high performance computing on graphics processing units: hgpu.org

Programming

hgpu.org » Programming

Acceleration of Block-Aware Matrix Factorization on Heterogeneous Platforms

Gregory W. Somers

View

Download (PDF)

Tags: ATI, ATI Radeon HD 7950, Computer science, Factorization, Heterogeneous systems, Linear Algebra, OpenCL, Thesis

September 20, 2016 by hgpu

Feynman Machine: The Universal Dynamical Systems Computer

Eric Laukien, Richard Crowder, Fergal Byrne

View

Download (PDF)

Tags: AMD Radeon R9 290, Artificial intelligence, ATI, Computer science, Deep learning, Mathematics, Neuroscience, OpenCL

September 20, 2016 by hgpu

Runtime Support for Adaptive Power Capping on Heterogeneous SoCs

Yun Wu, Dimitrios S. Nikolopoulos, Roger Woods

View

Download (PDF)

Tags: ARM, Benchmarking, Computer science, Energy-efficient computing, FPGA, Heterogeneous systems, OpenCL, OpenMP, SoC

September 20, 2016 by hgpu

The CUDA LATCH Binary Descriptor: Because Sometimes Faster Means Better

Christopher Parker, Matthew Daiter, Kareem Omar, Gil Levi, Tal Hassner

View

Download (PDF)

Source codes

Tags: Computer science, Computer vision, CUDA, nVidia, nVidia GeForce GTX 1080, Package

September 17, 2016 by hgpu

Parallel Dynamics Computation using Prefix Sum Operations

Yajue Yang, Yuanqing Wu, Jia Pan

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, Robotics, Tesla K40

September 17, 2016 by hgpu

A parallel pattern for iterative stencil + reduce

M. Aldinucci, M. Danelutto, M. Drocco, P. Kilpatrick, C. Misale, G. Peretti Pezzi, M. Torquati

View

Download (PDF)

Tags: ARM, Computer science, nVidia, OpenCL, Stencil computation, Tesla K40, Tesla M2090

September 17, 2016 by hgpu

Agent-Based Modeling on High Performance Computing Architectures

Nuno Fachada

View

Download (PDF)

Source codes

Tags: cpu, GPGPU, HPC, Java, OpenCL, Thesis

September 16, 2016 by fakenmc

Data Analysis of Minimally-Structured Heterogeneous Logs: An experimental study of log template extraction and anomaly detection based on Recurrent Neural Network and Naive Bayes

Chang Liu

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, LSTM, NLP, nVidia, Package, RNN, Thesis

September 13, 2016 by hgpu

Scheduling of Linear Algebra Kernels on Multiple Heterogeneous Resources

Olivier Beaumont, Terry Cojean, Lionel Eyraud-Dubois, Abdou Guermouche, Suraj Kumar

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Factorization, Heterogeneous systems, Linear Algebra, nVidia, Tesla K40

September 13, 2016 by hgpu

OpenMP as a High-Level Specification Language for Parallelism And its use in Evaluating Parallel Programming Systems

Max Grossman, Jun Shirako, Vivek Sarkar

View

Download (PDF)

Source codes

Tags: Code generation, Compilers, Computer science, CUDA, LLVM, nVidia, OpenMP, Package

September 13, 2016 by hgpu

An efficient numerical method for solving the Boltzmann equation in multidimensions

Giacomo Dimarco, Raphael Loubere, Jacek Narski, Thomas Rey

View

Download (PDF)

Tags: Algorithms, Boltzmann equation, cfd, CUDA, Fluid dynamics, Mathematics, MPI, Numerical Analysis, nVidia, OpenMP, Physics

September 13, 2016 by hgpu

A New Architecture for Optimization Modeling Frameworks

Matt Wytock, Steven Diamond, Felix Heide, Stephen Boyd

View

Download (PDF)

Source codes

Tags: Algorithms, CUDA, Deep learning, Linear Algebra, Mathematics, nVidia, nVidia GeForce GTX Titan X, Package, Python

September 13, 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

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

Programming

Acceleration of Block-Aware Matrix Factorization on Heterogeneous Platforms

Feynman Machine: The Universal Dynamical Systems Computer

Runtime Support for Adaptive Power Capping on Heterogeneous SoCs

The CUDA LATCH Binary Descriptor: Because Sometimes Faster Means Better

Parallel Dynamics Computation using Prefix Sum Operations

A parallel pattern for iterative stencil + reduce

Agent-Based Modeling on High Performance Computing Architectures

Data Analysis of Minimally-Structured Heterogeneous Logs: An experimental study of log template extraction and anomaly detection based on Recurrent Neural Network and Naive Bayes

Scheduling of Linear Algebra Kernels on Multiple Heterogeneous Resources

OpenMP as a High-Level Specification Language for Parallelism And its use in Evaluating Parallel Programming Systems

An efficient numerical method for solving the Boltzmann equation in multidimensions

A New Architecture for Optimization Modeling Frameworks

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)