high performance computing on graphics processing units: hgpu.org

Applications

hgpu.org » paper

GPU Parallelization for Unstructured Sparse Matrix Problems with OpenMP 4.5 and OpenACC

Stefan Rosenberger, Gundolf Haase

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, nVidia, nVidia GeForce GTX 1060, OpenACC, OpenMP, Sparse matrix

November 21, 2017 by hgpu

Unified Deep Learning with CPU, GPU, and FPGA Technologies

Allen Rush, Ashish Sirasao, Mike Ignatowski

View

Download (PDF)

Tags: Computer science, Deep learning, FPGA, Heterogeneous systems, Machine learning, OpenCL

November 21, 2017 by hgpu

Hydra: a C++11 framework for data analysis in massively parallel platforms

A. A. Alves Junior, M. D. Sokoloff

View

Download (PDF)

Source codes

Tags: Computational Physics, Computer science, CUDA, Mathematical Software, nVidia, OpenMP, Package, Tesla K40

November 16, 2017 by hgpu

Launch-time Optimization of OpenCL Kernels

Andrew Siu Doug Lee

View

Download (PDF)

Tags: Computer science, LLVM, nVidia, nVidia GeForce GTX 780, OpenCL, Performance, Thesis

November 16, 2017 by hgpu

Accelerating HPC codes on Intel(R) Omni-Path Architecture networks: From particle physics to Machine Learning

Peter Boyle, Michael Chuvelev, Guido Cossu, Christopher Kelly, Christoph Lehner, Lawrence Meadows

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, Intel Xeon Phi, Machine learning, MPI, OpenMP, Package, Performance, Physics

November 16, 2017 by hgpu

Deep learning for galaxy surface brightness profile fitting

D. Tuccillo, M. Huertas-Company, E. Decenciere, S. Velasco-Forero, H. Dominguez Sanchez, P. Dimauro

View

Download (PDF)

Tags: Astrophysics, Deep learning, Keras, nVidia, nVidia GeForce GTX Titan X

November 16, 2017 by hgpu

Domain-Specific Acceleration and Auto-Parallelization of Legacy Scientific Code in FORTRAN 77 using Source-to-Source Compilation

Wim Vanderbauwhede, Gavin Davidson

View

Download (PDF)

Source codes

Tags: Compilers, Computer science, Fortran, Heterogeneous systems, Mathematical Software, Numerical Analysis, nVidia, nVidia GeForce GTX Titan X, OpenACC, OpenCL, OpenMP, Package

November 16, 2017 by hgpu

Vectorized algorithm for multidimensional Monte Carlo integration on modern GPU, CPU and MIC architectures

Przemyslaw Stpiczynski

View

Download (PDF)

Tags: Algorithms, Computer science, Intel Xeon Phi, Monte Carlo integration, nVidia, OpenACC, OpenMP, Pseudo-random number generators, Tesla K40

November 12, 2017 by hgpu

Scalable and massively parallel Monte Carlo photon transport simulations for heterogeneous computing platforms

Leiming Yu, Fanny Nina-Paravecino, David Kaeli, Qianqian Fang

View

Download (PDF)

Source codes

Tags: Algorithms, AMD R9 Nano, AMD Radeon RX 480, ATI, Computational Physics, Heterogeneous systems, nVidia, nVidia GeForce GTX 1050 Ti, nVidia GeForce GTX 1080 Ti, nVidia GeForce GTX 590, nVidia GeForce GTX 980 Ti, nVidia GeForce GTX Titan X, OpenCL, Package, Physics

November 12, 2017 by hgpu

Best Practice Guide – GPGPU

Momme Allalen, Vali Codreanu, Nevena Ilieva-Litova, Alan Gray, Anders Sjostrom, Volker Weinberg

View

Download (PDF)

Tags: Computer science, CUDA, OpenACC, OpenCL, OpenMP, Review

November 12, 2017 by hgpu

Low-power System-on-Chip Processors for Energy Efficient High Performance Computing: The Texas Instruments Keystone II

Gaurav Mitra

View

Download (PDF)

Tags: ARM, Benchmarking, Computer science, DSP, Heterogeneous systems, Matrix multiplication, nVidia, nVidia Jetson TK1, nVidia Tegra TX1, OpenCL, SoC, Thesis

November 12, 2017 by hgpu

Performance Evaluation of Deep Learning Tools in Docker Containers

Pengfei Xu, Shaohuai Shi, Xiaowen Chu

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, CUDA, Deep learning, nVidia, nVidia GeForce GTX 980, nVidia GeForce GTX Titan X, Package, Performance

November 12, 2017 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

GPU Parallelization for Unstructured Sparse Matrix Problems with OpenMP 4.5 and OpenACC

Unified Deep Learning with CPU, GPU, and FPGA Technologies

Hydra: a C++11 framework for data analysis in massively parallel platforms

Launch-time Optimization of OpenCL Kernels

Accelerating HPC codes on Intel(R) Omni-Path Architecture networks: From particle physics to Machine Learning

Deep learning for galaxy surface brightness profile fitting

Domain-Specific Acceleration and Auto-Parallelization of Legacy Scientific Code in FORTRAN 77 using Source-to-Source Compilation

Vectorized algorithm for multidimensional Monte Carlo integration on modern GPU, CPU and MIC architectures

Scalable and massively parallel Monte Carlo photon transport simulations for heterogeneous computing platforms

Best Practice Guide – GPGPU

Low-power System-on-Chip Processors for Energy Efficient High Performance Computing: The Texas Instruments Keystone II

Performance Evaluation of Deep Learning Tools in Docker Containers

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)