Update libaom to commit ID 1e227d41f0616de9548a673a83a21ef990b62591

media/libaom/README_MCP

@@ -10,4 +10,4 @@ The upstream aom git repository is:
 
     https://aomedia.googlesource.com/aom
 
-The git commit ID used was b25610052a1398032320008d69b51d2da94f5928.
+The git commit ID used was 1e227d41f0616de9548a673a83a21ef990b62591.

media/libaom/config/generic/config/aom_config.asm

@@ -14,6 +14,7 @@ ARCH_MIPS equ 0
 ARCH_PPC equ 0
 ARCH_X86 equ 0
 ARCH_X86_64 equ 0
+CONFIG_2PASS_PARTITION_SEARCH_LVL equ 1
 CONFIG_ACCOUNTING equ 0
 CONFIG_ANALYZER equ 0
 CONFIG_AV1_DECODER equ 1
@@ -21,30 +22,35 @@ CONFIG_AV1_ENCODER equ 0
 CONFIG_BIG_ENDIAN equ 0
 CONFIG_BITSTREAM_DEBUG equ 0
 CONFIG_COEFFICIENT_RANGE_CHECKING equ 0
-CONFIG_COLLECT_INTER_MODE_RD_STATS equ 1
+CONFIG_COLLECT_INTER_MODE_RD_STATS equ 0
 CONFIG_COLLECT_RD_STATS equ 0
 CONFIG_DEBUG equ 0
-CONFIG_DENOISE equ 0
-CONFIG_DIST_8X8 equ 1
+CONFIG_DENOISE equ 1
+CONFIG_DIST_8X8 equ 0
 CONFIG_ENTROPY_STATS equ 0
 CONFIG_FILEOPTIONS equ 1
+CONFIG_FIX_GF_LENGTH equ 1
 CONFIG_FP_MB_STATS equ 0
 CONFIG_GCC equ 1
 CONFIG_GCOV equ 0
+CONFIG_GLOBAL_MOTION_SEARCH equ 1
 CONFIG_GPROF equ 0
 CONFIG_INSPECTION equ 0
 CONFIG_INTERNAL_STATS equ 0
 CONFIG_INTER_STATS_ONLY equ 0
 CONFIG_LIBYUV equ 0
-CONFIG_LOWBITDEPTH equ 0
+CONFIG_LOWBITDEPTH equ 1
+CONFIG_MAX_DECODE_PROFILE equ 2
 CONFIG_MISMATCH_DEBUG equ 0
-CONFIG_MSVS equ 0
 CONFIG_MULTITHREAD equ 1
+CONFIG_NORMAL_TILE_MODE equ 0
 CONFIG_OS_SUPPORT equ 1
 CONFIG_PIC equ 0
 CONFIG_RD_DEBUG equ 0
+CONFIG_REDUCED_ENCODER_BORDER equ 0
 CONFIG_RUNTIME_CPU_DETECT equ 1
 CONFIG_SHARED equ 0
+CONFIG_SHARP_SETTINGS equ 0
 CONFIG_SIZE_LIMIT equ 0
 CONFIG_SPATIAL_RESAMPLING equ 1
 CONFIG_STATIC equ 1

media/libaom/config/generic/config/aom_config.h

@@ -16,6 +16,7 @@
 #define ARCH_PPC 0
 #define ARCH_X86 0
 #define ARCH_X86_64 0
+#define CONFIG_2PASS_PARTITION_SEARCH_LVL 1
 #define CONFIG_ACCOUNTING 0
 #define CONFIG_ANALYZER 0
 #define CONFIG_AV1_DECODER 1
@@ -23,30 +24,35 @@
 #define CONFIG_BIG_ENDIAN 0
 #define CONFIG_BITSTREAM_DEBUG 0
 #define CONFIG_COEFFICIENT_RANGE_CHECKING 0
-#define CONFIG_COLLECT_INTER_MODE_RD_STATS 1
+#define CONFIG_COLLECT_INTER_MODE_RD_STATS 0
 #define CONFIG_COLLECT_RD_STATS 0
 #define CONFIG_DEBUG 0
-#define CONFIG_DENOISE 0
-#define CONFIG_DIST_8X8 1
+#define CONFIG_DENOISE 1
+#define CONFIG_DIST_8X8 0
 #define CONFIG_ENTROPY_STATS 0
 #define CONFIG_FILEOPTIONS 1
+#define CONFIG_FIX_GF_LENGTH 1
 #define CONFIG_FP_MB_STATS 0
 #define CONFIG_GCC 1
 #define CONFIG_GCOV 0
+#define CONFIG_GLOBAL_MOTION_SEARCH 1
 #define CONFIG_GPROF 0
 #define CONFIG_INSPECTION 0
 #define CONFIG_INTERNAL_STATS 0
 #define CONFIG_INTER_STATS_ONLY 0
 #define CONFIG_LIBYUV 0
-#define CONFIG_LOWBITDEPTH 0
+#define CONFIG_LOWBITDEPTH 1
+#define CONFIG_MAX_DECODE_PROFILE 2
 #define CONFIG_MISMATCH_DEBUG 0
-#define CONFIG_MSVS 0
 #define CONFIG_MULTITHREAD 1
+#define CONFIG_NORMAL_TILE_MODE 0
 #define CONFIG_OS_SUPPORT 1
 #define CONFIG_PIC 0
 #define CONFIG_RD_DEBUG 0
+#define CONFIG_REDUCED_ENCODER_BORDER 0
 #define CONFIG_RUNTIME_CPU_DETECT 1
 #define CONFIG_SHARED 0
+#define CONFIG_SHARP_SETTINGS 0
 #define CONFIG_SIZE_LIMIT 0
 #define CONFIG_SPATIAL_RESAMPLING 1
 #define CONFIG_STATIC 1

media/libaom/config/generic/config/av1_rtcd.h

@@ -1,6 +1,6 @@
 // This file is generated. Do not edit.
-#ifndef AOM_RTCD_H_
-#define AOM_RTCD_H_
+#ifndef AV1_RTCD_H_
+#define AV1_RTCD_H_
 
 #ifdef RTCD_C
 #define RTCD_EXTERN
@@ -141,6 +141,27 @@ void av1_highbd_dr_prediction_z2_c(uint16_t *dst, ptrdiff_t stride, int bw, int
 void av1_highbd_dr_prediction_z3_c(uint16_t *dst, ptrdiff_t stride, int bw, int bh, const uint16_t *above, const uint16_t *left, int upsample_left, int dx, int dy, int bd);
 #define av1_highbd_dr_prediction_z3 av1_highbd_dr_prediction_z3_c
 
+void av1_highbd_inv_txfm_add_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+#define av1_highbd_inv_txfm_add av1_highbd_inv_txfm_add_c
+
+void av1_highbd_inv_txfm_add_16x16_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+#define av1_highbd_inv_txfm_add_16x16 av1_highbd_inv_txfm_add_16x16_c
+
+void av1_highbd_inv_txfm_add_16x8_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+#define av1_highbd_inv_txfm_add_16x8 av1_highbd_inv_txfm_add_16x8_c
+
+void av1_highbd_inv_txfm_add_32x32_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+#define av1_highbd_inv_txfm_add_32x32 av1_highbd_inv_txfm_add_32x32_c
+
+void av1_highbd_inv_txfm_add_4x4_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+#define av1_highbd_inv_txfm_add_4x4 av1_highbd_inv_txfm_add_4x4_c
+
+void av1_highbd_inv_txfm_add_8x16_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+#define av1_highbd_inv_txfm_add_8x16 av1_highbd_inv_txfm_add_8x16_c
+
+void av1_highbd_inv_txfm_add_8x8_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+#define av1_highbd_inv_txfm_add_8x8 av1_highbd_inv_txfm_add_8x8_c
+
 void av1_highbd_iwht4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, int bd);
 #define av1_highbd_iwht4x4_16_add av1_highbd_iwht4x4_16_add_c
 
@@ -237,9 +258,9 @@ void av1_jnt_convolve_x_c(const uint8_t *src, int src_stride, uint8_t *dst, int
 void av1_jnt_convolve_y_c(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams *filter_params_x, const InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params);
 #define av1_jnt_convolve_y av1_jnt_convolve_y_c
 
-void av1_selfguided_restoration_c(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_c(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
 #define av1_selfguided_restoration av1_selfguided_restoration_c
 
 void av1_upsample_intra_edge_c(uint8_t *p, int sz);
@@ -293,7 +314,7 @@ cfl_predict_lbd_fn get_predict_lbd_fn_c(TX_SIZE tx_size);
 cfl_subtract_average_fn get_subtract_average_fn_c(TX_SIZE tx_size);
 #define get_subtract_average_fn get_subtract_average_fn_c
 
-void aom_rtcd(void);
+void av1_rtcd(void);
 
 #include "config/aom_config.h"
 

media/libaom/config/linux/arm/config/aom_config.asm

@@ -14,6 +14,7 @@
 .equ ARCH_PPC, 0
 .equ ARCH_X86, 0
 .equ ARCH_X86_64, 0
+.equ CONFIG_2PASS_PARTITION_SEARCH_LVL, 1
 .equ CONFIG_ACCOUNTING, 0
 .equ CONFIG_ANALYZER, 0
 .equ CONFIG_AV1_DECODER, 1
@@ -21,30 +22,35 @@
 .equ CONFIG_BIG_ENDIAN, 0
 .equ CONFIG_BITSTREAM_DEBUG, 0
 .equ CONFIG_COEFFICIENT_RANGE_CHECKING, 0
-.equ CONFIG_COLLECT_INTER_MODE_RD_STATS, 1
+.equ CONFIG_COLLECT_INTER_MODE_RD_STATS, 0
 .equ CONFIG_COLLECT_RD_STATS, 0
 .equ CONFIG_DEBUG, 0
-.equ CONFIG_DENOISE, 0
-.equ CONFIG_DIST_8X8, 1
+.equ CONFIG_DENOISE, 1
+.equ CONFIG_DIST_8X8, 0
 .equ CONFIG_ENTROPY_STATS, 0
 .equ CONFIG_FILEOPTIONS, 1
+.equ CONFIG_FIX_GF_LENGTH, 1
 .equ CONFIG_FP_MB_STATS, 0
 .equ CONFIG_GCC, 1
 .equ CONFIG_GCOV, 0
+.equ CONFIG_GLOBAL_MOTION_SEARCH, 1
 .equ CONFIG_GPROF, 0
 .equ CONFIG_INSPECTION, 0
 .equ CONFIG_INTERNAL_STATS, 0
 .equ CONFIG_INTER_STATS_ONLY, 0
 .equ CONFIG_LIBYUV, 0
-.equ CONFIG_LOWBITDEPTH, 0
+.equ CONFIG_LOWBITDEPTH, 1
+.equ CONFIG_MAX_DECODE_PROFILE, 2
 .equ CONFIG_MISMATCH_DEBUG, 0
-.equ CONFIG_MSVS, 0
 .equ CONFIG_MULTITHREAD, 1
+.equ CONFIG_NORMAL_TILE_MODE, 0
 .equ CONFIG_OS_SUPPORT, 1
-.equ CONFIG_PIC, 0
+.equ CONFIG_PIC, 1
 .equ CONFIG_RD_DEBUG, 0
+.equ CONFIG_REDUCED_ENCODER_BORDER, 0
 .equ CONFIG_RUNTIME_CPU_DETECT, 1
 .equ CONFIG_SHARED, 0
+.equ CONFIG_SHARP_SETTINGS, 0
 .equ CONFIG_SIZE_LIMIT, 0
 .equ CONFIG_SPATIAL_RESAMPLING, 1
 .equ CONFIG_STATIC, 1

