high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

TAP: A TLP-Aware Cache Management Policy for a CPU-GPU Heterogeneous Architecture

Jaekyu Lee, Hyesoon Kim

View

Download (PDF)

Tags: Computer science, Heterogeneous systems, Memory, Performance

January 25, 2012 by hgpu

Dynamically Managed Data for CPU-GPU Architectures

Thomas B. Jablin, James A. Jablin, Prakash Prabhu, Feng Liu, David I. August

View

Download (PDF)

Tags: Computer science, CUDA, Data Structures and Algorithms, Memory model, nVidia, nVidia GeForce GTX 480, Performance

January 19, 2012 by hgpu

FPGA Based Acceleration of Decimal Operations

Alberto Nannarelli

View

Download (PDF)

Tags: Computer science, Finance, FPGA, Performance

January 16, 2012 by hgpu

Spectral Method Characterization on FPGA and GPU Accelerators

Karl Pereira, Peter Athanas, Heshan Lin, Wu Feng

View

Download (PDF)

Tags: Computer science, CUDA, DSP, FFT, FPGA, nVidia, nVidia GeForce GTX 280, Performance, Tesla C2050

January 15, 2012 by hgpu

A Hybrid Circular Queue Method for Iterative Stencil Computations on GPUs

Yang Yang, Hui-Min Cui, Xiao-Bing Feng, Jing-Ling Xue

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, Performance, Tesla C2050

January 10, 2012 by hgpu

A class of communication-avoiding algorithms for solving general dense linear systems on CPU/GPU parallel machines

Marc Baboulin, Simplice Donfack, Laura Grigori, Adrien Remy, Stanimire Tomov, Jack Dongarra

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Factorization, Linear Algebra, nVidia, Performance, Tesla S2050

January 8, 2012 by hgpu

Block-asynchronous Multigrid Smoothers for GPU-accelerated Systems

Hartwig Anzt, Stanimire Tomov, Mark Gates, Jack Dongarra, Vincent Heuveline

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Linear Algebra, nVidia, Performance, Tesla C2070

January 8, 2012 by hgpu

Implementation of Kd-Trees on the GPU to Achieve Real Time Graphics Processing

Will W. Martin

View

Download (PDF)

Tags: 3D Graphics and Realism, Algorithms, Computer science, KD-tree, nVidia, Performance, Raytracing

January 8, 2012 by hgpu

A GPU Implementation of Inclusion-based Points-to Analysis

Mario Mendez-Lojo, Martin Burtscher, Keshav Pingali

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, CUDA, Graph theory, nVidia, Package, Performance, Programming techniques, Tesla C2070

January 5, 2012 by hgpu

PARRAY: A Unifying Array Representation for Heterogeneous Parallelism

Yifeng Chen, Xiang Cui, Hong Mei

View

Download (PDF)

Tags: Code generation, Computer science, CUDA, FFT, GPU cluster, Heterogeneous systems, MPI, nVidia, Optimization, Performance, Programming techniques, Pthreads, Tesla C1060

January 5, 2012 by hgpu

Efficient mapping of the training of Convolutional Neural Networks to a CUDA-based cluster

Jonatan Ward, Sergey Andreev, Francisco Heredia, Bogdan Lazar, Zlatka Manevska

View

Download (PDF)

Tags: Algorithms, CNN, Computer science, CUDA, GPU cluster, Neural networks, nVidia, nVidia GeForce GTX 570, Performance

January 4, 2012 by hgpu

Automatic SIMD Code Generation

Roland Leissa

View

Download (PDF)

Tags: Algorithms, Code generation, Computer science, Optimization, Performance, Software Engineering, Thesis

January 4, 2012 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

TAP: A TLP-Aware Cache Management Policy for a CPU-GPU Heterogeneous Architecture

Dynamically Managed Data for CPU-GPU Architectures

FPGA Based Acceleration of Decimal Operations

Spectral Method Characterization on FPGA and GPU Accelerators

A Hybrid Circular Queue Method for Iterative Stencil Computations on GPUs

A class of communication-avoiding algorithms for solving general dense linear systems on CPU/GPU parallel machines

Block-asynchronous Multigrid Smoothers for GPU-accelerated Systems

Implementation of Kd-Trees on the GPU to Achieve Real Time Graphics Processing

A GPU Implementation of Inclusion-based Points-to Analysis

PARRAY: A Unifying Array Representation for Heterogeneous Parallelism

Efficient mapping of the training of Convolutional Neural Networks to a CUDA-based cluster

Automatic SIMD Code Generation

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)