Merge branch 'master' into sync-2024Jan24

tests/buildkite/test-win64-gpu.ps1

@@ -32,6 +32,8 @@ Foreach-Object {
 
 Write-Host "--- Run Python tests"
 python -X faulthandler -m pytest -v -s -rxXs --fulltrace tests/python
+if ($LASTEXITCODE -ne 0) { throw "Last command failed" }
 Write-Host "--- Run Python tests with GPU"
 python -X faulthandler -m pytest -v -s -rxXs --fulltrace -m "(not slow) and (not mgpu)"`
   tests/python-gpu
+if ($LASTEXITCODE -ne 0) { throw "Last command failed" }

tests/ci_build/Dockerfile.i386

@@ -0,0 +1,8 @@
+FROM i386/debian:sid
+
+ENV DEBIAN_FRONTEND noninteractive
+SHELL ["/bin/bash", "-c"]   # Use Bash as shell
+
+RUN \
+    apt-get update && \
+    apt-get install -y tar unzip wget git build-essential ninja-build cmake

tests/ci_build/change_version.py

@@ -7,6 +7,7 @@ needed, run CMake .
     If this is a RC release, the version for JVM packages has the form
     <major>.<minor>.<patch>-RC1
 """
+
 import argparse
 import datetime
 import os

tests/ci_build/test_r_package.py

@@ -1,4 +1,5 @@
 """Utilities for packaging R code and running tests."""
+
 import argparse
 import os
 import shutil

tests/ci_build/test_utils.py

@@ -1,4 +1,5 @@
 """Utilities for the CI."""
+
 import os
 from datetime import datetime, timedelta
 from functools import wraps

tests/cpp/CMakeLists.txt

@@ -19,8 +19,38 @@ if (USE_HIP)
 endif (USE_HIP)
 
 file(GLOB_RECURSE SYCL_TEST_SOURCES "plugin/test_sycl_*.cc")
-if(NOT PLUGIN_SYCL)
-  list(REMOVE_ITEM TEST_SOURCES ${SYCL_TEST_SOURCES})
+list(REMOVE_ITEM TEST_SOURCES ${SYCL_TEST_SOURCES})
+
+if(PLUGIN_SYCL)
+  set(CMAKE_CXX_COMPILER "icpx")
+  file(GLOB_RECURSE SYCL_TEST_SOURCES "plugin/test_sycl_*.cc")
+  add_library(plugin_sycl_test OBJECT ${SYCL_TEST_SOURCES})
+
+  target_include_directories(plugin_sycl_test
+    PRIVATE
+    ${gtest_SOURCE_DIR}/include
+    ${xgboost_SOURCE_DIR}/include
+    ${xgboost_SOURCE_DIR}/dmlc-core/include
+    ${xgboost_SOURCE_DIR}/rabit/include)
+
+  target_compile_definitions(plugin_sycl_test PUBLIC -DXGBOOST_USE_SYCL=1)
+
+  target_link_libraries(plugin_sycl_test PUBLIC -fsycl)
+
+  set_target_properties(plugin_sycl_test PROPERTIES
+  COMPILE_FLAGS -fsycl
+  CXX_STANDARD 17
+  CXX_STANDARD_REQUIRED ON
+  POSITION_INDEPENDENT_CODE ON)
+  if(USE_OPENMP)
+    find_package(OpenMP REQUIRED)
+    set_target_properties(plugin_sycl_test PROPERTIES
+    COMPILE_FLAGS "-fsycl -qopenmp")
+  endif()
+  # Get compilation and link flags of plugin_sycl and propagate to testxgboost
+  target_link_libraries(testxgboost PUBLIC plugin_sycl_test)
+  # Add all objects of plugin_sycl to testxgboost
+  target_sources(testxgboost INTERFACE $<TARGET_OBJECTS:plugin_sycl_test>)
 endif()
 
 if(PLUGIN_FEDERATED)