media/libaom/config/linux/arm/config/aom_config.h

@@ -16,6 +16,7 @@
 #define ARCH_PPC 0
 #define ARCH_X86 0
 #define ARCH_X86_64 0
+#define CONFIG_2PASS_PARTITION_SEARCH_LVL 1
 #define CONFIG_ACCOUNTING 0
 #define CONFIG_ANALYZER 0
 #define CONFIG_AV1_DECODER 1
@@ -23,30 +24,35 @@
 #define CONFIG_BIG_ENDIAN 0
 #define CONFIG_BITSTREAM_DEBUG 0
 #define CONFIG_COEFFICIENT_RANGE_CHECKING 0
-#define CONFIG_COLLECT_INTER_MODE_RD_STATS 1
+#define CONFIG_COLLECT_INTER_MODE_RD_STATS 0
 #define CONFIG_COLLECT_RD_STATS 0
 #define CONFIG_DEBUG 0
-#define CONFIG_DENOISE 0
-#define CONFIG_DIST_8X8 1
+#define CONFIG_DENOISE 1
+#define CONFIG_DIST_8X8 0
 #define CONFIG_ENTROPY_STATS 0
 #define CONFIG_FILEOPTIONS 1
+#define CONFIG_FIX_GF_LENGTH 1
 #define CONFIG_FP_MB_STATS 0
 #define CONFIG_GCC 1
 #define CONFIG_GCOV 0
+#define CONFIG_GLOBAL_MOTION_SEARCH 1
 #define CONFIG_GPROF 0
 #define CONFIG_INSPECTION 0
 #define CONFIG_INTERNAL_STATS 0
 #define CONFIG_INTER_STATS_ONLY 0
 #define CONFIG_LIBYUV 0
-#define CONFIG_LOWBITDEPTH 0
+#define CONFIG_LOWBITDEPTH 1
+#define CONFIG_MAX_DECODE_PROFILE 2
 #define CONFIG_MISMATCH_DEBUG 0
-#define CONFIG_MSVS 0
 #define CONFIG_MULTITHREAD 1
+#define CONFIG_NORMAL_TILE_MODE 0
 #define CONFIG_OS_SUPPORT 1
-#define CONFIG_PIC 0
+#define CONFIG_PIC 1
 #define CONFIG_RD_DEBUG 0
+#define CONFIG_REDUCED_ENCODER_BORDER 0
 #define CONFIG_RUNTIME_CPU_DETECT 1
 #define CONFIG_SHARED 0
+#define CONFIG_SHARP_SETTINGS 0
 #define CONFIG_SIZE_LIMIT 0
 #define CONFIG_SPATIAL_RESAMPLING 1
 #define CONFIG_STATIC 1

media/libaom/config/linux/arm/config/aom_dsp_rtcd.h

@@ -1412,7 +1412,7 @@ void aom_dsp_rtcd(void);
 #include "aom_ports/arm.h"
 static void setup_rtcd_internal(void)
 {
-    int flags = arm_cpu_caps();
+    int flags = aom_arm_cpu_caps();
 
     (void)flags;
 

media/libaom/config/linux/arm/config/aom_scale_rtcd.h

@@ -76,7 +76,7 @@ void aom_scale_rtcd(void);
 #include "aom_ports/arm.h"
 static void setup_rtcd_internal(void)
 {
-    int flags = arm_cpu_caps();
+    int flags = aom_arm_cpu_caps();
 
     (void)flags;
 

media/libaom/config/linux/arm/config/av1_rtcd.h

@@ -1,6 +1,6 @@
 // This file is generated. Do not edit.
-#ifndef AOM_RTCD_H_
-#define AOM_RTCD_H_
+#ifndef AV1_RTCD_H_
+#define AV1_RTCD_H_
 
 #ifdef RTCD_C
 #define RTCD_EXTERN
@@ -147,6 +147,27 @@ void av1_highbd_dr_prediction_z2_c(uint16_t *dst, ptrdiff_t stride, int bw, int
 void av1_highbd_dr_prediction_z3_c(uint16_t *dst, ptrdiff_t stride, int bw, int bh, const uint16_t *above, const uint16_t *left, int upsample_left, int dx, int dy, int bd);
 #define av1_highbd_dr_prediction_z3 av1_highbd_dr_prediction_z3_c
 
+void av1_highbd_inv_txfm_add_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+#define av1_highbd_inv_txfm_add av1_highbd_inv_txfm_add_c
+
+void av1_highbd_inv_txfm_add_16x16_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+#define av1_highbd_inv_txfm_add_16x16 av1_highbd_inv_txfm_add_16x16_c
+
+void av1_highbd_inv_txfm_add_16x8_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+#define av1_highbd_inv_txfm_add_16x8 av1_highbd_inv_txfm_add_16x8_c
+
+void av1_highbd_inv_txfm_add_32x32_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+#define av1_highbd_inv_txfm_add_32x32 av1_highbd_inv_txfm_add_32x32_c
+
+void av1_highbd_inv_txfm_add_4x4_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+#define av1_highbd_inv_txfm_add_4x4 av1_highbd_inv_txfm_add_4x4_c
+
+void av1_highbd_inv_txfm_add_8x16_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+#define av1_highbd_inv_txfm_add_8x16 av1_highbd_inv_txfm_add_8x16_c
+
+void av1_highbd_inv_txfm_add_8x8_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+#define av1_highbd_inv_txfm_add_8x8 av1_highbd_inv_txfm_add_8x8_c
+
 void av1_highbd_iwht4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, int bd);
 #define av1_highbd_iwht4x4_16_add av1_highbd_iwht4x4_16_add_c
 
@@ -248,15 +269,15 @@ void av1_jnt_convolve_y_c(const uint8_t *src, int src_stride, uint8_t *dst, int
 void av1_jnt_convolve_y_neon(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams *filter_params_x, const InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params);
 RTCD_EXTERN void (*av1_jnt_convolve_y)(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams *filter_params_x, const InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params);
 
-void av1_selfguided_restoration_c(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-void av1_selfguided_restoration_neon(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-RTCD_EXTERN void (*av1_selfguided_restoration)(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_c(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_neon(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+RTCD_EXTERN int (*av1_selfguided_restoration)(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
 
 void av1_upsample_intra_edge_c(uint8_t *p, int sz);
 #define av1_upsample_intra_edge av1_upsample_intra_edge_c
@@ -265,7 +286,8 @@ void av1_upsample_intra_edge_high_c(uint16_t *p, int sz, int bd);
 #define av1_upsample_intra_edge_high av1_upsample_intra_edge_high_c
 
 void av1_warp_affine_c(const int32_t *mat, const uint8_t *ref, int width, int height, int stride, uint8_t *pred, int p_col, int p_row, int p_width, int p_height, int p_stride, int subsampling_x, int subsampling_y, ConvolveParams *conv_params, int16_t alpha, int16_t beta, int16_t gamma, int16_t delta);
-#define av1_warp_affine av1_warp_affine_c
+void av1_warp_affine_neon(const int32_t *mat, const uint8_t *ref, int width, int height, int stride, uint8_t *pred, int p_col, int p_row, int p_width, int p_height, int p_stride, int subsampling_x, int subsampling_y, ConvolveParams *conv_params, int16_t alpha, int16_t beta, int16_t gamma, int16_t delta);
+RTCD_EXTERN void (*av1_warp_affine)(const int32_t *mat, const uint8_t *ref, int width, int height, int stride, uint8_t *pred, int p_col, int p_row, int p_width, int p_height, int p_stride, int subsampling_x, int subsampling_y, ConvolveParams *conv_params, int16_t alpha, int16_t beta, int16_t gamma, int16_t delta);
 
 void av1_wiener_convolve_add_src_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, const ConvolveParams *conv_params);
 void av1_wiener_convolve_add_src_neon(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, const ConvolveParams *conv_params);
@@ -323,7 +345,7 @@ cfl_subtract_average_fn get_subtract_average_fn_c(TX_SIZE tx_size);
 cfl_subtract_average_fn get_subtract_average_fn_neon(TX_SIZE tx_size);
 RTCD_EXTERN cfl_subtract_average_fn (*get_subtract_average_fn)(TX_SIZE tx_size);
 
-void aom_rtcd(void);
+void av1_rtcd(void);
 
 #include "config/aom_config.h"
 
@@ -331,7 +353,7 @@ void aom_rtcd(void);
 #include "aom_ports/arm.h"
 static void setup_rtcd_internal(void)
 {
-    int flags = arm_cpu_caps();
+    int flags = aom_arm_cpu_caps();
 
     (void)flags;
 
@@ -359,6 +381,8 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_NEON) av1_jnt_convolve_y = av1_jnt_convolve_y_neon;
     av1_selfguided_restoration = av1_selfguided_restoration_c;
     if (flags & HAS_NEON) av1_selfguided_restoration = av1_selfguided_restoration_neon;
+    av1_warp_affine = av1_warp_affine_c;
+    if (flags & HAS_NEON) av1_warp_affine = av1_warp_affine_neon;
     av1_wiener_convolve_add_src = av1_wiener_convolve_add_src_c;
     if (flags & HAS_NEON) av1_wiener_convolve_add_src = av1_wiener_convolve_add_src_neon;
     cdef_filter_block = cdef_filter_block_c;

media/libaom/config/linux/ia32/config/aom_config.asm

@@ -14,6 +14,7 @@ ARCH_MIPS equ 0
 ARCH_PPC equ 0
 ARCH_X86 equ 1
 ARCH_X86_64 equ 0
+CONFIG_2PASS_PARTITION_SEARCH_LVL equ 1
 CONFIG_ACCOUNTING equ 0
 CONFIG_ANALYZER equ 0
 CONFIG_AV1_DECODER equ 1
@@ -21,30 +22,35 @@ CONFIG_AV1_ENCODER equ 0
 CONFIG_BIG_ENDIAN equ 0
 CONFIG_BITSTREAM_DEBUG equ 0
 CONFIG_COEFFICIENT_RANGE_CHECKING equ 0
-CONFIG_COLLECT_INTER_MODE_RD_STATS equ 1
+CONFIG_COLLECT_INTER_MODE_RD_STATS equ 0
 CONFIG_COLLECT_RD_STATS equ 0
 CONFIG_DEBUG equ 0
-CONFIG_DENOISE equ 0
-CONFIG_DIST_8X8 equ 1
+CONFIG_DENOISE equ 1
+CONFIG_DIST_8X8 equ 0
 CONFIG_ENTROPY_STATS equ 0
 CONFIG_FILEOPTIONS equ 1
+CONFIG_FIX_GF_LENGTH equ 1
 CONFIG_FP_MB_STATS equ 0
 CONFIG_GCC equ 1
 CONFIG_GCOV equ 0
+CONFIG_GLOBAL_MOTION_SEARCH equ 1
 CONFIG_GPROF equ 0
 CONFIG_INSPECTION equ 0
 CONFIG_INTERNAL_STATS equ 0
 CONFIG_INTER_STATS_ONLY equ 0
 CONFIG_LIBYUV equ 0
-CONFIG_LOWBITDEPTH equ 0
+CONFIG_LOWBITDEPTH equ 1
+CONFIG_MAX_DECODE_PROFILE equ 2
 CONFIG_MISMATCH_DEBUG equ 0
-CONFIG_MSVS equ 0
 CONFIG_MULTITHREAD equ 1
+CONFIG_NORMAL_TILE_MODE equ 0
 CONFIG_OS_SUPPORT equ 1
 CONFIG_PIC equ 1
 CONFIG_RD_DEBUG equ 0
+CONFIG_REDUCED_ENCODER_BORDER equ 0
 CONFIG_RUNTIME_CPU_DETECT equ 1
 CONFIG_SHARED equ 0
+CONFIG_SHARP_SETTINGS equ 0
 CONFIG_SIZE_LIMIT equ 0
 CONFIG_SPATIAL_RESAMPLING equ 1
 CONFIG_STATIC equ 1

