dmlc/dgl

The ALG2 for cusparsespmm under performed when feature size is small

Ouverte

#4 090 ouverte le 7 juin 2022

 (2 commentaires) (0 réaction) (0 personne assignée)Python (2 928 forks)batch import
help wanted

Métriques du dépôt

Stars
 (12 665 étoiles)
Métriques de merge PR
 (Métriques PR en attente)

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

Guide contributeur