tests/cpp/c_api/test_c_api.cc

@@ -1,5 +1,5 @@
 /**
- * Copyright 2019-2023 XGBoost contributors
+ * Copyright 2019-2024 XGBoost contributors
  */
 #include <gtest/gtest.h>
 #include <xgboost/c_api.h>
@@ -212,8 +212,8 @@ TEST(CAPI, JsonModelIO) {
   bst_ulong saved_len{0};
   XGBoosterSaveModelToBuffer(handle, R"({"format": "ubj"})", &saved_len, &saved);
   ASSERT_EQ(len, saved_len);
-  auto l = StringView{data, len};
-  auto r = StringView{saved, saved_len};
+  auto l = StringView{data, static_cast<size_t>(len)};
+  auto r = StringView{saved, static_cast<size_t>(saved_len)};
   ASSERT_EQ(l.size(), r.size());
   ASSERT_EQ(l, r);
 

tests/cpp/helpers.cc

@@ -1,5 +1,5 @@
 /**
- * Copyright 2016-2023 by XGBoost contributors
+ * Copyright 2016-2024 by XGBoost contributors
  */
 #include "helpers.h"
 
@@ -216,7 +216,7 @@ SimpleLCG::StateType SimpleLCG::Max() const { return max(); }
 static_assert(SimpleLCG::max() - SimpleLCG::min());
 
 void RandomDataGenerator::GenerateLabels(std::shared_ptr<DMatrix> p_fmat) const {
-  RandomDataGenerator{p_fmat->Info().num_row_, this->n_targets_, 0.0f}.GenerateDense(
+  RandomDataGenerator{static_cast<bst_row_t>(p_fmat->Info().num_row_), this->n_targets_, 0.0f}.GenerateDense(
       p_fmat->Info().labels.Data());
   CHECK_EQ(p_fmat->Info().labels.Size(), this->rows_ * this->n_targets_);
   p_fmat->Info().labels.Reshape(this->rows_, this->n_targets_);
@@ -458,7 +458,7 @@ void RandomDataGenerator::GenerateCSR(
   EXPECT_EQ(row_count, dmat->Info().num_row_);
 
   if (with_label) {
-    RandomDataGenerator{dmat->Info().num_row_, this->n_targets_, 0.0f}.GenerateDense(
+    RandomDataGenerator{static_cast<bst_row_t>(dmat->Info().num_row_), this->n_targets_, 0.0f}.GenerateDense(
         dmat->Info().labels.Data());
     CHECK_EQ(dmat->Info().labels.Size(), this->rows_ * this->n_targets_);
     dmat->Info().labels.Reshape(this->rows_, this->n_targets_);

tests/cpp/helpers.h

@@ -1,5 +1,5 @@
 /**
- * Copyright 2016-2023 by XGBoost contributors
+ * Copyright 2016-2024 by XGBoost contributors
  */
 #pragma once
 
@@ -238,7 +238,7 @@ class RandomDataGenerator {
 
   bst_bin_t bins_{0};
   std::vector<FeatureType> ft_;
-  bst_cat_t max_cat_;
+  bst_cat_t max_cat_{32};
 
   Json ArrayInterfaceImpl(HostDeviceVector<float>* storage, size_t rows, size_t cols) const;
 

tests/cpp/plugin/test_sycl_multiclass_obj.cc

@@ -2,7 +2,11 @@
  * Copyright 2018-2023 XGBoost contributors
  */
 #include <gtest/gtest.h>
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wtautological-constant-compare"
+#pragma GCC diagnostic ignored "-W#pragma-messages"
 #include <xgboost/context.h>
+#pragma GCC diagnostic pop
 
