high performance computing on graphics processing units: hgpu.org

Programming

On Runtime Systems for Task-based Programming on Heterogeneous Platforms

Samuel Thibault

View

Tags: Computer science, CUDA, Distributed computing, Heterogeneous systems, nVidia, nVidia Quadro FX 5800, OpenCL, Operating systems, StarPU, Task scheduling, Tesla C2050, Tesla K20, Tesla M2075, Thesis

December 23, 2018 by hgpu

Software Platform for Hybrid Resource Management of Many-core Accelerators

Taeyoung Kim

View

Download (PDF)

Tags: Computer science, Design space exploration, Intel Xeon Phi, OpenCL, Thesis

December 16, 2018 by hgpu

Performance Analysis of a Stereo Matching Implementation in OpenCL

Stephan Rotheneder

View

Download (PDF)

Tags: Computer science, Computer vision, nVidia, nVidia GeForce GTX 1060, nVidia GeForce GTX 1080 Ti, nVidia GeForce GTX 750 Ti, nVidia Quadro 1000 M, OpenCL, Stereo vision

December 16, 2018 by hgpu

Developing acquisition systems based on FPGA with OpenCL

Víctor Calvo Pampliega

View

Download (PDF)

Tags: Computer science, Data acquisition, FPGA, OpenCL, Thesis

December 16, 2018 by hgpu

High Performance Portable Tsunami Simulations on Many-core CPU, GPU, and FPGA

Fumiya Kono

View

Download (PDF)

Tags: AMD FirePro W8100, AMD FirePro W9100, AMD Radeon R9 280X, ATI, CUDA, Earth and Space Sciences, FPGA, Intel Xeon Phi, Numerical simulation, nVidia, OpenCL, Tesla K20, Thesis

December 9, 2018 by hgpu

ASW: Accelerating Smith-Waterman Algorithm on Coupled CPU-GPU Architecture

Huihui Zou, Shanjiang Tang, Ce Yu, Hao Fu, Yusen Li, Wenjie Tang

View

Download (PDF)

Tags: Algorithms, APU, Bioinformatics, Biology, CUDA, Heterogeneous systems, nVidia, nVidia GeForce GTX 750, OpenCL, Sequence alignment, Smith-Waterman algorithm

December 9, 2018 by hgpu

Optimization of a discontinuous finite element solver with OpenCL and StarPU

Philippe Helluy, Laura Mendoza, Bruno Weber

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, Hybrid computing, nVidia, nVidia GeForce GTX 1050 Ti, nVidia Quadro P 6000, OpenCL, Package, Task scheduling

December 9, 2018 by hgpu

Mix-and-Match: A Model-driven Runtime Optimisation Strategy for BFS on GPUs

Merijn Verstraaten, Ana Lucia Varbanescu, Cees de Laat

View

Download (PDF)

Source codes

Tags: Breadth-First Search, Computer science, CUDA, nVidia, nVidia GeForce GTX Titan X, OpenCL, Package

December 2, 2018 by hgpu

PanJoin: A Partition-based Adaptive Stream Join

Fei Pan, Hans-Arno Jacobsen

View

Download (PDF)

Tags: Algorithms, Computer science, Databases, FPGA, OpenCL

December 2, 2018 by hgpu

CLort: High Throughput and Low Energy Network Intrusion Detection on IoT Devices with Embedded GPUs

Charalampos Stylianopoulos, Linus Johansson, Oskar Olsson, Magnus Almgren

View

Download (PDF)

Source codes

Tags: ARM, Computer science, IoT, OpenCL, Package, Security

November 25, 2018 by hgpu

SWIFOLD: Smith-Waterman implementation on FPGA with OpenCL for long DNA sequences

Enzo Rucci, Carlos Garcia, Guillermo Botella, Armando De Giusti, Marcelo Naiouf, Manuel Prieto-Matias

View

Download (PDF)

Source codes

Tags: Algorithms, Biology, FPGA, OpenCL, Package, Smith-Waterman algorithm

November 25, 2018 by hgpu

Accelerating Low-End Edge Computing with Cross-Kernel Functionality Abstraction

Chao Wu, Yaoxue Zhang, Yuezhi Zhou, Qiushi Li

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 1080 Ti, OpenCL, Performance

November 18, 2018 by hgpu

ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation

SeedFold: Scaling Biomolecular Structure Prediction

Tilus: A Tile-Level GPU Kernel Programming Language

Tilus: A Tile-Level GPGPU Programming Language for Low-Precision Computation

Memory-Efficient Acceleration of Block Low-Rank Foundation Models on Resource Constrained GPUs

BoltzGen:Toward Universal Binder Design

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

cuPilot: A Strategy-Coordinated Multi-agent Framework for CUDA Kernel Evolution

MATLAB Tensor Core models

Accurate Models of NVIDIA Tensor Cores

TritonForge: Transform PyTorch Operations into Optimized GPU Kernels with LLMs

TritonForge: Profiling-Guided Framework for Automated Triton Kernel Optimization

RLTune: Hybrid Learning and Optimization-Based Dynamic Scheduling for DL Workloads on Heterogeneous GPU Clusters

Hybrid Learning and Optimization-Based Dynamic Scheduling for DL Workloads on Heterogeneous GPU Clusters

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Programming

On Runtime Systems for Task-based Programming on Heterogeneous Platforms

Software Platform for Hybrid Resource Management of Many-core Accelerators

Performance Analysis of a Stereo Matching Implementation in OpenCL

Developing acquisition systems based on FPGA with OpenCL

High Performance Portable Tsunami Simulations on Many-core CPU, GPU, and FPGA

ASW: Accelerating Smith-Waterman Algorithm on Coupled CPU-GPU Architecture

Optimization of a discontinuous finite element solver with OpenCL and StarPU

Mix-and-Match: A Model-driven Runtime Optimisation Strategy for BFS on GPUs

PanJoin: A Partition-based Adaptive Stream Join

CLort: High Throughput and Low Energy Network Intrusion Detection on IoT Devices with Embedded GPUs

SWIFOLD: Smith-Waterman implementation on FPGA with OpenCL for long DNA sequences

Accelerating Low-End Edge Computing with Cross-Kernel Functionality Abstraction

Recent source codes

ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation

SeedFold: Scaling Biomolecular Structure Prediction

Tilus: A Tile-Level GPU Kernel Programming Language

Memory-Efficient Acceleration of Block Low-Rank Foundation Models on Resource Constrained GPUs

BoltzGen:Toward Universal Binder Design

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

cuPilot: A Strategy-Coordinated Multi-agent Framework for CUDA Kernel Evolution

MATLAB Tensor Core models

TritonForge: Transform PyTorch Operations into Optimized GPU Kernels with LLMs

RLTune: Hybrid Learning and Optimization-Based Dynamic Scheduling for DL Workloads on Heterogeneous GPU Clusters

Most viewed papers (last 30 days)