high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

An N log N Parallel Fast Direct Solver for Kernel Matrices

Chenhan D. Yu, William B. March, George Biros

View

Download (PDF)

Source codes

Tags: Algorithms, Computational Complexity, Computer science, Factorization, Intel Xeon Phi, Machine learning, Package, Performance

January 16, 2017 by hgpu

An FPGA Accelerator for Molecular Dynamics Simulation Using OpenCL

Hasitha Muthumala Waidyasooriya, Masanori Hariyama, Kota Kasahara

View

Download (PDF)

Tags: Chemistry, FPGA, Heterogeneous systems, Molecular dynamics, OpenCL, Performance, Physics

January 10, 2017 by hgpu

An initial performance review of software components for a heterogeneous computing platform

Ivan Svogor

View

Download (PDF)

Tags: ATI, ATI Radeon HD 7750, Computer science, Energy-efficient computing, FPGA, Heterogeneous systems, OpenCL, Performance, Robotics

January 4, 2017 by hgpu

Language Modeling with Gated Convolutional Networks

Yann N. Dauphin, Angela Fan, Michael Auli, David Grangier

View

Download (PDF)

Tags: Computer science, CUDA, Deep learning, NLP, nVidia, Performance, Tesla M40, Torch

December 26, 2016 by hgpu

Performance Optimisation of Smoothed Particle Hydrodynamics Algorithms for Multi/Many-Core Architectures

Fabio Baruffa, Luigi Iapichino, Nicolay J. Hammer, Vasileios Karakasis

View

Download (PDF)

Tags: Algorithms, Astrophysics, Computational Physics, Computer science, Instrumentation and Methods for Astrophysics, Intel Xeon Phi, OpenMP, Performance, Physics

December 20, 2016 by hgpu

Efficient Realization of Householder Transform through Algorithm-Architecture Co-design for Acceleration of QR Factorization

Farhad Merchant, Tarun Vatwani, Anupam Chattopadhyay, Soumyendu Raha, S K Nandy, Ranjani Narayan

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Factorization, FPGA, Linear Algebra, Mathematical Software, Matrix multiplication, nVidia, Performance, Tesla C2050

December 17, 2016 by hgpu

Automating the Last-Mile for High Performance Dense Linear Algebra

Richard Michael Veras, Tze Meng Low, Tyler Michael Smith, Robert van de Geijn, Franz Franchetti

View

Download (PDF)

Tags: Code generation, Computer science, Intel Xeon Phi, Linear Algebra, Performance

December 14, 2016 by hgpu

Performance Evaluation and Optimization of HPCG benchmark on CPU + MIC platform

Qingyi Pan, Xiaoying Wang

View

Download (PDF)

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

December 10, 2016 by hgpu

Adaptive Work-Efficient Connected Components on the GPU

Michael Sutton, Tal Ben-Nun, Amnon Barak, Sreepathi Pai, Keshav Pingali

View

Download (PDF)

Tags: Computer science, nVidia, Performance, Tesla M60

December 10, 2016 by hgpu

A Comparison of GPU Execution Time Prediction using Machine Learning and Analytical Modeling

Marcos Amaris, Raphael Y. de Camargo, Mohamed Dyab, Alfredo Goldman, Denis Trystram

View

Download (PDF)

Source codes

Tags: Analytical model, Benchmarking, Computer science, Heterogeneous systems, Machine learning, nVidia, nVidia GeForce GTX 680, nVidia GeForce GTX 970, nVidia GeForce GTX 980, nVidia GeForce GTX Titan, nVidia GeForce GTX Titan Black, nVidia GeForce GTX Titan X, nVidia Quadro K5200, Package, Performance, Tesla K20, Tesla K40

December 6, 2016 by hgpu

OpenACC cache Directive: Opportunities and Optimizations

Ahmad Lashgar, Amirali Baniasadi

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, CUDA, nVidia, OpenACC, OpenCL, Package, Performance, Tesla K20

December 3, 2016 by hgpu

Should I use TensorFlow?

Martin Schrimpf

View

Download (PDF)

Tags: Computer science, CUDA, Deep learning, Machine learning, nVidia, Performance, Python, TensorFlow

December 3, 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

An N log N Parallel Fast Direct Solver for Kernel Matrices

An FPGA Accelerator for Molecular Dynamics Simulation Using OpenCL

An initial performance review of software components for a heterogeneous computing platform

Language Modeling with Gated Convolutional Networks

Performance Optimisation of Smoothed Particle Hydrodynamics Algorithms for Multi/Many-Core Architectures

Efficient Realization of Householder Transform through Algorithm-Architecture Co-design for Acceleration of QR Factorization

Automating the Last-Mile for High Performance Dense Linear Algebra

Performance Evaluation and Optimization of HPCG benchmark on CPU + MIC platform

Adaptive Work-Efficient Connected Components on the GPU

A Comparison of GPU Execution Time Prediction using Machine Learning and Analytical Modeling

OpenACC cache Directive: Opportunities and Optimizations

Should I use TensorFlow?

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)