85b2fb3eee
* Integrating a faster version of grow_gpu plugin 1. Removed the older files to reduce duplication 2. Moved all of the grow_gpu files under 'exact' folder 3. All of them are inside 'exact' namespace to avoid any conflicts 4. Fixed a bug in benchmark.py while running only 'grow_gpu' plugin 5. Added cub and googletest submodules to ease integration and unit-testing 6. Updates to CMakeLists.txt to directly build cuda objects into libxgboost * Added support for building gpu plugins through make flow 1. updated makefile and config.mk to add right targets 2. added unit-tests for gpu exact plugin code * 1. Added support for building gpu plugin using 'make' flow as well 2. Updated instructions for building and testing gpu plugin * Fix travis-ci errors for PR#2360 1. lint errors on unit-tests 2. removed googletest, instead depended upon dmlc-core provide gtest cache * Some more fixes to travis-ci lint failures PR#2360 * Added Rory's copyrights to the files containing code from both. * updated copyright statement as per Rory's request * moved the static datasets into a script to generate them at runtime * 1. memory usage print when silent=0 2. tests/ and test/ folder organization 3. removal of the dependency of googletest for just building xgboost 4. coding style updates for .cuh as well * Fixes for compilation warnings * add cuda object files as well when JVM_BINDINGS=ON
51 lines
1.7 KiB
Python
51 lines
1.7 KiB
Python
# pylint: skip-file
|
|
import sys, argparse
|
|
import xgboost as xgb
|
|
import numpy as np
|
|
from sklearn.datasets import make_classification
|
|
import time
|
|
|
|
n = 1000000
|
|
num_rounds = 500
|
|
|
|
def run_benchmark(args, gpu_algorithm, cpu_algorithm):
|
|
print("Generating dataset: {} rows * {} columns".format(args.rows,args.columns))
|
|
X, y = make_classification(args.rows, n_features=args.columns, random_state=7)
|
|
dtrain = xgb.DMatrix(X, y)
|
|
|
|
param = {'objective': 'binary:logistic',
|
|
'tree_method': 'exact',
|
|
'max_depth': 6,
|
|
'silent': 1,
|
|
'eval_metric': 'auc'}
|
|
|
|
param['updater'] = gpu_algorithm
|
|
print("Training with '%s'" % param['updater'])
|
|
tmp = time.time()
|
|
xgb.train(param, dtrain, args.iterations)
|
|
print ("Time: %s seconds" % (str(time.time() - tmp)))
|
|
|
|
param['updater'] = cpu_algorithm
|
|
print("Training with '%s'" % param['updater'])
|
|
tmp = time.time()
|
|
xgb.train(param, dtrain, args.iterations)
|
|
print ("Time: %s seconds" % (str(time.time() - tmp)))
|
|
|
|
|
|
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--algorithm', choices=['all', 'grow_gpu', 'grow_gpu_hist'], required=True)
|
|
parser.add_argument('--rows',type=int,default=1000000)
|
|
parser.add_argument('--columns',type=int,default=50)
|
|
parser.add_argument('--iterations',type=int,default=500)
|
|
args = parser.parse_args()
|
|
|
|
if 'grow_gpu_hist' in args.algorithm:
|
|
run_benchmark(args, args.algorithm, 'grow_fast_histmaker')
|
|
if 'grow_gpu' in args.algorithm:
|
|
run_benchmark(args, args.algorithm, 'grow_colmaker')
|
|
if 'all' in args.algorithm:
|
|
run_benchmark(args, 'grow_gpu', 'grow_colmaker')
|
|
run_benchmark(args, 'grow_gpu_hist', 'grow_fast_histmaker')
|
|
|