Merge "webmdec: Fix for reaching eof in webm_guess_framerate"

diff --git a/.mailmap b/.mailmap
index fb82a24..0bfda12 100644 (file)
--- a/.mailmap
+++ b/.mailmap
@@ -1,18 +1,26 @@
 Adrian Grange <agrange@google.com>
+Alex Converse <aconverse@google.com> <alex.converse@gmail.com>
 Alexis Ballier <aballier@gentoo.org> <alexis.ballier@gmail.com>
+Alpha Lam <hclam@google.com> <hclam@chromium.org>
+Deb Mukherjee <debargha@google.com>
+Erik Niemeyer <erik.a.niemeyer@intel.com> <erik.a.niemeyer@gmail.com>
+Guillaume Martres <gmartres@google.com> <smarter3@gmail.com>
 Hangyu Kuang <hkuang@google.com>
 Jim Bankoski <jimbankoski@google.com>
-John Koleszar <jkoleszar@google.com>
 Johann Koenig <johannkoenig@google.com>
 Johann Koenig <johannkoenig@google.com> <johann.koenig@duck.com>
-Johann Koenig <johannkoenig@google.com> <johannkoenig@dhcp-172-19-7-52.mtv.corp.google.com>
+John Koleszar <jkoleszar@google.com>
+Joshua Litt <joshualitt@google.com> <joshualitt@chromium.org>
+Marco Paniconi <marpan@google.com>
+Marco Paniconi <marpan@google.com> <marpan@chromium.org>
 Pascal Massimino <pascal.massimino@gmail.com>
+Paul Wilkins <paulwilkins@google.com>
+Ralph Giles <giles@xiph.org> <giles@entropywave.com>
+Ralph Giles <giles@xiph.org> <giles@mozilla.com>
 Sami Pietilä <samipietila@google.com>
+Tamar Levy <tamar.levy@intel.com>
+Tamar Levy <tamar.levy@intel.com> <levytamar82@gmail.com>
 Tero Rintaluoma <teror@google.com> <tero.rintaluoma@on2.com>
 Timothy B. Terriberry <tterribe@xiph.org> Tim Terriberry <tterriberry@mozilla.com>
 Tom Finegan <tomfinegan@google.com>
-Ralph Giles <giles@xiph.org> <giles@entropywave.com>
-Ralph Giles <giles@xiph.org> <giles@mozilla.com>
-Alpha Lam <hclam@google.com> <hclam@chromium.org>
-Deb Mukherjee <debargha@google.com>
 Yaowu Xu <yaowu@google.com> <yaowu@xuyaowu.com>

diff --git a/AUTHORS b/AUTHORS
index a9aa481..2f63d7c 100644 (file)
--- a/AUTHORS
+++ b/AUTHORS
@@ -3,10 +3,11 @@
 
