Commit history

1. Commits on Mar 11, 2025

   • signed 8-bit integer support

     

     verstatx

     authored and

     syurkevi

     committed
     cdbbc75View commit details

     Copy full SHA for cdbbc75

     View code at this pointBrowse repository at this point
2. Commits on Jan 14, 2025

   • Extend test for convolve2GradientNN function to verify zero padding fix in PR 3519 (#3631)

     christophe-murphy

     authored
     5c2ea29View commit details

     Copy full SHA for 5c2ea29

     View code at this pointBrowse repository at this point
3. Commits on Jan 9, 2025

   • 3580 bug investigate test failures when running with cuda 126 (#3588)

     Show description for f4edcf2
     

     christophe-murphy

     and

     FloopCZ

     authored
     f4edcf2View commit details

     Copy full SHA for f4edcf2

     View code at this pointBrowse repository at this point
4. Commits on Jan 21, 2023

   • Update convolve tests tolerances for floating point types

     umar456

     committed
     e5b1047View commit details

     Copy full SHA for e5b1047

     View code at this pointBrowse repository at this point
5. Commits on Oct 4, 2022

   • Update clang-format version on github workflow

     umar456

     committed
     e401fceView commit details

     Copy full SHA for e401fce

     View code at this pointBrowse repository at this point

   • Update deprecated macro from GTest. Add workaround for older versions

     umar456

     committed
     83edd09View commit details

     Copy full SHA for 83edd09

     View code at this pointBrowse repository at this point
6. Commits on Aug 18, 2021

   • Fix reference count if array used in JIT operations.

     Show description for a57b291
     

     umar456

     authored and

     9prady9

     committed
     a57b291View commit details

     Copy full SHA for a57b291

     View code at this pointBrowse repository at this point
7. Commits on May 20, 2021

   • Increase half type error tolerance to 0.07 for convolve tests

     9prady9

     committed
     34833d1View commit details

     Copy full SHA for 34833d1

     View code at this pointBrowse repository at this point
8. Commits on Aug 12, 2020

   • Fix problems in RNG for older compute architectures with fp16

     

     umar456

     authored and

     9prady9

     committed
     fe0c8d5View commit details

     Copy full SHA for fe0c8d5

     View code at this pointBrowse repository at this point
9. Commits on Apr 28, 2020

   • Create a test library to speed up test compilation

     

     umar456

     authored and

     9prady9

     committed
     fd01d59View commit details

     Copy full SHA for fd01d59

     View code at this pointBrowse repository at this point
10. Commits on Apr 22, 2020

    • Address all warnings with -Wall flags in GCC 9.3

      

      umar456

      authored and

      9prady9

      committed
      3f56eb7View commit details

      Copy full SHA for 3f56eb7

      View code at this pointBrowse repository at this point
11. Commits on Apr 13, 2020

    • Make cudnn dependency optional (#2836)

      Show description for fc99193
      

      syurkevi

      and

      umar456

      authored
      fc99193View commit details

      Copy full SHA for fc99193

      View code at this pointBrowse repository at this point
12. Commits on Apr 8, 2020

    • fix zero padding in convolve2NN (#2820)

      Show description for decde4e
      syurkevi

      authored
      decde4eView commit details

      Copy full SHA for decde4e

      View code at this pointBrowse repository at this point
13. Commits on Feb 15, 2020

    • Format source files per clang-format style

      9prady9

      committed
      2c819beView commit details

      Copy full SHA for 2c819be

      View code at this pointBrowse repository at this point
14. Commits on Aug 29, 2019

    • Dilated convolve2 and backward gradients (#2359)

      Show description for dae7c16
      

      syurkevi

      authored and

      umar456

      committed
      dae7c16View commit details

      Copy full SHA for dae7c16

      View code at this pointBrowse repository at this point
15. Commits on May 30, 2019

    • Fix convolve3 launch configuration in CUDA backend

      Show description for b5286ef
      

      9prady9

      authored and

      umar456

      committed
      b5286efView commit details

      Copy full SHA for b5286ef

      View code at this pointBrowse repository at this point
16. Commits on Jan 24, 2019

    • Use SUPPORTED_TYPE_CHECK macro to test for supported type

      Show description for 9763d2f
      umar456

      committed
      9763d2fView commit details

      Copy full SHA for 9763d2f

      View code at this pointBrowse repository at this point
17. Commits on Jan 1, 2019

