binary translation, processor (micro)architecture, code compression, code optimization, GPU compute,
cloud workloads, dense server, cloud platforms, end-to-end machine learning and scaling (up,out) ML

Google Scholar profile: https://scholar.google.pt/citations?user=pnmGA74AAAAJ&hl=en&oi=ao