 Aaron Watry <awatry@gmail.com>
 Abo Talib Mahfoodh <ab.mahfoodh@gmail.com>
+Adam Xu <adam@xuyaowu.com>
 Adrian Grange <agrange@google.com>
 Ahmad Sharif <asharif@google.com>
 Alexander Voronov <avoronov@graphics.cs.msu.ru>
-Alex Converse <alex.converse@gmail.com>
+Alex Converse <aconverse@google.com>
 Alexis Ballier <aballier@gentoo.org>
 Alok Ahuja <waveletcoeff@gmail.com>
 Alpha Lam <hclam@google.com>
@@ -14,44 +15,58 @@ A.Mahfoodh <ab.mahfoodh@gmail.com>
 Ami Fischman <fischman@chromium.org>
 Andoni Morales Alastruey <ylatuya@gmail.com>
 Andres Mejia <mcitadel@gmail.com>
+Andrew Russell <anrussell@google.com>
 Aron Rosenberg <arosenberg@logitech.com>
 Attila Nagy <attilanagy@google.com>
 changjun.yang <changjun.yang@intel.com>
+Charles 'Buck' Krasic <ckrasic@google.com>
 chm <chm@rock-chips.com>
 Christian Duvivier <cduvivier@google.com>
 Daniel Kang <ddkang@google.com>
 Deb Mukherjee <debargha@google.com>
+Dim Temp <dimtemp0@gmail.com>
 Dmitry Kovalev <dkovalev@google.com>
 Dragan Mrdjan <dmrdjan@mips.com>
-Erik Niemeyer <erik.a.niemeyer@gmail.com>
+Ehsan Akhgari <ehsan.akhgari@gmail.com>
+Erik Niemeyer <erik.a.niemeyer@intel.com>
 Fabio Pedretti <fabio.ped@libero.it>
 Frank Galligan <fgalligan@google.com>
 Fredrik Söderquist <fs@opera.com>
 Fritz Koenig <frkoenig@google.com>
 Gaute Strokkenes <gaute.strokkenes@broadcom.com>
 Giuseppe Scrivano <gscrivano@gnu.org>
+Gordana Cmiljanovic <gordana.cmiljanovic@imgtec.com>
 Guillaume Martres <gmartres@google.com>
 Guillermo Ballester Valor <gbvalor@gmail.com>
 Hangyu Kuang <hkuang@google.com>
+Hanno Böck <hanno@hboeck.de>
 Henrik Lundin <hlundin@google.com>
 Hui Su <huisu@google.com>
 Ivan Maltz <ivanmaltz@google.com>
+Jacek Caban <cjacek@gmail.com>
+JackyChen <jackychen@google.com>
 James Berry <jamesberry@google.com>
+James Yu <james.yu@linaro.org>
 James Zern <jzern@google.com>
+Jan Gerber <j@mailb.org>
 Jan Kratochvil <jan.kratochvil@redhat.com>
 Janne Salonen <jsalonen@google.com>
 Jeff Faust <jfaust@google.com>
 Jeff Muizelaar <jmuizelaar@mozilla.com>
 Jeff Petkau <jpet@chromium.org>
+Jia Jia <jia.jia@linaro.org>
 Jim Bankoski <jimbankoski@google.com>
 Jingning Han <jingning@google.com>
+Joey Parrish <joeyparrish@google.com>
 Johann Koenig <johannkoenig@google.com>
 John Koleszar <jkoleszar@google.com>
+John Stark <jhnstrk@gmail.com>
 Joshua Bleecher Snyder <josh@treelinelabs.com>
 Joshua Litt <joshualitt@google.com>
 Justin Clift <justin@salasaga.org>
 Justin Lebar <justin.lebar@gmail.com>
 KO Myung-Hun <komh@chollian.net>
+Lawrence Velázquez <larryv@macports.org>
 Lou Quillio <louquillio@google.com>
 Luca Barbato <lu_zero@gentoo.org>
 Makoto Kato <makoto.kt@gmail.com>
@@ -65,6 +80,7 @@ Michael Kohler <michaelkohler@live.com>
 Mike Frysinger <vapier@chromium.org>
 Mike Hommey <mhommey@mozilla.com>
 Mikhal Shemer <mikhal@google.com>
+Minghai Shang <minghai@google.com>
 Morton Jonuschat <yabawock@gmail.com>
 Parag Salasakar <img.mips1@gmail.com>
 Pascal Massimino <pascal.massimino@gmail.com>
@@ -72,6 +88,8 @@ Patrik Westin <patrik.westin@gmail.com>
 Paul Wilkins <paulwilkins@google.com>
 Pavol Rusnak <stick@gk2.sk>
 Paweł Hajdan <phajdan@google.com>
+Pengchong Jin <pengchong@google.com>
+Peter de Rivaz <peter.derivaz@gmail.com>
 Philip Jägenstedt <philipj@opera.com>
 Priit Laes <plaes@plaes.org>
 Rafael Ávila de Espíndola <rafael.espindola@gmail.com>
@@ -79,22 +97,29 @@ Rafaël Carré <funman@videolan.org>
 Ralph Giles <giles@xiph.org>
 Rob Bradford <rob@linux.intel.com>
 Ronald S. Bultje <rbultje@google.com>
+Rui Ueyama <ruiu@google.com>
 Sami Pietilä <samipietila@google.com>
 Scott Graham <scottmg@chromium.org>
 Scott LaVarnway <slavarnway@google.com>
+Sean McGovern <gseanmcg@gmail.com>
+Sergey Ulanov <sergeyu@chromium.org>
 Shimon Doodkin <helpmepro1@gmail.com>
 Stefan Holmer <holmer@google.com>
 Suman Sunkara <sunkaras@google.com>
 Taekhyun Kim <takim@nvidia.com>
 Takanori MATSUURA <t.matsuu@gmail.com>
 Tamar Levy <tamar.levy@intel.com>
+Tao Bai <michaelbai@chromium.org>
 Tero Rintaluoma <teror@google.com>
 Thijs Vermeir <thijsvermeir@gmail.com>
+Tim Kopp <tkopp@google.com>
 Timothy B. Terriberry <tterribe@xiph.org>
 Tom Finegan <tomfinegan@google.com>
 Vignesh Venkatasubramanian <vigneshv@google.com>
 Yaowu Xu <yaowu@google.com>
+Yongzhe Wang <yongzhe@google.com>
 Yunqing Wang <yunqingwang@google.com>
+Zoe Liu <zoeliu@google.com>
 Google Inc.
 The Mozilla Foundation
 The Xiph.Org Foundation

