high performance computing on graphics processing units: hgpu.org

Programming

hgpu.org » Programming

A Diversified Multi-Start Algorithm for Unconstrained Binary Quadratic Problems Leveraging the Graphics Processor Unit

Mark W. Lewis

View

Tags: Algorithms, Artificial intelligence, Benchmarking, Computer science, CUDA, Metaheuristics, nVidia, nVidia GeForce GTS 780 Ti

June 5, 2017 by hgpu

SparkJNI: A Reference Design for a Heterogeneous Apache Spark Framework

Tudor Alexandru Voicu

View

Download (PDF)

Tags: big data, Computer science, FPGA, Heterogeneous systems, Hybrid computing, Java, OpenCL, Spark, Thesis

June 1, 2017 by hgpu

Fast MPEG-CDVS Encoder with GPU-CPU Hybrid Computing

Lingyu Duan, Wei Sun, Xinfeng Zhang, Jie Chen, Jianxiong Yin, Simon See, Tiejun Huang, Alex C. Kot, Wen Gao

View

Download (PDF)

Tags: Benchmarking, CUDA, Hybrid computing, Image processing, Neural networks, nVidia, nVidia GeForce GTX 1060, nVidia GeForce GTX 1080, nVidia GeForce GTX 1080 Ti, nVidia Tegra TX1, Tesla M40

June 1, 2017 by hgpu

A Unified Optimization Approach for Sparse Tensor Operations on GPUs

Bangtian Liu, Chengyao Wen, Anand D.Sarwate, Maryam Mehri Dehnavi

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Linear Algebra, Mathematical Software, nVidia, nVidia GeForce GTX Titan X, Sparse matrix

June 1, 2017 by hgpu

Optimizing Memory Efficiency for Convolution Kernels on Kepler GPUs

Xiaoming Chen, Jianxu Chen, Danny Z. Chen, Xiaobo Sharon Hu

View

Download (PDF)

Tags: CNN, Computer science, Computer vision, CUDA, Deep learning, Neural networks, nVidia, Tesla K40

June 1, 2017 by hgpu

Accelerating Discrete Wavelet Transforms on GPUs

David Barina, Michal Kula, Michal Matysek, Pavel Zemcik

View

Download (PDF)

Tags: ATI, ATI Radeon HD 6970, Computer science, Discrete Wavelet Transform, HLSL, Image processing, nVidia, nVidia GeForce GTX Titan X, OpenCL, Pixel shaders

May 24, 2017 by hgpu

Implementing Efficient, Portable Computations for Machine Learning

Matthew Walter Moskewicz

View

Download (PDF)

Source codes

Tags: Algorithms, AMD R9 Nano, ATI, Computer science, Computer vision, CUDA, Deep learning, Machine learning, Neural networks, nVidia, nVidia GeForce GTX Titan X, OpenCL, Package, Thesis

May 24, 2017 by hgpu

Intel Xeon Phi acceleration of Hybrid Total FETI solver

Michal Merta, Lubomir Riha, Ondrej Meca, Alexandros Markopoulos, Tomas Brzobohaty, Tomas Kozubek, Vit Vondrak

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, Intel Xeon Phi, Laplace and Poisson equation, OpenMP, Package, Sparse direct solvers, Sparse matrix

May 24, 2017 by hgpu

Parallel and in-process compilation of individuals for genetic programming on GPU

Hakan Ayral, Songul Albayrak

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Genetic programming, nVidia, nVidia GRID K520, Operating systems, Package

May 24, 2017 by hgpu

Espresso: Efficient Forward Propagation for BCNNs

Fabrizio Pedersoli, George Tzanetakis, Andrea Tagliasacchi

View

Download (PDF)

Tags: Computer science, CUDA, Deep learning, Neural networks, nVidia, nVidia GeForce GTX 960

May 24, 2017 by hgpu

GPUMap: A Transparently GPU-Accelerated Map Function

Ivan Pachev

View

Download (PDF)

Tags: Computer science, CUDA, Distributed computing, Java, MapReduce, nVidia, nVidia GeForce GTX 980, Python, Thesis

May 22, 2017 by hgpu

MEDINA: MECCA Development in Accelerators – KPP Fortran to CUDA source-to-source Preprocessor

Michail Alvanos, Theodoros Christoudias

View

Download (PDF)

Source codes

Tags: Chemistry, Compilers, Computer science, CUDA, Fortran, nVidia, Package, Python

May 22, 2017 by hgpu

KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization

MSKernelBench & CUDAMaster

Making LLMs Optimize Multi-Scenario CUDA Kernels Like Experts

EvoScientist: Harness Vibe Research with Self-evolving AI Scientists

EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery

RepoLaunch: Automating Build and Test Pipeline of Code Repositories on ANY Language and ANY Platform

RepoLaunch: Automating Build & Test Pipeline of Code Repositories on ANY Language and ANY Platform

RepoLaunch: Automating Build and Test Pipeline of Code Repositories on ANY Language and ANY Platform

RepoLaunch: Automating Build & Test Pipeline of Code Repositories on ANY Language and ANY Platform

CONCUR: a benchmark designed to evaluate multithreaded Java code generated by LLMs

CONCUR: Benchmarking LLMs for Concurrent Code Generation

HIPRT: Ray Tracing using HIP

Ray Tracing using HIP

MXFP4 Training Support Codebase

Practical FP4 Training for Large-Scale MoE Models on Hopper GPUs

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

CUDABench: Benchmarking LLMs for Text-to-CUDA Generation

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Programming

A Diversified Multi-Start Algorithm for Unconstrained Binary Quadratic Problems Leveraging the Graphics Processor Unit

SparkJNI: A Reference Design for a Heterogeneous Apache Spark Framework

Fast MPEG-CDVS Encoder with GPU-CPU Hybrid Computing

A Unified Optimization Approach for Sparse Tensor Operations on GPUs

Optimizing Memory Efficiency for Convolution Kernels on Kepler GPUs

Accelerating Discrete Wavelet Transforms on GPUs

Implementing Efficient, Portable Computations for Machine Learning

Intel Xeon Phi acceleration of Hybrid Total FETI solver

Parallel and in-process compilation of individuals for genetic programming on GPU

Espresso: Efficient Forward Propagation for BCNNs

GPUMap: A Transparently GPU-Accelerated Map Function

MEDINA: MECCA Development in Accelerators – KPP Fortran to CUDA source-to-source Preprocessor

Recent source codes

KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization

MSKernelBench & CUDAMaster

EvoScientist: Harness Vibe Research with Self-evolving AI Scientists

RepoLaunch: Automating Build and Test Pipeline of Code Repositories on ANY Language and ANY Platform

RepoLaunch: Automating Build and Test Pipeline of Code Repositories on ANY Language and ANY Platform

CONCUR: a benchmark designed to evaluate multithreaded Java code generated by LLMs

HIPRT: Ray Tracing using HIP

MXFP4 Training Support Codebase

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

CUDABench: Benchmarking LLMs for Text-to-CUDA Generation

Most viewed papers (last 30 days)