media/libaom/config/linux/ia32/config/aom_config.h

@@ -16,6 +16,7 @@
 #define ARCH_PPC 0
 #define ARCH_X86 1
 #define ARCH_X86_64 0
+#define CONFIG_2PASS_PARTITION_SEARCH_LVL 1
 #define CONFIG_ACCOUNTING 0
 #define CONFIG_ANALYZER 0
 #define CONFIG_AV1_DECODER 1
@@ -23,30 +24,35 @@
 #define CONFIG_BIG_ENDIAN 0
 #define CONFIG_BITSTREAM_DEBUG 0
 #define CONFIG_COEFFICIENT_RANGE_CHECKING 0
-#define CONFIG_COLLECT_INTER_MODE_RD_STATS 1
+#define CONFIG_COLLECT_INTER_MODE_RD_STATS 0
 #define CONFIG_COLLECT_RD_STATS 0
 #define CONFIG_DEBUG 0
-#define CONFIG_DENOISE 0
-#define CONFIG_DIST_8X8 1
+#define CONFIG_DENOISE 1
+#define CONFIG_DIST_8X8 0
 #define CONFIG_ENTROPY_STATS 0
 #define CONFIG_FILEOPTIONS 1
+#define CONFIG_FIX_GF_LENGTH 1
 #define CONFIG_FP_MB_STATS 0
 #define CONFIG_GCC 1
 #define CONFIG_GCOV 0
+#define CONFIG_GLOBAL_MOTION_SEARCH 1
 #define CONFIG_GPROF 0
 #define CONFIG_INSPECTION 0
 #define CONFIG_INTERNAL_STATS 0
 #define CONFIG_INTER_STATS_ONLY 0
 #define CONFIG_LIBYUV 0
-#define CONFIG_LOWBITDEPTH 0
+#define CONFIG_LOWBITDEPTH 1
+#define CONFIG_MAX_DECODE_PROFILE 2
 #define CONFIG_MISMATCH_DEBUG 0
-#define CONFIG_MSVS 0
 #define CONFIG_MULTITHREAD 1
+#define CONFIG_NORMAL_TILE_MODE 0
 #define CONFIG_OS_SUPPORT 1
 #define CONFIG_PIC 1
 #define CONFIG_RD_DEBUG 0
+#define CONFIG_REDUCED_ENCODER_BORDER 0
 #define CONFIG_RUNTIME_CPU_DETECT 1
 #define CONFIG_SHARED 0
+#define CONFIG_SHARP_SETTINGS 0
 #define CONFIG_SIZE_LIMIT 0
 #define CONFIG_SPATIAL_RESAMPLING 1
 #define CONFIG_STATIC 1

media/libaom/config/linux/ia32/config/aom_dsp_rtcd.h

@@ -28,6 +28,7 @@ RTCD_EXTERN void (*aom_blend_a64_hmask)(uint8_t *dst, uint32_t dst_stride, const
 
 void aom_blend_a64_mask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 void aom_blend_a64_mask_sse4_1(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
+void aom_blend_a64_mask_avx2(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 RTCD_EXTERN void (*aom_blend_a64_mask)(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 
 void aom_blend_a64_vmask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int w, int h);
@@ -1230,6 +1231,7 @@ RTCD_EXTERN void (*aom_highbd_v_predictor_8x8)(uint16_t *dst, ptrdiff_t y_stride
 
 void aom_lowbd_blend_a64_d16_mask_c(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 void aom_lowbd_blend_a64_d16_mask_sse4_1(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
+void aom_lowbd_blend_a64_d16_mask_avx2(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 RTCD_EXTERN void (*aom_lowbd_blend_a64_d16_mask)(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 
 void aom_lpf_horizontal_14_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);
@@ -1725,6 +1727,7 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_SSE4_1) aom_blend_a64_hmask = aom_blend_a64_hmask_sse4_1;
     aom_blend_a64_mask = aom_blend_a64_mask_c;
     if (flags & HAS_SSE4_1) aom_blend_a64_mask = aom_blend_a64_mask_sse4_1;
+    if (flags & HAS_AVX2) aom_blend_a64_mask = aom_blend_a64_mask_avx2;
     aom_blend_a64_vmask = aom_blend_a64_vmask_c;
     if (flags & HAS_SSE4_1) aom_blend_a64_vmask = aom_blend_a64_vmask_sse4_1;
     aom_convolve8_horiz = aom_convolve8_horiz_c;
@@ -2125,6 +2128,7 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_SSE2) aom_highbd_v_predictor_8x8 = aom_highbd_v_predictor_8x8_sse2;
     aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_c;
     if (flags & HAS_SSE4_1) aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_sse4_1;
+    if (flags & HAS_AVX2) aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_avx2;
     aom_lpf_horizontal_14 = aom_lpf_horizontal_14_c;
     if (flags & HAS_SSE2) aom_lpf_horizontal_14 = aom_lpf_horizontal_14_sse2;
     aom_lpf_horizontal_14_dual = aom_lpf_horizontal_14_dual_c;

media/libaom/config/linux/ia32/config/av1_rtcd.h

@@ -1,6 +1,6 @@
 // This file is generated. Do not edit.
-#ifndef AOM_RTCD_H_
-#define AOM_RTCD_H_
+#ifndef AV1_RTCD_H_
+#define AV1_RTCD_H_
 
 #ifdef RTCD_C
 #define RTCD_EXTERN
@@ -58,10 +58,12 @@ RTCD_EXTERN void (*apply_selfguided_restoration)(const uint8_t *dat, int width,
 
 void av1_build_compound_diffwtd_mask_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 void av1_build_compound_diffwtd_mask_sse4_1(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
+void av1_build_compound_diffwtd_mask_avx2(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 RTCD_EXTERN void (*av1_build_compound_diffwtd_mask)(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 
 void av1_build_compound_diffwtd_mask_d16_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 void av1_build_compound_diffwtd_mask_d16_sse4_1(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
+void av1_build_compound_diffwtd_mask_d16_avx2(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 RTCD_EXTERN void (*av1_build_compound_diffwtd_mask_d16)(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 
 void av1_build_compound_diffwtd_mask_highbd_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w, int bd);
@@ -170,6 +172,36 @@ void av1_highbd_dr_prediction_z2_c(uint16_t *dst, ptrdiff_t stride, int bw, int
 void av1_highbd_dr_prediction_z3_c(uint16_t *dst, ptrdiff_t stride, int bw, int bh, const uint16_t *above, const uint16_t *left, int upsample_left, int dx, int dy, int bd);
 #define av1_highbd_dr_prediction_z3 av1_highbd_dr_prediction_z3_c
 
+void av1_highbd_inv_txfm_add_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_avx2(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_16x16_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_16x16_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_16x16)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_16x8_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_16x8_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_16x8)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_32x32_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_32x32_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_32x32_avx2(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_32x32)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_4x4_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_4x4_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_4x4)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_8x16_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_8x16_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_8x16)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_8x8_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_8x8_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_8x8)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
 void av1_highbd_iwht4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, int bd);
 #define av1_highbd_iwht4x4_16_add av1_highbd_iwht4x4_16_add_c
 
@@ -206,8 +238,7 @@ void av1_highbd_wiener_convolve_add_src_avx2(const uint8_t *src, ptrdiff_t src_s
 RTCD_EXTERN void (*av1_highbd_wiener_convolve_add_src)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, const ConvolveParams *conv_params, int bps);
 
 void av1_inv_txfm2d_add_16x16_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_16x16_sse4_1(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_16x16)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_16x16 av1_inv_txfm2d_add_16x16_c
 
 void av1_inv_txfm2d_add_16x32_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_16x32 av1_inv_txfm2d_add_16x32_c
@@ -225,8 +256,7 @@ void av1_inv_txfm2d_add_32x16_c(const int32_t *input, uint16_t *output, int stri
 #define av1_inv_txfm2d_add_32x16 av1_inv_txfm2d_add_32x16_c
 
 void av1_inv_txfm2d_add_32x32_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_32x32_avx2(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_32x32)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_32x32 av1_inv_txfm2d_add_32x32_c
 
 void av1_inv_txfm2d_add_32x64_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_32x64 av1_inv_txfm2d_add_32x64_c
@@ -251,8 +281,7 @@ void av1_inv_txfm2d_add_64x32_c(const int32_t *input, uint16_t *output, int stri
 #define av1_inv_txfm2d_add_64x32 av1_inv_txfm2d_add_64x32_c
 
 void av1_inv_txfm2d_add_64x64_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_64x64_sse4_1(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_64x64)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_64x64 av1_inv_txfm2d_add_64x64_c
 
 void av1_inv_txfm2d_add_8x16_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_8x16 av1_inv_txfm2d_add_8x16_c
@@ -292,18 +321,18 @@ void av1_jnt_convolve_y_sse2(const uint8_t *src, int src_stride, uint8_t *dst, i
 void av1_jnt_convolve_y_avx2(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams *filter_params_x, const InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params);
 RTCD_EXTERN void (*av1_jnt_convolve_y)(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams *filter_params_x, const InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params);
 
-void av1_selfguided_restoration_c(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-void av1_selfguided_restoration_sse4_1(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-void av1_selfguided_restoration_avx2(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-RTCD_EXTERN void (*av1_selfguided_restoration)(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_c(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_sse4_1(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_avx2(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+RTCD_EXTERN int (*av1_selfguided_restoration)(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
 
 void av1_upsample_intra_edge_c(uint8_t *p, int sz);
 void av1_upsample_intra_edge_sse4_1(uint8_t *p, int sz);
@@ -395,7 +424,7 @@ cfl_subtract_average_fn get_subtract_average_fn_sse2(TX_SIZE tx_size);
 cfl_subtract_average_fn get_subtract_average_fn_avx2(TX_SIZE tx_size);
 RTCD_EXTERN cfl_subtract_average_fn (*get_subtract_average_fn)(TX_SIZE tx_size);
 
