projects / platform / upstream / libvpx.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 90c5493) | patch
VPX: Add vpx_highbd_quantize_b_32x32_avx2().
authorScott LaVarnway <slavarnway@google.com>
Mon, 25 Jul 2022 12:52:27 +0000 (05:52 -0700)
committerScott LaVarnway <slavarnway@google.com>
Tue, 26 Jul 2022 11:41:17 +0000 (04:41 -0700)
commit90ef3906a2af36a0f973709302785de92a7e12a1
tree90e56f871bd0cc14496d92412201ee5c03325508tree | snapshot
parent90c5493ff5d805676233252be633d2eedd5ceb50commit | diff
VPX: Add vpx_highbd_quantize_b_32x32_avx2().

Up to 11.78x faster than vpx_quantize_b_32x32_sse2() for full
calculations.

~1.7% overall encoder improvement for the test clip used.

Bug: b/237714063

Change-Id: Ib759056db94d3487239cb2748ffef1184a89ae18
test/vp9_quantize_test.cc diff | blob | history
vpx_dsp/vpx_dsp_rtcd_defs.pl diff | blob | history
vpx_dsp/x86/highbd_quantize_intrin_avx2.c diff | blob | history
Domain: Multimedia / Codec;