    • Update all source files based on clang-format rules

      

      umar456

      authored and

      9prady9

      committed
      7128623View commit details

      Copy full SHA for 7128623

      View code at this pointBrowse repository at this point
18. Commits on Aug 1, 2018

    • Using the new ASSERT*_ARRAY_EQ macros for tests

      Show description for ca61e34
      

      Mark Poscablo

      authored and

      9prady9

      committed
      ca61e34View commit details

      Copy full SHA for ca61e34

      View code at this pointBrowse repository at this point
19. Commits on Jun 19, 2018

    • Cleanup tests. Fix warnings when running with asan. (#2199)

      Show description for 7c6fa42
      

      mlloreda

      authored and

      umar456

      committed
      7c6fa42View commit details

      Copy full SHA for 7c6fa42

      View code at this pointBrowse repository at this point
20. Commits on Aug 29, 2017

    • reduce number of launched blocks

      

      syurkevi

      authored and

      pavanky

      committed
      66f010fView commit details

      Copy full SHA for 66f010f

      View code at this pointBrowse repository at this point
21. Commits on Jun 19, 2017

    • Add matching af_free_host and use vector instead of new in tests

      

      umar456

      authored and

      pavanky

      committed
      7cf4f9aView commit details

      Copy full SHA for 7cf4f9a

      View code at this pointBrowse repository at this point

    • convolve tests for complex types

      

      9prady9

      authored and

      mlloreda

      committed
      18278eaView commit details

      Copy full SHA for 18278ea

      View code at this pointBrowse repository at this point
22. Commits on Jan 2, 2016

    • Fix clang warnings (std::abs, pragma ignores)

      Show description for c2d7e42
      shehzan10

      committed
      c2d7e42View commit details

      Copy full SHA for c2d7e42

      View code at this pointBrowse repository at this point
23. Commits on Nov 3, 2015

    • Add intl/uintl to convolve and fftconvolve

      

      shehzan10

      authored and

      umar456

      committed
      401f130View commit details

      Copy full SHA for 401f130

      View code at this pointBrowse repository at this point
24. Commits on Sep 22, 2015

    • Added short (s16) and ushort (u16) types for CPU

      Show description for ebfe9e5
      shehzan10

      committed
      ebfe9e5View commit details

      Copy full SHA for ebfe9e5

      View code at this pointBrowse repository at this point
25. Commits on Jun 8, 2015

    • BUGFIX/TEST: fftConvolve now does multi dimensional batching properly

      Show description for 55bf057
      pavanky

      committed
      55bf057View commit details

      Copy full SHA for 55bf057

      View code at this pointBrowse repository at this point
26. Commits on May 28, 2015

    • TEST: Adding GFOR tests for convolve

      pavanky

      committed
      2631d68View commit details

      Copy full SHA for 2631d68

      View code at this pointBrowse repository at this point
27. Commits on May 25, 2015

    • API: rename af_weak_copy/af_destroy_array to af_retain/af_release

      Show description for ba75031
      umar456

      committed
      ba75031View commit details

      Copy full SHA for ba75031

      View code at this pointBrowse repository at this point
28. Commits on May 15, 2015

    • FEAT: convolve automatically switches to frequency domain when necessary

      pavanky

      committed
      9002e68View commit details

      Copy full SHA for 9002e68

      View code at this pointBrowse repository at this point
29. Commits on May 14, 2015

    • Making the expand parameter an enum for convolutions

      pavanky

      committed
      7990c2cView commit details

      Copy full SHA for 7990c2c

      View code at this pointBrowse repository at this point
30. Commits on Apr 18, 2015

    • Remove unnecessary template parameters from tests

      umar456

      committed
      4e7338aView commit details

      Copy full SHA for 4e7338a

      View code at this pointBrowse repository at this point
31. Commits on Mar 19, 2015

    • Revised documentation for convolve

      Show description for e379a90
      9prady9

      committed
      e379a90View commit details

      Copy full SHA for e379a90

      View code at this pointBrowse repository at this point
32. Commits on Mar 8, 2015

    • Make tests C++03 complient.

      Show description for cc07a2c
      umar456

      committed
      cc07a2cView commit details

      Copy full SHA for cc07a2c

      View code at this pointBrowse repository at this point
33. Commits on Mar 6, 2015

    • FEAT: filter in convolutions is cast to the accum type

      pavanky

      committed
      b1e87b3View commit details

      Copy full SHA for b1e87b3

      View code at this pointBrowse repository at this point