 #include "../objective/test_multiclass_obj.h"
 

tests/cpp/plugin/test_sycl_partition_builder.cc

@@ -0,0 +1,91 @@
+/**
+ * Copyright 2020-2024 by XGBoost contributors
+ */
+#include <gtest/gtest.h>
+
+#include <string>
+#include <utility>
+#include <vector>
+
+#include "../../../plugin/sycl/common/partition_builder.h"
+#include "../../../plugin/sycl/device_manager.h"
+#include "../helpers.h"
+
+namespace xgboost::sycl::common {
+
+TEST(SyclPartitionBuilder, BasicTest) {
+  constexpr size_t kNodes = 5;
+  // Number of rows for each node
+  std::vector<size_t> rows = { 5, 5, 10, 1, 2 };
+
+  DeviceManager device_manager;
+  auto qu = device_manager.GetQueue(DeviceOrd::SyclDefault());
+  PartitionBuilder builder;
+  builder.Init(&qu, kNodes, [&](size_t i) {
+    return rows[i];
+  });
+
+  // We test here only the basics, thus syntetic partition builder is adopted
+  // Number of rows to go left for each node.
+  std::vector<size_t> rows_for_left_node = { 2, 0, 7, 1, 2 };
+
+  size_t first_row_id = 0;
+  for(size_t nid = 0; nid < kNodes; ++nid) {
+    size_t n_rows_nodes = rows[nid];
+
+    auto rid_buff = builder.GetData(nid);
+    size_t rid_buff_size = rid_buff.size();
+    auto* rid_buff_ptr = rid_buff.data();
+
+    size_t n_left  = rows_for_left_node[nid];
+    size_t n_right = rows[nid] - n_left;
+
+    qu.submit([&](::sycl::handler& cgh) {
+      cgh.parallel_for<>(::sycl::range<1>(n_left), [=](::sycl::id<1> pid) {
+        int row_id = first_row_id + pid[0];
+        rid_buff_ptr[pid[0]] = row_id;
+      });
+    });
+    qu.wait();
+    first_row_id += n_left;
+
+    // We are storing indexes for the right side in the tail of the array to save some memory
+    qu.submit([&](::sycl::handler& cgh) {
+      cgh.parallel_for<>(::sycl::range<1>(n_right), [=](::sycl::id<1> pid) {
+        int row_id = first_row_id + pid[0];
+        rid_buff_ptr[rid_buff_size - pid[0] - 1] = row_id;
+      });
+    });
+    qu.wait();
+    first_row_id += n_right;
+
+    builder.SetNLeftElems(nid, n_left);
+    builder.SetNRightElems(nid, n_right);
+  }
+
+  ::sycl::event event;
+  std::vector<size_t> v(*std::max_element(rows.begin(), rows.end()));
+  size_t row_id = 0;
+  for(size_t nid = 0; nid < kNodes; ++nid) {
+    builder.MergeToArray(nid, v.data(), event);
+    qu.wait();
+
+    // Check that row_id for left side are correct
+    for(size_t j = 0; j < rows_for_left_node[nid]; ++j) {
+       ASSERT_EQ(v[j], row_id++);
+    }
+
+    // Check that row_id for right side are correct
+    for(size_t j = 0; j < rows[nid] - rows_for_left_node[nid]; ++j) {
+      ASSERT_EQ(v[rows[nid] - j - 1], row_id++);
+    }
+
+    // Check that number of left/right rows are correct
+    size_t n_left  = builder.GetNLeftElems(nid);
+    size_t n_right = builder.GetNRightElems(nid);
+    ASSERT_EQ(n_left, rows_for_left_node[nid]);
+    ASSERT_EQ(n_right, (rows[nid] - rows_for_left_node[nid]));
+  }
+}
+
+}  // namespace xgboost::common

tests/cpp/plugin/test_sycl_predictor.cc

@@ -2,11 +2,19 @@
  * Copyright 2017-2023 XGBoost contributors
  */
 #include <gtest/gtest.h>
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wtautological-constant-compare"
+#pragma GCC diagnostic ignored "-W#pragma-messages"
 #include <xgboost/predictor.h>
+#pragma GCC diagnostic pop
 
