Research interests
I was a PhD candidate in the Electronic Systems group from 2010 to 2015. In November 2015 I successfully defended my thesis titled Improving GPU Performance – Reducing Memory Conflicts and Latency.
My main research interests are focused on GPUs, especially GPU architecture and programmability. Other research includes the efficient mapping of irregular voting algorithms on GPUs. For example histogramming of images and line- and circle-detection using the Hough transform.
Link to my Google scholar profile.
List of publications
R-GPU: A Reconfigurable GPU Architecture
Gert-Jan van den Braak, Henk Corporaal,
ACM Transactions on Architecture and Code Optimization (TACO),
2016
Download PDF |
Link to DOI
Tags: GPU, architecture
GPU research in the ES-group
Gert-Jan van den Braak,
NIRICT GPGPU meeting,
2015
Download PDF
Tags: GPU
Improving GPU performance - reducing memory conflicts and latency
Gert-Jan van den Braak,
PhD thesis,
2015
Download PDF |
Link to publication
Tags: GPU, CUDA, architecture, hough transform, Voting Algorithms, Histogram, hash functions
Configurable XOR Hash Functions for Banked Scratchpad Memories in GPUs
Gert-Jan van den Braak, Juan Gómez-Luna, José María González-Linares, Henk Corporaal, Nicolás Guil,
IEEE Transactions on Computers,
2015
Download PDF |
Link to DOI
Tags: GPU, scratchpad memory, hash functions
Supplementary File to Adaptive and Transparent Cache Bypassing for GPUs
Ang Li, Gert-Jan van den Braak, Akash Kumar and Henk Corporaal,
SC,
2015
Download PDF
Tags:
Adaptive and Transparent Cache Bypassing for GPUs (nominated for Best Paper and Best Student Paper)
Ang Li, Gert-Jan van den Braak, Akash Kumar and Henk Corporaal,
The International Conference for High Performance Computing, Networking, Storage and Analysis (SC),
2015
Download PDF
Tags: GPU, cache
Fine-Grained Synchronizations and Dataflow Programming on GPUs
Ang Li, Gert-Jan van den Braak, Henk Corporaal and Akash Kumar,
International Conference on Supercomputing (ICS),
2015
Download PDF
Tags: GPU, synchronizations, Spin-lock, Dataflow
A Study of the Potential of Locality-Aware Thread Scheduling for GPUs
Cedric Nugteren, Gert-Jan van den Braak, Henk Corporaal,
7th International Workshop on Multi-/Many-Core Computing Systems (MuCoCoS),
2014
Link to publication
Tags: GPU, thread scheduling
A Detailed GPU Cache Model Based on Reuse Distance Theory
Cedric Nugteren, Gert-Jan van den Braak, Henk Corporaal, Henri Bal,
High Performance Computer Architecture (HPCA),
2014
Link to publication
Tags: GPU, cache model
Roofline-aware DVFS for GPUs
Cedric Nugteren, Gert-Jan van den Braak and Henk Corporaal,
ADAPT,
2014
Download PDF |
Link to DOI
Tags: GPU, roofline, DVFS
Simulation and Architecture Improvements of Atomic Operations on GPU Scratchpad Memory
Gert-Jan van den Braak, Juan Gómez-Luna, Henk Corporaal, José María González-Linares, Nicolás Guil,
IEEE International Conference on Computer Design (ICCD),
2013
Download PDF |
Link to DOI
Tags: GPU, scratchpad memory, atomic operations, hash functions
GPU-CC: a Reconfigurable GPU Architecture with Communicating Cores
Gert-Jan van den Braak, Henk Corporaal,
M-SCOPES,
2013
Download PDF |
Link to DOI
Tags: GPU, architecture
Future of GPGPU Micro-Architectural Parameters
C. Nugteren, G.J.W.v.d. Braak, H. Corporaal,
DATE '13: Design, Automation and Test in Europe,
2013
Download PDF |
Link to publication
Tags: GPU, architecture
Introduction to GPGPU and GPU-architectures
Gert-Jan van den Braak,
GPGPU-day (Amsterdam),
2012
Download PDF
Tags: GPU, architecture
GPU-Vote: A Framework for Accelerating Voting Algorithms on GPU
Gert-Jan van den Braak, Cedric Nugteren, Bart Mesman and Henk Corporaal,
Euro-Par,
2012
Download PDF |
Link to DOI
Tags: GPU, Voting Algorithms, hough transform, Histogram
Fast Hough Transform on GPUs: Exploration of Algorithm Trade-Offs
Gert-Jan van den Braak, Cedric Nugteren, Bart Mesman, Henk Corporaal,
in Proceedings of the 13th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS’11), Ghent, Belgium,
2011
Download PDF |
Link to DOI
Tags: GPU, hough transform
High Performance Predictable Histogramming on GPUs: Exploring and Evaluating Algorithm Trade-offs
C. Nugteren, G.J.W.v.d. Braak, H. Corporaal and B. Mesman,
GPGPU: Fourth Workshop on General Purpose Processing on Graphics Processing Units at ASPLOS'11,
2011
Download PDF |
Link to DOI
Tags: GPU, application, Histogram
Fast Huffman Decoding by Exploiting Data Level Parallelism
Tim Drijvers, Carlos Alba Pinto, Henk Corporaal, Bart Mesman, Gert-Jan van den Braak,
SAMOS,
2010
Download PDF |
Link to DOI
Tags: SIMD, Huffman
Compile-time GPU memory access optimizations
Gert-Jan van den Braak, Bart Mesman, Henk Corporaal,
International Conference on Embedded Computer Systems: Architecture, Modelling and Simulation (SAMOS) ,
2010
Download PDF |
Link to DOI
Tags: GPU, memory, auto-tuning