-void aom_rtcd(void);
+void av1_rtcd(void);
 
 #ifdef RTCD_C
 #include "aom_ports/x86.h"
@@ -410,8 +439,10 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_AVX2) apply_selfguided_restoration = apply_selfguided_restoration_avx2;
     av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_c;
     if (flags & HAS_SSE4_1) av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_sse4_1;
+    if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_avx2;
     av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_c;
     if (flags & HAS_SSE4_1) av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_sse4_1;
+    if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_avx2;
     av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_c;
     if (flags & HAS_SSSE3) av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_ssse3;
     if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_avx2;
@@ -453,6 +484,22 @@ static void setup_rtcd_internal(void)
     av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_c;
     if (flags & HAS_SSSE3) av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_ssse3;
     if (flags & HAS_AVX2) av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_avx2;
+    av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_sse4_1;
+    if (flags & HAS_AVX2) av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_avx2;
+    av1_highbd_inv_txfm_add_16x16 = av1_highbd_inv_txfm_add_16x16_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_16x16 = av1_highbd_inv_txfm_add_16x16_sse4_1;
+    av1_highbd_inv_txfm_add_16x8 = av1_highbd_inv_txfm_add_16x8_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_16x8 = av1_highbd_inv_txfm_add_16x8_sse4_1;
+    av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_sse4_1;
+    if (flags & HAS_AVX2) av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_avx2;
+    av1_highbd_inv_txfm_add_4x4 = av1_highbd_inv_txfm_add_4x4_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_4x4 = av1_highbd_inv_txfm_add_4x4_sse4_1;
+    av1_highbd_inv_txfm_add_8x16 = av1_highbd_inv_txfm_add_8x16_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_8x16 = av1_highbd_inv_txfm_add_8x16_sse4_1;
+    av1_highbd_inv_txfm_add_8x8 = av1_highbd_inv_txfm_add_8x8_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_8x8 = av1_highbd_inv_txfm_add_8x8_sse4_1;
     av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_c;
     if (flags & HAS_SSE4_1) av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_sse4_1;
     if (flags & HAS_AVX2) av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_avx2;
@@ -470,14 +517,8 @@ static void setup_rtcd_internal(void)
     av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_c;
     if (flags & HAS_SSSE3) av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_ssse3;
     if (flags & HAS_AVX2) av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_avx2;
-    av1_inv_txfm2d_add_16x16 = av1_inv_txfm2d_add_16x16_c;
-    if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_16x16 = av1_inv_txfm2d_add_16x16_sse4_1;
-    av1_inv_txfm2d_add_32x32 = av1_inv_txfm2d_add_32x32_c;
-    if (flags & HAS_AVX2) av1_inv_txfm2d_add_32x32 = av1_inv_txfm2d_add_32x32_avx2;
     av1_inv_txfm2d_add_4x4 = av1_inv_txfm2d_add_4x4_c;
     if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_4x4 = av1_inv_txfm2d_add_4x4_sse4_1;
-    av1_inv_txfm2d_add_64x64 = av1_inv_txfm2d_add_64x64_c;
-    if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_64x64 = av1_inv_txfm2d_add_64x64_sse4_1;
     av1_inv_txfm2d_add_8x8 = av1_inv_txfm2d_add_8x8_c;
     if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_8x8 = av1_inv_txfm2d_add_8x8_sse4_1;
     av1_inv_txfm_add = av1_inv_txfm_add_c;

media/libaom/config/linux/x64/config/aom_config.asm

@@ -14,6 +14,7 @@ ARCH_MIPS equ 0
 ARCH_PPC equ 0
 ARCH_X86 equ 0
 ARCH_X86_64 equ 1
+CONFIG_2PASS_PARTITION_SEARCH_LVL equ 1
 CONFIG_ACCOUNTING equ 0
 CONFIG_ANALYZER equ 0
 CONFIG_AV1_DECODER equ 1
@@ -21,30 +22,35 @@ CONFIG_AV1_ENCODER equ 0
 CONFIG_BIG_ENDIAN equ 0
 CONFIG_BITSTREAM_DEBUG equ 0
 CONFIG_COEFFICIENT_RANGE_CHECKING equ 0
-CONFIG_COLLECT_INTER_MODE_RD_STATS equ 1
+CONFIG_COLLECT_INTER_MODE_RD_STATS equ 0
 CONFIG_COLLECT_RD_STATS equ 0
 CONFIG_DEBUG equ 0
-CONFIG_DENOISE equ 0
-CONFIG_DIST_8X8 equ 1
+CONFIG_DENOISE equ 1
+CONFIG_DIST_8X8 equ 0
 CONFIG_ENTROPY_STATS equ 0
 CONFIG_FILEOPTIONS equ 1
+CONFIG_FIX_GF_LENGTH equ 1
 CONFIG_FP_MB_STATS equ 0
 CONFIG_GCC equ 1
 CONFIG_GCOV equ 0
+CONFIG_GLOBAL_MOTION_SEARCH equ 1
 CONFIG_GPROF equ 0
 CONFIG_INSPECTION equ 0
 CONFIG_INTERNAL_STATS equ 0
 CONFIG_INTER_STATS_ONLY equ 0
 CONFIG_LIBYUV equ 0
-CONFIG_LOWBITDEPTH equ 0
+CONFIG_LOWBITDEPTH equ 1
+CONFIG_MAX_DECODE_PROFILE equ 2
 CONFIG_MISMATCH_DEBUG equ 0
-CONFIG_MSVS equ 0
 CONFIG_MULTITHREAD equ 1
+CONFIG_NORMAL_TILE_MODE equ 0
 CONFIG_OS_SUPPORT equ 1
 CONFIG_PIC equ 0
 CONFIG_RD_DEBUG equ 0
+CONFIG_REDUCED_ENCODER_BORDER equ 0
 CONFIG_RUNTIME_CPU_DETECT equ 1
 CONFIG_SHARED equ 0
+CONFIG_SHARP_SETTINGS equ 0
 CONFIG_SIZE_LIMIT equ 0
 CONFIG_SPATIAL_RESAMPLING equ 1
 CONFIG_STATIC equ 1

media/libaom/config/linux/x64/config/aom_config.h

@@ -16,6 +16,7 @@
 #define ARCH_PPC 0
 #define ARCH_X86 0
 #define ARCH_X86_64 1
+#define CONFIG_2PASS_PARTITION_SEARCH_LVL 1
 #define CONFIG_ACCOUNTING 0
 #define CONFIG_ANALYZER 0
 #define CONFIG_AV1_DECODER 1
@@ -23,30 +24,35 @@
 #define CONFIG_BIG_ENDIAN 0
 #define CONFIG_BITSTREAM_DEBUG 0
 #define CONFIG_COEFFICIENT_RANGE_CHECKING 0
-#define CONFIG_COLLECT_INTER_MODE_RD_STATS 1
+#define CONFIG_COLLECT_INTER_MODE_RD_STATS 0
 #define CONFIG_COLLECT_RD_STATS 0
 #define CONFIG_DEBUG 0
-#define CONFIG_DENOISE 0
-#define CONFIG_DIST_8X8 1
+#define CONFIG_DENOISE 1
+#define CONFIG_DIST_8X8 0
 #define CONFIG_ENTROPY_STATS 0
 #define CONFIG_FILEOPTIONS 1
+#define CONFIG_FIX_GF_LENGTH 1
 #define CONFIG_FP_MB_STATS 0
 #define CONFIG_GCC 1
 #define CONFIG_GCOV 0
+#define CONFIG_GLOBAL_MOTION_SEARCH 1
 #define CONFIG_GPROF 0
 #define CONFIG_INSPECTION 0
 #define CONFIG_INTERNAL_STATS 0
 #define CONFIG_INTER_STATS_ONLY 0
 #define CONFIG_LIBYUV 0
-#define CONFIG_LOWBITDEPTH 0
+#define CONFIG_LOWBITDEPTH 1
+#define CONFIG_MAX_DECODE_PROFILE 2
 #define CONFIG_MISMATCH_DEBUG 0
-#define CONFIG_MSVS 0
 #define CONFIG_MULTITHREAD 1
+#define CONFIG_NORMAL_TILE_MODE 0
 #define CONFIG_OS_SUPPORT 1
 #define CONFIG_PIC 0
 #define CONFIG_RD_DEBUG 0
+#define CONFIG_REDUCED_ENCODER_BORDER 0
 #define CONFIG_RUNTIME_CPU_DETECT 1
 #define CONFIG_SHARED 0
+#define CONFIG_SHARP_SETTINGS 0
 #define CONFIG_SIZE_LIMIT 0
 #define CONFIG_SPATIAL_RESAMPLING 1
 #define CONFIG_STATIC 1

media/libaom/config/linux/x64/config/aom_dsp_rtcd.h

@@ -28,6 +28,7 @@ RTCD_EXTERN void (*aom_blend_a64_hmask)(uint8_t *dst, uint32_t dst_stride, const
 
 void aom_blend_a64_mask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 void aom_blend_a64_mask_sse4_1(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
+void aom_blend_a64_mask_avx2(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 RTCD_EXTERN void (*aom_blend_a64_mask)(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 
 void aom_blend_a64_vmask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int w, int h);
@@ -1232,6 +1233,7 @@ void aom_highbd_v_predictor_8x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const ui
 
 void aom_lowbd_blend_a64_d16_mask_c(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 void aom_lowbd_blend_a64_d16_mask_sse4_1(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
+void aom_lowbd_blend_a64_d16_mask_avx2(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 RTCD_EXTERN void (*aom_lowbd_blend_a64_d16_mask)(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 
 void aom_lpf_horizontal_14_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);
@@ -1727,6 +1729,7 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_SSE4_1) aom_blend_a64_hmask = aom_blend_a64_hmask_sse4_1;
     aom_blend_a64_mask = aom_blend_a64_mask_c;
     if (flags & HAS_SSE4_1) aom_blend_a64_mask = aom_blend_a64_mask_sse4_1;
+    if (flags & HAS_AVX2) aom_blend_a64_mask = aom_blend_a64_mask_avx2;
     aom_blend_a64_vmask = aom_blend_a64_vmask_c;
     if (flags & HAS_SSE4_1) aom_blend_a64_vmask = aom_blend_a64_vmask_sse4_1;
     aom_convolve8_horiz = aom_convolve8_horiz_sse2;
@@ -1811,6 +1814,7 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_AVX2) aom_highbd_lpf_vertical_8_dual = aom_highbd_lpf_vertical_8_dual_avx2;
     aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_c;
     if (flags & HAS_SSE4_1) aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_sse4_1;
+    if (flags & HAS_AVX2) aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_avx2;
     aom_paeth_predictor_16x16 = aom_paeth_predictor_16x16_c;
     if (flags & HAS_SSSE3) aom_paeth_predictor_16x16 = aom_paeth_predictor_16x16_ssse3;
     if (flags & HAS_AVX2) aom_paeth_predictor_16x16 = aom_paeth_predictor_16x16_avx2;

media/libaom/config/linux/x64/config/av1_rtcd.h

@@ -1,6 +1,6 @@
 // This file is generated. Do not edit.
-#ifndef AOM_RTCD_H_
-#define AOM_RTCD_H_
+#ifndef AV1_RTCD_H_
+#define AV1_RTCD_H_
 
