P
Paulo C. Santos
Researcher at Universidade Federal do Rio Grande do Sul
Publications - 35
Citations - 333
Paulo C. Santos is an academic researcher from Universidade Federal do Rio Grande do Sul. The author has contributed to research in topics: Computer science & Memory management. The author has an hindex of 8, co-authored 25 publications receiving 178 citations. Previous affiliations of Paulo C. Santos include University of Rio Grande.
Papers
More filters
Proceedings ArticleDOI
Operand size reconfiguration for big data processing in memory
Paulo C. Santos,Geraldo F. Oliveira,Diego G. Tome,Marco A. Z. Alves,Eduardo Cunha de Almeida,Luigi Carro +5 more
TL;DR: The Reconfigurable Vector Unit (RVU) is presented that enables massive and adaptive in-memory processing, extending the native HMC instructions and also increasing its effectiveness.
Proceedings ArticleDOI
Large vector extensions inside the HMC
TL;DR: This paper introduces the HIVE architecture, which allows performing common vector operations directly inside the HMC, avoiding contention on the interconnections as well as cache pollution and shows that the simple instructions provided by HMC actually hurt performance for streaming applications.
Proceedings ArticleDOI
A Compiler for Automatic Selection of Suitable Processing-in-Memory Instructions
Hameeza Ahmed,Paulo C. Santos,João Paulo Cardoso de Lima,Rafael Fao de Moura,Marco A. Z. Alves,Antonio Carlos Schneider Beck,Luigi Carro +6 more
TL;DR: This work presents the Processing-In-Memory cOmpiler (PRIMO), a compiler able to efficiently exploit large vector units on a PIM architecture, directly from the original code.
Book ChapterDOI
NIM: An HMC-Based Machine for Neuron Computation
TL;DR: This work presents a neural in-memory simulator capable of executing deep learning applications inside 3D-stacked memories that was able to overperform traditional multi-core devices, while reducing overall system energy consumption.
Proceedings ArticleDOI
Design space exploration for PIM architectures in 3D-stacked memories
João Paulo Cardoso de Lima,Paulo C. Santos,Marco A. Z. Alves,Antonio Carlos Schneider Beck,Luigi Carro +4 more
TL;DR: The results show that the most straightforward approach can provide the highest performance while consuming the lowest amount of area and power, which makes it the most suitable design found in this survey for an energy-efficient in-memory accelerator, whether it goes in High-Performance Computing or Embedded Systems.