high performance computing on graphics processing units: hgpu.org

hgpu.org » nVidia

Isolated Scheduling for Distributed Training Tasks in GPU Clusters

Xinchi Han, Weihao Jiang, Peirui Cao, Qinwei Yang, Yunzhuo Liu, Shuyao Qi, Shengkai Lin, Shizhen Zhao

View

Download (PDF)

Source codes

Tags: Computer science, GPU cluster, Machine learning, Neural networks, nVidia, nVidia V100, Package

August 13, 2023 by hgpu

Bandicoot: C++ Library for GPU Linear Algebra and Scientific Computing

Ryan R. Curtin, Marcus Edel, Conrad Sanderson

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Linear Algebra, nVidia, nVidia GeForce RTX 2080 Ti, OpenCL, Package, Programming techniques

July 30, 2023 by hgpu

Fast Knowledge Graph Completion using Graphics Processing Units

Chun-Hee Lee, Dong-oh Kang, Hwa Jeon Song

View

Download (PDF)

Tags: AI, Algorithms, Computer science, CUDA, Databases, Graph theory, nVidia, nVidia A100

July 30, 2023 by hgpu

A portable C++ library for memory and compute abstraction on multi-core CPUs and GPUs

Pietro Incardona, Aryaman Gupta, Serhii Yaskovets, Ivo F. Sbalzarini

View

Download (PDF)

Source codes

Tags: AMD RX Vega 64, ATI, Computer science, CUDA, nVidia, nVidia A100, nVidia GeForce RTX 3090, OpenACC, OpenCL, OpenMP, Package, Performance, performance portability, SYCL

July 30, 2023 by hgpu

Creating a Dataset Supporting Translation Between OpenMP Fortran and C++ Code

Bin Lei, Caiwen Ding, Le Chen, Pei-Hung Lin, Chunhua Liao

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Fortran, Machine learning, nVidia, nVidia RTX 6000 Ada, OpenMP, Package

July 24, 2023 by hgpu

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

Hanyan Cao, Feng Pan, Yijia Wang, Pan Zhang

View

Download (PDF)

Source codes

Tags: Artificial intelligence, Computer science, Neural networks, nVidia, nVidia A100, Package

July 24, 2023 by hgpu

Maximizing Parallelism and GPU Utilization For Direct GPU Compilation Through Ensemble Execution

Shilei Tian, Barbara Chapman, Johannes Doerfert

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, LLVM, nVidia, nVidia A100, OpenMP, Performance

July 24, 2023 by hgpu

Mystique: Enabling Accurate and Scalable Generation of Production AI Benchmarks

Mingyu Liang, Wenyin Fu, Louis Feng, Zhongyi Lin, Pavani Panakanti, Shengbao Zheng, Srinivas Sridharan, Christina Delimitrou

View

Download (PDF)

Source codes

Tags: AI, Benchmarking, Code generation, Computer science, CUDA, nVidia, Package, Performance, PyTorch, Tesla A100, Tesla V100

July 16, 2023 by hgpu

Towards Intelligent Runtime Framework for Distributed Heterogeneous Systems

Polykarpos Thomadakis

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, Machine learning, Nuclear physics, nVidia, OpenCL, Physics, Task scheduling, Tesla V100, Thesis

July 16, 2023 by hgpu

Tile-based Lightweight Integer Compression in GPU

Anil Shanbhag, Bobbi W. Yogatama, Xiangyao Yu, Samuel Madden

View

Download (PDF)

Source codes

Tags: Algorithms, Compression, Computer science, CUDA, nVidia, nVidia V100, Package

July 16, 2023 by hgpu

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

Zhihe Zhao, Neiwen Ling, Nan Guan, Guoliang Xing

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, Deep learning, Neural networks, nVidia, nVidia GeForce RTX 2060, nVidia Jetson TX2

July 16, 2023 by hgpu

Improving the Performance, Portability, and Productivity of Hardware Accelerators

Pablo Antonio Martínez Sánchez

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, Linear Algebra, Matrix multiplication, Neural networks, nVidia, nVidia GeForce RTX 2080, nVidia GeForce RTX 2080 Ti, Performance, performance portability, Thesis

July 16, 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

Isolated Scheduling for Distributed Training Tasks in GPU Clusters

Bandicoot: C++ Library for GPU Linear Algebra and Scientific Computing

Fast Knowledge Graph Completion using Graphics Processing Units

A portable C++ library for memory and compute abstraction on multi-core CPUs and GPUs

Creating a Dataset Supporting Translation Between OpenMP Fortran and C++ Code

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

Maximizing Parallelism and GPU Utilization For Direct GPU Compilation Through Ensemble Execution

Mystique: Enabling Accurate and Scalable Generation of Production AI Benchmarks

Towards Intelligent Runtime Framework for Distributed Heterogeneous Systems

Tile-based Lightweight Integer Compression in GPU

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

Improving the Performance, Portability, and Productivity of Hardware Accelerators

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)