8 Commits

Author SHA1 Message Date
Andy Adinets
72cd1517d6 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()
2018-08-30 14:28:47 +12:00
trivialfis
2c502784ff Span class. (#3548)
* Add basic Span class based on ISO++20.

* Use Span<Entry const> instead of Inst in SparsePage.

* Add DeviceSpan in HostDeviceVector, use it in regression obj.
2018-08-14 17:58:11 +12:00
Rory Mitchell
645996b12f Remove accidental SparsePage copies (#3583) 2018-08-12 17:49:38 -07:00
Rory Mitchell
a96039141a
Dmatrix refactor stage 1 (#3301)
* Use sparse page as singular CSR matrix representation

* Simplify dmatrix methods

* Reduce statefullness of batch iterators

* BREAKING CHANGE: Remove prob_buffer_row parameter. Users are instead recommended to sample their dataset as a preprocessing step before using XGBoost.
2018-06-07 10:25:58 +12:00
Rory Mitchell
a185ddfe03
Implement GPU accelerated coordinate descent algorithm (#3178)
* Implement GPU accelerated coordinate descent algorithm. 

* Exclude external memory tests for GPU
2018-04-20 14:56:35 +12:00
Rory Mitchell
ccf80703ef
Clang-tidy static analysis (#3222)
* Clang-tidy static analysis

* Modernise checks

* Google coding standard checks

* Identifier renaming according to Google style
2018-04-19 18:57:13 +12:00
Vadim Khotilovich
706be4e5d4
Additional improvements for gblinear (#3134)
* fix rebase conflict

* [core] additional gblinear improvements

* [R] callback for gblinear coefficients history

* force eta=1 for gblinear python tests

* add top_k to GreedyFeatureSelector

* set eta=1 in shotgun test

* [core] fix SparsePage processing in gblinear; col-wise multithreading in greedy updater

* set sorted flag within TryInitColData

* gblinear tests: use scale, add external memory test

* fix multiclass for greedy updater

* fix whitespace

* fix typo
2018-03-13 01:27:13 -05:00
Rory Mitchell
10eb05a63a
Refactor linear modelling and add new coordinate descent updater (#3103)
* Refactor linear modelling and add new coordinate descent updater

* Allow unsorted column iterator

* Add prediction cacheing to gblinear
2018-02-17 09:17:01 +13:00