Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Sobre

Sobre

Recebi o doutoramento em Engenharia Electrotécnica e de Computadores pela Universidade do Porto (Portugal) em 2001. Atualmente sou professor auxiliar na Faculdade de Engenharia da Universidade do Porto e investigador sénior do INESC TEC. Sou membro de IEEE, ACM e Euromicro.

Os meus interesses de investigação centram-se no projeto de sistemas digitais dedicados para aplicações complexas e exigentes. Estou particularmente interessado em três áreas:

1. Concepção de sistemas digitais auto-adaptáveis
2. Computação reconfigurável baseada em FPGA
3. Aceleração de hardware para sistemas embarcados (com ênfase em sistemas de telecomunicações e bio-médicos)

Alguns tópicos concretos de investigação são:
     - Reconfiguração dinâmica de FPGAs
     - Geração de configurações FPGA em tempo de execução
     - Síntese física rápida para circuitos digitais
     - Arquiteturas virtuais de hardware programável
     - Migração de tarefas transparente de software → hardware

Tópicos
de interesse
Detalhes

Detalhes

  • Nome

    João Canas Ferreira
  • Cargo

    Investigador Sénior
  • Desde

    01 novembro 1988
007
Publicações

2022

A Flexible HLS Hoeffding Tree Implementation for Runtime Learning on FPGA

Autores
Sousa, LM; Paulino, N; Ferreira, JC; Bispo, J;

Publicação
2022 IEEE 21ST MEDITERRANEAN ELECTROTECHNICAL CONFERENCE (IEEE MELECON 2022)

Abstract
Decision trees are often preferred when implementing Machine Learning in embedded systems for their simplicity and scalability. Hoeffding Trees are a type of Decision Trees that take advantage of the Hoeffding Bound to allow them to learn patterns in data without having to continuously store the data samples for future reprocessing. This makes them especially suitable for deployment on embedded devices. In this work we highlight the features of a HLS implementation of the Hoeffding Tree. The implementation parameters include the feature size of the samples (D), the number of output classes (K), and the maximum number of nodes to which the tree is allowed to grow (Nd). We target a Xilinx MPSoC ZCU102, and evaluate: the design's resource requirements and clock frequency for different numbers of classes and feature size, the execution time on several synthetic datasets of varying sizes (N) and the execution time and accuracy for two datasets from UCI. For a problem size of D=3, K=5, and N=40000, a single decision tree operating at 103MHz is capable of 8.3x faster inference than the 1.2 GHz ARM Cortex-A53 core. Compared to a reference implementation of the Hoeffding tree, we achieve comparable classification accuracy for the UCI datasets.

2021

Transparent Control Flow Transfer between CPU and Accelerators for HPC

Autores
Granhao, D; Ferreira, JC;

Publicação
ELECTRONICS

Abstract
Heterogeneous platforms with FPGAs have started to be employed in the High-Performance Computing (HPC) field to improve performance and overall efficiency. These platforms allow the use of specialized hardware to accelerate software applications, but require the software to be adapted in what can be a prolonged and complex process. The main goal of this work is to describe and evaluate mechanisms that can transparently transfer the control flow between CPU and FPGA within the scope of HPC. Combining such a mechanism with transparent software profiling and accelerator configuration could lead to an automatic way of accelerating regular applications. In this work, a mechanism based on the ptrace system call is proposed, and its performance on the Intel Xeon+FPGA platform is evaluated. The feasibility of the proposed approach is demonstrated by a working prototype that performs the transparent control flow transfer of any function call to a matching hardware accelerator. This approach is more general than shared library interposition at the cost of a small time overhead in each accelerator use (about 1.3 ms in the prototype implementation).

