high performance computing on graphics processing units: hgpu.org

Carla Osthoff, Roberto Pinto Souto, Fabricio Vilasboas, Pablo Grunmann, Pedro L. Silva Dias, Francieli Boito, Rodrigo Kassick, Laercio Pilla, Philippe Navaux, Claudio Schepke, Nicolas Maillard, Jairo Panetta, Pedro Pais Lopes, Robert Walko

View

Download (PDF)

Tags: CUDA, Earth and Space Sciences, nVidia, nVidia GeForce GTX 285, Performance, Tesla C2050

April 10, 2012 by hgpu

A Study of Productivity and Performance of Modern Vector Processors

Paul Springer

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia Quadro FX 6000, OpenCL, Performance, Thesis

April 9, 2012 by hgpu

Bound the Peak Performance of SGEMM on GPU with software-controlled fast memory

Junjie Lai, Andre Seznec

View

Download (PDF)

Tags: Computer science, CUBLAS, CUDA, nVidia, nVidia GeForce GTX 580, Performance

April 7, 2012 by hgpu

Optimized Strategies for Mapping Three-dimensional FFTs onto CUDA GPUs

Jing Wu, Joseph JaJa

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, FFT, nVidia, nVidia GeForce GTX 280, nVidia GeForce GTX 480, Performance, Tesla C1060, Tesla C2050

March 30, 2012 by hgpu

Performance evaluation of GPU memory hierarchy using the FFT

Jacobo Lobeiras, Margarita Amor, Ramon Doallo

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, FFT, nVidia, nVidia GeForce GTX 280, nVidia GeForce GTX 480, Performance, Signal processing

March 30, 2012 by hgpu

Auto-tuning a High-Level Language Targeted to GPU Codes

Scott Grauer-Gray, Lifan Xu, Robert Searles, Sudhee Ayalasomayajula, John Cavazos

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce 9800 GT, nVidia GeForce GTX 280, OpenCL, Optimization, Performance, Programming techniques, Stereo vision, Tesla C2050

March 28, 2012 by hgpu

Improving Performance of OpenCL on CPUs

Ralf Karrenberg, Sebastian Hack

View

Download (PDF)

Tags: Code generation, Computer science, Data parallelism, OpenCL, Performance

March 27, 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

Computing Performance Benchmarks among CPU, GPU, and FPGA

Image Convolution Processing: a GPU versus FPGA Comparison

Priority-Based Task Management in a GPGPU Megakernel

Performance Exploration of Selected Manually and Automatically Parallelized Codes on GPUs

Improving Atmospheric Model Performance on a Multi-Core Cluster System

A Study of Productivity and Performance of Modern Vector Processors

Bound the Peak Performance of SGEMM on GPU with software-controlled fast memory

Optimized Strategies for Mapping Three-dimensional FFTs onto CUDA GPUs

Performance evaluation of GPU memory hierarchy using the FFT

Auto-tuning a High-Level Language Targeted to GPU Codes

Improving Performance of OpenCL on CPUs

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)