high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

Testing Tesla architecture for scientific computing: The performance of matrix-vector product

Pawel Maciol, Krzysztof Banas

View

Tags: Computer science, CUDA, Linear Algebra, Matrix multiplication, nVidia, nVidia GeForce 8800 GTX, Performance, Tesla C870

July 10, 2011 by hgpu

A Comparison of FPGA and GPU for Real-Time Phase-based Optical Flow, Stereo, and Local Image Features

Karl Pauwels, Matteo Tomasi, Javier Diaz Alonso, Eduardo Ros, Marc M. Van Hulle

Tags: Computer science, Computer vision, FPGA, Optical flow, Performance

July 10, 2011 by hgpu

Power and Performance Characterization of Computational Kernels on the GPU

Y. Jiao, H. Lin, P. Balaji, W. Feng

View

Download (PDF)

Tags: Computer science, Energy-efficient computing, FFT, nVidia, nVidia GeForce GTX 280, OpenCL, Performance

July 9, 2011 by hgpu

GPU volume rendering in 3D echocardiography: Real-time pre-processing and ray-casting

Gabriel Kiss, Erik Steen, Jon Petter Asen, Hans G. Torp

Tags: CUDA, Heart, Medicine, nVidia, OpenCL, Performance, Rendering, Visualization

July 9, 2011 by hgpu

Frameworks for GPU Accelerators: A comprehensive evaluation using 2D/3D image registration

Richard Membarth, Frank Hannig, Jurgen Teich, Mario Korner, Wieland Eckert

View

Download (PDF)

Tags: CUDA, Image processing, Image registration, nVidia, nVidia Quadro FX 5800, OpenCL, Performance, RapidMind, Tesla C2050

July 9, 2011 by hgpu

Comparing performance and energy efficiency of FPGAs and GPUs for high productivity computing

Brahim Betkaoui, David B. Thomas, Wayne Luk

View

Download (PDF)

Tags: Computer science, CUDA, Energy-efficient computing, FPGA, nVidia, Performance, Tesla C1060

July 7, 2011 by hgpu

A Hybrid Computing Platform Digital Wideband Receiver Design and Performance Measurement

K. George, C.-I. H. Chen

Tags: FPGA, nVidia, Performance, Signal processing, Tesla C2050

June 30, 2011 by hgpu

A comparative benchmarking of the FFT on Fermi and Evergreen GPUs

M.F. Ahmed, O. Haridy

Tags: ATI, ATI Radeon HD 5870, Benchmarking, Computer science, FFT, Hardware Architecture, nVidia, nVidia GeForce GTX 480, Performance

June 30, 2011 by hgpu

GPU-Based Heuristic Solver for Linear Sum Assignment Problems Under Real-time Constraints

Roberto Roverso, Amgad Naiem, Mohammed El-Beltagy, Sameh El-Ansary

View

Download (PDF)

Tags: CUDA, Mathematical Software, Mathematics, nVidia, nVidia GeForce GTX 295, Optimization, Performance

June 29, 2011 by hgpu

Efficient implementation of the overlap operator on multi-GPUs

Andrei Alexandru, Michael Lujan, Craig Pelissier, Ben Gamari, Frank X. Lee

View

Download (PDF)

Tags: GPU cluster, High Energy Physics - Lattice, MPI, nVidia, Performance, Physics, Tesla M2070

June 27, 2011 by hgpu

Implementation and Performance Analysis of SEAL Encryption on FPGA, GPU and Multi-core Processors

Kostas Theoharoulis, Charalambos Antoniadis, Nikolaos Bellas, Christos D. Antonopoulos

Tags: Algorithms, Computer science, FPGA, Performance, Security

June 22, 2011 by hgpu

Architecture, Design, and Experimental Evaluation of a Lightfield Descriptor Depth Buffer Algorithm on Reconfigurable Logic and on a GPU

Matina Lakka, Grigorios Chrysos, Ioannis Papaefstathiou, Apostolos Dollas

Tags: Computer science, FPGA, Information Retrieval, nVidia, Performance

June 16, 2011 by hgpu

KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels

CuTile Benchmark Suite: Performance and Productivity Tradeoffs for GPU Kernel Programming on Blackwell Architecture

Evaluating CUDA Tile for AI Workloads on Hopper and Blackwell GPUs

MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU

Device Virtual Machine (DVM)

DVM: Real-Time Kernel Generation for Dynamic AI Models

Agentic Code Optimization via Compiler-LLM Cooperation

AutoKernel: Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels

AutoKernel: Autonomous GPU Kernel Optimization via Iterative Agent-Driven Search

LLM.Q: Quantized LLM training in pure CUDA/C++

LLMQ: Efficient Lower-Precision LLM Training for Consumer GPUs

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Testing Tesla architecture for scientific computing: The performance of matrix-vector product

A Comparison of FPGA and GPU for Real-Time Phase-based Optical Flow, Stereo, and Local Image Features

Power and Performance Characterization of Computational Kernels on the GPU

GPU volume rendering in 3D echocardiography: Real-time pre-processing and ray-casting

Frameworks for GPU Accelerators: A comprehensive evaluation using 2D/3D image registration

Comparing performance and energy efficiency of FPGAs and GPUs for high productivity computing

A Hybrid Computing Platform Digital Wideband Receiver Design and Performance Measurement

A comparative benchmarking of the FFT on Fermi and Evergreen GPUs

GPU-Based Heuristic Solver for Linear Sum Assignment Problems Under Real-time Constraints

Efficient implementation of the overlap operator on multi-GPUs

Implementation and Performance Analysis of SEAL Encryption on FPGA, GPU and Multi-core Processors

Architecture, Design, and Experimental Evaluation of a Lightfield Descriptor Depth Buffer Algorithm on Reconfigurable Logic and on a GPU

Recent source codes

KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels

CUDA Kernel Fusion Benchmarks

IntelliKit: Agent-first tooling for AMD hardware

DITRON: Distributed Compiler based on Triton for Parallel Systems

CuTile Benchmark Suite: Performance and Productivity Tradeoffs for GPU Kernel Programming on Blackwell Architecture

MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU

Device Virtual Machine (DVM)

Agentic Code Optimization via Compiler-LLM Cooperation

AutoKernel: Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels

LLM.Q: Quantized LLM training in pure CUDA/C++

Most viewed papers (last 30 days)