high performance computing on graphics processing units: hgpu.org

Programming

hgpu.org » Programming

MAGMA Embedded: Towards a Dense Linear Algebra Library for Energy Efficient Extreme Computing

Azzam Haidar, Stanimire Tomov, Piotr Luszczek, Jack Dongarra

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Factorization, Linear Algebra, nVidia, nVidia Jetson TK1, Package

October 6, 2015 by hgpu

Optimizing GPU-accelerated Group-By and Aggregation

Tomas Karnagel, Rene Mueller, Guy M. Lohman

View

Download (PDF)

Tags: Computer science, CUDA, Databases, nVidia, nVidia GeForce GTX Titan

October 6, 2015 by hgpu

CVC: The Contourlet Video Compression algorithm for real-time applications

Stamos Katsigiannis, Georgios Papaioannou, Dimitris Maroulis

View

Download (PDF)

Tags: Algorithms, Compression, CUDA, Image processing, nVidia, nVidia GeForce GXT 570, YCoCg

October 6, 2015 by hgpu

Brute-Force k-Nearest Neighbors Search on the GPU

Shengren Li, Nina Amenta

View

Download (PDF)

Tags: Computer science, CUDA, Matrix multiplication, Nearest neighbour, nVidia, nVidia GeForce GTX 460, Sorting

October 3, 2015 by hgpu

Tuned and GPU-accelerated parallel data mining from comparable corpora

Krzysztof Wolk, Krzysztof Marasek

View

Download (PDF)

Tags: Algorithms, Computer science, Data mining, Machine learning, NLP, nVidia, nVidia GeForce GTX 660

October 3, 2015 by hgpu

Fast Algorithms for Convolutional Neural Networks

Andrew Lavin

View

Download (PDF)

Tags: Algorithms, CNN, Computer science, Deep learning, FFT, Image recognition, Machine learning, Neural networks

October 3, 2015 by hgpu

Analysis of A Splitting Approach for the Parallel Solution of Linear Systems on GPU Cards

Ang Li, Radu Serban, Dan Negrut

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Linear Algebra, nVidia, Package, Sparse direct solvers, Tesla K20

September 30, 2015 by hgpu

Solving prime-field ECDLPs on GPUs with OpenCL

Erik Boss

View

Download (PDF)

Tags: ATI, ATI Radeon HD 7850, Computer science, nVidia, nVidia GeForce GTX 780, OpenCL, Security, Thesis

September 29, 2015 by hgpu

Performance Testing of GPU-Based Approximate Matching Algorithm on Network Traffic

Mujeeb B Jimoh

View

Download (PDF)

Tags: Computer science, CUDA, Databases, nVidia, nVidia GeForce GTX Titan, Security, Thesis

September 29, 2015 by hgpu

A Design Framework for Mapping Dataflow Graphs onto Heterogeneous Multiprocessor Platforms

Shuoxin Lin

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, DSP, Heterogeneous systems, nVidia, nVidia GeForce GTX 680, Thesis

September 29, 2015 by hgpu

The Dynamical Kernel Scheduler – Part 1

Andreas Adelmann, Uldis Locans, Andreas Suter

View

Download (PDF)

Tags: Algorithms, Computational Physics, CUDA, FFT, Intel Xeon Phi, Monte Carlo simulation, nVidia, OpenCL, OpenMP, Physics

September 29, 2015 by hgpu

From Pixels to Torques: Policy Learning using Deep Dynamical Convolutional Networks

John-Alexander M. Assael

View

Download (PDF)

Source codes

Tags: CNN, Computer science, CUDA, Deep learning, Lua, Machine learning, nVidia, Package, Tesla K40, Thesis

September 26, 2015 by hgpu

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

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

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

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

LLMQ: Efficient Lower-Precision LLM Training for Consumer GPUs

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

True 4-Bit Quantized CNN Training on CPU

True 4-Bit Quantized Convolutional Neural Network Training on CPU: Achieving Full-Precision Parity

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

Hunting CUDA Bugs at Scale with cuFuzz

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Programming

MAGMA Embedded: Towards a Dense Linear Algebra Library for Energy Efficient Extreme Computing

Optimizing GPU-accelerated Group-By and Aggregation

CVC: The Contourlet Video Compression algorithm for real-time applications

Brute-Force k-Nearest Neighbors Search on the GPU

Tuned and GPU-accelerated parallel data mining from comparable corpora

Fast Algorithms for Convolutional Neural Networks

Analysis of A Splitting Approach for the Parallel Solution of Linear Systems on GPU Cards

Solving prime-field ECDLPs on GPUs with OpenCL

Performance Testing of GPU-Based Approximate Matching Algorithm on Network Traffic

A Design Framework for Mapping Dataflow Graphs onto Heterogeneous Multiprocessor Platforms

The Dynamical Kernel Scheduler – Part 1

From Pixels to Torques: Policy Learning using Deep Dynamical Convolutional Networks

Recent source codes

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

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

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

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

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

True 4-Bit Quantized CNN Training on CPU

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

Most viewed papers (last 30 days)