IEEE 32nd International Symposium on Computer Architecture and High Performance Computing

Porto, Portugal, September 8-11, 2020


**** SBAC-PAD2020 Live on YouTube ****

SBAC-PAD2020 deadline postponed to June 28, 2020

Following the recommendations/guidelines from the World Health Organization (WHO), regarding the Coronavirus disease (COVID-19) outbreak, SBAC-PAD2020 will be converted to an online event.

However, the outbreak's impact led to several requests for postponing significantly the deadlines. Following those requests, the SBAC-PAD2020's organization decided to postpone the deadline for the abstract/paper submission to June 28, 2020.

Stay safe!

Aims and Scope

SBAC-PAD is an international symposium, started in 1987, which has continuously presented an overview of new developments, applications, and trends in parallel and distributed computing technologies. SBAC­-PAD is open for faculty members, researchers, specialists and graduate students around the world.

Authors are invited to submit manuscripts on a wide range of high-performance and distributed computing areas. Topics of interest include (but are not limited to):

The 2020 symposium will be held at the Department of Computer Science, Faculty of Sciences of University of Porto, in Portugal. Porto is a historic and varied city, from the warren of narrow streets that make up the ancient Ribeira district through to the grand plaza of the Trindade district. The region is famed for the production of Port, which is still stored and matured in the vast cellars that stretch along the banks of the Douro River. It was selected as the best European destination three years in a row (2017, 2018, 2019). It is a very lively city, second largest in Portugal, hosting the second largest university.

This year's edition will start with an exciting event on big data, machine learning and quantum computing, the Summer School on Machine Learning and Big Data with Quantum Computing!

Bem vindos ao Porto!

Keynote Speakers

We are pleased to announce our distinguished invited speakers.


Authors are invited to contribute to the following tracks:

Important Dates


General Chairs

Program Chairs

Publicity Chairs

Workshop Chairs

Publications Chairs


Paper Submission

Papers submitted to SBAC-PAD 2020 must describe original research results and must not have been published or simultaneously submitted anywhere else.

Manuscripts must be prepared with the IEEE latex macro package using the bibliography latex template and submitted via the EasyChair Conference Management System as one pdf file. The strict page limit for initial submission and camera-ready version is 8 pages in the aforementioned format. A maximum of 2 extra pages can be bought at 100 Euros per page. To be published in the SBAC-PAD 2020 Symposium Proceedings and to be eligible for publication at the IEEE Xplore, one of the authors must register at the full rate (non student). Authors may not use a single registration for multiple papers.

Each paper will receive a minimum of three reviews by members of the international technical program committee. Papers will be selected based on their originality, relevance, technical clarity and quality of presentation. Authors of selected papers will be invited to submit extended versions of their papers for publication on the Journal of Parallel and Distributed Computing (JPDC).

Accepted Papers

Registration (Closed)


Monday – September 07, 2020
Summer School (SMBQ)

Tuesday – September 08, 2020
Summer School (SMBQ)    and    Workshop (WAMCA)

Time in UTCWednesday – September 09, 2020
09:45 – 10:00Opening

10:00-11:00Keynote Session - Speaker(Chair: Philippe Navaux)
Slack Channel: #keynote-frank

11:00 – 12:00Session 1 (Chair: Shanjiang Tang)
A Robotic Communication Middleware Combining High Performance and High Reliability
Slack Channel: #s1-p1
MASA-StarPU: Parallel Sequence Comparison with Multiple Scheduling Policies and Pruning
Slack Channel: #s1-p2
PSU: A Framework for Dynamic Software Updates in Multi-threaded C-Language Programs
Slack Channel: #s1-p3
Towards Communication Profile, Topology and Node Failure Aware Process Placement
Slack Channel: #s1-p4

12:00 – 12:15Break

12:15 – 12:45Session 2 (Chair: Claude Tadonki)
Reliable and energy-aware mapping of streaming series-parallel applications onto hierarchical platforms
Slack Channel: #s2-p1
Selective Protection for Sparse Iterative Solvers to Reduce the Resilience Overhead
Slack Channel: #s2-p2

