GPU Parallelization of a Hybrid Pseudospectral Geophysical Turbulence Framework Using CUDA
Atmosphere, 2020 An existing hybrid MPI-OpenMP scheme is augmented with a CUDA-based fine grain parallelization approach for multidimensional distributed Fourier transforms, in a well-characterized pseudospectral fluid turbulence code.
Duane L Rosenberg +2 more
exaly +4 more sources
GSGP-CUDA — A CUDA framework for Geometric Semantic Genetic Programming [PDF]
SoftwareX, 2022 14 pages, 3 ...
Leonardo Trujillo +2 more
exaly +5 more sources
COX : Exposing CUDA Warp-level Functions to CPUs [PDF]
ACM Transactions on Architecture and Code Optimization (TACO), 2022 As CUDA becomes the de facto programming language among data parallel applications such as high-performance computing or machine learning applications, running CUDA on other platforms becomes a compelling option.
Ruobing Han +3 more
openalex +2 more sources
CUDA-LLM: LLMs Can Write Efficient CUDA Kernels
arXiv.orgLarge Language Models (LLMs) have demonstrated strong capabilities in general-purpose code generation. However, generating the code which is deeply hardware-specific, architecture-aware, and performance-critical, especially for massively parallel GPUs, remains a complex challenge.
Chen, Wentao +4 more
openaire +3 more sources
CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning
arXiv.orgThe exponential growth in demand for GPU computing resources has created an urgent need for automated CUDA optimization strategies. While recent advances in LLMs show promise for code generation, current SOTA models achieve low success rates in improving CUDA speed.
Li, Xiaoya +4 more
openaire +3 more sources
CUDA: Convolution-Based Unlearnable Datasets [PDF]
Computer Vision and Pattern Recognition, 2023 Large-scale training of modern deep learning models heavily relies on publicly available data on the web. This potentially unauthorized usage of online data leads to concerns regarding data privacy.
Vinu Sankar Sadasivan +2 more
semanticscholar +1 more source
CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition [PDF]
International Conference on Learning Representations, 2023 Class imbalance problems frequently occur in real-world tasks, and conventional deep learning algorithms are well known for performance degradation on imbalanced training datasets.
Sumyeong Ahn, Jongwoo Ko, Se-Young Yun
semanticscholar +1 more source
Correlation between adolescents’ dietary safety management competency and value recognition, efficacy, and competency of convergence using dietary area: a descriptive study [PDF]
Korean Journal of Community Nutrition, 2023 Objectives: This study aimed to investigate the correlation between adolescents’ dietary safety management competency, value recognition, efficacy, and competency of convergence using the dietary area (CUDA).
Yunhwa Kim, Yeon-Kyung Lee
doaj +1 more source
Cuda św. Menasa (wg rękopisu IFAO copte inv. 315-322)
Vox Patrum, 2021 Pierwsze kolekcje cudów św. Menasa zostały zebrane przez kler sanktuarium świętego w Abu Mina. Dysponujemy bardzo różnorodnym zbiorami zachowanymi w kilku językach, jednak to zbiory koptyjskie najwierniej przekazują pierwotną zawartość cudów wraz z ich ...
Przemysław Piwowarczyk
doaj +1 more source
cuCatch: A Debugging Tool for Efficiently Catching Memory Safety Violations in CUDA Applications
Proc. ACM Program. Lang., 2023 CUDA, OpenCL, and OpenACC are the primary means of writing general-purpose software for NVIDIA GPUs, all of which are subject to the same well-documented memory safety vulnerabilities currently plaguing software written in C and C++.
M. Tarek Ibn Ziad +4 more
semanticscholar +1 more source