Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / a25d16c86f0d870408bc8b941aa755093417b0f0
commita25d16c86f0d870408bc8b941aa755093417b0f0[log] [tgz]
authorVidhya Sudhan Loganathan <vidhyasudhan.loganathan@arm.com>Fri Nov 16 11:33:12 2018 +0000
committerGeorgios Pinitas <georgios.pinitas@arm.com>Fri Nov 16 17:37:40 2018 +0000
treeb62d145a4e5009d894262a7ffa66cdba8260bb03
parenta7b54f44e2bf133179f24a34007bc93237dd2265 [diff]
COMPMID-1266 : Add support for FP16 in CLWinogradConvolutionLayer: 5x5 kernels

Introduced F32 accumulation for F16 winograd gemm and output transform
WinogradConvolution will be available for F16 only if fast math flag is enabled

Change-Id: I215593c205236a0f9669218437bb40b184ec6a4f
13 files changed
tree: b62d145a4e5009d894262a7ffa66cdba8260bb03
  1. .clang-format
  2. .clang-tidy
  3. .github/
  4. .gitmodules
  5. 3rdparty
  6. LICENSE
  7. README.md
  8. SConscript
  9. SConstruct
  10. arm_compute/
  11. data
  12. docs/
  13. examples/
  14. include/
  15. opencl-1.2-stubs/
  16. opengles-3.1-stubs/
  17. scripts/
  18. src/
  19. support/
  20. tests/
  21. utils/
README.md

Please report issues here: https://github.com/ARM-software/ComputeLibrary/issues Make sure you are using the latest version of the library before opening an issue. Thanks

News:

Related projects:

Documentation available here:

Binaries available here:

Support: developer-compute@arm.com

License & Contributions: The software is provided under MIT license. Contributions to this project are accepted under the same license.