diff --git a/CHANGELOG b/CHANGELOG
index 97c9a7b..a318784 100644 (file)
--- a/CHANGELOG
+++ b/CHANGELOG
@@ -1,3 +1,26 @@
+2015-04-03 v1.4.0 "Indian Runner Duck"
+  This release includes significant improvements to the VP9 codec.
+
+  - Upgrading:
+    This release is ABI incompatible with 1.3.0. It drops the compatibility
+    layer, requiring VPX_IMG_FMT_* instead of IMG_FMT_*, and adds several codec
+    controls for VP9.
+
+  - Enhancements:
+    Faster VP9 encoding and decoding
+    Multithreaded VP9 decoding (tile and frame-based)
+    Multithreaded VP9 encoding - on by default
+    YUV 4:2:2 and 4:4:4 support in VP9
+    10 and 12bit support in VP9
+    64bit ARM support by replacing ARM assembly with intrinsics
+
+  - Bug Fixes:
+    Fixes a VP9 bitstream issue in Profile 1. This only affected non-YUV 4:2:0
+    files.
+
+  - Known Issues:
+    Frame Parallel decoding fails for segmented and non-420 files.
+
 2013-11-15 v1.3.0 "Forest"
   This release introduces the VP9 codec in a backward-compatible way.
   All existing users of VP8 can continue to use the library without

diff --git a/README b/README
index 4584cb5..fcd1c2e 100644 (file)
--- a/README
+++ b/README
@@ -1,4 +1,4 @@
-README - 30 May 2014
+README - 23 March 2015
 
 Welcome to the WebM VP8/VP9 Codec SDK!
 
@@ -72,6 +72,7 @@ COMPILING THE APPLICATIONS/LIBRARIES:
     x86-darwin11-gcc
     x86-darwin12-gcc
     x86-darwin13-gcc
+    x86-darwin14-gcc
     x86-iphonesimulator-gcc
     x86-linux-gcc
     x86-linux-icc
@@ -89,6 +90,7 @@ COMPILING THE APPLICATIONS/LIBRARIES:
     x86_64-darwin11-gcc
     x86_64-darwin12-gcc
     x86_64-darwin13-gcc
+    x86_64-darwin14-gcc
     x86_64-iphonesimulator-gcc
     x86_64-linux-gcc
     x86_64-linux-icc
@@ -105,6 +107,7 @@ COMPILING THE APPLICATIONS/LIBRARIES:
     universal-darwin11-gcc
     universal-darwin12-gcc
     universal-darwin13-gcc
+    universal-darwin14-gcc
     generic-gnu
 
   The generic-gnu target, in conjunction with the CROSS environment variable,

diff --git a/build/make/Makefile b/build/make/Makefile
index e048e9c..fc7749a 100644 (file)
--- a/build/make/Makefile
+++ b/build/make/Makefile
@@ -383,8 +383,8 @@ LIBS=$(call enabled,LIBS)
 .libs: $(LIBS)
        @touch $@
 $(foreach lib,$(filter %_g.a,$(LIBS)),$(eval $(call archive_template,$(lib))))
-$(foreach lib,$(filter %so.$(VERSION_MAJOR).$(VERSION_MINOR).$(VERSION_PATCH),$(LIBS)),$(eval $(call so_template,$(lib))))
-$(foreach lib,$(filter %$(VERSION_MAJOR).dylib,$(LIBS)),$(eval $(call dl_template,$(lib))))
+$(foreach lib,$(filter %so.$(SO_VERSION_MAJOR).$(SO_VERSION_MINOR).$(SO_VERSION_PATCH),$(LIBS)),$(eval $(call so_template,$(lib))))
+$(foreach lib,$(filter %$(SO_VERSION_MAJOR).dylib,$(LIBS)),$(eval $(call dl_template,$(lib))))
 
