high performance computing on graphics processing units: hgpu.org

Applications

hgpu.org » paper

Electric potential and field calculation of charged BEM triangles and rectangles by Gaussian cubature

Ferenc Gluck, Daniel Hilk

View

Download (PDF)

Tags: Computational Physics, nVidia, OpenCL, Physics, Tesla K40

June 16, 2016 by hgpu

NCAM: Near-Data Processing for Nearest Neighbor Search

Vincent T. Lee, Carlo C. del Mundo, Armin Alaghi, Luis Ceze, Mark Oskin, Ali Farhadi

View

Download (PDF)

Tags: Computer science, CUDA, Machine learning, Nearest neighbour, nVidia, nVidia GeForce GTX Titan X, nVidia Jetson TK1

June 16, 2016 by hgpu

Omnivore: An Optimizer for Multi-device Deep Learning on CPUs and GPUs

Stefan Hadjis, Ce Zhang, Ioannis Mitliagkas, Christopher Re

View

Download (PDF)

Tags: Computer science, CUDA, Deep learning, Machine learning, Neural networks, nVidia, nVidia GeForce GTX Titan X

June 16, 2016 by hgpu

Multi-Tenant Virtual GPUs for Optimising Performance of a Financial Risk Application

Javier Prades, Blesson Varghese, Carlos Reano, Federico Silla

View

Download (PDF)

Tags: Computer science, CUDA, Finance, nVidia, Tesla K20

June 16, 2016 by hgpu

Performance-Portable Many-Core Plasma Simulations: Porting PIConGPU to OpenPower and Beyond

Erik Zenker, Rene Widera, Axel Hubl, Guido Juckeland, Andreas Knupfer, Wolfgang E. Nagel, Michael Bussmann

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Heterogeneous systems, nVidia, OpenMP, Package, Particle-in-cell methods, Physics, Plasma physics, Programming techniques, Tesla K80

June 14, 2016 by hgpu

First Application of Lattice QCD to Pezy-SC Processor

Tatsumi Aoyama, Ken-Ichi Ishikawa, Yasuyuki Kimura, Hideo Matsufuru, Atsushi Sato, Tomohiro Suzuki, Sunao Torii

View

Download (PDF)

Tags: High Energy Physics - Lattice, Matrix multiplication, OpenCL, Physics, QCD

June 14, 2016 by hgpu

OpenCL-Based Erasure Coding on Heterogeneous Architectures

Guoyang Chen, Huiyang Zhou, Xipeng Shen, Josh Gahm, Narayan Venkat, Skip Booth, John Marshall

View

Download (PDF)

Tags: Algorithms, APU, ATI, Computer science, Error recovery, FPGA, Heterogeneous systems, nVidia, OpenCL, Tesla K40

June 14, 2016 by hgpu

Processing Big Data in Main Memory and on GPU

Meisam Fathi Salmi

View

Download (PDF)

Tags: big data, Computer science, CUDA, Hadoop, Java, OpenCL, Scala, Spark, Thesis

June 14, 2016 by hgpu

Multi-GPU Implementation of Machine Learning Algorithm using CUDA and OpenCL

Jan Masek, Radim Burget, Lukas Povoda, Malay Kishore Dutta

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Machine learning, Nearest neighbour, nVidia, nVidia GeForce GTX 690, OpenCL

June 14, 2016 by hgpu

Analysis and Parameter Prediction of Compiler Transformation for Graphics Processors

Alberto Magni

View

Download (PDF)

Source codes

Tags: ATI, ATI Radeon HD 5970, ATI Radeon HD 7970, Computer science, Machine learning, Neural networks, nVidia, nVidia GeForce GTX 480, OpenCL, Package, performance portability, Tesla K20, Thesis

June 9, 2016 by hgpu

Decoupled Vector-Fetch Architecture with a Scalarizing Compiler

Yunsup Lee

View

Download (PDF)

Tags: Computer science, CUDA, Electronic design automation, Heterogeneous systems, LLVM, OpenCL, Performance, PTX, SoC, Thesis

June 9, 2016 by hgpu

OpenMP Parallelization and Optimization of Graph-based Machine Learning Algorithms

Zhaoyi Meng, Alice Koniges, Yun (Helen) He, Samuel Williams, Thorsten Kurth, Brandon Cook, Jack Deslippe, Andrea L. Bertozzi

View

Download (PDF)

Tags: Clustering, Computer science, Intel Xeon Phi, Machine learning, OpenMP

June 9, 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

Electric potential and field calculation of charged BEM triangles and rectangles by Gaussian cubature

NCAM: Near-Data Processing for Nearest Neighbor Search

Omnivore: An Optimizer for Multi-device Deep Learning on CPUs and GPUs

Multi-Tenant Virtual GPUs for Optimising Performance of a Financial Risk Application

Performance-Portable Many-Core Plasma Simulations: Porting PIConGPU to OpenPower and Beyond

First Application of Lattice QCD to Pezy-SC Processor

OpenCL-Based Erasure Coding on Heterogeneous Architectures

Processing Big Data in Main Memory and on GPU

Multi-GPU Implementation of Machine Learning Algorithm using CUDA and OpenCL

Analysis and Parameter Prediction of Compiler Transformation for Graphics Processors

Decoupled Vector-Fetch Architecture with a Scalarizing Compiler

OpenMP Parallelization and Optimization of Graph-based Machine Learning Algorithms

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)