 #ifdef RTCD_C
 #define RTCD_EXTERN
@@ -58,10 +58,12 @@ RTCD_EXTERN void (*apply_selfguided_restoration)(const uint8_t *dat, int width,
 
 void av1_build_compound_diffwtd_mask_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 void av1_build_compound_diffwtd_mask_sse4_1(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
+void av1_build_compound_diffwtd_mask_avx2(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 RTCD_EXTERN void (*av1_build_compound_diffwtd_mask)(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 
 void av1_build_compound_diffwtd_mask_d16_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 void av1_build_compound_diffwtd_mask_d16_sse4_1(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
+void av1_build_compound_diffwtd_mask_d16_avx2(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 RTCD_EXTERN void (*av1_build_compound_diffwtd_mask_d16)(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 
 void av1_build_compound_diffwtd_mask_highbd_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w, int bd);
@@ -173,6 +175,36 @@ void av1_highbd_dr_prediction_z2_c(uint16_t *dst, ptrdiff_t stride, int bw, int
 void av1_highbd_dr_prediction_z3_c(uint16_t *dst, ptrdiff_t stride, int bw, int bh, const uint16_t *above, const uint16_t *left, int upsample_left, int dx, int dy, int bd);
 #define av1_highbd_dr_prediction_z3 av1_highbd_dr_prediction_z3_c
 
+void av1_highbd_inv_txfm_add_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_avx2(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_16x16_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_16x16_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_16x16)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_16x8_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_16x8_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_16x8)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_32x32_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_32x32_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_32x32_avx2(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_32x32)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_4x4_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_4x4_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_4x4)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_8x16_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_8x16_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_8x16)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_8x8_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_8x8_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_8x8)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
 void av1_highbd_iwht4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, int bd);
 #define av1_highbd_iwht4x4_16_add av1_highbd_iwht4x4_16_add_c
 
@@ -209,8 +241,7 @@ void av1_highbd_wiener_convolve_add_src_avx2(const uint8_t *src, ptrdiff_t src_s
 RTCD_EXTERN void (*av1_highbd_wiener_convolve_add_src)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, const ConvolveParams *conv_params, int bps);
 
 void av1_inv_txfm2d_add_16x16_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_16x16_sse4_1(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_16x16)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_16x16 av1_inv_txfm2d_add_16x16_c
 
 void av1_inv_txfm2d_add_16x32_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_16x32 av1_inv_txfm2d_add_16x32_c
@@ -228,8 +259,7 @@ void av1_inv_txfm2d_add_32x16_c(const int32_t *input, uint16_t *output, int stri
 #define av1_inv_txfm2d_add_32x16 av1_inv_txfm2d_add_32x16_c
 
 void av1_inv_txfm2d_add_32x32_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_32x32_avx2(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_32x32)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_32x32 av1_inv_txfm2d_add_32x32_c
 
 void av1_inv_txfm2d_add_32x64_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_32x64 av1_inv_txfm2d_add_32x64_c
@@ -254,8 +284,7 @@ void av1_inv_txfm2d_add_64x32_c(const int32_t *input, uint16_t *output, int stri
 #define av1_inv_txfm2d_add_64x32 av1_inv_txfm2d_add_64x32_c
 
 void av1_inv_txfm2d_add_64x64_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_64x64_sse4_1(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_64x64)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_64x64 av1_inv_txfm2d_add_64x64_c
 
 void av1_inv_txfm2d_add_8x16_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_8x16 av1_inv_txfm2d_add_8x16_c
@@ -295,18 +324,18 @@ void av1_jnt_convolve_y_sse2(const uint8_t *src, int src_stride, uint8_t *dst, i
 void av1_jnt_convolve_y_avx2(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams *filter_params_x, const InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params);
 RTCD_EXTERN void (*av1_jnt_convolve_y)(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams *filter_params_x, const InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params);
 
-void av1_selfguided_restoration_c(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-void av1_selfguided_restoration_sse4_1(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-void av1_selfguided_restoration_avx2(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-RTCD_EXTERN void (*av1_selfguided_restoration)(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_c(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_sse4_1(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_avx2(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+RTCD_EXTERN int (*av1_selfguided_restoration)(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
 
 void av1_upsample_intra_edge_c(uint8_t *p, int sz);
 void av1_upsample_intra_edge_sse4_1(uint8_t *p, int sz);
@@ -398,7 +427,7 @@ cfl_subtract_average_fn get_subtract_average_fn_sse2(TX_SIZE tx_size);
 cfl_subtract_average_fn get_subtract_average_fn_avx2(TX_SIZE tx_size);
 RTCD_EXTERN cfl_subtract_average_fn (*get_subtract_average_fn)(TX_SIZE tx_size);
 
-void aom_rtcd(void);
+void av1_rtcd(void);
 
 #ifdef RTCD_C
 #include "aom_ports/x86.h"
@@ -413,8 +442,10 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_AVX2) apply_selfguided_restoration = apply_selfguided_restoration_avx2;
     av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_c;
     if (flags & HAS_SSE4_1) av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_sse4_1;
+    if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_avx2;
     av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_c;
     if (flags & HAS_SSE4_1) av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_sse4_1;
+    if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_avx2;
     av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_c;
     if (flags & HAS_SSSE3) av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_ssse3;
     if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_avx2;
@@ -451,6 +482,22 @@ static void setup_rtcd_internal(void)
     av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_c;
     if (flags & HAS_SSSE3) av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_ssse3;
     if (flags & HAS_AVX2) av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_avx2;
+    av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_sse4_1;
+    if (flags & HAS_AVX2) av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_avx2;
+    av1_highbd_inv_txfm_add_16x16 = av1_highbd_inv_txfm_add_16x16_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_16x16 = av1_highbd_inv_txfm_add_16x16_sse4_1;
+    av1_highbd_inv_txfm_add_16x8 = av1_highbd_inv_txfm_add_16x8_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_16x8 = av1_highbd_inv_txfm_add_16x8_sse4_1;
+    av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_sse4_1;
+    if (flags & HAS_AVX2) av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_avx2;
+    av1_highbd_inv_txfm_add_4x4 = av1_highbd_inv_txfm_add_4x4_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_4x4 = av1_highbd_inv_txfm_add_4x4_sse4_1;
+    av1_highbd_inv_txfm_add_8x16 = av1_highbd_inv_txfm_add_8x16_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_8x16 = av1_highbd_inv_txfm_add_8x16_sse4_1;
+    av1_highbd_inv_txfm_add_8x8 = av1_highbd_inv_txfm_add_8x8_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_8x8 = av1_highbd_inv_txfm_add_8x8_sse4_1;
     av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_c;
     if (flags & HAS_SSE4_1) av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_sse4_1;
     if (flags & HAS_AVX2) av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_avx2;
@@ -468,14 +515,8 @@ static void setup_rtcd_internal(void)
     av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_c;
     if (flags & HAS_SSSE3) av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_ssse3;
     if (flags & HAS_AVX2) av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_avx2;
-    av1_inv_txfm2d_add_16x16 = av1_inv_txfm2d_add_16x16_c;
-    if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_16x16 = av1_inv_txfm2d_add_16x16_sse4_1;
-    av1_inv_txfm2d_add_32x32 = av1_inv_txfm2d_add_32x32_c;
-    if (flags & HAS_AVX2) av1_inv_txfm2d_add_32x32 = av1_inv_txfm2d_add_32x32_avx2;
     av1_inv_txfm2d_add_4x4 = av1_inv_txfm2d_add_4x4_c;
     if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_4x4 = av1_inv_txfm2d_add_4x4_sse4_1;
-    av1_inv_txfm2d_add_64x64 = av1_inv_txfm2d_add_64x64_c;
-    if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_64x64 = av1_inv_txfm2d_add_64x64_sse4_1;
     av1_inv_txfm2d_add_8x8 = av1_inv_txfm2d_add_8x8_c;
     if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_8x8 = av1_inv_txfm2d_add_8x8_sse4_1;
     av1_inv_txfm_add = av1_inv_txfm_add_c;

media/libaom/config/mac/x64/config/aom_config.asm

@@ -14,6 +14,7 @@ ARCH_MIPS equ 0
 ARCH_PPC equ 0
 ARCH_X86 equ 0
 ARCH_X86_64 equ 1
+CONFIG_2PASS_PARTITION_SEARCH_LVL equ 1
 CONFIG_ACCOUNTING equ 0
 CONFIG_ANALYZER equ 0
 CONFIG_AV1_DECODER equ 1
@@ -21,30 +22,35 @@ CONFIG_AV1_ENCODER equ 0
 CONFIG_BIG_ENDIAN equ 0
 CONFIG_BITSTREAM_DEBUG equ 0
 CONFIG_COEFFICIENT_RANGE_CHECKING equ 0
-CONFIG_COLLECT_INTER_MODE_RD_STATS equ 1
+CONFIG_COLLECT_INTER_MODE_RD_STATS equ 0
 CONFIG_COLLECT_RD_STATS equ 0
 CONFIG_DEBUG equ 0
-CONFIG_DENOISE equ 0
-CONFIG_DIST_8X8 equ 1
+CONFIG_DENOISE equ 1
+CONFIG_DIST_8X8 equ 0
 CONFIG_ENTROPY_STATS equ 0
 CONFIG_FILEOPTIONS equ 1
+CONFIG_FIX_GF_LENGTH equ 1
 CONFIG_FP_MB_STATS equ 0
 CONFIG_GCC equ 1
 CONFIG_GCOV equ 0
+CONFIG_GLOBAL_MOTION_SEARCH equ 1
 CONFIG_GPROF equ 0
 CONFIG_INSPECTION equ 0
 CONFIG_INTERNAL_STATS equ 0
 CONFIG_INTER_STATS_ONLY equ 0
 CONFIG_LIBYUV equ 0
-CONFIG_LOWBITDEPTH equ 0
+CONFIG_LOWBITDEPTH equ 1
+CONFIG_MAX_DECODE_PROFILE equ 2
 CONFIG_MISMATCH_DEBUG equ 0
-CONFIG_MSVS equ 0
 CONFIG_MULTITHREAD equ 1
+CONFIG_NORMAL_TILE_MODE equ 0
 CONFIG_OS_SUPPORT equ 1
 CONFIG_PIC equ 0
 CONFIG_RD_DEBUG equ 0
+CONFIG_REDUCED_ENCODER_BORDER equ 0
 CONFIG_RUNTIME_CPU_DETECT equ 1
 CONFIG_SHARED equ 0
+CONFIG_SHARP_SETTINGS equ 0
 CONFIG_SIZE_LIMIT equ 0
 CONFIG_SPATIAL_RESAMPLING equ 1
 CONFIG_STATIC equ 1