 INSTALL-LIBS=$(call cond_enabled,CONFIG_INSTALL_LIBS,INSTALL-LIBS)
 ifeq ($(MAKECMDGOALS),dist)

diff --git a/configure b/configure
index ebd516c..e05dd69 100755 (executable)
--- a/configure
+++ b/configure
@@ -261,8 +261,6 @@ ARCH_EXT_LIST="
     sse4_1
     avx
     avx2
-
-    altivec
 "
 HAVE_LIST="
     ${ARCH_EXT_LIST}

diff --git a/libs.mk b/libs.mk
index e48d55c..3046e1b 100644 (file)
--- a/libs.mk
+++ b/libs.mk
@@ -230,25 +230,27 @@ $(BUILD_PFX)libvpx_g.a: $(LIBVPX_OBJS)
 
 BUILD_LIBVPX_SO         := $(if $(BUILD_LIBVPX),$(CONFIG_SHARED))
 
+SO_VERSION_MAJOR := 2
+SO_VERSION_MINOR := 0
+SO_VERSION_PATCH := 0
 ifeq ($(filter darwin%,$(TGT_OS)),$(TGT_OS))
-LIBVPX_SO               := libvpx.$(VERSION_MAJOR).dylib
+LIBVPX_SO               := libvpx.$(SO_VERSION_MAJOR).dylib
 EXPORT_FILE             := libvpx.syms
 LIBVPX_SO_SYMLINKS      := $(addprefix $(LIBSUBDIR)/, \
                              libvpx.dylib  )
 else
-LIBVPX_SO               := libvpx.so.$(VERSION_MAJOR).$(VERSION_MINOR).$(VERSION_PATCH)
+LIBVPX_SO               := libvpx.so.$(SO_VERSION_MAJOR).$(SO_VERSION_MINOR).$(SO_VERSION_PATCH)
 EXPORT_FILE             := libvpx.ver
-SYM_LINK                := libvpx.so
 LIBVPX_SO_SYMLINKS      := $(addprefix $(LIBSUBDIR)/, \
-                             libvpx.so libvpx.so.$(VERSION_MAJOR) \
-                             libvpx.so.$(VERSION_MAJOR).$(VERSION_MINOR))
+                             libvpx.so libvpx.so.$(SO_VERSION_MAJOR) \
+                             libvpx.so.$(SO_VERSION_MAJOR).$(SO_VERSION_MINOR))
 endif
 
 LIBS-$(BUILD_LIBVPX_SO) += $(BUILD_PFX)$(LIBVPX_SO)\
                            $(notdir $(LIBVPX_SO_SYMLINKS))
 $(BUILD_PFX)$(LIBVPX_SO): $(LIBVPX_OBJS) $(EXPORT_FILE)
 $(BUILD_PFX)$(LIBVPX_SO): extralibs += -lm
-$(BUILD_PFX)$(LIBVPX_SO): SONAME = libvpx.so.$(VERSION_MAJOR)
+$(BUILD_PFX)$(LIBVPX_SO): SONAME = libvpx.so.$(SO_VERSION_MAJOR)
 $(BUILD_PFX)$(LIBVPX_SO): EXPORTS_FILE = $(EXPORT_FILE)
 
 libvpx.ver: $(call enabled,CODEC_EXPORTS)

diff --git a/vp8/common/debugmodes.c b/vp8/common/debugmodes.c
index 46064e6..159fddc 100644 (file)
--- a/vp8/common/debugmodes.c
+++ b/vp8/common/debugmodes.c
@@ -81,7 +81,6 @@ void vp8_print_modes_and_motion_vectors(MODE_INFO *mi, int rows, int cols, int f
     fprintf(mvs, "\n");
 
     /* print out the block modes */
-    mb_index = 0;
     fprintf(mvs, "Mbs for Frame %d\n", frame);
     {
         int b_row;
@@ -129,7 +128,6 @@ void vp8_print_modes_and_motion_vectors(MODE_INFO *mi, int rows, int cols, int f
 
