dmlc/dgl

The ALG2 for cusparsespmm under performed when feature size is small

Open

#4.090 aberto em 7 de jun. de 2022

Ver no GitHub
 (2 comments) (0 reactions) (0 assignees)Python (2.928 forks)batch import
help wanted

Métricas do repositório

Stars
 (12.665 stars)
Métricas de merge de PR
 (Nenhuma PRs mesclada em 30d)

Description

🐛 Bug

@yzh119 report the ALG2 seems performed badly for cusparsespmm when the feature size is small.

To Reproduce

Steps to reproduce the behavior:

Expected behavior

Environment

  • DGL Version (e.g., 1.0):
  • Backend Library & Version (e.g., PyTorch 0.4.1, MXNet/Gluon 1.3):
  • OS (e.g., Linux):
  • How you installed DGL (conda, pip, source):
  • Build command you used (if compiling from source):
  • Python version:
  • CUDA/cuDNN version (if applicable):
  • GPU models and configuration (e.g. V100):
  • Any other relevant information:

Additional context

Guia do colaborador