media/libaom/config/mac/x64/config/aom_config.h

@@ -16,6 +16,7 @@
 #define ARCH_PPC 0
 #define ARCH_X86 0
 #define ARCH_X86_64 1
+#define CONFIG_2PASS_PARTITION_SEARCH_LVL 1
 #define CONFIG_ACCOUNTING 0
 #define CONFIG_ANALYZER 0
 #define CONFIG_AV1_DECODER 1
@@ -23,30 +24,35 @@
 #define CONFIG_BIG_ENDIAN 0
 #define CONFIG_BITSTREAM_DEBUG 0
 #define CONFIG_COEFFICIENT_RANGE_CHECKING 0
-#define CONFIG_COLLECT_INTER_MODE_RD_STATS 1
+#define CONFIG_COLLECT_INTER_MODE_RD_STATS 0
 #define CONFIG_COLLECT_RD_STATS 0
 #define CONFIG_DEBUG 0
-#define CONFIG_DENOISE 0
-#define CONFIG_DIST_8X8 1
+#define CONFIG_DENOISE 1
+#define CONFIG_DIST_8X8 0
 #define CONFIG_ENTROPY_STATS 0
 #define CONFIG_FILEOPTIONS 1
+#define CONFIG_FIX_GF_LENGTH 1
 #define CONFIG_FP_MB_STATS 0
 #define CONFIG_GCC 1
 #define CONFIG_GCOV 0
+#define CONFIG_GLOBAL_MOTION_SEARCH 1
 #define CONFIG_GPROF 0
 #define CONFIG_INSPECTION 0
 #define CONFIG_INTERNAL_STATS 0
 #define CONFIG_INTER_STATS_ONLY 0
 #define CONFIG_LIBYUV 0
-#define CONFIG_LOWBITDEPTH 0
+#define CONFIG_LOWBITDEPTH 1
+#define CONFIG_MAX_DECODE_PROFILE 2
 #define CONFIG_MISMATCH_DEBUG 0
-#define CONFIG_MSVS 0
 #define CONFIG_MULTITHREAD 1
+#define CONFIG_NORMAL_TILE_MODE 0
 #define CONFIG_OS_SUPPORT 1
 #define CONFIG_PIC 0
 #define CONFIG_RD_DEBUG 0
+#define CONFIG_REDUCED_ENCODER_BORDER 0
 #define CONFIG_RUNTIME_CPU_DETECT 1
 #define CONFIG_SHARED 0
+#define CONFIG_SHARP_SETTINGS 0
 #define CONFIG_SIZE_LIMIT 0
 #define CONFIG_SPATIAL_RESAMPLING 1
 #define CONFIG_STATIC 1

media/libaom/config/mac/x64/config/aom_dsp_rtcd.h

@@ -28,6 +28,7 @@ RTCD_EXTERN void (*aom_blend_a64_hmask)(uint8_t *dst, uint32_t dst_stride, const
 
 void aom_blend_a64_mask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 void aom_blend_a64_mask_sse4_1(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
+void aom_blend_a64_mask_avx2(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 RTCD_EXTERN void (*aom_blend_a64_mask)(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 
 void aom_blend_a64_vmask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int w, int h);
@@ -1232,6 +1233,7 @@ void aom_highbd_v_predictor_8x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const ui
 
 void aom_lowbd_blend_a64_d16_mask_c(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 void aom_lowbd_blend_a64_d16_mask_sse4_1(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
+void aom_lowbd_blend_a64_d16_mask_avx2(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 RTCD_EXTERN void (*aom_lowbd_blend_a64_d16_mask)(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 
 void aom_lpf_horizontal_14_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);
@@ -1727,6 +1729,7 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_SSE4_1) aom_blend_a64_hmask = aom_blend_a64_hmask_sse4_1;
     aom_blend_a64_mask = aom_blend_a64_mask_c;
     if (flags & HAS_SSE4_1) aom_blend_a64_mask = aom_blend_a64_mask_sse4_1;
+    if (flags & HAS_AVX2) aom_blend_a64_mask = aom_blend_a64_mask_avx2;
     aom_blend_a64_vmask = aom_blend_a64_vmask_c;
     if (flags & HAS_SSE4_1) aom_blend_a64_vmask = aom_blend_a64_vmask_sse4_1;
     aom_convolve8_horiz = aom_convolve8_horiz_sse2;
@@ -1811,6 +1814,7 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_AVX2) aom_highbd_lpf_vertical_8_dual = aom_highbd_lpf_vertical_8_dual_avx2;
     aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_c;
     if (flags & HAS_SSE4_1) aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_sse4_1;
+    if (flags & HAS_AVX2) aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_avx2;
     aom_paeth_predictor_16x16 = aom_paeth_predictor_16x16_c;
     if (flags & HAS_SSSE3) aom_paeth_predictor_16x16 = aom_paeth_predictor_16x16_ssse3;
     if (flags & HAS_AVX2) aom_paeth_predictor_16x16 = aom_paeth_predictor_16x16_avx2;

media/libaom/config/mac/x64/config/av1_rtcd.h

@@ -1,6 +1,6 @@
 // This file is generated. Do not edit.
-#ifndef AOM_RTCD_H_
-#define AOM_RTCD_H_
+#ifndef AV1_RTCD_H_
+#define AV1_RTCD_H_
 
 #ifdef RTCD_C
 #define RTCD_EXTERN
@@ -58,10 +58,12 @@ RTCD_EXTERN void (*apply_selfguided_restoration)(const uint8_t *dat, int width,
 
 void av1_build_compound_diffwtd_mask_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 void av1_build_compound_diffwtd_mask_sse4_1(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
+void av1_build_compound_diffwtd_mask_avx2(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 RTCD_EXTERN void (*av1_build_compound_diffwtd_mask)(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 
 void av1_build_compound_diffwtd_mask_d16_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 void av1_build_compound_diffwtd_mask_d16_sse4_1(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
+void av1_build_compound_diffwtd_mask_d16_avx2(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 RTCD_EXTERN void (*av1_build_compound_diffwtd_mask_d16)(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 
 void av1_build_compound_diffwtd_mask_highbd_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w, int bd);
@@ -173,6 +175,36 @@ void av1_highbd_dr_prediction_z2_c(uint16_t *dst, ptrdiff_t stride, int bw, int
 void av1_highbd_dr_prediction_z3_c(uint16_t *dst, ptrdiff_t stride, int bw, int bh, const uint16_t *above, const uint16_t *left, int upsample_left, int dx, int dy, int bd);
 #define av1_highbd_dr_prediction_z3 av1_highbd_dr_prediction_z3_c
 
+void av1_highbd_inv_txfm_add_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_avx2(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_16x16_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_16x16_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_16x16)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_16x8_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_16x8_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_16x8)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_32x32_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_32x32_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_32x32_avx2(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_32x32)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_4x4_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_4x4_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_4x4)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_8x16_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_8x16_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_8x16)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_8x8_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_8x8_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_8x8)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
 void av1_highbd_iwht4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, int bd);
 #define av1_highbd_iwht4x4_16_add av1_highbd_iwht4x4_16_add_c
 
@@ -209,8 +241,7 @@ void av1_highbd_wiener_convolve_add_src_avx2(const uint8_t *src, ptrdiff_t src_s
 RTCD_EXTERN void (*av1_highbd_wiener_convolve_add_src)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, const ConvolveParams *conv_params, int bps);
 
 void av1_inv_txfm2d_add_16x16_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_16x16_sse4_1(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_16x16)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_16x16 av1_inv_txfm2d_add_16x16_c
 
 void av1_inv_txfm2d_add_16x32_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_16x32 av1_inv_txfm2d_add_16x32_c
@@ -228,8 +259,7 @@ void av1_inv_txfm2d_add_32x16_c(const int32_t *input, uint16_t *output, int stri
 #define av1_inv_txfm2d_add_32x16 av1_inv_txfm2d_add_32x16_c
 
 void av1_inv_txfm2d_add_32x32_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_32x32_avx2(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_32x32)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_32x32 av1_inv_txfm2d_add_32x32_c
 
 void av1_inv_txfm2d_add_32x64_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_32x64 av1_inv_txfm2d_add_32x64_c
@@ -254,8 +284,7 @@ void av1_inv_txfm2d_add_64x32_c(const int32_t *input, uint16_t *output, int stri
 #define av1_inv_txfm2d_add_64x32 av1_inv_txfm2d_add_64x32_c
 
 void av1_inv_txfm2d_add_64x64_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_64x64_sse4_1(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_64x64)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_64x64 av1_inv_txfm2d_add_64x64_c
 
 void av1_inv_txfm2d_add_8x16_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_8x16 av1_inv_txfm2d_add_8x16_c
@@ -295,18 +324,18 @@ void av1_jnt_convolve_y_sse2(const uint8_t *src, int src_stride, uint8_t *dst, i
 void av1_jnt_convolve_y_avx2(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams *filter_params_x, const InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params);
 RTCD_EXTERN void (*av1_jnt_convolve_y)(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams *filter_params_x, const InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params);
 
-void av1_selfguided_restoration_c(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-void av1_selfguided_restoration_sse4_1(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-void av1_selfguided_restoration_avx2(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-RTCD_EXTERN void (*av1_selfguided_restoration)(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_c(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_sse4_1(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_avx2(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+RTCD_EXTERN int (*av1_selfguided_restoration)(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
 
 void av1_upsample_intra_edge_c(uint8_t *p, int sz);
 void av1_upsample_intra_edge_sse4_1(uint8_t *p, int sz);
@@ -398,7 +427,7 @@ cfl_subtract_average_fn get_subtract_average_fn_sse2(TX_SIZE tx_size);
 cfl_subtract_average_fn get_subtract_average_fn_avx2(TX_SIZE tx_size);
 RTCD_EXTERN cfl_subtract_average_fn (*get_subtract_average_fn)(TX_SIZE tx_size);
 
-void aom_rtcd(void);
+void av1_rtcd(void);
 
