Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

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

Browse Source 
* 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()
This commit is contained in:
Andy Adinets
2018-08-30 04:28:47 +02:00
committed by Rory Mitchell
parent 58d783df16
commit 72cd1517d6
45 changed files with 1141 additions and 560 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
src/data/sparse_page_raw_format.cc
View File

@@ -15,13 +15,15 @@ DMLC_REGISTRY_FILE_TAG(sparse_page_raw_format);
class SparsePageRawFormat : public SparsePageFormat {
public:
bool Read(SparsePage* page, dmlc::SeekStream* fi) override {
if (!fi->Read(&(page->offset))) return false;
CHECK_NE(page->offset.size(), 0U) << "Invalid SparsePage file";
page->data.resize(page->offset.back());
if (page->data.size() != 0) {
CHECK_EQ(fi->Read(dmlc::BeginPtr(page->data),
(page->data).size() * sizeof(Entry)),
(page->data).size() * sizeof(Entry))
auto& offset_vec = page->offset.HostVector();
if (!fi->Read(&offset_vec)) return false;
auto& data_vec = page->data.HostVector();
CHECK_NE(page->offset.Size(), 0U) << "Invalid SparsePage file";
data_vec.resize(offset_vec.back());
if (page->data.Size() != 0) {
CHECK_EQ(fi->Read(dmlc::BeginPtr(data_vec),
(page->data).Size() * sizeof(Entry)),
(page->data).Size() * sizeof(Entry))
<< "Invalid SparsePage file";
}
return true;
@@ -31,15 +33,17 @@ class SparsePageRawFormat : public SparsePageFormat {
dmlc::SeekStream* fi,
const std::vector<bst_uint>& sorted_index_set) override {
if (!fi->Read(&disk_offset_)) return false;
auto& offset_vec = page->offset.HostVector();
auto& data_vec = page->data.HostVector();
// setup the offset
page->offset.clear();
page->offset.push_back(0);
offset_vec.clear();
offset_vec.push_back(0);
for (unsigned int fid : sorted_index_set) {
CHECK_LT(fid + 1, disk_offset_.size());
size_t size = disk_offset_[fid + 1] - disk_offset_[fid];
page->offset.push_back(page->offset.back() + size);
offset_vec.push_back(offset_vec.back() + size);
}
page->data.resize(page->offset.back());
data_vec.resize(offset_vec.back());
// read in the data
size_t begin = fi->Tell();
size_t curr_offset = 0;
@@ -53,14 +57,14 @@ class SparsePageRawFormat : public SparsePageFormat {
size_t j, size_to_read = 0;
for (j = i; j < sorted_index_set.size(); ++j) {
if (disk_offset_[sorted_index_set[j]] == disk_offset_[fid] + size_to_read) {
size_to_read += page->offset[j + 1] - page->offset[j];
size_to_read += offset_vec[j + 1] - offset_vec[j];
} else {
break;
}
}
if (size_to_read != 0) {
CHECK_EQ(fi->Read(dmlc::BeginPtr(page->data) + page->offset[i],
CHECK_EQ(fi->Read(dmlc::BeginPtr(data_vec) + offset_vec[i],
size_to_read * sizeof(Entry)),
size_to_read * sizeof(Entry))
<< "Invalid SparsePage file";
@@ -76,11 +80,13 @@ class SparsePageRawFormat : public SparsePageFormat {
}
void Write(const SparsePage& page, dmlc::Stream* fo) override {
CHECK(page.offset.size() != 0 && page.offset[0] == 0);
CHECK_EQ(page.offset.back(), page.data.size());
fo->Write(page.offset);
if (page.data.size() != 0) {
fo->Write(dmlc::BeginPtr(page.data), page.data.size() * sizeof(Entry));
const auto& offset_vec = page.offset.HostVector();
const auto& data_vec = page.data.HostVector();
CHECK(page.offset.Size() != 0 && offset_vec[0] == 0);
CHECK_EQ(offset_vec.back(), page.data.Size());
fo->Write(offset_vec);
if (page.data.Size() != 0) {
fo->Write(dmlc::BeginPtr(data_vec), page.data.Size() * sizeof(Entry));
}
}