Replaced std::vector with HostDeviceVector in MetaInfo and SparsePage. (#3446)

* Replaced std::vector with HostDeviceVector in MetaInfo and SparsePage.

- added distributions to HostDeviceVector
- using HostDeviceVector for labels, weights and base margings in MetaInfo
- using HostDeviceVector for offset and data in SparsePage
- other necessary refactoring

* Added const version of HostDeviceVector API calls.

- const versions added to calls that can trigger data transfers, e.g. DevicePointer()
- updated the code that uses HostDeviceVector
- objective functions now accept const HostDeviceVector<bst_float>& for predictions

* Updated src/linear/updater_gpu_coordinate.cu.

* Added read-only state for HostDeviceVector sync.

- this means no copies are performed if both host and devices access
  the HostDeviceVector read-only

* Fixed linter and test errors.

- updated the lz4 plugin
- added ConstDeviceSpan to HostDeviceVector
- using device % dh::NVisibleDevices() for the physical device number,
  e.g. in calls to cudaSetDevice()

* Fixed explicit template instantiation errors for HostDeviceVector.

- replaced HostDeviceVector<unsigned int> with HostDeviceVector<int>

* Fixed HostDeviceVector tests that require multiple GPUs.

- added a mock set device handler; when set, it is called instead of cudaSetDevice()

src/predictor/cpu_predictor.cc

@@ -112,7 +112,7 @@ class CPUPredictor : public Predictor {
         ntree_limit * model.param.num_output_group >= model.trees.size()) {
       auto it = cache_.find(dmat);
       if (it != cache_.end()) {
-        HostDeviceVector<bst_float>& y = it->second.predictions;
+        const HostDeviceVector<bst_float>& y = it->second.predictions;
         if (y.Size() != 0) {
           out_preds->Resize(y.Size());
           std::copy(y.HostVector().begin(), y.HostVector().end(),
@@ -128,7 +128,7 @@ class CPUPredictor : public Predictor {
                           HostDeviceVector<bst_float>* out_preds,
                           const gbm::GBTreeModel& model) const {
     size_t n = model.param.num_output_group * info.num_row_;
-    const std::vector<bst_float>& base_margin = info.base_margin_;
+    const auto& base_margin = info.base_margin_.HostVector();
     out_preds->Resize(n);
     std::vector<bst_float>& out_preds_h = out_preds->HostVector();
     if (base_margin.size() == n) {
@@ -282,7 +282,7 @@ class CPUPredictor : public Predictor {
     }
     // start collecting the contributions
     auto iter = p_fmat->RowIterator();
-    const std::vector<bst_float>& base_margin = info.base_margin_;
+    const auto& base_margin = info.base_margin_.HostVector();
     iter->BeforeFirst();
     while (iter->Next()) {
       auto &batch = iter->Value();