 #ifdef RTCD_C
 #include "aom_ports/x86.h"
@@ -413,8 +442,10 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_AVX2) apply_selfguided_restoration = apply_selfguided_restoration_avx2;
     av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_c;
     if (flags & HAS_SSE4_1) av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_sse4_1;
+    if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_avx2;
     av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_c;
     if (flags & HAS_SSE4_1) av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_sse4_1;
+    if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_avx2;
     av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_c;
     if (flags & HAS_SSSE3) av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_ssse3;
     if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_avx2;
@@ -451,6 +482,22 @@ static void setup_rtcd_internal(void)
     av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_c;
     if (flags & HAS_SSSE3) av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_ssse3;
     if (flags & HAS_AVX2) av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_avx2;
+    av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_sse4_1;
+    if (flags & HAS_AVX2) av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_avx2;
+    av1_highbd_inv_txfm_add_16x16 = av1_highbd_inv_txfm_add_16x16_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_16x16 = av1_highbd_inv_txfm_add_16x16_sse4_1;
+    av1_highbd_inv_txfm_add_16x8 = av1_highbd_inv_txfm_add_16x8_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_16x8 = av1_highbd_inv_txfm_add_16x8_sse4_1;
+    av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_sse4_1;
+    if (flags & HAS_AVX2) av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_avx2;
+    av1_highbd_inv_txfm_add_4x4 = av1_highbd_inv_txfm_add_4x4_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_4x4 = av1_highbd_inv_txfm_add_4x4_sse4_1;
+    av1_highbd_inv_txfm_add_8x16 = av1_highbd_inv_txfm_add_8x16_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_8x16 = av1_highbd_inv_txfm_add_8x16_sse4_1;
+    av1_highbd_inv_txfm_add_8x8 = av1_highbd_inv_txfm_add_8x8_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_8x8 = av1_highbd_inv_txfm_add_8x8_sse4_1;
     av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_c;
     if (flags & HAS_SSE4_1) av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_sse4_1;
     if (flags & HAS_AVX2) av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_avx2;
@@ -468,14 +515,8 @@ static void setup_rtcd_internal(void)
     av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_c;
     if (flags & HAS_SSSE3) av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_ssse3;
     if (flags & HAS_AVX2) av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_avx2;
-    av1_inv_txfm2d_add_16x16 = av1_inv_txfm2d_add_16x16_c;
-    if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_16x16 = av1_inv_txfm2d_add_16x16_sse4_1;
-    av1_inv_txfm2d_add_32x32 = av1_inv_txfm2d_add_32x32_c;
-    if (flags & HAS_AVX2) av1_inv_txfm2d_add_32x32 = av1_inv_txfm2d_add_32x32_avx2;
     av1_inv_txfm2d_add_4x4 = av1_inv_txfm2d_add_4x4_c;
     if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_4x4 = av1_inv_txfm2d_add_4x4_sse4_1;
-    av1_inv_txfm2d_add_64x64 = av1_inv_txfm2d_add_64x64_c;
-    if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_64x64 = av1_inv_txfm2d_add_64x64_sse4_1;
     av1_inv_txfm2d_add_8x8 = av1_inv_txfm2d_add_8x8_c;
     if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_8x8 = av1_inv_txfm2d_add_8x8_sse4_1;
     av1_inv_txfm_add = av1_inv_txfm_add_c;

media/libaom/config/win/ia32/config/aom_config.asm

@@ -14,6 +14,7 @@ ARCH_MIPS equ 0
 ARCH_PPC equ 0
 ARCH_X86 equ 1
 ARCH_X86_64 equ 0
+CONFIG_2PASS_PARTITION_SEARCH_LVL equ 1
 CONFIG_ACCOUNTING equ 0
 CONFIG_ANALYZER equ 0
 CONFIG_AV1_DECODER equ 1
@@ -21,30 +22,35 @@ CONFIG_AV1_ENCODER equ 0
 CONFIG_BIG_ENDIAN equ 0
 CONFIG_BITSTREAM_DEBUG equ 0
 CONFIG_COEFFICIENT_RANGE_CHECKING equ 0
-CONFIG_COLLECT_INTER_MODE_RD_STATS equ 1
+CONFIG_COLLECT_INTER_MODE_RD_STATS equ 0
 CONFIG_COLLECT_RD_STATS equ 0
 CONFIG_DEBUG equ 0
-CONFIG_DENOISE equ 0
-CONFIG_DIST_8X8 equ 1
+CONFIG_DENOISE equ 1
+CONFIG_DIST_8X8 equ 0
 CONFIG_ENTROPY_STATS equ 0
 CONFIG_FILEOPTIONS equ 1
+CONFIG_FIX_GF_LENGTH equ 1
 CONFIG_FP_MB_STATS equ 0
 CONFIG_GCC equ 1
 CONFIG_GCOV equ 0
+CONFIG_GLOBAL_MOTION_SEARCH equ 1
 CONFIG_GPROF equ 0
 CONFIG_INSPECTION equ 0
 CONFIG_INTERNAL_STATS equ 0
 CONFIG_INTER_STATS_ONLY equ 0
 CONFIG_LIBYUV equ 0
-CONFIG_LOWBITDEPTH equ 0
+CONFIG_LOWBITDEPTH equ 1
+CONFIG_MAX_DECODE_PROFILE equ 2
 CONFIG_MISMATCH_DEBUG equ 0
-CONFIG_MSVS equ 1
 CONFIG_MULTITHREAD equ 1
+CONFIG_NORMAL_TILE_MODE equ 0
 CONFIG_OS_SUPPORT equ 1
 CONFIG_PIC equ 0
 CONFIG_RD_DEBUG equ 0
+CONFIG_REDUCED_ENCODER_BORDER equ 0
 CONFIG_RUNTIME_CPU_DETECT equ 1
 CONFIG_SHARED equ 0
+CONFIG_SHARP_SETTINGS equ 0
 CONFIG_SIZE_LIMIT equ 0
 CONFIG_SPATIAL_RESAMPLING equ 1
 CONFIG_STATIC equ 1

media/libaom/config/win/ia32/config/aom_config.h

@@ -16,6 +16,7 @@
 #define ARCH_PPC 0
 #define ARCH_X86 1
 #define ARCH_X86_64 0
+#define CONFIG_2PASS_PARTITION_SEARCH_LVL 1
 #define CONFIG_ACCOUNTING 0
 #define CONFIG_ANALYZER 0
 #define CONFIG_AV1_DECODER 1
@@ -23,30 +24,35 @@
 #define CONFIG_BIG_ENDIAN 0
 #define CONFIG_BITSTREAM_DEBUG 0
 #define CONFIG_COEFFICIENT_RANGE_CHECKING 0
-#define CONFIG_COLLECT_INTER_MODE_RD_STATS 1
+#define CONFIG_COLLECT_INTER_MODE_RD_STATS 0
 #define CONFIG_COLLECT_RD_STATS 0
 #define CONFIG_DEBUG 0
-#define CONFIG_DENOISE 0
-#define CONFIG_DIST_8X8 1
+#define CONFIG_DENOISE 1
+#define CONFIG_DIST_8X8 0
 #define CONFIG_ENTROPY_STATS 0
 #define CONFIG_FILEOPTIONS 1
+#define CONFIG_FIX_GF_LENGTH 1
 #define CONFIG_FP_MB_STATS 0
 #define CONFIG_GCC 1
 #define CONFIG_GCOV 0
+#define CONFIG_GLOBAL_MOTION_SEARCH 1
 #define CONFIG_GPROF 0
 #define CONFIG_INSPECTION 0
 #define CONFIG_INTERNAL_STATS 0
 #define CONFIG_INTER_STATS_ONLY 0
 #define CONFIG_LIBYUV 0
-#define CONFIG_LOWBITDEPTH 0
+#define CONFIG_LOWBITDEPTH 1
+#define CONFIG_MAX_DECODE_PROFILE 2
 #define CONFIG_MISMATCH_DEBUG 0
-#define CONFIG_MSVS 1
 #define CONFIG_MULTITHREAD 1
+#define CONFIG_NORMAL_TILE_MODE 0
 #define CONFIG_OS_SUPPORT 1
 #define CONFIG_PIC 0
 #define CONFIG_RD_DEBUG 0
+#define CONFIG_REDUCED_ENCODER_BORDER 0
 #define CONFIG_RUNTIME_CPU_DETECT 1
 #define CONFIG_SHARED 0
+#define CONFIG_SHARP_SETTINGS 0
 #define CONFIG_SIZE_LIMIT 0
 #define CONFIG_SPATIAL_RESAMPLING 1
 #define CONFIG_STATIC 1

media/libaom/config/win/ia32/config/aom_dsp_rtcd.h

@@ -28,6 +28,7 @@ RTCD_EXTERN void (*aom_blend_a64_hmask)(uint8_t *dst, uint32_t dst_stride, const
 
 void aom_blend_a64_mask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 void aom_blend_a64_mask_sse4_1(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
+void aom_blend_a64_mask_avx2(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 RTCD_EXTERN void (*aom_blend_a64_mask)(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 
 void aom_blend_a64_vmask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int w, int h);
@@ -1230,6 +1231,7 @@ RTCD_EXTERN void (*aom_highbd_v_predictor_8x8)(uint16_t *dst, ptrdiff_t y_stride
 
 void aom_lowbd_blend_a64_d16_mask_c(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 void aom_lowbd_blend_a64_d16_mask_sse4_1(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
+void aom_lowbd_blend_a64_d16_mask_avx2(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 RTCD_EXTERN void (*aom_lowbd_blend_a64_d16_mask)(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 
 void aom_lpf_horizontal_14_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);
@@ -1725,6 +1727,7 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_SSE4_1) aom_blend_a64_hmask = aom_blend_a64_hmask_sse4_1;
     aom_blend_a64_mask = aom_blend_a64_mask_c;
     if (flags & HAS_SSE4_1) aom_blend_a64_mask = aom_blend_a64_mask_sse4_1;
+    if (flags & HAS_AVX2) aom_blend_a64_mask = aom_blend_a64_mask_avx2;
     aom_blend_a64_vmask = aom_blend_a64_vmask_c;
     if (flags & HAS_SSE4_1) aom_blend_a64_vmask = aom_blend_a64_vmask_sse4_1;
     aom_convolve8_horiz = aom_convolve8_horiz_c;
@@ -2125,6 +2128,7 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_SSE2) aom_highbd_v_predictor_8x8 = aom_highbd_v_predictor_8x8_sse2;
     aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_c;
     if (flags & HAS_SSE4_1) aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_sse4_1;
+    if (flags & HAS_AVX2) aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_avx2;
     aom_lpf_horizontal_14 = aom_lpf_horizontal_14_c;
     if (flags & HAS_SSE2) aom_lpf_horizontal_14 = aom_lpf_horizontal_14_sse2;
     aom_lpf_horizontal_14_dual = aom_lpf_horizontal_14_dual_c;

media/libaom/config/win/ia32/config/av1_rtcd.h

@@ -1,6 +1,6 @@
 // This file is generated. Do not edit.
-#ifndef AOM_RTCD_H_
-#define AOM_RTCD_H_
+#ifndef AV1_RTCD_H_
+#define AV1_RTCD_H_
 
 #ifdef RTCD_C
 #define RTCD_EXTERN
@@ -58,10 +58,12 @@ RTCD_EXTERN void (*apply_selfguided_restoration)(const uint8_t *dat, int width,
 
 void av1_build_compound_diffwtd_mask_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 void av1_build_compound_diffwtd_mask_sse4_1(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
+void av1_build_compound_diffwtd_mask_avx2(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 RTCD_EXTERN void (*av1_build_compound_diffwtd_mask)(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 
 void av1_build_compound_diffwtd_mask_d16_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 void av1_build_compound_diffwtd_mask_d16_sse4_1(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
+void av1_build_compound_diffwtd_mask_d16_avx2(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 RTCD_EXTERN void (*av1_build_compound_diffwtd_mask_d16)(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 
 void av1_build_compound_diffwtd_mask_highbd_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w, int bd);
@@ -170,6 +172,36 @@ void av1_highbd_dr_prediction_z2_c(uint16_t *dst, ptrdiff_t stride, int bw, int
 void av1_highbd_dr_prediction_z3_c(uint16_t *dst, ptrdiff_t stride, int bw, int bh, const uint16_t *above, const uint16_t *left, int upsample_left, int dx, int dy, int bd);
 #define av1_highbd_dr_prediction_z3 av1_highbd_dr_prediction_z3_c
 
