7663de956c
This makes GPU Hist robust in distributed environment as some workers might not be associated with any data in either training or evaluation. * Disable rabit mock test for now: See #5012 . * Disable dask-cudf test at prediction for now: See #5003 * Launch dask job for all workers despite they might not have any data. * Check 0 rows in elementwise evaluation metrics. Using AUC and AUC-PR still throws an error. See #4663 for a robust fix. * Add tests for edge cases. * Add `LaunchKernel` wrapper handling zero sized grid. * Move some parts of allreducer into a cu file. * Don't validate feature names when the booster is empty. * Sync number of columns in DMatrix. As num_feature is required to be the same across all workers in data split mode. * Filtering in dask interface now by default syncs all booster that's not empty, instead of using rank 0. * Fix Jenkins' GPU tests. * Install dask-cuda from source in Jenkins' test. Now all tests are actually running. * Restore GPU Hist tree synchronization test. * Check UUID of running devices. The check is only performed on CUDA version >= 10.x, as 9.x doesn't have UUID field. * Fix CMake policy and project variables. Use xgboost_SOURCE_DIR uniformly, add policy for CMake >= 3.13. * Fix copying data to CPU * Fix race condition in cpu predictor. * Fix duplicated DMatrix construction. * Don't download extra nccl in CI script.
77 lines
2.8 KiB
Python
77 lines
2.8 KiB
Python
import numpy as np
|
|
import sys
|
|
import unittest
|
|
import pytest
|
|
import xgboost
|
|
|
|
sys.path.append("tests/python")
|
|
from regression_test_utilities import run_suite, parameter_combinations, \
|
|
assert_results_non_increasing
|
|
|
|
|
|
def assert_gpu_results(cpu_results, gpu_results):
|
|
for cpu_res, gpu_res in zip(cpu_results, gpu_results):
|
|
# Check final eval result roughly equivalent
|
|
assert np.allclose(cpu_res["eval"][-1],
|
|
gpu_res["eval"][-1], 1e-2, 1e-2)
|
|
|
|
|
|
datasets = ["Boston", "Cancer", "Digits", "Sparse regression",
|
|
"Sparse regression with weights", "Small weights regression"]
|
|
|
|
|
|
class TestGPU(unittest.TestCase):
|
|
def test_gpu_hist(self):
|
|
test_param = parameter_combinations({'gpu_id': [0],
|
|
'max_depth': [2, 8],
|
|
'max_leaves': [255, 4],
|
|
'max_bin': [2, 256],
|
|
'grow_policy': ['lossguide']})
|
|
test_param.append({'single_precision_histogram': True})
|
|
test_param.append({'min_child_weight': 0,
|
|
'lambda': 0})
|
|
for param in test_param:
|
|
param['tree_method'] = 'gpu_hist'
|
|
gpu_results = run_suite(param, select_datasets=datasets)
|
|
assert_results_non_increasing(gpu_results, 1e-2)
|
|
param['tree_method'] = 'hist'
|
|
cpu_results = run_suite(param, select_datasets=datasets)
|
|
assert_gpu_results(cpu_results, gpu_results)
|
|
|
|
def test_with_empty_dmatrix(self):
|
|
# FIXME(trivialfis): This should be done with all updaters
|
|
kRows = 0
|
|
kCols = 100
|
|
|
|
X = np.empty((kRows, kCols))
|
|
y = np.empty((kRows))
|
|
|
|
dtrain = xgboost.DMatrix(X, y)
|
|
|
|
bst = xgboost.train({'verbosity': 2,
|
|
'tree_method': 'gpu_hist',
|
|
'gpu_id': 0},
|
|
dtrain,
|
|
verbose_eval=True,
|
|
num_boost_round=6,
|
|
evals=[(dtrain, 'Train')])
|
|
|
|
kRows = 100
|
|
X = np.random.randn(kRows, kCols)
|
|
|
|
dtest = xgboost.DMatrix(X)
|
|
predictions = bst.predict(dtest)
|
|
np.testing.assert_allclose(predictions, 0.5, 1e-6)
|
|
|
|
@pytest.mark.mgpu
|
|
def test_specified_gpu_id_gpu_update(self):
|
|
variable_param = {'gpu_id': [1],
|
|
'max_depth': [8],
|
|
'max_leaves': [255, 4],
|
|
'max_bin': [2, 64],
|
|
'grow_policy': ['lossguide'],
|
|
'tree_method': ['gpu_hist']}
|
|
for param in parameter_combinations(variable_param):
|
|
gpu_results = run_suite(param, select_datasets=datasets)
|
|
assert_results_non_increasing(gpu_results, 1e-2)
|