Benchmarking a new paradigm: Experimental analysis and characterization of a real processing-in-memory system

J Gómez-Luna, I El Hajj, I Fernandez… - IEEE …, 2022 - ieeexplore.ieee.org
Many modern workloads, such as neural networks, databases, and graph processing, are
fundamentally memory-bound. For such workloads, the data movement between main …

Benchmarking a new paradigm: An experimental analysis of a real processing-in-memory architecture

J Gómez-Luna, IE Hajj, I Fernandez… - arxiv preprint arxiv …, 2021 - arxiv.org
Many modern workloads, such as neural networks, databases, and graph processing, are
fundamentally memory-bound. For such workloads, the data movement between main …

Boyi: A systematic framework for automatically deciding the right execution model of OpenCL applications on FPGAs

J Jiang, Z Wang, X Liu, J Gómez-Luna… - Proceedings of the …, 2020 - dl.acm.org
FPGA vendors provide OpenCL software development kits for easier programmability, with
the goal of replacing the time-consuming and error-prone register-transfer level (RTL) …

Atomic Cache: Enabling Efficient Fine-Grained Synchronization with Relaxed Memory Consistency on GPGPUs Through In-Cache Atomic Operations

Y Zhang, M Wang, W Wang, Y Mai… - 2024 57th IEEE/ACM …, 2024 - ieeexplore.ieee.org
General-purpose graphics processing unit (GPGPU), widely recognized as an exceptional
computing platform for de-ploying emerging parallel applications, requires strict adherence …

Configurable XOR hash functions for banked scratchpad memories in GPUs

GJ van den Braak, J Gomez-Luna… - IEEE Transactions …, 2015 - ieeexplore.ieee.org
Scratchpad memories in GPU architectures are employed as software-controlled caches to
increase the effective GPU memory bandwidth. Through the use of well-known optimization …

[PDF][PDF] Analysis and modeling of the timing bahavior of GPU architectures

P Voudouris, GJ van den Braak - 2014 - research.tue.nl
Graphics processing units (GPUs) offer massive parallelism. Since a couple of years GPUs
can also be used for more general purpose applications; a wide variety of applications can …

[PDF][PDF] Benchmarking a New Paradigm: An Experimental Analysis of a Real Processing-in-Memory Architecture

IE Hajj, I Fernandez, C Giannoula… - arxiv: 2105.03814 …, 2021 - people.inf.ethz.ch
Many modern workloads, such as neural networks, databases, and graph processing, are
fundamentally memory-bound. For such workloads, the data movement between main …

[PDF][PDF] Improving GPU performance: reducing memory conflicts and latency

GJW van den Braak - 2015 - research.tue.nl
Modern day life is unimaginable without all the ICT technology we use every day, like
computers, tablets, smart phones, digital cameras, etc. All this technology uses an enormous …