Difference between revisions of "Porting/ncnn"

From RCS Wiki
Jump to navigation Jump to search
(Finished: Update Vulkan dependency docs)
(VSX Targets)
Line 14: Line 14:
 
* CI missing for POWER9/Clang
 
* CI missing for POWER9/Clang
 
* Replace SSE with native VSX
 
* Replace SSE with native VSX
 +
 +
= VSX Targets =
 +
 +
When running Real-ESRGAN in ncnn on POWER9, most CPU time (over 81%) is spent inside [https://github.com/Tencent/ncnn/blob/575098640c254be2208095254f3e5de412751447/src/layer/x86/convolution_3x3_winograd.h#L613 <code>gemm_transB_packed_tile</code> in <code>convolution_3x3_winograd.h</code>], which uses SSE2. This may be a good target for rewriting in native VSX.
  
 
= See Also =
 
= See Also =

Revision as of 05:11, 18 December 2023

Finished

In progress

  • CI missing for POWER9/Clang
  • Replace SSE with native VSX

VSX Targets

When running Real-ESRGAN in ncnn on POWER9, most CPU time (over 81%) is spent inside gemm_transB_packed_tile in convolution_3x3_winograd.h, which uses SSE2. This may be a good target for rewriting in native VSX.

See Also