high performance computing on graphics processing units: hgpu.org

hgpu.org » Applications » Computer science

An Approach for Maximizing Performance on Heterogeneous Clusters of CPU and GPU

Nam-Luc Tran, Sabri Skhiri, Arnaud Schils, Edgar Isaac Hiroshi Leon Saiki

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Heterogeneous systems, Machine learning, Nearest neighbour, nVidia, nVidia GeForce GTX Titan, Package

December 2, 2014 by hgpu

Scalability and Optimization Strategies for GPU Enhanced Neural Networks (GeNN)

Naresh Balaji, Esin Yavuz, Thomas Nowotny

View

Download (PDF)

Source codes

Tags: Algorithms, Code generation, Computer science, CUDA, Neural networks, nVidia, nVidia GeForce GT 755 M, Package

December 2, 2014 by hgpu

Scalable Verification Techniques for Data-Parallel Programs

Nathan Yong Seng Chong

View

Download (PDF)

Source codes

Tags: ARM, Benchmarking, Computer science, CUDA, nVidia, nVidia GeForce GTX 570, OpenCL, Package, Tesla M2050, Thesis

November 25, 2014 by hgpu

Mobile GPGPU Acceleration of Embodied Robot Simulation

Simon Jones, Matthew Studley, Alan Winfield

View

Download (PDF)

Source codes

Tags: Computer science, OpenCL, Package, Robotics

November 16, 2014 by hgpu

CUDArray: CUDA-based NumPy

Anders Boesen Lindbo Larsen

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Neural networks, nVidia, Package, Python

November 16, 2014 by hgpu

Whippletree: Task-based Scheduling of Dynamic Workloads on the GPU

Markus Steinberger, Michael Kenzel, Pedro Boechat, Bernhard Kerbl, Mark Dokter, Dieter Schmalstieg

View

Download (PDF)

Source codes

Tags: 3D Graphics and Realism, Computer science, CUDA, nVidia, nVidia GeForce GTX 580, nVidia GeForce GTX 680, nVidia GeForce GTX Titan, Package, Rendering

November 13, 2014 by hgpu

Bounds on the Energy Consumption of Computational Kernels

Andrew Gearhart

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Energy-efficient computing, Heterogeneous systems, nVidia, Package, Tesla K20, Thesis

November 3, 2014 by hgpu

Contract-Based General-Purpose GPU Programming

Alexey Kolesnichenko, Christopher M. Poskitt, Sebastian Nanz, Bertrand Meyer

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, CUDA, nVidia, nVidia Quadro K 2000 M, Package, Software Engineering

October 27, 2014 by hgpu

Introducing CURRENNT – the Munich open-source CUDA RecurREnt Neural Network Toolkit

Felix Weninger, Johannes Bergmann, Bjorn Schuller

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Neural networks, nVidia, nVidia GeForce GTX 560, Package, Speech recognition

October 22, 2014 by hgpu

A Performance Comparison of Sort and Scan Libraries for GPUs

Bruce Merry

View

Download (PDF)

Source codes

Tags: Algorithms, AMD Radeon R9 270, ATI, Benchmarking, Computer science, CUDA, nVidia, nVidia GeForce GTX 480, OpenCL, Package, Sorting, Tesla K40

October 20, 2014 by hgpu

KBLAS: An Optimized Library for Dense Matrix-Vector Multiplication on GPU Accelerators

Ahmad Abdelfattah, David Keyes, Hatem Ltaief

View

Download (PDF)

Source codes

Tags: Computer science, CUBLAS, CUDA, Linear Algebra, Mathematical Software, nVidia, Package, Tesla K20

October 8, 2014 by hgpu

Deep Dynamic Neural Networks for Gesture Segmentation and Recognition

Di Wu, Ling Shao

View

Download (PDF)

Source codes

Tags: CNN, Computer science, CUDA, Neural networks, nVidia, Package, Python, Rendering

October 4, 2014 by hgpu

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

DuoReduce: MLIR's benchmark

Hardware-Assisted Software Testing and Debugging for Heterogeneous Computing

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Packages

An Approach for Maximizing Performance on Heterogeneous Clusters of CPU and GPU

Scalability and Optimization Strategies for GPU Enhanced Neural Networks (GeNN)

Scalable Verification Techniques for Data-Parallel Programs

Mobile GPGPU Acceleration of Embodied Robot Simulation

CUDArray: CUDA-based NumPy

Whippletree: Task-based Scheduling of Dynamic Workloads on the GPU

Bounds on the Energy Consumption of Computational Kernels

Contract-Based General-Purpose GPU Programming

Introducing CURRENNT – the Munich open-source CUDA RecurREnt Neural Network Toolkit

A Performance Comparison of Sort and Scan Libraries for GPUs

KBLAS: An Optimized Library for Dense Matrix-Vector Multiplication on GPU Accelerators

Deep Dynamic Neural Networks for Gesture Segmentation and Recognition

Recent source codes

PELSI: Power-Efficient Layer-Switched Inference

Ouroboros: Virtualized Queues for dynamic memory management

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

Most viewed papers (last 30 days)