Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Remove various synchronisations from cuda API calls, instrument monitor (#4205)

Browse Source 
* Remove various synchronisations from cuda API calls, instrument monitor
with nvtx profiler ranges.
This commit is contained in:
Rory Mitchell
2019-03-10 15:01:23 +13:00
committed by GitHub
parent f83e62dca5
commit 4eeeded7d1
9 changed files with 116 additions and 104 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
doc/gpu/index.rst
View File

@@ -195,6 +195,10 @@ Training time time on 1,000,000 rows x 50 columns with 500 boosting iterations a
See `GPU Accelerated XGBoost <https://xgboost.ai/2016/12/14/GPU-accelerated-xgboost.html>`_ and `Updates to the XGBoost GPU algorithms <https://xgboost.ai/2018/07/04/gpu-xgboost-update.html>`_ for additional performance benchmarks of the ``gpu_exact`` and ``gpu_hist`` tree methods.
Developer notes
==========
The application may be profiled with annotations by specifying USE_NTVX to cmake and providing the path to the stand-alone nvtx header via NVTX_HEADER_DIR. Regions covered by the 'Monitor' class in cuda code will automatically appear in the nsight profiler.
**********
References
**********