Skip to content
GitLab
Commit bbe5e032 authored by Yunqing Wang's avatar Yunqing Wang
Browse files

Fix ref_stride in sad function 

Used ref_stride.

Change-Id: I31f0a3bb935520f54d11a1d87315627f162ae845
parent 4db08237
v1.14.0-linphone 1.4.X experimental feature/update_to_v1.9.0-linphone feature/uwp_nuget forest frame_parallel highbitdepth indianrunnerduck javanwhistlingduck khakicampbell linphone linphone-android linphone-old longtailedduck m29-baseline m31-baseline m49-2623 m52-2743 m54-2840 m56-2924 m66-3359 m68-3440 mandarinduck mcw mcw2 nextgen nextgenv2 pcs-2013 playground sandbox/Jingning/experimental sandbox/Jingning/transcode sandbox/Jingning/vpx sandbox/aconverse@google.com/ansbench sandbox/debargha/playground sandbox/hkuang/frame_parallel sandbox/hkuang@google.com/decode sandbox/jimbankoski@google.com/proposed-aom sandbox/jingning@google.com/decoder_test_suite sandbox/jingning@google.com/experimental sandbox/jzern@google.com/test sandbox/wangch@google.com/vp9 sandbox/yaowu@google.com/mergeaom stable-vp9-decoder v1.12.0-linphone v1.6.1_linphone v1.7.0-linphone v1.9.0-linphone vp9-preview v1.9.0 v1.9.0-rc1 v1.8.2 v1.8.1 v1.8.0 v1.7.0 v1.6.1 v1.6.0 v1.5.0 v1.4.0 v1.3.0
No related merge requests found
Hide whitespace changes
Inline Side-by-side
Showing
with 7 additions and 7 deletions
vp9/common/x86/sadmxn_x86.c
+ 7
− 7
View file @ bbe5e032
...@@ -30,9 +30,9 @@ unsigned int vp9_sad16x3_sse2( ...@@ -30,9 +30,9 @@ unsigned int vp9_sad16x3_sse2(
s1 = _mm_loadu_si128((const __m128i *)(src_ptr + 1 * src_stride)); s1 = _mm_loadu_si128((const __m128i *)(src_ptr + 1 * src_stride));
s2 = _mm_loadu_si128((const __m128i *)(src_ptr + 2 * src_stride)); s2 = _mm_loadu_si128((const __m128i *)(src_ptr + 2 * src_stride));
r0 = _mm_loadu_si128((const __m128i *)(ref_ptr + 0 * src_stride)); r0 = _mm_loadu_si128((const __m128i *)(ref_ptr + 0 * ref_stride));
r1 = _mm_loadu_si128((const __m128i *)(ref_ptr + 1 * src_stride)); r1 = _mm_loadu_si128((const __m128i *)(ref_ptr + 1 * ref_stride));
r2 = _mm_loadu_si128((const __m128i *)(ref_ptr + 2 * src_stride)); r2 = _mm_loadu_si128((const __m128i *)(ref_ptr + 2 * ref_stride));
sad = _mm_sad_epu8(s0, r0); sad = _mm_sad_epu8(s0, r0);
sad = _mm_add_epi16(sad, _mm_sad_epu8(s1, r1)); sad = _mm_add_epi16(sad, _mm_sad_epu8(s1, r1));
...@@ -57,10 +57,10 @@ unsigned int vp9_sad3x16_sse2( ...@@ -57,10 +57,10 @@ unsigned int vp9_sad3x16_sse2(
s1 = _mm_cvtsi32_si128 (*(const int *)(src_ptr + 1 * src_stride)); s1 = _mm_cvtsi32_si128 (*(const int *)(src_ptr + 1 * src_stride));
s2 = _mm_cvtsi32_si128 (*(const int *)(src_ptr + 2 * src_stride)); s2 = _mm_cvtsi32_si128 (*(const int *)(src_ptr + 2 * src_stride));
s3 = _mm_cvtsi32_si128 (*(const int *)(src_ptr + 3 * src_stride)); s3 = _mm_cvtsi32_si128 (*(const int *)(src_ptr + 3 * src_stride));
r0 = _mm_cvtsi32_si128 (*(const int *)(ref_ptr + 0 * src_stride)); r0 = _mm_cvtsi32_si128 (*(const int *)(ref_ptr + 0 * ref_stride));
r1 = _mm_cvtsi32_si128 (*(const int *)(ref_ptr + 1 * src_stride)); r1 = _mm_cvtsi32_si128 (*(const int *)(ref_ptr + 1 * ref_stride));
r2 = _mm_cvtsi32_si128 (*(const int *)(ref_ptr + 2 * src_stride)); r2 = _mm_cvtsi32_si128 (*(const int *)(ref_ptr + 2 * ref_stride));
r3 = _mm_cvtsi32_si128 (*(const int *)(ref_ptr + 3 * src_stride)); r3 = _mm_cvtsi32_si128 (*(const int *)(ref_ptr + 3 * ref_stride));
s0 = _mm_unpacklo_epi8(s0, s1); s0 = _mm_unpacklo_epi8(s0, s1);
r0 = _mm_unpacklo_epi8(r0, r1); r0 = _mm_unpacklo_epi8(r0, r1);
......
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment