high performance computing on graphics processing units: hgpu.org

hgpu.org » Benchmarking

A Performance Comparison of Algebraic Multigrid Preconditioners on CPUs, GPUs, and Xeon Phis

K. Rupp, J. Weinbub, F. Rudolf, A. Morhammer, T. Grasser, A. Jungel

View

Tags: AMD FirePro W9100, ATI, Benchmarking, Computer science, CUDA, Intel Xeon Phi, Linear Algebra, nVidia, OpenCL, OpenMP, Performance, Tesla K20

September 9, 2015 by hgpu

Dissecting GPU Memory Hierarchy through Microbenchmarking

Xinxin Mei, Xiaowen Chu

View

Download (PDF)

Source codes

Tags: Benchmarking, cache, Computer science, CUDA, Hardware Architecture, nVidia, nVidia GeForce GTX 560 Ti, nVidia GeForce GTX 780, nVidia GeForce GTX 980, Package

September 9, 2015 by hgpu

Partitioning Large Scale Deep Belief Networks Using Dropout

Yanping Huang, Sai Zhang

View

Download (PDF)

Source codes

Tags: Benchmarking, Databases, Deep learning, Machine learning, nVidia, nVidia GeForce 8800 GS, Python, Statistics

August 31, 2015 by hgpu

Boosting Java Performance using GPGPUs

James Clarkson, Christos Kotselidis, Gavin Brown, Mikel Lujan

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, Heterogeneous systems, Java, nVidia, Performance, Tesla K20

August 28, 2015 by hgpu

Automatic Optimization of Thread Mapping for a GPGPU Programming Framework

Kazuhiko Ohno, Tomoharu Kamiya, Takanori Maruyama, Masaki Matsumoto

View

Download (PDF)

Tags: Benchmarking, Compilers, Computer science, CUDA, Memory model, nVidia, nVidia GeForce GTX 980

July 15, 2015 by hgpu

Evaluating the capabilities of the Xeon Phi platform in the context of software-only, thread-level speculation

Alvaro Estebanez, Diego R. Llanos, Arturo Gonzalez-Escribano

View

Download (PDF)

Tags: Benchmarking, Computer science, Intel Xeon Phi, Performance

July 13, 2015 by hgpu

Best bang for your buck: GPU nodes for GROMACS biomolecular simulations

Carsten Kutzner, Szilard Pall, Martin Fechner, Ansgar Esztermann, Bert L. de Groot, Helmut Grubmuller

View

Download (PDF)

Source codes

Tags: Benchmarking, Biological Physics, Biomolecules, Computational Physics, Computer science, Molecular dynamics, Molecular simulation, MPI, nVidia, Package, Performance, Tesla K20, Tesla K40

July 6, 2015 by hgpu

Intra-Application Data-Communication Characterization

Imran Ashraf, Vlad-Mihai Sima, Koen Bertels

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, nVidia, nVidia GeForce GT 640

June 30, 2015 by hgpu

Autotuning Tensor Contraction Computations on GPUs

Axel Rivera, Mary Hall, Paul D. Hovland, Elizabeth Jessup, Thomas Nelson, Boyana Norris

View

Download (PDF)

Tags: Benchmarking, Code generation, Computer science, CUDA, Matrix multiplication, nVidia, OpenACC, Tesla C2050, Tesla K20

June 19, 2015 by hgpu

Practical Symbolic Execution Analysis and Methodology for GPU Programs

Peng Li

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, CUDA, nVidia, nVidia GeForce GTX 480, Package, Thesis

June 10, 2015 by hgpu

Machine Learning Based Auto-tuning for Enhanced OpenCL Performance Portability

Thomas L. Falch, Anne C. Elster

View

Download (PDF)

Tags: ATI, ATI Radeon HD 7970, Benchmarking, Computer science, Deep learning, Heterogeneous systems, Machine learning, Neural networks, nVidia, OpenCL, Tesla K40

June 5, 2015 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

A Performance Comparison of Algebraic Multigrid Preconditioners on CPUs, GPUs, and Xeon Phis

Dissecting GPU Memory Hierarchy through Microbenchmarking

Partitioning Large Scale Deep Belief Networks Using Dropout

Boosting Java Performance using GPGPUs

Automatic Optimization of Thread Mapping for a GPGPU Programming Framework

Evaluating the capabilities of the Xeon Phi platform in the context of software-only, thread-level speculation

Best bang for your buck: GPU nodes for GROMACS biomolecular simulations

Intra-Application Data-Communication Characterization

Autotuning Tensor Contraction Computations on GPUs

Practical Symbolic Execution Analysis and Methodology for GPU Programs

Machine Learning Based Auto-tuning for Enhanced OpenCL Performance Portability

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)