Cupbop: Making cuda a portable language
CUDA is designed specifically for NVIDIA GPUs and is not compatible with non-NVIDIA
devices. Enabling CUDA execution on alternative backends could greatly benefit the …
devices. Enabling CUDA execution on alternative backends could greatly benefit the …
A comparison of two performance portability metrics
A Marowka - Concurrency and Computation: Practice and …, 2023 - Wiley Online Library
The rise in the demand for new performance portability frameworks for heterogeneous
computing systems has brought with it a number of proposals of workable metrics for …
computing systems has brought with it a number of proposals of workable metrics for …
Performance portable Vlasov code with C++ parallel algorithm
This paper presents the performance portable implementation of a kinetic plasma simulation
code with C++ parallel algorithm to run across multiple CPUs and GPUs. Relying on the …
code with C++ parallel algorithm to run across multiple CPUs and GPUs. Relying on the …
Evaluating the performance portability of SYCL across CPUs and GPUs on bandwidth-bound applications
IZ Reguly - Proceedings of the SC'23 Workshops of The …, 2023 - dl.acm.org
In this paper, we evaluate the portability of the SYCL programming model on some of the
latest CPUs and GPUs from a wide range of vendors, utilizing the two main compilers …
latest CPUs and GPUs from a wide range of vendors, utilizing the two main compilers …
[HTML][HTML] Enabling performance portability on the LiGen drug discovery pipeline
In recent years, there has been a growing interest in developing high-performance
implementations of drug discovery processing software. To target modern GPU …
implementations of drug discovery processing software. To target modern GPU …
[PDF][PDF] Taking GPU Programming Models to Task for Performance Portability
JH Davis, P Sivaraman, I Minn… - arXiv preprint arXiv …, 2024 - pssg.cs.umd.edu
Ensuring high productivity in scientific software development necessitates developing and
maintaining a single codebase that can run efficiently on a range of accelerator-based …
maintaining a single codebase that can run efficiently on a range of accelerator-based …
Performance portability of sparse block diagonal matrix multiple vector multiplications on gpus
KZ Ibrahim, C Yang, P Maris - 2022 IEEE/ACM International …, 2022 - ieeexplore.ieee.org
The emergence of accelerator-based computer architectures and programming models
makes it challenging to achieve performance portability for large-scale scientific simulation …
makes it challenging to achieve performance portability for large-scale scientific simulation …
An Evaluative Comparison of Performance Portability across GPU Programming Models
JH Davis, P Sivaraman, I Minn, K Parasyris… - arXiv preprint arXiv …, 2024 - arxiv.org
Ensuring high productivity in scientific software development necessitates developing and
maintaining a single codebase that can run efficiently on a range of accelerator-based …
maintaining a single codebase that can run efficiently on a range of accelerator-based …
Exploring Scalability in C++ Parallel STL Implementations
Since the advent of parallel algorithms in the C++ 17 Standard Template Library (STL), the
STL has become a viable framework for creating performance-portable applications. Given …
STL has become a viable framework for creating performance-portable applications. Given …
pSTL-Bench: A Micro-Benchmark Suite for Assessing Scalability of C++ Parallel STL Implementations
Since the advent of parallel algorithms in the C++ 17 Standard Template Library (STL), the
STL has become a viable framework for creating performance-portable applications. Given …
STL has become a viable framework for creating performance-portable applications. Given …