high performance computing on graphics processing units: hgpu.org

hgpu.org » OpenCL

Optimising Convolutional Neural Networks Inference on Low-Powered GPUs

Simon Rovder, Jose Cano, Michael O'Boyle

View

Download (PDF)

Tags: Computer science, Deep learning, Heterogeneous systems, Neural networks, OpenCL

February 10, 2019 by hgpu

Heterogeneous Distributed Big Data Clustering on Sparse Grids

David Pfander, Gregor Daiss, Dirk Pfluger

View

Download (PDF)

Source codes

Tags: Clustering, Computer science, Data mining, Distributed computing, Heterogeneous systems, Machine learning, MPI, nVidia, OpenCL, Package, performance portability, Tesla P100

February 10, 2019 by hgpu

Efficient Implementation and Optimization of Geometric Multigrid Operations in the LIFT Framework

Martin Lucke

View

Download (PDF)

Tags: Computer science, Differential equations, nVidia, nVidia GeForce GTX 1080, OpenCL, Partial differential equations, PDEs, performance portability, Thesis

January 27, 2019 by hgpu

Direct N-body code on low-power embedded ARM GPUs

David Goz, Sara Bertocco, Luca Tornatore, Giuliano Taffoni

View

Download (PDF)

Tags: ARM, Astrophysics, FPGA, Heterogeneous systems, Instrumentation and Methods for Astrophysics, N-body simulation, OpenCL, OpenMPI, SoC

January 27, 2019 by hgpu

Exploring FPGA-specific Optimizations for Irregular OpenCL Applications

Mohamed W. Hassan, Ahmed E. Helal, Peter M. Athanas, Wu-Chun Feng, Yasser Y. Hanafy

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, FPGA, HLS, Linear Algebra, OpenCL, Package

January 20, 2019 by hgpu

Tango: A Deep Neural Network Benchmark Suite for Various Accelerators

Aajna Karki, Chethan Palangotu Keshava, Spoorthi Mysore Shivakumar, Joshua Skow, Goutam Madhukeshwar Hegde, Hyeran Jeon

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, CUDA, Deep learning, FPGA, Machine learning, Neural networks, nVidia, nVidia Jetson TX1, OpenCL, Package

January 20, 2019 by hgpu

Auto-tuned OpenCL kernel co-execution in OmpSs for heterogeneous systems

B. P'erez, E. Stafford, J. L. Bosque, R. Beivide, S. Mateo, X. Teruel, X. Martorell, E. Ayguad'e

View

Download (PDF)

Tags: Computer science, Heterogeneous systems, nVidia, OmpSs, OpenCL, Tesla K20

January 13, 2019 by hgpu

BitCracker: BitLocker meets GPUs

Elena Agostini, Massimo Bernaschi

View

Download (PDF)

Source codes

Tags: AES, ATI, ATI Radeon HD 7990, Computer science, CUDA, nVidia, nVidia GeForce GTX Titan, nVidia GeForce GTX Titan X, OpenCL, Package, Security, Tesla K80, Tesla P100, Tesla V100

January 13, 2019 by hgpu

HG-Caffe: Mobile and Embedded Neural Network GPU (OpenCL) Inference Engine with FP16 Supporting

Zhuoran Ji

View

Download (PDF)

Source codes

Tags: Caffe, Computer science, Deep learning, Machine learning, Neural networks, OpenCL, Package

January 13, 2019 by hgpu

HeteroCL: A Multi-Paradigm Programming Infrastructure for Software-Defined Reconfigurable Computing

Yi-Hsiang Lai, Yuze Chi, Yuwei Hu, Jie Wang, Cody Hao Yu, Yuan Zhou, Jason Cong, Zhiru Zhang

View

Download (PDF)

Tags: Algorithms, Compilers, Computer science, FPGA, Heterogeneous systems, HLS, OpenCL, Python

January 6, 2019 by hgpu

Towards Automatic Transformation of Legacy Scientific Code into OpenCL for Optimal Performance on FPGAs

Wim Vanderbauwhede, Syed Waqar Nabi

View

Download (PDF)

Source codes

Tags: Compilers, Computer science, Fortran, FPGA, Heterogeneous systems, nVidia, nVidia GeForce GTX Titan, OpenACC, OpenCL, OpenMP, Package

January 6, 2019 by hgpu

A Survey on Optimized Implementation of Deep Learning Models on the NVIDIA Jetson Platform

Sparsh Mittal

View

Download (PDF)

Tags: Computer science, CUDA, Deep learning, nVidia, nVidia Jetson TK1, nVidia Jetson TX1, nVidia Jetson TX2, OpenCL, survey

December 30, 2018 by hgpu

Code Generation for Cryptographic Kernels using Multi-word Modular Arithmetic on GPU

GSParLib

GSParLib: A multi-level programming interface unifying OpenCL and CUDA for expressing stream and data parallelism

Keras Sig: Efficient Path Signature Computation on GPU in Keras 3

KSig: GPU-accelerated computation of popular time series kernels

A User’s Guide to KSig: GPU-Accelerated Computation of the Signature Kernel

IterApp: Iterative Application Skeleton

Boosting Performance of Iterative Applications on GPUs: Kernel Batching with CUDA Graphs

SCALE-Ahead-Of-Time Compilation of CUDA for AMD GPUs

LeetDecoding: A PyTorch Library for Exponentially Decaying Causal Linear Attention with CUDA Implementations

Anari-visionaray

Data Parallel Visualization and Rendering on the RAMSES Supercomputer with ANARI

PROM: an open-source software framework to enhance the robustness and performance of predictive models against such changes during deployment

Enhancing Deployment-Time Predictive Model Robustness for Code Analysis and Optimization

DeepSpeed: a deep learning optimization library that makes distributed training and inference easy, efficient, and effective

Scalable Access-Pattern Aware I/O Acceleration and Multi-Tiered Data Management for HPC and AI Workloads

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Optimising Convolutional Neural Networks Inference on Low-Powered GPUs

Heterogeneous Distributed Big Data Clustering on Sparse Grids

Efficient Implementation and Optimization of Geometric Multigrid Operations in the LIFT Framework

Direct N-body code on low-power embedded ARM GPUs

Exploring FPGA-specific Optimizations for Irregular OpenCL Applications

Tango: A Deep Neural Network Benchmark Suite for Various Accelerators

Auto-tuned OpenCL kernel co-execution in OmpSs for heterogeneous systems

BitCracker: BitLocker meets GPUs

HG-Caffe: Mobile and Embedded Neural Network GPU (OpenCL) Inference Engine with FP16 Supporting

HeteroCL: A Multi-Paradigm Programming Infrastructure for Software-Defined Reconfigurable Computing

Towards Automatic Transformation of Legacy Scientific Code into OpenCL for Optimal Performance on FPGAs

A Survey on Optimized Implementation of Deep Learning Models on the NVIDIA Jetson Platform

Recent source codes

Code Generation for Cryptographic Kernels using Multi-word Modular Arithmetic on GPU

GSParLib

Keras Sig: Efficient Path Signature Computation on GPU in Keras 3

KSig: GPU-accelerated computation of popular time series kernels

IterApp: Iterative Application Skeleton

SCALE-Ahead-Of-Time Compilation of CUDA for AMD GPUs

LeetDecoding: A PyTorch Library for Exponentially Decaying Causal Linear Attention with CUDA Implementations

Anari-visionaray

PROM: an open-source software framework to enhance the robustness and performance of predictive models against such changes during deployment

DeepSpeed: a deep learning optimization library that makes distributed training and inference easy, efficient, and effective

Most viewed papers (last 30 days)