 
     /* print out the block modes */
-    mb_index = 0;
     fprintf(mvs, "MVs for Frame %d\n", frame);
     {
         int b_row;

diff --git a/vp8/common/mfqe.c b/vp8/common/mfqe.c
index 0693326..edd6ca0 100644 (file)
--- a/vp8/common/mfqe.c
+++ b/vp8/common/mfqe.c
@@ -153,11 +153,11 @@ static void multiframe_quality_enhance_block
         actd = (vp8_variance16x16(yd, yd_stride, VP8_ZEROS, 0, &sse)+128)>>8;
         act = (vp8_variance16x16(y, y_stride, VP8_ZEROS, 0, &sse)+128)>>8;
 #ifdef USE_SSD
-        sad = (vp8_variance16x16(y, y_stride, yd, yd_stride, &sse));
+        vp8_variance16x16(y, y_stride, yd, yd_stride, &sse);
         sad = (sse + 128)>>8;
-        usad = (vp8_variance8x8(u, uv_stride, ud, uvd_stride, &sse));
+        vp8_variance8x8(u, uv_stride, ud, uvd_stride, &sse);
         usad = (sse + 32)>>6;
-        vsad = (vp8_variance8x8(v, uv_stride, vd, uvd_stride, &sse));
+        vp8_variance8x8(v, uv_stride, vd, uvd_stride, &sse);
         vsad = (sse + 32)>>6;
 #else
         sad = (vp8_sad16x16(y, y_stride, yd, yd_stride, UINT_MAX) + 128) >> 8;
@@ -170,11 +170,11 @@ static void multiframe_quality_enhance_block
         actd = (vp8_variance8x8(yd, yd_stride, VP8_ZEROS, 0, &sse)+32)>>6;
         act = (vp8_variance8x8(y, y_stride, VP8_ZEROS, 0, &sse)+32)>>6;
 #ifdef USE_SSD
-        sad = (vp8_variance8x8(y, y_stride, yd, yd_stride, &sse));
+        vp8_variance8x8(y, y_stride, yd, yd_stride, &sse);
         sad = (sse + 32)>>6;
-        usad = (vp8_variance4x4(u, uv_stride, ud, uvd_stride, &sse));
+        vp8_variance4x4(u, uv_stride, ud, uvd_stride, &sse);
         usad = (sse + 8)>>4;
-        vsad = (vp8_variance4x4(v, uv_stride, vd, uvd_stride, &sse));
+        vp8_variance4x4(v, uv_stride, vd, uvd_stride, &sse);
         vsad = (sse + 8)>>4;
 #else
         sad = (vp8_sad8x8(y, y_stride, yd, yd_stride, UINT_MAX) + 32) >> 6;

diff --git a/vp8/decoder/decodeframe.c b/vp8/decoder/decodeframe.c
index ab03c90..4f404bd 100644 (file)
--- a/vp8/decoder/decodeframe.c
+++ b/vp8/decoder/decodeframe.c
@@ -1069,7 +1069,6 @@ int vp8_decode_frame(VP8D_COMP *pbi)
                 pc->vert_scale = clear[6] >> 6;
             }
             data += 7;
-            clear += 7;
         }
         else
         {

diff --git a/vp8/encoder/firstpass.c b/vp8/encoder/firstpass.c
index 85767ef..84b9fae 100644 (file)
--- a/vp8/encoder/firstpass.c
+++ b/vp8/encoder/firstpass.c
@@ -2969,7 +2969,6 @@ static void find_next_key_frame(VP8_COMP *cpi, FIRSTPASS_STATS *this_frame)
      */
     decay_accumulator = 1.0;
     boost_score = 0.0;
-    loop_decay_rate = 1.00;       /* Starting decay rate */
 
     for (i = 0 ; i < cpi->twopass.frames_to_key ; i++)
     {
@@ -3213,7 +3212,7 @@ static void find_next_key_frame(VP8_COMP *cpi, FIRSTPASS_STATS *this_frame)
         int new_width = cpi->oxcf.Width;
         int new_height = cpi->oxcf.Height;
 
-        int projected_buffer_level = (int)cpi->buffer_level;
+        int projected_buffer_level;
         int tmp_q;
 
         double projected_bits_perframe;

diff --git a/vp8/encoder/picklpf.c b/vp8/encoder/picklpf.c
index f0c8f28..a55a1ea 100644 (file)
--- a/vp8/encoder/picklpf.c
+++ b/vp8/encoder/picklpf.c
@@ -142,7 +142,7 @@ void vp8cx_pick_filter_level_fast(YV12_BUFFER_CONFIG *sd, VP8_COMP *cpi)
     int min_filter_level = get_min_filter_level(cpi, cm->base_qindex);
     int max_filter_level = get_max_filter_level(cpi, cm->base_qindex);
     int filt_val;
-    int best_filt_val = cm->filter_level;
+    int best_filt_val;
     YV12_BUFFER_CONFIG * saved_frame = cm->frame_to_show;
 
