projects / platform / upstream / libvpx.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: ccc101e) | patch
Optimize Neon implementation of high bitdepth MSE functions
authorSalome Thirot <salome.thirot@arm.com>
Mon, 27 Feb 2023 17:58:18 +0000 (17:58 +0000)
committerSalome Thirot <salome.thirot@arm.com>
Wed, 1 Mar 2023 13:35:03 +0000 (13:35 +0000)
commit096cd0ba8ab2126682a9f6f01d6c8c0084d2f8ab
tree78bc826ead7aee09fc052f7c73f9039b78b73e87tree | snapshot
parentccc101e6bb63c2af340b993c57fad0f3810aee27commit | diff
Optimize Neon implementation of high bitdepth MSE functions

Currently MSE functions just call the variance helpers but don't
actually use the computed sum. This patch adds dedicated helpers to
perform the computation of sse.

Add the corresponding tests as well.

Change-Id: I96a8590e3410e84d77f7187344688e02efe03902
test/variance_test.cc diff | blob | history
vpx_dsp/arm/highbd_variance_neon.c diff | blob | history
Domain: Multimedia / Codec;