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/common/hist_util.cc

@@ -35,6 +35,7 @@ void HistCutMatrix::Init(DMatrix* p_fmat, uint32_t max_num_bins) {
 
   auto iter = p_fmat->RowIterator();
   iter->BeforeFirst();
+  const auto& weights = info.weights_.HostVector();
   while (iter->Next()) {
      auto &batch = iter->Value();
     #pragma omp parallel num_threads(nthread)
@@ -50,7 +51,8 @@ void HistCutMatrix::Init(DMatrix* p_fmat, uint32_t max_num_bins) {
           SparsePage::Inst inst = batch[i];
           for (auto& ins : inst) {
             if (ins.index >= begin && ins.index < end) {
-              sketchs[ins.index].Push(ins.fvalue, info.GetWeight(ridx));
+              sketchs[ins.index].Push(ins.fvalue,
+                                      weights.size() > 0 ? weights[ridx] : 1.0f);
             }
           }
         }