[Bug 2240398] New: Review Request: pocketfft - A PyTorch FFT math header

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



https://bugzilla.redhat.com/show_bug.cgi?id=2240398

            Bug ID: 2240398
           Summary: Review Request: pocketfft - A PyTorch FFT math header
           Product: Fedora
           Version: rawhide
                OS: Linux
            Status: NEW
         Component: Package Review
          Severity: medium
          Assignee: nobody@xxxxxxxxxxxxxxxxx
          Reporter: trix@xxxxxxxxxx
        QA Contact: extras-qa@xxxxxxxxxxxxxxxxx
                CC: package-review@xxxxxxxxxxxxxxxxxxxxxxx
  Target Milestone: ---
    Classification: Fedora



Spec URL: https://trix.fedorapeople.org/pocketfft.spec
SRPM URL:
https://trix.fedorapeople.org/pocketfft-1.0%5egit20230214.076cb3d-1.fc40.src.rpm

PocketFFT for C++                                                               
=================                                                               

This is a heavily modified implementation of FFTPack [1,2], with the following  
advantages:                                                                     

- Strictly C++11 compliant                                                      
- More accurate twiddle factor computation                                      
- Worst case complexity for transform sizes with large prime factors is         
  `N*log(N)`, because Bluestein's algorithm [3] is used for these cases.        
- Supports multidimensional arrays and selection of the axes to be transformed. 
- Supports `float`, `double`, and `long double` types.                          
- Supports fully complex and half-complex (i.e. complex-to-real and             
  real-to-complex) FFTs. For half-complex transforms, several conventions for   
  representing the complex-valued side are supported (reduced-size complex      
  array, FFTPACK-style half-complex format and Hartley transform).              
- Supports discrete cosine and sine transforms (Types I-IV)                     
- Makes use of CPU vector instructions when performing 2D and
higher-dimensional                                                              
  transforms, if they are available.                                            
- Has a small internal cache for transform plans, which speeds up repeated      
  transforms of the same length (most significant for 1D transforms).           
- Has optional multi-threading support for multidimensional transforms


The intended use in PyTorch is shown in this commit of in the wip spec
https://github.com/trixirt/pytorch-fedora/commit/51922a40f512b8272eaa3c68319072c4857d3668


Reproducible: Always


-- 
You are receiving this mail because:
You are on the CC list for the bug.
You are always notified about changes to this product and component
https://bugzilla.redhat.com/show_bug.cgi?id=2240398

Report this comment as SPAM: https://bugzilla.redhat.com/enter_bug.cgi?product=Bugzilla&format=report-spam&short_desc=Report%20of%20Bug%202240398%23c0
_______________________________________________
package-review mailing list -- package-review@xxxxxxxxxxxxxxxxxxxxxxx
To unsubscribe send an email to package-review-leave@xxxxxxxxxxxxxxxxxxxxxxx
Fedora Code of Conduct: https://docs.fedoraproject.org/en-US/project/code-of-conduct/
List Guidelines: https://fedoraproject.org/wiki/Mailing_list_guidelines
List Archives: https://lists.fedoraproject.org/archives/list/package-review@xxxxxxxxxxxxxxxxxxxxxxx
Do not reply to spam, report it: https://pagure.io/fedora-infrastructure/new_issue




[Index of Archives]     [Fedora Users]     [Fedora Desktop]     [Fedora SELinux]     [Yosemite Conditions]     [KDE Users]

  Powered by Linux