drgpum

A memory profiler for NVIDIA GPUs to explore memory inefficiencies in GPU-accelerated applications.

https://github.com/lin-mao/drgpum

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
✓
DOI references
Found 5 DOI reference(s) in README
✓
Academic publication links
Links to: zenodo.org
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (7.5%) to scientific vocabulary

Keywords

cuda-programming gpu-memory gpu-memory-profiler gpu-profiler memory-management

Last synced: 6 months ago · JSON representation ·

Repository

A memory profiler for NVIDIA GPUs to explore memory inefficiencies in GPU-accelerated applications.

Basic Info

Host: GitHub
Owner: Lin-Mao
License: bsd-3-clause
Language: Python
Default Branch: main
Homepage:
Size: 248 KB

Statistics

Stars: 25
Watchers: 3
Forks: 3
Open Issues: 0
Releases: 2

Topics

cuda-programming gpu-memory gpu-memory-profiler gpu-profiler memory-management

Created over 3 years ago · Last pushed over 1 year ago

Metadata Files

Readme License Citation Roadmap

README.md

DrGPUM

DrGPUM is a memory profiler for NVIDIA GPUs to explore memory inefficiencies in GPU-accelerated applications.

Quick Start

```bash git clone --recursive https://github.com/Lin-Mao/DrGPUM.git && cd DrGPUM

git submodule update --init --recursive

Specify PyTorch dir

export PYTORCHDIR=pathto_pytorch/torch

Install DrGPUM

./bin/install

Setup environment variables

export DrGPUMPATH=$(pwd)/gvprof export PATH=${DrGPUMPATH}/bin:$PATH export PATH=${DrGPUMPATH}/hpctoolkit/bin:$PATH export PATH=${DrGPUMPATH}/redshow/bin:$PATH

Test a sample

cd samples/vectorAdd.f32 make gvprof -v -e memory_liveness ./vectorAdd ```

Documentation

Papers

Mao Lin, Keren Zhou, and Pengfei Su. 2023. DrGPUM: Guiding Memory Optimization for GPU-accelerated Applications. In Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3 (ASPLOS ’23), March 25–29, 2023, Vancouver, BC, Canada. ACM, New York, NY, USA, 15 pages.

Owner

Name: Mao Lin
Login: Lin-Mao
Kind: user
Location: Merced, CA
Company: University of California, Merced

Website: linmao.org
Repositories: 2
Profile: https://github.com/Lin-Mao

Citation (CITATION.bib)

@inproceedings{lin2023drgpum,
  title={DrGPUM: Guiding Memory Optimization for GPU-Accelerated Applications},
  author={Lin, Mao and Zhou, Keren and Su, Pengfei},
  booktitle={Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3},
  pages={164--178},
  year={2023},
  isbn={9781450399180},
  publisher={Association for Computing Machinery},
  address={New York, NY, USA},
  url={https://doi.org/10.1145/3582016.3582044},
  doi={10.1145/3582016.3582044},
  keywords={GPU profilers, Memory management, CUDA, GPUs},
  location={Vancouver, BC, Canada},
  series={ASPLOS 2023}
}

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science