     /* Replace unfiltered frame buffer with a new one */
@@ -274,8 +274,7 @@ void vp8cx_pick_filter_level(YV12_BUFFER_CONFIG *sd, VP8_COMP *cpi)
 
     int filter_step;
     int filt_high = 0;
-    /* Start search at previous frame filter level */
-    int filt_mid = cm->filter_level;
+    int filt_mid;
     int filt_low = 0;
     int filt_best;
     int filt_direction = 0;

diff --git a/vp8/encoder/rdopt.c b/vp8/encoder/rdopt.c
index 29da926..582c8bc 100644 (file)
--- a/vp8/encoder/rdopt.c
+++ b/vp8/encoder/rdopt.c
@@ -1661,7 +1661,6 @@ void vp8_mv_pred
             mv.as_mv.row = mvx[vcnt/2];
             mv.as_mv.col = mvy[vcnt/2];
 
-            find = 1;
             /* sr is set to 0 to allow calling function to decide the search
              * range.
              */
@@ -2293,7 +2292,6 @@ void vp8_rd_pick_inter_mode(VP8_COMP *cpi, MACROBLOCK *x, int recon_yoffset,
                 mode_mv[NEWMV].as_int = d->bmi.mv.as_int;
 
                 /* Further step/diamond searches as necessary */
-                n = 0;
                 further_steps = (cpi->sf.max_step_search_steps - 1) - step_param;
 
                 n = num00;
@@ -2560,8 +2558,6 @@ void vp8_rd_pick_inter_mode(VP8_COMP *cpi, MACROBLOCK *x, int recon_yoffset,
                                                intra_rd_penalty, cpi, x);
             if (this_rd < best_mode.rd || x->skip)
             {
-                /* Note index of best mode so far */
-                best_mode_index = mode_index;
                 *returnrate = rd.rate2;
                 *returndistortion = rd.distortion2;
                 update_best_mode(&best_mode, this_rd, &rd, other_cost, x);

diff --git a/vp8/encoder/x86/quantize_sse2.c b/vp8/encoder/x86/quantize_sse2.c
index 291d219..f56e646 100644 (file)
--- a/vp8/encoder/x86/quantize_sse2.c
+++ b/vp8/encoder/x86/quantize_sse2.c
@@ -35,7 +35,7 @@
 void vp8_regular_quantize_b_sse2(BLOCK *b, BLOCKD *d)
 {
     char eob = 0;
-    short *zbin_boost_ptr  = b->zrun_zbin_boost;
+    short *zbin_boost_ptr;
     short *qcoeff_ptr      = d->qcoeff;
     DECLARE_ALIGNED_ARRAY(16, short, x, 16);
     DECLARE_ALIGNED_ARRAY(16, short, y, 16);

diff --git a/vp9/common/vp9_rtcd_defs.pl b/vp9/common/vp9_rtcd_defs.pl
index 39b5908..d0a03ce 100644 (file)
--- a/vp9/common/vp9_rtcd_defs.pl
+++ b/vp9/common/vp9_rtcd_defs.pl
@@ -1028,16 +1028,20 @@ add_proto qw/void vp9_sad32x32x8/, "const uint8_t *src_ptr, int  src_stride, con
 specialize qw/vp9_sad32x32x8/;
 
 add_proto qw/void vp9_sad16x16x8/, "const uint8_t *src_ptr, int  src_stride, const uint8_t *ref_ptr, int  ref_stride, uint32_t *sad_array";
-specialize qw/vp9_sad16x16x8 sse4/;
+specialize qw/vp9_sad16x16x8 sse4_1/;
+$vp9_sad16x16x8_sse4_1=vp9_sad16x16x8_sse4;
 
 add_proto qw/void vp9_sad16x8x8/, "const uint8_t *src_ptr, int  src_stride, const uint8_t *ref_ptr, int  ref_stride, uint32_t *sad_array";
-specialize qw/vp9_sad16x8x8 sse4/;
+specialize qw/vp9_sad16x8x8 sse4_1/;
+$vp9_sad16x8x8_sse4_1=vp9_sad16x8x8_sse4;
 