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wtautological-constant-compare"
 #include "../../../src/data/adapter.h"
-#include "../../../src/data/proxy_dmatrix.h"
 #include "../../../src/gbm/gbtree.h"
+#pragma GCC diagnostic pop
+
+#include "../../../src/data/proxy_dmatrix.h"
 #include "../../../src/gbm/gbtree_model.h"
 #include "../filesystem.h"  // dmlc::TemporaryDirectory
 #include "../helpers.h"

tests/cpp/plugin/test_sycl_regression_obj.cc

@@ -2,7 +2,11 @@
  * Copyright 2017-2019 XGBoost contributors
  */
 #include <gtest/gtest.h>
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wtautological-constant-compare"
+#pragma GCC diagnostic ignored "-W#pragma-messages"
 #include <xgboost/objective.h>
+#pragma GCC diagnostic pop
 #include <xgboost/context.h>
 
 #include "../helpers.h"

tests/python-gpu/load_pickle.py

@@ -1,5 +1,6 @@
 """Loading a pickled model generated by test_pickling.py, only used by
 `test_gpu_with_dask.py`"""
+
 import json
 import os
 

tests/python-gpu/test_gpu_pickling.py

@@ -1,4 +1,5 @@
 """Test model IO with pickle."""
+
 import os
 import pickle
 import subprocess

tests/python-gpu/test_gpu_prediction.py

@@ -152,6 +152,7 @@ class TestGPUPredict:
 
     @pytest.mark.parametrize("device", ["cpu", "cuda"])
     @pytest.mark.skipif(**tm.no_cupy())
+    @pytest.mark.skipif(**tm.no_cudf())
     def test_inplace_predict_device_type(self, device: str) -> None:
         """Test inplace predict with different device and data types.
 

tests/python-gpu/test_gpu_with_sklearn.py

@@ -249,7 +249,7 @@ def test_custom_objective(
         clf.fit(X, y)
 
 
-@pytest.mark.skipif(**tm.no_pandas())
+@pytest.mark.skipif(**tm.no_cudf())
 def test_ranking_qid_df():
     import cudf
 

tests/python/test_basic_models.py

@@ -7,6 +7,7 @@ import pytest
 
 import xgboost as xgb
 from xgboost import testing as tm
+from xgboost.core import Integer
 from xgboost.testing.updater import ResetStrategy
 
 dpath = tm.data_dir(__file__)
@@ -97,15 +98,15 @@ class TestModels:
     def test_boost_from_prediction(self):
         # Re-construct dtrain here to avoid modification
         margined, _ = tm.load_agaricus(__file__)
-        bst = xgb.train({'tree_method': 'hist'}, margined, 1)
+        bst = xgb.train({"tree_method": "hist"}, margined, 1)
         predt_0 = bst.predict(margined, output_margin=True)
         margined.set_base_margin(predt_0)
-        bst = xgb.train({'tree_method': 'hist'}, margined, 1)
+        bst = xgb.train({"tree_method": "hist"}, margined, 1)
         predt_1 = bst.predict(margined)
 
         assert np.any(np.abs(predt_1 - predt_0) > 1e-6)
         dtrain, _ = tm.load_agaricus(__file__)
-        bst = xgb.train({'tree_method': 'hist'}, dtrain, 2)
+        bst = xgb.train({"tree_method": "hist"}, dtrain, 2)
         predt_2 = bst.predict(dtrain)
         assert np.all(np.abs(predt_2 - predt_1) < 1e-6)
 
@@ -331,10 +332,15 @@ class TestModels:
         dtrain: xgb.DMatrix,
         num_parallel_tree: int,
         num_classes: int,
-        num_boost_round: int
+        num_boost_round: int,
+        use_np_type: bool,
     ):
         beg = 3
-        end = 7
+        if use_np_type:
+            end: Integer = np.int32(7)
+        else:
+            end = 7
+
         sliced: xgb.Booster = booster[beg:end]
         assert sliced.feature_types == booster.feature_types
 
@@ -345,7 +351,7 @@ class TestModels:
         sliced = booster[beg:end:2]
         assert sliced_trees == len(sliced.get_dump())
 
