high performance computing on graphics processing units: hgpu.org

hgpu.org » CUDA

MPI-GPU parallelism in iterative eigensolvers for block-tridiagonal matrices

A. Lamas Davina, J. E. Roman

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Factorization, MPI, nVidia, Tesla K80

February 2, 2017 by hgpu

Autotuning GPU Kernels via Static and Predictive Analysis

Robert V. Lim, Boyana Norris, Allen D. Malony

View

Download (PDF)

Tags: Code generation, Computer science, CUDA, nVidia, Performance, PTX, Tesla K20, Tesla M2050, Tesla M40

February 2, 2017 by hgpu

Parallel Implementations of the Cholesky Decomposition on CPUs and GPUs

Joao Paulo Tarasconi Ruschel

View

Download (PDF)

Source codes

Tags: Algorithms, Benchmarking, Computer science, CUDA, Linear Algebra, Matrix decomposition, nVidia, OpenCL, OpenMP, Package, Performance, Tesla K80, Thesis

January 26, 2017 by hgpu

A GPU-Based Solution to Fast Calculation of Betweenness Centrality on Large Weighted Networks

Rui Fan, Ke Xu, Jichang Zhao

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, CUDA, nVidia, nVidia GeForce GTX 980, Package

January 26, 2017 by hgpu

Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, Jeff Dean

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Deep learning, GPU cluster, Machine learning, Neural networks, nVidia, TensorFlow, Tesla K40

January 26, 2017 by hgpu

DeepBach: a Steerable Model for Bach chorales generation

Gaetan Hadjeres, Francois Pachet

View

Download (PDF)

Source codes

Tags: Artificial intelligence, Computer science, CUDA, Deep learning, Keras, nVidia, nVidia GeForce GTX 980 Ti, Package

January 23, 2017 by hgpu

GPGPU Performance Estimation with Core and Memory Frequency Scaling

Qiang Wang, Xiaowen Chu

View

Download (PDF)

Tags: Computer science, CUDA, Hardware, nVidia, nVidia GeForce GTX 980, Performance

January 23, 2017 by hgpu

A task-driven implementation of a simple numerical solver for hyperbolic conservation laws

Mohamed Essadki, Jonathan Jung, Adam Larat, Milan Pelletier, Vincent Perrier

View

Download (PDF)

Tags: Computer science, CUDA, Mathematical Software, Numerical Analysis, nVidia, Task scheduling, Tesla K40

January 23, 2017 by hgpu

OpenNMT: Open-Source Toolkit for Neural Machine Translation

Guillaume Klein, Yoon Kim, Yuntian Deng, Jean Senellart, Alexander M. Rush

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, Machine learning, NLP, nVidia, nVidia GeForce GTX 1080, Package, Python, Torch

January 19, 2017 by hgpu

Parallelizing Exact and Approximate String Matching via Inclusive Scan on a GPU

Yasuaki Mitani, Fumihiko Ino, Kenichi Hagihara

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, CUDA, nVidia, nVidia GeForce GTX Titan X, Package, String matching

January 19, 2017 by hgpu

Light Loss-Less Data Compression, with GPU Implementation

Shunji Funasaka, Koji Nakano, Yasuaki Ito

View

Download (PDF)

Tags: Algorithms, Compression, Computer science, CUDA, nVidia, nVidia GeForce GTX 1080

January 19, 2017 by hgpu

Using efficient parallelization in Graphic Processing Units to parameterize stochastic fire propagation models

Monica Denham, Karina Laneri, Juan Manuel Morales

View

Download (PDF)

Source codes

Tags: Biology, CUDA, Earth and Space Sciences, nVidia, nVidia GeForce GTX 780, nVidia GeForce GTX Titan, Package, Tesla C2070, Tesla K40

January 16, 2017 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

MPI-GPU parallelism in iterative eigensolvers for block-tridiagonal matrices

Autotuning GPU Kernels via Static and Predictive Analysis

Parallel Implementations of the Cholesky Decomposition on CPUs and GPUs

A GPU-Based Solution to Fast Calculation of Betweenness Centrality on Large Weighted Networks

Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

DeepBach: a Steerable Model for Bach chorales generation

GPGPU Performance Estimation with Core and Memory Frequency Scaling

A task-driven implementation of a simple numerical solver for hyperbolic conservation laws

OpenNMT: Open-Source Toolkit for Neural Machine Translation

Parallelizing Exact and Approximate String Matching via Inclusive Scan on a GPU

Light Loss-Less Data Compression, with GPU Implementation

Using efficient parallelization in Graphic Processing Units to parameterize stochastic fire propagation models

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)