 add_proto qw/void vp9_sad8x16x8/, "const uint8_t *src_ptr, int  src_stride, const uint8_t *ref_ptr, int  ref_stride, uint32_t *sad_array";
-specialize qw/vp9_sad8x16x8 sse4/;
+specialize qw/vp9_sad8x16x8 sse4_1/;
+$vp9_sad8x16x8_sse4_1=vp9_sad8x16x8_sse4;
 
 add_proto qw/void vp9_sad8x8x8/, "const uint8_t *src_ptr, int  src_stride, const uint8_t *ref_ptr, int  ref_stride, uint32_t *sad_array";
-specialize qw/vp9_sad8x8x8 sse4/;
+specialize qw/vp9_sad8x8x8 sse4_1/;
+$vp9_sad8x8x8_sse4_1=vp9_sad8x8x8_sse4;
 
 add_proto qw/void vp9_sad8x4x8/, "const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array";
 specialize qw/vp9_sad8x4x8/;
@@ -1046,7 +1050,8 @@ add_proto qw/void vp9_sad4x8x8/, "const uint8_t *src_ptr, int src_stride, const
 specialize qw/vp9_sad4x8x8/;
 
 add_proto qw/void vp9_sad4x4x8/, "const uint8_t *src_ptr, int  src_stride, const uint8_t *ref_ptr, int  ref_stride, uint32_t *sad_array";
-specialize qw/vp9_sad4x4x8 sse4/;
+specialize qw/vp9_sad4x4x8 sse4_1/;
+$vp9_sad4x4x8_sse4_1=vp9_sad4x4x8_sse4;
 
 add_proto qw/void vp9_sad64x64x4d/, "const uint8_t *src_ptr, int  src_stride, const uint8_t* const ref_ptr[], int  ref_stride, unsigned int *sad_array";
 specialize qw/vp9_sad64x64x4d sse2 avx2 neon/;

diff --git a/vp9/encoder/vp9_pickmode.c b/vp9/encoder/vp9_pickmode.c
index 370c3e7..894da9b 100644 (file)
--- a/vp9/encoder/vp9_pickmode.c
+++ b/vp9/encoder/vp9_pickmode.c
@@ -378,16 +378,18 @@ static void model_rd_for_sb_y_large(VP9_COMP *cpi, BLOCK_SIZE bsize,
       struct macroblockd_plane *const pd = &xd->plane[i];
       const TX_SIZE uv_tx_size = get_uv_tx_size(&xd->mi[0].src_mi->mbmi, pd);
       const BLOCK_SIZE unit_size = txsize_to_bsize[uv_tx_size];
-      const int sf = (bw - b_width_log2_lookup[unit_size]) +
-          (bh - b_height_log2_lookup[unit_size]);
-      const BLOCK_SIZE bs = get_plane_block_size(bsize, pd);
+      const BLOCK_SIZE uv_bsize = get_plane_block_size(bsize, pd);
+      const int uv_bw = b_width_log2_lookup[uv_bsize];
+      const int uv_bh = b_height_log2_lookup[uv_bsize];
+      const int sf = (uv_bw - b_width_log2_lookup[unit_size]) +
+          (uv_bh - b_height_log2_lookup[unit_size]);
       const uint32_t uv_dc_thr = pd->dequant[0] * pd->dequant[0] >> (6 - sf);
       const uint32_t uv_ac_thr = pd->dequant[1] * pd->dequant[1] >> (6 - sf);
       int j = i - 1;
 
       vp9_build_inter_predictors_sbp(xd, mi_row, mi_col, bsize, i);
-      var_uv[j] = cpi->fn_ptr[bs].vf(p->src.buf, p->src.stride,
-                             pd->dst.buf, pd->dst.stride, &sse_uv[j]);
+      var_uv[j] = cpi->fn_ptr[uv_bsize].vf(p->src.buf, p->src.stride,
+          pd->dst.buf, pd->dst.stride, &sse_uv[j]);
 
       if (var_uv[j] < uv_ac_thr || var_uv[j] == 0) {
         if (sse_uv[j] - var_uv[j] < uv_dc_thr || sse_uv[j] == var_uv[j])