Exploring AMD GPU scheduling details by experimenting with “worst practices”

N Otterness, JH Anderson - … of the 29th International Conference on Real …, 2021 - dl.acm.org
Graphics processing units (GPUs) have been the target of a significant body of recent real-
time research, but research is often hampered by the “black box” nature of GPU hardware …

SYCL in the edge: performance and energy evaluation for heterogeneous acceleration

Y Faqir-Rhazoui, C García - The Journal of Supercomputing, 2024 - Springer
Edge computing is essential to handle increasing data volumes and processing capacities. It
provides real-time and secure data processing near data sources, like smart devices …

Machine Learning Techniques for Understanding and Predicting Memory Interference in CPU-GPU Embedded Systems

A Masola, N Capodieci, B Rouxel… - 2023 IEEE 29th …, 2023 - ieeexplore.ieee.org
Nowadays, heterogeneous embedded platforms are extensively used in various low-latency
applications, including the automotive industry, real-time IoT systems, and automated …

Developing real-time GPU-sharing platforms for artificial-intelligence applications

NM Otterness - 2022 - search.proquest.com
In modern autonomous systems such as self-driving cars, sustained safe operation requires
running complex software at rates possible only with the help of specialized computational …

CI/CD Efforts for Validation, Verification and Benchmarking OpenMP Implementations

A Jarmusch, F Cabarcas, S Pophale, A Kallai… - … Workshop on OpenMP, 2024 - Springer
Software developers must adapt to keep up with the changing capabilities of platforms so
that they can utilize the power of High-Performance Computers (HPC), including exascale …

SYCL in the Edge: Performance Evaluation for Heterogeneous Acceleration

Y Faqir-Rhazoui, C García - 2023 - researchsquare.com
Edge computing is essential to handle increasing data volumes and processing capacities. It
provides real-time, secure data processing near data sources, like smart devices, alleviating …

Memory interference and performance prediction in GPU-accelerated heterogeneous systems

A Masola - 2024 - repository.unipr.it
Oggigiorno, una varietà di applicazioni, tra cui fabbriche automatizzate, veicoli autonomi e
Sistemi Cyber Fisici (CPS), stanno vivendo una crescita significativa. Date le diverse sfide …

[PDF][PDF] Porting a large cosmology code to GPU, a case study examining JAX and OpenMP.

N Demeure, T Kisner, R Keskitalo, R Thomas, J Borrill… - cug.org
In recent years, a common pattern has emerged where numerical software is designed
around a Python interface calling high-performance kernels written in a lower level …

[PDF][PDF] Υλοποίηση multi-GPU L3 BLAS βιβλιοθήκης με POSIX Threads και HIP

Σ Πούτας - 2024 - dspace.lib.ntua.gr
Περίληψη Σκοπός της παρούσας διπλωματικής εργασίας είναι η εξερεύνηση διαφορετικών
υλοποιήσεων μιας βιβλιοθήκης δρομολόγησης υπο-προβλημάτων γραμμικής άλγεβρας σε …

Performance portability and evaluation of heterogeneous components of SeisSol targeted to AMD GPUs

D Simon - 2021 - mediatum.ub.tum.de
GPUs (Graphics processing units) are commonly used in high-performance computing to
improve the execution time of parallelizable programs. SeisSol, as such a program, can …