high performance computing on graphics processing units: hgpu.org

Manuel López-Martínez, Germán Díaz-Flórez, Santiago Villagrana-Barraza, Luis O. Solís-Sánchez, Héctor A. Guerrero-Osuna, Genaro M. Soto-Zarazúa, Carlos A. Olvera-Olvera

View

Download (PDF)

Tags: CUDA, Deep learning, Distributed computing, HPC, Image processing, Neural networks, nVidia, nVidia GeForce GTX 1050 Ti

June 4, 2023 by hgpu

Communication-minimizing Asynchronous Tensor Parallelism

Siddharth Singh, Zack Sating, Abhinav Bhatele

View

Download (PDF)

Tags: Computer science, CUDA, GPU cluster, Neural networks, nVidia, nVidia A100

May 28, 2023 by hgpu

Performance Optimization using Multimodal Modeling and Heterogeneous GNN

Akash Dutta, Jordi Alcaraz, Ali TehraniJamsaz, Eduardo Cesar, Anna Sikora, Ali Jannesari

View

Download (PDF)

Tags: AMD Radeon HD 7970, ATI, Benchmarking, Computer science, Deep learning, Heterogeneous systems, Neural networks, nVidia, nVidia GeForce GTX 970, OpenCL, OpenMP

May 14, 2023 by hgpu

ParaGraph: Weighted Graph Representation for Performance Optimization of HPC Kernels

Ali TehraniJamsaz, Alok Mishra, Akash Dutta, Abid M. Malik, Barbara Chapman, Ali Jannesari

View

Download (PDF)

Tags: AMD Radeon Instinct Mi50, ATI, Computer science, HPC, Machine learning, Neural networks, nVidia, nVidia V100, OpenMP, Performance

April 16, 2023 by hgpu

Energy-Efficient GPU Clusters Scheduling for Deep Learning

Diandian Gu, Xintong Xie, Gang Huang, Xin Jin, Xuanzhe Liu

View

Download (PDF)

Tags: Computer science, Deep learning, Energy-efficient computing, GPU cluster, Neural networks, nVidia, Tesla V100

April 16, 2023 by hgpu

Task parallelism-based architectures on FPGA to optimize the energy efficiency of AI at the edge

Rafael Gadea-Gironés, Jorge Fe, Jose M. Monzo

View

Download (PDF)

Tags: Artificial intelligence, Computer science, Energy-efficient computing, FPGA, Neural networks, OpenCL

April 2, 2023 by hgpu

Over-synchronization in GPU Programs

profile_util: simple C++ library to report memory, timing, thread affinity

Profile Util library: A quick and easy way to get MPI, OpenMP and GPU runtime information

MaC: Mamba CPU performance predictor

MambaCPU: Enhanced Correlation Mining with State Space Models for CPU Performance Prediction

Mixed-precision finite element kernels

Mixed-precision finite element kernels and assembly: Rounding error analysis and hardware acceleration

SHMT: The Simultaneous and Heterogenous Multithreading project

General-Purpose Computing on Tensor Processors

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

EnergyUCB-Bandit

Online Energy Optimization in GPUs: A Multi-Armed Bandit Approach

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Monadic Deep Learning

qecGPT: decoding Quantum Error-correcting Codes with Generative Pre-trained Transformers

Miriam: Exploiting Elastic Kernels for Real-time Multi-DNN Inference on Edge GPU

Improving the Performance, Portability, and Productivity of Hardware Accelerators

Managing, Profiling, and Optimizing Heterogeneous GPU Workloads

Improving Performance of Iterative Applications through Interleaved Execution of Approximated CUDA Kernels

A High-Performance Computing Cluster for Distributed Deep Learning: A Practical Case of Weed Classification Using Convolutional Neural Network Models

Communication-minimizing Asynchronous Tensor Parallelism

Performance Optimization using Multimodal Modeling and Heterogeneous GNN

ParaGraph: Weighted Graph Representation for Performance Optimization of HPC Kernels

Energy-Efficient GPU Clusters Scheduling for Deep Learning

Task parallelism-based architectures on FPGA to optimize the energy efficiency of AI at the edge

Recent source codes

Kokkidio: Kokkos+Eigen - write fast, readable multi-platform code

LLaMA-Inference-Bench

MATAR

Over-synchronization in GPU Programs

profile_util: simple C++ library to report memory, timing, thread affinity

MaC: Mamba CPU performance predictor

Mixed-precision finite element kernels

SHMT: The Simultaneous and Heterogenous Multithreading project

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

EnergyUCB-Bandit

Most viewed papers (last 30 days)