Optimization of row-wise histogram construction #3522
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ulti_val_dense_opt
shiyu1994
requested review from
btrotta,
chivee,
guolinke,
henry0312,
huanzhang12,
jameslamb,
Laurae2,
StrikerRUS and
wxchan
as code owners
guolinke
reviewed
Nov 12, 2020
guolinke
reviewed
Nov 12, 2020
src/io/dataset.cpp
Outdated
| } | ||
| CHECK(local_offsets.size() == offsets.size()); | ||
| for (size_t i = 0; i < local_offsets.size(); ++i) { | ||
| CHECK(local_offsets[i] == offsets[i]); |
There was a problem hiding this comment.
what is local_offsets used for? only for checking?
There was a problem hiding this comment.
the passed-in offset is already the offset of dense features? why need to re-campute local_offset ?
There was a problem hiding this comment.
This is just for checking.
guolinke
reviewed
Nov 12, 2020
src/io/dataset.cpp
Outdated
| sum_dense_ratio /= static_cast<double>(most_freq_bins.size()); | ||
| CHECK(local_offsets.size() == offsets.size()); | ||
| for (size_t i = 0; i < local_offsets.size(); ++i) { | ||
| CHECK(local_offsets[i] == offsets[i]); |
|
Update row-wise and sep-row-wise time. The master branch uses row-wise.
|
Co-authored-by: Guolin Ke <guolin.ke@outlook.com>
…into multi_val_opt
guolinke
reviewed
Nov 13, 2020
guolinke
approved these changes
Nov 13, 2020
shiyu1994
force-pushed
the
multi_val_opt
branch
from
633eb17 to
1e10eb1
Compare
Closed
|
This pull request has been automatically locked since there has not been any recent activity since it was closed. To start a new related discussion, open a new issue at https://github.com/microsoft/LightGBM/issues including a reference to this. |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR is to optimize row-wise histogram construction. For dense multi-value bin, the original bins, without offsets added, are stored, which saves memory when the max bin number per feature is small. For both dense and sparse multi-value, we try to use single precision floating point in histogram buffers, and use avx-256 instructions to speedup histogram construction.