high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

Hardware thread reordering to boost OpenCL throughput on FPGAs

Amir Momeni, Hamed Tabkhi, Gunar Schirner, David Kaeli

View

Download (PDF)

Tags: Computer science, FPGA, Hardware, OpenCL, Performance

November 30, 2016 by hgpu

Parallelizing Word2Vec in Multi-Core and Many-Core Architectures

Shihao Ji, Nadathur Satish, Sheng Li, Pradeep Dubey

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, Intel Xeon Phi, NLP, nVidia, nVidia GeForce GTX Titan X, Performance, Tesla K40

November 30, 2016 by hgpu

A Metric for Performance Portability

S. J. Pennycook, J. D. Sewall, V. W. Lee

View

Download (PDF)

Tags: Computer science, CUDA, OpenACC, OpenCL, Performance, performance portability

November 25, 2016 by hgpu

Performance Analysis of CUDA and OpenCL By Implementation of Cryptographic Algorithms

Manas Mahapatra

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GT 525 M, OpenCL, Performance, Security, Thesis

November 23, 2016 by hgpu

How to scale distributed deep learning?

Peter H. Jin, Qiaochu Yuan, Forrest Iandola, Kurt Keutzer

View

Download (PDF)

Tags: Computer science, CUDA, Deep learning, GPU cluster, nVidia, Performance, Tesla K20, Tesla K80

November 19, 2016 by hgpu

Performance Analysis of Parallel Sorting Algorithms using GPU Computing

Neetu Faujdar, SP Ghrera

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, nVidia, nVidia GeForce GTX 460, Performance, Sorting

November 19, 2016 by hgpu

Autotuning CUDA Compiler Parameters for Heterogeneous Applications using the OpenTuner Framework

Pedro Bruel, Marcos Amaris, Alfredo Goldman

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, CUDA, Heterogeneous systems, Matrix multiplication, nVidia, nVidia GeForce GTX 750, nVidia GeForce GTX 980, Package, Performance, Tesla K40

November 16, 2016 by hgpu

Efficient Communications in Training Large Scale Neural Networks

Linnan Wang, Wei Wu, George Bosilca, Richard Vuduc, Zenglin Xu

View

Download (PDF)

Tags: Caffe, Computer science, CUDA, Deep learning, MPI, Neural networks, nVidia, OpenMPI, Performance

November 16, 2016 by hgpu

Benchmarking performance of a hybrid Xeon/Xeon Phi system for parallel computation of similarity measures between large vectors

Pawel Czarnul

View

Download (PDF)

Tags: Benchmarking, Computer science, Intel Xeon Phi, OpenMP, Performance

November 16, 2016 by hgpu

Hybrid CPU-GPU generation of the Hamiltonian and Overlap matrices in FLAPW methods

Diego Fabregat-Traver, Davor Davidovic, Markus Hohnerbach, Edoardo Di Napoli

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, Performance, Tesla K20, Tesla K40, Tesla K80

November 3, 2016 by hgpu

Classification Performance of Convolutional Neural Networks

Niklas Mattsson

View

Download (PDF)

Tags: Computer science, Deep learning, Neural networks, nVidia, nVidia GeForce GTX 960, nVidia Tegra TX1, Performance, Python, Theano, Thesis

November 1, 2016 by hgpu

Towards Automating Multi-dimensional Data Decomposition for Executing a Single-GPU Code on a Multi-GPU System

Ryotaro Sakai, Fumihiko Ino, Kenichi Hagihara

View

Download (PDF)

Tags: Computer science, CUDA, Matrix multiplication, nVidia, Performance, Tesla K40

November 1, 2016 by hgpu

MSCCL++: A GPU-driven communication stack for scalable AI applications

MSCCL++: Rethinking GPU Communication Abstractions for Cutting-edge AI Applications

Benchmark compute shader of Unity against InteropUnityCUDA

InteropUnityCUDA: A Tool for Interoperability Between Unity and CUDA

Data-efficient LLM Fine-tuning for Code Generation

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

DeepCompile: A Compiler-Driven Approach to Optimizing Distributed Deep Learning Training

Large Language Model Powered C-to-CUDA Code Translation: A Novel Auto-Parallelization Framework

GigaAPI: a user-space API that simplifies multi-GPU programming, bridging the gap between the capabilities of parallel GPU systems and the ability of developers to harness their full potential

GigaAPI for GPU Parallelization

Coccinelle: a C code transformation engine using SmPL for matches, refactorings, and bug fixing

Advances in Semantic Patching for HPC-oriented Refactorings with Coccinelle

* * *

high performance computing on graphics processing units: hgpu.org

Hardware thread reordering to boost OpenCL throughput on FPGAs

Parallelizing Word2Vec in Multi-Core and Many-Core Architectures

A Metric for Performance Portability

Performance Analysis of CUDA and OpenCL By Implementation of Cryptographic Algorithms

How to scale distributed deep learning?

Performance Analysis of Parallel Sorting Algorithms using GPU Computing

Autotuning CUDA Compiler Parameters for Heterogeneous Applications using the OpenTuner Framework

Efficient Communications in Training Large Scale Neural Networks

Benchmarking performance of a hybrid Xeon/Xeon Phi system for parallel computation of similarity measures between large vectors

Hybrid CPU-GPU generation of the Hamiltonian and Overlap matrices in FLAPW methods

Classification Performance of Convolutional Neural Networks

Towards Automating Multi-dimensional Data Decomposition for Executing a Single-GPU Code on a Multi-GPU System

Recent source codes

MSCCL++: A GPU-driven communication stack for scalable AI applications

Benchmark compute shader of Unity against InteropUnityCUDA

Data-efficient LLM Fine-tuning for Code Generation

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

Large Language Model Powered C-to-CUDA Code Translation: A Novel Auto-Parallelization Framework

GigaAPI: a user-space API that simplifies multi-GPU programming, bridging the gap between the capabilities of parallel GPU systems and the ability of developers to harness their full potential

Coccinelle: a C code transformation engine using SmPL for matches, refactorings, and bug fixing

DuoReduce: MLIR's benchmark

Shamrock: Multi-GPU hydrodynamics for astrophysics

LLMPerf: GPU Performance Modeling meets Large Language Models

Most viewed papers (last 30 days)