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

Distributed Fast Histogram Algorithm (#4011)

Browse Source 
* add back train method but mark as deprecated

* add back train method but mark as deprecated

* add back train method but mark as deprecated

* fix scalastyle error

* fix scalastyle error

* fix scalastyle error

* fix scalastyle error

* init

* allow hist algo

* more changes

* temp

* update

* remove hist sync

* udpate rabit

* change hist size

* change the histogram

* update kfactor

* sync per node stats

* temp

* update

* final

* code clean

* update rabit

* more cleanup

* fix errors

* fix failed tests

* enforce c++11

* fix lint issue

* broadcast subsampled feature correctly

* revert some changes

* fix lint issue

* enable monotone and interaction constraints

* don't specify default for monotone and interactions

* update docs
This commit is contained in:
Nan Zhu
2019-02-05 05:12:53 -08:00
committed by GitHub
parent 8905df4a18
commit ae3bb9c2d5
16 changed files with 169 additions and 88 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
src/common/hist_util.cc
View File

@@ -83,9 +83,9 @@ void HistCutMatrix::Init
summary_array[i].Reserve(max_num_bins * kFactor);
summary_array[i].SetPrune(out, max_num_bins * kFactor);
}
CHECK_EQ(summary_array.size(), in_sketchs->size());
size_t nbytes = WXQSketch::SummaryContainer::CalcMemCost(max_num_bins * kFactor);
sreducer.Allreduce(dmlc::BeginPtr(summary_array), nbytes, summary_array.size());
this->min_val.resize(sketchs.size());
row_ptr.push_back(0);
for (size_t fid = 0; fid < summary_array.size(); ++fid) {
@@ -479,14 +479,14 @@ void GHistBuilder::BuildHist(const std::vector<GradientPair>& gpair,
#pragma omp parallel for num_threads(std::min(nthread, n_blocks)) schedule(guided)
for (bst_omp_uint iblock = 0; iblock < n_blocks; iblock++) {
const size_t istart = iblock*block_size;
const size_t iend = (((iblock+1)*block_size > size) ? size : istart + block_size);
const size_t istart = iblock * block_size;
const size_t iend = (((iblock + 1) * block_size > size) ? size : istart + block_size);
const size_t bin = 2*thread_init_[0]*nbins_;
memcpy(hist_data + istart, (data + bin + istart), sizeof(double)*(iend - istart));
const size_t bin = 2 * thread_init_[0] * nbins_;
memcpy(hist_data + istart, (data + bin + istart), sizeof(double) * (iend - istart));
for (size_t i_bin_part = 1; i_bin_part < n_worked_bins; ++i_bin_part) {
const size_t bin = 2*thread_init_[i_bin_part]*nbins_;
const size_t bin = 2 * thread_init_[i_bin_part] * nbins_;
for (size_t i = istart; i < iend; i++) {
hist_data[i] += data[bin + i];
}

11
src/common/hist_util.h
View File

@@ -13,6 +13,7 @@
#include "row_set.h"
#include "../tree/param.h"
#include "./quantile.h"
#include "../include/rabit/rabit.h"
namespace xgboost {
@@ -43,6 +44,10 @@ struct GHistEntry {
sum_hess += e.sum_hess;
}
inline static void Reduce(GHistEntry& a, const GHistEntry& b) { // NOLINT(*)
a.Add(b);
}
/*! \brief set sum to be difference of two GHistEntry's */
inline void SetSubtract(const GHistEntry& a, const GHistEntry& b) {
sum_grad = a.sum_grad - b.sum_grad;
@@ -166,7 +171,7 @@ class GHistIndexBlockMatrix {
};
/*!
* \brief histogram of graident statistics for a single node.
* \brief histogram of gradient statistics for a single node.
* Consists of multiple GHistEntry's, each entry showing total graident statistics
* for that particular bin
* Uses global bin id so as to represent all features simultaneously
@@ -254,6 +259,10 @@ class GHistBuilder {
// construct a histogram via subtraction trick
void SubtractionTrick(GHistRow self, GHistRow sibling, GHistRow parent);
uint32_t GetNumBins() {
return nbins_;
}
private:
/*! \brief number of threads for parallel computation */
size_t nthread_;

2
src/common/random.h
View File

@@ -17,6 +17,8 @@
#include <numeric>
#include <random>
#include "io.h"
namespace xgboost {
namespace common {
/*!