Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Segmented reduce #11

Merged
merged 36 commits into from
Jan 5, 2024
Merged

Segmented reduce #11

merged 36 commits into from
Jan 5, 2024

Conversation

andyD123
Copy link
Owner

@andyD123 andyD123 commented Jan 5, 2024

example of binned reduction: not yet completed

@andyD123
sort of lambda version of binned reduction, needs more work
f3f1cda
@andyD123
add sln
446986a
@andyD123
adding load_partial and blend2 methods to VecDouble to make it work f…
f26d29c 
…or scan implementations
@andyD123
add some MSVC project updates
2195745
@andyD123
bit buggy but works in principal
7093986
@andyD123
forgot proj file
5dcba78
@andyD123
Merge branch 'main' into SegmentedReduce
c7f05e0
@andyD123
xx
88b92b6
@andyD123
xx
bd2a916
@andyD123
sort of working
7df1cec
@andyD123
minor tweaks to scratch
b607ecc
@andyD123
very rough encapsulation of bionned accumulate-needs work
9bc6a58
@andyD123
re working binned sumation example and accumulator function
5625b3f
@andyD123
project config changes
57b74dd
@andyD123
add clang debug and fixing crash bug in pairs summation caused by usi…
c8db3a0 
…ng aligned load

on unalighned data in accumulate_transform.h
@andyD123
clean up scratch
2849388
@andyD123
clean up simple binned accumulator
3c900b7
@andyD123
cleaning scratch example
ee05381
@andyD123
binned accumulator clean up firts cut header
fe556ea 
needs work
@andyD123
fix compiltion bug
0c20126
@andyD123
update proj and soln files
805c499
@andyD123
proj files update
c72b5d1
@andyD123
fix testbuild
88bb4f5
@andyD123
fixing tests compile
dab3b68
@andyD123
minor fix and add tests for binned accumulation
2111e52
@andyD123
more cleaning
92651d7
@andyD123
more tidy with float types
120d08d
@andyD123
adding extra function to example for simple cases
bcbf440
@andyD123
more tweaking and tests
4776de1
@andyD123
reducing noise by using power of 2 numerics for truncation levels
2f853bd
@andyD123
Copy link
Owner Author

andyD123 commented Jan 5, 2024

example showing error reduction when using kahan, pairwise reduction compared to std::reduce also partial implementation
of binned/ segmented reduction which is much more robust against effects of cancellation

@andyD123 andyD123 merged commit 6887cf7 into main Jan 5, 2024
2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@andyD123