12:45 – 13:30Break

13:30 – 14:30Session 3 (Chair: Cristiana Bentes)
sputniPIC: an Implicit Particle-in-Cell Code for Multi-GPU Systems
Slack Channel: #s3-p1
Scalable and Efficient Spatial-Aware Parallelization Strategies for Multimedia Retrieval
Slack Channel: #s3-p2
Scheduling Methods to Reduce Response Latency of Function as a Service
Slack Channel: #s3-p3
Using Skip Graphs for Increased NUMA Locality
Slack Channel: #s3-p4

14:30 – 14:45Break

14:45 – 15:45Session 4 (Chair: Alba Melo)
Energy-Efficient Time Series Analysis Using Transprecision Computing
Slack Channel: #s4-p1
High Performance and Portable Convolution Operators for ARM-based Multicore Processors
Slack Channel: #s4-p2
High-Performance Low-Memory Lowering: GEMM-based Algorithms for DNN Convolution
Slack Channel: #s4-p3
Optimized Transactional Data Structure Approach to Concurrency Control for In-Memory Databases
Slack Channel: #s4-p4

Time in UTCThursday – September 10, 2020
10:00-11:00Keynote Session - Speaker(Chair: Inês Dutra)
Slack Channel: #keynote-brice

11:00 – 12:00Session 5 (Chair: Alfredo Goldman)
Exploiting Non-Conventional DVFS on GPUs: Application to Deep Learning
Slack Channel: #s5-p1
Design space exploration of accelerators and end-to-end DNN evaluation with TFLITE-SOC
Slack Channel: #s5-p2
Hardware Multiversioning for Fail-Operational Multithreaded Applications
Slack Channel: #s5-p3
On-chip Parallel Photonic Reservoir Computing using Multiple Delay lines
Slack Channel: #s5-p4

12:00 – 12:15Break

12:15 – 12:45Session 6 (Chair: Gabriel Falcão)
Online Sharing-Aware Thread Mapping in Software Transactional Memory
Slack Channel: #s6-p1
Optically Connected Memory for Disaggregated Data Centers
Slack Channel: #s6-p2

12:45 – 13:30Break

13:30 – 14:30Session 7 (Chair: Giovanni Agosta)
On the Memory Underutilization: Exploring Disaggregated Memory on HPC Systems
Slack Channel: #s7-p1
TASO: Time and Space Optimization for Memory-Constrained DNN Inference
Slack Channel: #s7-p2
A Fast and Concise Parallel Implementation of the 8x8 2D IDCT using Halide
Slack Channel: #s7-p3
Controlling Garbage Collection and Request Admission to Improve Performance of FaaS Applications
Slack Channel: #s7-p4

14:30 – 14:45Break

14:45 – 15:15Session 8 (Chair: Lúcia Drummond)
Predicting the Energy consumption of CUDA kernels using SimGrid
Slack Channel: #s8-p1
XPySom: High-Performance Self-Organizing Maps
Slack Channel: #s8-p2

15:15 – 15:30Break

15:30-16:30Keynote Session - Speaker(Chair: Inês Dutra)
Slack Channel: #keynote-christine

Time in UTCFriday – September 11, 2020
10:00-11:00Keynote Session - Speaker(Chair: Laurent Lefèvre)
Slack Channel: #keynote-carlos

11:00 – 12:00Session 9 (Chair: Nuno Roma)
AIR: A Light-Weight Yet High-Performance Dataflow Engine based on Asynchronous Iterative Routing
Slack Channel: #s9-p1
An Optimal Model for Optimizing the Placement and Parallelism of Data Stream Processing Applications on Cloud-Edge Computing
Slack Channel: #s9-p2
Evaluating Computation and Data Placements in Edge Infrastructures through a Common Simulator
Slack Channel: #s9-p3
Optimizing Green Energy Consumption of Fog Computing Architectures
Slack Channel: #s9-p4

12:00-12:30Best Paper and Closing


Accepted papers will be published by IEEE Society and by IEEExplore.

Steering Committee