high performance computing on graphics processing units: hgpu.org

Applications

hgpu.org » paper

Towards Interactive Visual Exploration of Parallel Programs using a Domain-specific Language

Tobias Klein

View

Tags: Computer science, CUDA, DSL, Heterogeneous systems, Image processing, nVidia, nVidia Quadro 6000, OpenCL, Thesis, Visualization

January 29, 2016 by hgpu

GPU-Accelerated Recurrent Neural Networks: OpenCLLink and SymbolicC

Zdenek Buk

View

Download (PDF)

Source codes

Tags: Computer science, Deep learning, Machine learning, Neural networks, nVidia, OpenCL, Package, RNN

January 29, 2016 by hgpu

GeNN: a code generation framework for accelerated brain simulations

Esin Yavuz, James Turner, Thomas Nowotny

View

Download (PDF)

Source codes

Tags: Biology, Code generation, CUDA, Neural networks, Neuroscience, Numerical simulation, nVidia, nVidia Quadro K 2000 M, Package, Tesla C2070, Tesla K40

January 29, 2016 by hgpu

Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition

Francisco Javier Ordonez, Daniel Roggen

View

Download (PDF)

Source codes

Tags: Computer science, Deep learning, LSTM, Machine learning, Neural networks, Package, Python, RNN, Theano

January 26, 2016 by hgpu

Compositional Compilation for Sparse, Irregular Data Parallelism

Adam Harries, Michel Steuwer, Murray Cole, Alan Gray, Christophe Dubach

View

Download (PDF)

Tags: Computer science, Data parallelism, nVidia, OpenCL, Sparse matrix, Tesla K40

January 26, 2016 by hgpu

Improving GPU-accelerated Adaptive IDW Interpolation Algorithm Using Fast kNN Search

Gang Mei, Nengxiong Xu, Liangliang Xu

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Nearest neighbour, nVidia, nVidia GeForce GT 730 M

January 26, 2016 by hgpu

Task Parallel Incomplete Cholesky Factorization using 2D Partitioned-Block Layout

Kyungjoo Kim, Sivasankaran Rajamanickam, George Stelle, H. Carter Edwards, Stephen L. Olivier

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, Factorization, Intel Xeon Phi, Mathematical Software, Package, Sparse matrix

January 26, 2016 by hgpu

Power Consumption Modeling and Prediction in a Hybrid CPU-GPU-MIC Supercomputer

Alina Sirbu, Ozalp Babaoglu

View

Download (PDF)

Source codes

Tags: Computer science, Energy-efficient computing, Intel Xeon Phi, Package, Python, Task scheduling

January 26, 2016 by hgpu

Parallel Explicit FEM Algorithms Using GPU’s

Seyed Parsa Banihashemi

View

Download (PDF)

Tags: Algorithms, AMD Radeon R9 280X, ATI, ATI Radeon HD 7970, Computer science, FEM, Finite element method, nVidia, nVidia GeForce GTX Titan, OpenCL, Particle swarm optimization, Performance, Tesla M2090, Thesis

January 22, 2016 by hgpu

Heterogeneous (CPU+GPU) Working-set Hash Tables

Ziaul Choudhury, Suresh Purini

View

Download (PDF)

Tags: Computer science, CUDA, Hashing, Heterogeneous systems, nVidia, Tesla K20

January 22, 2016 by hgpu

Exploring LLVM Infrastructure for Simplified Multi-GPU Programming

Alexander Matz, Mark Hummel, Holger Froning

View

Download (PDF)

Tags: Computer science, CUDA, LLVM, nVidia, OpenCL, Tesla K80

January 22, 2016 by hgpu

Basker: A Threaded Sparse LU Factorization Utilizing Hierarchical Parallelism and Data Layouts

Joshua Dennis Booth, Sivasankaran Rajamanickam, Heidi K. Thornquist

View

Download (PDF)

Tags: Algorithms, Computer science, Factorization, Intel Xeon Phi, Sparse direct solvers, Sparse matrix

January 22, 2016 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

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

* * *

high performance computing on graphics processing units: hgpu.org

Applications

Towards Interactive Visual Exploration of Parallel Programs using a Domain-specific Language

GPU-Accelerated Recurrent Neural Networks: OpenCLLink and SymbolicC

GeNN: a code generation framework for accelerated brain simulations

Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition

Compositional Compilation for Sparse, Irregular Data Parallelism

Improving GPU-accelerated Adaptive IDW Interpolation Algorithm Using Fast kNN Search

Task Parallel Incomplete Cholesky Factorization using 2D Partitioned-Block Layout

Power Consumption Modeling and Prediction in a Hybrid CPU-GPU-MIC Supercomputer

Parallel Explicit FEM Algorithms Using GPU’s

Heterogeneous (CPU+GPU) Working-set Hash Tables

Exploring LLVM Infrastructure for Simplified Multi-GPU Programming

Basker: A Threaded Sparse LU Factorization Utilizing Hierarchical Parallelism and Data Layouts

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

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

KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization

Most viewed papers (last 30 days)