-
Notifications
You must be signed in to change notification settings - Fork 3
Various CUDA Optimizations #1
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.
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
Open
lilinitsy
wants to merge
54
commits into
scope-ml:main
Choose a base branch
from
lilinitsy:master
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from all commits
Commits
Show all changes
54 commits
Select commit
Hold shift + click to select a range
168217d
Remove old cuda architectures incompatible with version 12
lilinitsy e8ee3e6
buggy (wrong results) of LS kernel batched
lilinitsy 0a649bb
some updates???
lilinitsy b8b9e15
index properly in the curve_bytes calculation...
lilinitsy ace28ad
Multiple lightcurves batched, but not faster; need some improvements
lilinitsy 52e54b2
backup
lilinitsy be405e3
Batch updates
lilinitsy a16e378
Minor updates
lilinitsy 7c5c7c8
ffastmath on and some GPU intrinsics
lilinitsy 2f36a81
Use two asynchronous cuda streams, which leads to a large performance…
lilinitsy a681cd3
Updates to improve accuracy; runtime for testing 100k periods decreas…
lilinitsy 7fe18a0
Get multiple streams working, minor improvement
lilinitsy ac75555
clang-format
lilinitsy 310de6a
Move cuda stream synchronization outside loop
lilinitsy 04b2955
Remove extraneous chronos usage
lilinitsy 8419b2f
Synchronize streams before destroying
lilinitsy 0b60864
Increase the number of batched curves
lilinitsy 9f6eb21
Modify inner loop condition
lilinitsy 18500e0
Move synchronize
lilinitsy b6cc7e2
restrict conditional entropy pointers
lilinitsy b03f020
Pinned memory for CE
lilinitsy 036159c
3 cuda streams for CE
lilinitsy 8521b23
Use registers instead of shared memory in conditional entropy kernel
lilinitsy 5aa4f3e
Copy local hists to local memory
lilinitsy 1a19575
Cleanup on CE
lilinitsy 45031c8
Cleanup on CE
lilinitsy 21d122d
Change block size
a37cef5
Pyx speedups using list comprehension
lilinitsy 34b8769
Tune threadcount and batch size
lilinitsy b60e830
More tuning for v100
lilinitsy a5e347b
More tuning for running on 1 v100
lilinitsy 5083b32
List comprehension when returning stats in pyx
lilinitsy 6c19ff4
Update pyx to reserve memory beforehand
lilinitsy 39b5617
update pyx
lilinitsy 5edbd7e
ls.pyx updates
lilinitsy a16331a
pyx update, set streams to 4
lilinitsy 8feafdf
Add OpenMP to Cmakelists
lilinitsy 0593b7a
Pyx updates for CE
lilinitsy ba4a9e9
Adjust thread count
lilinitsy 40854f9
Change threads for ce
lilinitsy f135693
Testingw ithout pinned on v100
lilinitsy dfeadbb
Use shared memory (Faster on V100, slower on 1080)
lilinitsy 6adb53a
ce update
lilinitsy 49d69c3
updates to threadcounts per kernel
lilinitsy 4b416c0
Pinned memory for aov
lilinitsy 13fed4c
Threadcount adjustments
lilinitsy 9593fbc
streams for AOV
lilinitsy c4c2bf5
Move atomic adds in FoldBinKernel
lilinitsy 54785b6
Remove numphasebinoverlap loop from FoldBinKernel
lilinitsy 7e59a60
Finally ran clang-format
lilinitsy dd4c9ea
Remove extraneous files, clang-format, etc, ready for merge
lilinitsy 3bee0a8
Reformat cuda files with original clang-format
lilinitsy c7dddfe
Remove extraneous OpenMP message from CMakeLists
lilinitsy af08140
Fix __restrict to __restrict__ in certain places, remove tmp folder
lilinitsy File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or 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
Oops, something went wrong.
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.
Uh oh!
There was an error while loading. Please reload this page.