high performance computing on graphics processing units: hgpu.org

Ilya Lashuk, Aparna Chandramowlishwaran, Harper Langston, Tuan-Anh nguyen, Rahul Sampath, Aashay Shringarpure, Richard Vuduc, Lexing Ying, Denis Zorin, George Biros

View

Download (PDF)

Tags: Computer science, CUDA, Fast multipole method, Heterogeneous systems, MPI, nVidia, Programming techniques, Tesla M2070

July 5, 2012 by hgpu

Navigating An Evolutionary Fast Path to Exascale – Expanded Version

R.F. Barrett, S.D. Hammond, C.T. Vaughan, D.W. Doerfler, M.A. Heroux

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, nVidia, Tesla M2090

July 5, 2012 by hgpu

A Fast GPU-Based Motion Estimation Algorithm for H.264/AVC

Rafael Rodriguez-Sanchez, Jose Luis Martinez, Gerardo Fernandez-Escribano, Jose Luis Sanchez, Jose Manuel Claver

View

Download (PDF)

Tags: Compression, Computational Complexity, CUDA, H.264/AVC, Heterogeneous systems, Image processing, nVidia, nVidia GeForce GTX 480

July 4, 2012 by hgpu

A Scheduling Framework for a Heterogeneous Parallel Architecture

Wei Zhang

View

Download (PDF)

Tags: Computer science, CUDA, Distributed computing, Heterogeneous systems, nVidia, nVidia Quadro FX 1800, Task scheduling, Tesla C1060, Thesis

June 30, 2012 by hgpu

An Optimized Large-Scale Hybrid DGEMM Design for CPUs and ATI GPUs

Jiajia Li, Xingjian Li, Guangming Tan, Mingyu Chen, Ninghui Sun

View

Download (PDF)

Source codes

Tags: Algorithms, ATI, ATI CAL, ATI Radeon HD 5970, ATI Stream, Computer science, Heterogeneous systems, Matrix multiplication, Optimization, Package

June 29, 2012 by hgpu

OpenCL Floating Point Software on Heterogeneous Architectures – Portable or Not?

Miriam Leeser, Jaideep Ramachandran, Thomas Wahl, Devon Yablonski

View

Download (PDF)

Tags: Computer science, Heterogeneous systems, OpenCL

June 27, 2012 by hgpu

GreenGPU: A Holistic Approach to Energy Efficiency in GPU-CPU Heterogeneous Architectures

Kai Ma, Xue Li, Wei Chen, Chi Zhang, Xiaorui Wang

View

Download (PDF)

Tags: Computer science, CUDA, Energy-efficient computing, Heterogeneous systems, nVidia, nVidia GeForce 8800 GTX

June 26, 2012 by hgpu

Compiling a high-level language for GPUs: (via language support for architectures and compilers)

Christophe Dubach, Perry Cheng, Rodric Rabbah, David F. Bacon, Stephen J. Fink

View

Download (PDF)

Tags: ATI, ATI Radeon HD 5970, Compilers, Computer science, CUDA, Heterogeneous systems, Java, nVidia, nVidia GeForce 8800 GTX, nVidia GeForce GTX 580, OpenCL, Programming Languages

June 26, 2012 by hgpu

Agentic Code Optimization via Compiler-LLM Cooperation

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

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

SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits

Triton-Sanitizer: A Fast and Device-Agnostic Memory Sanitizer for Triton with Rich Diagnostic Context

* * *

high performance computing on graphics processing units: hgpu.org

Invitation to a Standard Programming Interface for Massively Parallel Computing Environment: OpenCL

A Generic Library for Stencil Computations

High Performance System in GPU and CUDA Media Processing System

A Massively Parallel Adaptive Fast Multipole Method on Heterogeneous Architectures

Navigating An Evolutionary Fast Path to Exascale – Expanded Version

A Fast GPU-Based Motion Estimation Algorithm for H.264/AVC

A Scheduling Framework for a Heterogeneous Parallel Architecture

An Optimized Large-Scale Hybrid DGEMM Design for CPUs and ATI GPUs

OpenCL Floating Point Software on Heterogeneous Architectures – Portable or Not?

GreenGPU: A Holistic Approach to Energy Efficiency in GPU-CPU Heterogeneous Architectures

Compiling a high-level language for GPUs: (via language support for architectures and compilers)

Recent source codes

Agentic Code Optimization via Compiler-LLM Cooperation

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

Device Virtual Machine (DVM)

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

SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits

Triton-Sanitizer: A Fast and Device-Agnostic Memory Sanitizer for Triton with Rich Diagnostic Context

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

True 4-Bit Quantized CNN Training on CPU

cuFuzz: A GPU-oriented coverage-guided fuzzer for userland CUDA application

KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization

Most viewed papers (last 30 days)