high performance computing on graphics processing units: hgpu.org

Programming

hgpu.org » Programming » OpenCL

cltorch: a Hardware-Agnostic Backend for the Torch Deep Neural Network Library, Based on OpenCL

Hugh Perkins

View

Download (PDF)

Source codes

Tags: Algorithms, CNN, Computer science, Deep learning, Machine learning, Neural networks, nVidia, nVidia GRID K520, OpenCL, Package

June 21, 2016 by hgpu

Splotch: porting and optimizing for the Xeon Phi

Timothy Dykes, Claudio Gheller, Marzia Rivi, Mel Krokos

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Intel Xeon Phi, Numerical simulation, nVidia, OpenCL, Package, Tesla K20, Visualization

June 16, 2016 by hgpu

Analysis and Parameter Prediction of Compiler Transformation for Graphics Processors

Alberto Magni

View

Download (PDF)

Source codes

Tags: ATI, ATI Radeon HD 5970, ATI Radeon HD 7970, Computer science, Machine learning, Neural networks, nVidia, nVidia GeForce GTX 480, OpenCL, Package, performance portability, Tesla K20, Thesis

June 9, 2016 by hgpu

clSPARSE: A Vendor-Optimized Open-Source Sparse BLAS Library

Joseph L. Greathouse, Kent Knox, Jakub Pola, Kiran Varaganti, Mayank Daga

View

Download (PDF)

Source codes

Tags: Algorithms, AMD Radeon R9 Fury X, ATI, Computer science, Linear Algebra, nVidia, nVidia GeForce GTX Titan X, OpenCL, Package, Sparse matrix

May 30, 2016 by hgpu

Employing Directive Based Compression Solutions on Accelerators Global Memory under OpenACC

Ebad Salehi

View

Download (PDF)

Source codes

Tags: Compression, Computer science, CUDA, nVidia, OpenACC, OpenCL, Package, Tesla K20, Thesis

May 21, 2016 by hgpu

DeepLearningKit – an GPU Optimized Deep Learning Framework for Apple’s iOS, OS X and tvOS developed in Metal and Swift

Amund Tveit, Torbjorn Morland, Thomas Brox Rost

View

Download (PDF)

Source codes

Tags: Computer science, Deep learning, Neural networks, OpenCL, Package, Video, Vulkan

May 17, 2016 by hgpu

Microbenchmarks for GPU characteristics: the occupancy roofline and the pipeline model

Jan Lemeire, Jan G. Cornelis, Laurent Segers

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, Java, nVidia, nVidia GeForce GT 640, nVidia Quadro K620, OpenCL, Package

May 9, 2016 by hgpu

Parallel Wavelet Schemes for Images

David Barina, Michal Kula, Pavel Zemcik

View

Download (PDF)

Source codes

Tags: AMD Radeon R9 290X, AMD Radeon R9 Fury, ATI, Compression, Discrete Wavelet Transform, Image processing, nVidia, nVidia GeForce GTX 580, nVidia GeForce GTX Titan X, OpenCL, Package

May 7, 2016 by hgpu

Array Program Transformation with Loo.py by Example: High-Order Finite Elements

Andreas Klockner, Lucas C. Wilcox, T. Warburton

View

Download (PDF)

Source codes

Tags: Algorithms, AMD Radeon R9 Fury, ATI, Code generation, Computer science, Fortran, Numerical Analysis, nVidia, nVidia GeForce GTX Titan X, OpenCL, Package, Performance, Prefetch, Programming Languages, Python, Tesla K40

April 29, 2016 by hgpu

Automatic Parallelization: Executing Sequential Programs on a Task-Based Parallel Runtime

Alcides Fonseca, Bruno Cabral, Joao Rafael, Ivo Correia

View

Download (PDF)

Source codes

Tags: Computer science, Java, OpenCL, Package, Programming Languages

April 29, 2016 by hgpu

To Co-Run, or Not To Co-Run: A Performance Study on Integrated Architectures

Feng Zhang, Jidong Zhai, Wenguang Chen, Bingsheng He, Shuhao Zhang

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, OpenCL, Package

April 26, 2016 by hgpu

Efficiency of general Krylov methods on GPUs – An experimental study

Hartwig Anzt, Jack Dongarra, Moritz Kreutzer, Gerhard Wellein, Martin Kohler

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Intel Xeon Phi, Linear Algebra, nVidia, OpenCL, Package, Sparse matrix, Tesla K40

April 16, 2016 by hgpu

IntelliKit: Agent-first tooling for AMD hardware

Kerncap: Automated Kernel Extraction and Isolation for AMD GPUs

DITRON: Distributed Compiler based on Triton for Parallel Systems

DITRON: Distributed Multi-level Tiling Compiler for Parallel Tensor Programs

CuTile Benchmark Suite: Performance and Productivity Tradeoffs for GPU Kernel Programming on Blackwell Architecture

Evaluating CUDA Tile for AI Workloads on Hopper and Blackwell GPUs

Agentic Code Optimization via Compiler-LLM Cooperation

MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU

Device Virtual Machine (DVM)

DVM: Real-Time Kernel Generation for Dynamic AI Models

AutoKernel: Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels

AutoKernel: Autonomous GPU Kernel Optimization via Iterative Agent-Driven Search

Triton-Sanitizer: A Fast and Device-Agnostic Memory Sanitizer for Triton with Rich Diagnostic Context

LLM.Q: Quantized LLM training in pure CUDA/C++

LLMQ: Efficient Lower-Precision LLM Training for Consumer GPUs

SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Programming

cltorch: a Hardware-Agnostic Backend for the Torch Deep Neural Network Library, Based on OpenCL

Splotch: porting and optimizing for the Xeon Phi

Analysis and Parameter Prediction of Compiler Transformation for Graphics Processors

clSPARSE: A Vendor-Optimized Open-Source Sparse BLAS Library

Employing Directive Based Compression Solutions on Accelerators Global Memory under OpenACC

DeepLearningKit – an GPU Optimized Deep Learning Framework for Apple’s iOS, OS X and tvOS developed in Metal and Swift

Microbenchmarks for GPU characteristics: the occupancy roofline and the pipeline model

Parallel Wavelet Schemes for Images

Array Program Transformation with Loo.py by Example: High-Order Finite Elements

Automatic Parallelization: Executing Sequential Programs on a Task-Based Parallel Runtime

To Co-Run, or Not To Co-Run: A Performance Study on Integrated Architectures

Efficiency of general Krylov methods on GPUs – An experimental study

Recent source codes

IntelliKit: Agent-first tooling for AMD hardware

DITRON: Distributed Compiler based on Triton for Parallel Systems

CuTile Benchmark Suite: Performance and Productivity Tradeoffs for GPU Kernel Programming on Blackwell Architecture

Agentic Code Optimization via Compiler-LLM Cooperation

MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU

Device Virtual Machine (DVM)

AutoKernel: Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels

Triton-Sanitizer: A Fast and Device-Agnostic Memory Sanitizer for Triton with Rich Diagnostic Context

LLM.Q: Quantized LLM training in pure CUDA/C++

SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits

Most viewed papers (last 30 days)