-        sliced = booster[beg: ...]
+        sliced = booster[beg:]
         sliced_trees = (num_boost_round - beg) * num_parallel_tree * num_classes
         assert sliced_trees == len(sliced.get_dump())
 
@@ -357,7 +363,7 @@ class TestModels:
         sliced_trees = end * num_parallel_tree * num_classes
         assert sliced_trees == len(sliced.get_dump())
 
-        sliced = booster[...: end]
+        sliced = booster[: end]
         sliced_trees = end * num_parallel_tree * num_classes
         assert sliced_trees == len(sliced.get_dump())
 
@@ -383,14 +389,14 @@ class TestModels:
         assert len(trees) == num_boost_round
 
         with pytest.raises(TypeError):
-            booster["wrong type"]
+            booster["wrong type"]  # type: ignore
         with pytest.raises(IndexError):
             booster[: num_boost_round + 1]
         with pytest.raises(ValueError):
             booster[1, 2]  # too many dims
         # setitem is not implemented as model is immutable during slicing.
         with pytest.raises(TypeError):
-            booster[...: end] = booster
+            booster[:end] = booster  # type: ignore
 
         sliced_0 = booster[1:3]
         np.testing.assert_allclose(
@@ -446,15 +452,21 @@ class TestModels:
 
         assert len(booster.get_dump()) == total_trees
 
-        self.run_slice(booster, dtrain, num_parallel_tree, num_classes, num_boost_round)
+        self.run_slice(
+            booster, dtrain, num_parallel_tree, num_classes, num_boost_round, False
+        )
 
         bytesarray = booster.save_raw(raw_format="ubj")
         booster = xgb.Booster(model_file=bytesarray)
-        self.run_slice(booster, dtrain, num_parallel_tree, num_classes, num_boost_round)
+        self.run_slice(
+            booster, dtrain, num_parallel_tree, num_classes, num_boost_round, False
+        )
 
         bytesarray = booster.save_raw(raw_format="deprecated")
         booster = xgb.Booster(model_file=bytesarray)
-        self.run_slice(booster, dtrain, num_parallel_tree, num_classes, num_boost_round)
+        self.run_slice(
+            booster, dtrain, num_parallel_tree, num_classes, num_boost_round, True
+        )
 
     def test_slice_multi(self) -> None:
         from sklearn.datasets import make_classification
@@ -479,7 +491,7 @@ class TestModels:
             },
             num_boost_round=num_boost_round,
             dtrain=Xy,
-            callbacks=[ResetStrategy()]
+            callbacks=[ResetStrategy()],
         )
         sliced = [t for t in booster]
         assert len(sliced) == 16

tests/python/test_predict.py

@@ -1,4 +1,5 @@
 """Tests for running inplace prediction."""
+
 from concurrent.futures import ThreadPoolExecutor
 
 import numpy as np
@@ -61,7 +62,7 @@ def run_predict_leaf(device: str) -> np.ndarray:
 
     validate_leaf_output(leaf, num_parallel_tree)
 
-    n_iters = 2
+    n_iters = np.int32(2)
     sliced = booster.predict(
         m,
         pred_leaf=True,

tests/python/test_with_sklearn.py

@@ -440,7 +440,7 @@ def test_regression():
         preds = xgb_model.predict(X[test_index])
         # test other params in XGBRegressor().fit
         preds2 = xgb_model.predict(
-            X[test_index], output_margin=True, iteration_range=(0, 3)
+            X[test_index], output_margin=True, iteration_range=(0, np.int16(3))
         )
         preds3 = xgb_model.predict(
             X[test_index], output_margin=True, iteration_range=None

tests/test_distributed/test_gpu_with_dask/test_gpu_with_dask.py

@@ -1,4 +1,5 @@
 """Copyright 2019-2023, XGBoost contributors"""
+
 import asyncio
 import json
 from collections import OrderedDict

tests/test_distributed/test_with_dask/test_with_dask.py

@@ -1,4 +1,5 @@
 """Copyright 2019-2022 XGBoost contributors"""
+
 import asyncio
 import json
 import os