Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
L
libsharp
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Deploy
Releases
Model registry
Monitor
Incidents
Service Desk
Analyze
Value stream analytics
Contributor analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Martin Reinecke
libsharp
Commits
da162187
Commit
da162187
authored
6 years ago
by
Martin Reinecke
Browse files
Options
Downloads
Patches
Plain Diff
add README.md
parent
78a35809
Branches
Branches containing commit
No related tags found
1 merge request
!16
Pol ispack
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
README.md
+35
-0
35 additions, 0 deletions
README.md
with
35 additions
and
0 deletions
README.md
0 → 100644
+
35
−
0
View file @
da162187
# Libsharp
Library for efficient spherical harmonic transforms at arbitrary spins,
supporting CPU vectorization, OpenMP and MPI.
## Paper
https://arxiv.org/abs/1303.4945
## News
### January 2019
This update features significant speedups thanks to important algorithmic
discoveries by Keiichi Ishioka
(https://www.jstage.jst.go.jp/article/jmsj/96/2/96_2018-019/_article and
personal communication).
These improvements reduce the fraction of CPU time spent on evaluating the
recurrences for Y_lm coefficients, which means that computing multiple
simultaneous SHTs no longer have a big performance advantage compared to SHTs
done one after the other.
As a consequence, libsharp support for simultaneous SHTs was dropped, making
its interface much simpler.
With the proper compilers and flags (see the file COMPILE for details) libsharp
is now built with support for SSE2, AVX, AVX2, FMA3, FMA4 and AVX512f and the
appropriate implementation is selected dynamically at runtime. This should
provide a very significant performance boost for everyone using pre-compiled
portable binaries.
### Compilation
The library uses the standard
`autotools`
mechanism for configuration,
compilation and installation. See the file
`COMPILE`
for configuration hints.
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment