Open mdymczyk opened 7 years ago
Add a GPU backend for tree model scoring (GBM/DRF).
The goal is to increase the throughput for scoring of large datasets (in mini-batch) and for large numbers of trees.
Possibly predict for all possible paths down the tree and pick the "right" path at the end, to avoid branch misprediction issues.
Might be related to the TF MOJO: https://github.com/h2oai/h2oai-prototypes/tree/master/tf-mojo
http://h2o-release.s3.amazonaws.com/h2o/rel-tutte/1/docs-website/h2o-genmodel/javadoc/index.html#quickstartmojo
pseudotensor
commented
7 years ago
Add a GPU backend for tree model scoring (GBM/DRF).
The goal is to increase the throughput for scoring of large datasets (in mini-batch) and for large numbers of trees.
Possibly predict for all possible paths down the tree and pick the "right" path at the end, to avoid branch misprediction issues.
Might be related to the TF MOJO: https://github.com/h2oai/h2oai-prototypes/tree/master/tf-mojo