2021

A Binary Translation Framework for Automated Hardware Generation

Autores
Paulino, N; Bispo, J; Ferreira, JC; Cardoso, JMP;

Publicação
IEEE MICRO

Abstract
As applications move to the edge, efficiency in computing power and power/energy consumption is required. Heterogeneous computing promises to meet these requirements through application-specific hardware accelerators. Runtime adaptivity might be of paramount importance to realize the potential of hardware specialization, but further study is required on workload retargeting and offloading to reconfigurable hardware. This article presents our framework for the exploration of both offloading and hardware generation techniques. The framework is currently able to process instruction sequences from MicroBlaze, ARMv8, and riscv32imaf binaries, and to represent them as Control and Dataflow Graphs for transformation to implementations of hardware modules. We illustrate the framework's capabilities for identifying binary sequences for hardware translation with a set of 13 benchmarks.

2021

Pedagogical Innovation in Pandemic Times: The Experience of a Microprocessor Programming Course

Autores
Lima, B; Granhao, D; Araujo, AJ; Ferreira, JC;

Publicação
2021 4TH INTERNATIONAL CONFERENCE OF THE PORTUGUESE SOCIETY FOR ENGINEERING EDUCATION (CISPEE)

Abstract
The 2019/2020 school year will always be remembered for the impact of the COVID-19 pandemic. For the first time in recent history, countries closed schools and forced instructors and students to quickly adjust to online classes. This sudden and forced shift to a method of teaching that was completely different from what we were used to presented several challenges and opportunities on a pedagogical level. In this paper we describe our experience as instructors in a course on microprocessor programming in the Master's Degree in Computer Science and Computing Engineering at the Faculty of Engineering of the University of Porto. Our approach included changes to the assessment plan, which became more distributed, and improvements in communication between students and instructors through the use of Slack. We found that the changes introduced were not only very well received by students, but also resulted in the best exam attendance and average final grade in the last 10 years of the course's history.

2021

On the Performance Effect of Loop Trace Window Size on Scheduling for Configurable Coarse Grain Loop Accelerators

Autores
Santos, T; Paulino, N; Bispo, J; Cardoso, JMP; Ferreira, JC;

Publicação
2021 INTERNATIONAL CONFERENCE ON FIELD-PROGRAMMABLE TECHNOLOGY (ICFPT)

Abstract
By using Dynamic Binary Translation, instruction traces from pre-compiled applications can be offloaded, at runtime, to FPGA-based accelerators, such as Coarse-Grained Loop Accelerators, in a transparent way. However, scheduling onto coarse-grain accelerators is challenging, with two of current known issues being the density of computations that can be mapped, and the effects of memory accesses on performance. Using an in-house framework for analysis of instruction traces, we explore the effect of different window sizes when applying list scheduling, to map the window operations to a coarse-grain loop accelerator model that has been previously experimentally validated. For all window sizes, we vary the number of ALUs and memory ports available in the model, and comment how these parameters affect the resulting latency. For a set of benchmarks taken from the PolyBench suite, compiled for the 32-bit MicroBlaze softcore, we have achieved an average iteration speedup of 5.10x for a basic block repeated 5 times and scheduled with 8 ALUs and memory ports, and an average speedup of 5.46x when not considering resource constraints. We also identify which benchmarks contribute to the difference between these two speedups, and breakdown their limiting factors. Finally, we reflect on the impact memory dependencies have on scheduling.

Teses
supervisionadas

2022

Study and Implementation of Processing Offload Techniques for Virtualized Systems

Autor
Ricardo André Miranda Pimenta de Castro

Instituição
UP-FEUP

2022

Scalable Digital Baseband Beamformer for Satellite Reception

Autor
Helder Henrique Avelar

Instituição
UP-FEUP

2022

Adaptive Computing for Edge-AI deployment

Autor
Ivo Micael Couceiro Brandão

Instituição
UNL-FCTNOVA

2022

Specializing Risc-V Cores for Performance and Power

Autor
Henrique Veloso de Sousa

Instituição
UP-FEUP

2021

Implementação de sistema de “beamforming” em FPGA para comunicação com satélites

Autor
Telmo Francisco da Costa Soares

Instituição
UP-FEUP