+void av1_highbd_inv_txfm_add_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_avx2(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_16x16_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_16x16_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_16x16)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_16x8_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_16x8_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_16x8)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_32x32_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_32x32_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_32x32_avx2(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_32x32)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_4x4_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_4x4_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_4x4)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_8x16_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_8x16_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_8x16)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_8x8_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_8x8_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_8x8)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
 void av1_highbd_iwht4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, int bd);
 #define av1_highbd_iwht4x4_16_add av1_highbd_iwht4x4_16_add_c
 
@@ -206,8 +238,7 @@ void av1_highbd_wiener_convolve_add_src_avx2(const uint8_t *src, ptrdiff_t src_s
 RTCD_EXTERN void (*av1_highbd_wiener_convolve_add_src)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, const ConvolveParams *conv_params, int bps);
 
 void av1_inv_txfm2d_add_16x16_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_16x16_sse4_1(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_16x16)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_16x16 av1_inv_txfm2d_add_16x16_c
 
 void av1_inv_txfm2d_add_16x32_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_16x32 av1_inv_txfm2d_add_16x32_c
@@ -225,8 +256,7 @@ void av1_inv_txfm2d_add_32x16_c(const int32_t *input, uint16_t *output, int stri
 #define av1_inv_txfm2d_add_32x16 av1_inv_txfm2d_add_32x16_c
 
 void av1_inv_txfm2d_add_32x32_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_32x32_avx2(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_32x32)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_32x32 av1_inv_txfm2d_add_32x32_c
 
 void av1_inv_txfm2d_add_32x64_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_32x64 av1_inv_txfm2d_add_32x64_c
@@ -251,8 +281,7 @@ void av1_inv_txfm2d_add_64x32_c(const int32_t *input, uint16_t *output, int stri
 #define av1_inv_txfm2d_add_64x32 av1_inv_txfm2d_add_64x32_c
 
 void av1_inv_txfm2d_add_64x64_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_64x64_sse4_1(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_64x64)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_64x64 av1_inv_txfm2d_add_64x64_c
 
 void av1_inv_txfm2d_add_8x16_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_8x16 av1_inv_txfm2d_add_8x16_c
@@ -292,18 +321,18 @@ void av1_jnt_convolve_y_sse2(const uint8_t *src, int src_stride, uint8_t *dst, i
 void av1_jnt_convolve_y_avx2(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams *filter_params_x, const InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params);
 RTCD_EXTERN void (*av1_jnt_convolve_y)(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams *filter_params_x, const InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params);
 
-void av1_selfguided_restoration_c(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-void av1_selfguided_restoration_sse4_1(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-void av1_selfguided_restoration_avx2(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-RTCD_EXTERN void (*av1_selfguided_restoration)(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_c(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_sse4_1(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_avx2(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+RTCD_EXTERN int (*av1_selfguided_restoration)(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
 
 void av1_upsample_intra_edge_c(uint8_t *p, int sz);
 void av1_upsample_intra_edge_sse4_1(uint8_t *p, int sz);
@@ -395,7 +424,7 @@ cfl_subtract_average_fn get_subtract_average_fn_sse2(TX_SIZE tx_size);
 cfl_subtract_average_fn get_subtract_average_fn_avx2(TX_SIZE tx_size);
 RTCD_EXTERN cfl_subtract_average_fn (*get_subtract_average_fn)(TX_SIZE tx_size);
 
-void aom_rtcd(void);
+void av1_rtcd(void);
 
 #ifdef RTCD_C
 #include "aom_ports/x86.h"
@@ -410,8 +439,10 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_AVX2) apply_selfguided_restoration = apply_selfguided_restoration_avx2;
     av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_c;
     if (flags & HAS_SSE4_1) av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_sse4_1;
+    if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_avx2;
     av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_c;
     if (flags & HAS_SSE4_1) av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_sse4_1;
+    if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_avx2;
     av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_c;
     if (flags & HAS_SSSE3) av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_ssse3;
     if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_avx2;
@@ -453,6 +484,22 @@ static void setup_rtcd_internal(void)
     av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_c;
     if (flags & HAS_SSSE3) av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_ssse3;
     if (flags & HAS_AVX2) av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_avx2;
+    av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_sse4_1;
+    if (flags & HAS_AVX2) av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_avx2;
+    av1_highbd_inv_txfm_add_16x16 = av1_highbd_inv_txfm_add_16x16_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_16x16 = av1_highbd_inv_txfm_add_16x16_sse4_1;
+    av1_highbd_inv_txfm_add_16x8 = av1_highbd_inv_txfm_add_16x8_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_16x8 = av1_highbd_inv_txfm_add_16x8_sse4_1;
+    av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_sse4_1;
+    if (flags & HAS_AVX2) av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_avx2;
+    av1_highbd_inv_txfm_add_4x4 = av1_highbd_inv_txfm_add_4x4_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_4x4 = av1_highbd_inv_txfm_add_4x4_sse4_1;
+    av1_highbd_inv_txfm_add_8x16 = av1_highbd_inv_txfm_add_8x16_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_8x16 = av1_highbd_inv_txfm_add_8x16_sse4_1;
+    av1_highbd_inv_txfm_add_8x8 = av1_highbd_inv_txfm_add_8x8_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_8x8 = av1_highbd_inv_txfm_add_8x8_sse4_1;
     av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_c;
     if (flags & HAS_SSE4_1) av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_sse4_1;
     if (flags & HAS_AVX2) av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_avx2;
@@ -470,14 +517,8 @@ static void setup_rtcd_internal(void)
     av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_c;
     if (flags & HAS_SSSE3) av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_ssse3;
     if (flags & HAS_AVX2) av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_avx2;
-    av1_inv_txfm2d_add_16x16 = av1_inv_txfm2d_add_16x16_c;
-    if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_16x16 = av1_inv_txfm2d_add_16x16_sse4_1;
-    av1_inv_txfm2d_add_32x32 = av1_inv_txfm2d_add_32x32_c;
-    if (flags & HAS_AVX2) av1_inv_txfm2d_add_32x32 = av1_inv_txfm2d_add_32x32_avx2;
     av1_inv_txfm2d_add_4x4 = av1_inv_txfm2d_add_4x4_c;
     if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_4x4 = av1_inv_txfm2d_add_4x4_sse4_1;
-    av1_inv_txfm2d_add_64x64 = av1_inv_txfm2d_add_64x64_c;
-    if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_64x64 = av1_inv_txfm2d_add_64x64_sse4_1;
     av1_inv_txfm2d_add_8x8 = av1_inv_txfm2d_add_8x8_c;
     if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_8x8 = av1_inv_txfm2d_add_8x8_sse4_1;
     av1_inv_txfm_add = av1_inv_txfm_add_c;

media/libaom/config/win/mingw32/config/aom_config.asm

@@ -14,6 +14,7 @@ ARCH_MIPS equ 0
 ARCH_PPC equ 0
 ARCH_X86 equ 1
 ARCH_X86_64 equ 0
+CONFIG_2PASS_PARTITION_SEARCH_LVL equ 1
 CONFIG_ACCOUNTING equ 0
 CONFIG_ANALYZER equ 0
 CONFIG_AV1_DECODER equ 1
@@ -21,30 +22,35 @@ CONFIG_AV1_ENCODER equ 0
 CONFIG_BIG_ENDIAN equ 0
 CONFIG_BITSTREAM_DEBUG equ 0
 CONFIG_COEFFICIENT_RANGE_CHECKING equ 0
-CONFIG_COLLECT_INTER_MODE_RD_STATS equ 1
+CONFIG_COLLECT_INTER_MODE_RD_STATS equ 0
 CONFIG_COLLECT_RD_STATS equ 0
 CONFIG_DEBUG equ 0
-CONFIG_DENOISE equ 0
-CONFIG_DIST_8X8 equ 1
+CONFIG_DENOISE equ 1
+CONFIG_DIST_8X8 equ 0
 CONFIG_ENTROPY_STATS equ 0
 CONFIG_FILEOPTIONS equ 1
+CONFIG_FIX_GF_LENGTH equ 1
 CONFIG_FP_MB_STATS equ 0
 CONFIG_GCC equ 1
 CONFIG_GCOV equ 0
+CONFIG_GLOBAL_MOTION_SEARCH equ 1
 CONFIG_GPROF equ 0
 CONFIG_INSPECTION equ 0
 CONFIG_INTERNAL_STATS equ 0
 CONFIG_INTER_STATS_ONLY equ 0
 CONFIG_LIBYUV equ 0
-CONFIG_LOWBITDEPTH equ 0
+CONFIG_LOWBITDEPTH equ 1
+CONFIG_MAX_DECODE_PROFILE equ 2
 CONFIG_MISMATCH_DEBUG equ 0
-CONFIG_MSVS equ 0
 CONFIG_MULTITHREAD equ 1
+CONFIG_NORMAL_TILE_MODE equ 0
 CONFIG_OS_SUPPORT equ 1
 CONFIG_PIC equ 0
 CONFIG_RD_DEBUG equ 0
+CONFIG_REDUCED_ENCODER_BORDER equ 0
 CONFIG_RUNTIME_CPU_DETECT equ 1
 CONFIG_SHARED equ 0
+CONFIG_SHARP_SETTINGS equ 0
 CONFIG_SIZE_LIMIT equ 0
 CONFIG_SPATIAL_RESAMPLING equ 1
 CONFIG_STATIC equ 1

media/libaom/config/win/mingw32/config/aom_config.h

@@ -16,6 +16,7 @@
 #define ARCH_PPC 0
 #define ARCH_X86 1
 #define ARCH_X86_64 0
+#define CONFIG_2PASS_PARTITION_SEARCH_LVL 1
 #define CONFIG_ACCOUNTING 0
 #define CONFIG_ANALYZER 0
 #define CONFIG_AV1_DECODER 1
@@ -23,30 +24,35 @@
 #define CONFIG_BIG_ENDIAN 0
 #define CONFIG_BITSTREAM_DEBUG 0
 #define CONFIG_COEFFICIENT_RANGE_CHECKING 0
-#define CONFIG_COLLECT_INTER_MODE_RD_STATS 1
+#define CONFIG_COLLECT_INTER_MODE_RD_STATS 0
 #define CONFIG_COLLECT_RD_STATS 0
 #define CONFIG_DEBUG 0
-#define CONFIG_DENOISE 0
-#define CONFIG_DIST_8X8 1
+#define CONFIG_DENOISE 1
+#define CONFIG_DIST_8X8 0
 #define CONFIG_ENTROPY_STATS 0
 #define CONFIG_FILEOPTIONS 1
+#define CONFIG_FIX_GF_LENGTH 1
 #define CONFIG_FP_MB_STATS 0
 #define CONFIG_GCC 1
 #define CONFIG_GCOV 0
+#define CONFIG_GLOBAL_MOTION_SEARCH 1
 #define CONFIG_GPROF 0
 #define CONFIG_INSPECTION 0
 #define CONFIG_INTERNAL_STATS 0
 #define CONFIG_INTER_STATS_ONLY 0
 #define CONFIG_LIBYUV 0
-#define CONFIG_LOWBITDEPTH 0
+#define CONFIG_LOWBITDEPTH 1
+#define CONFIG_MAX_DECODE_PROFILE 2
 #define CONFIG_MISMATCH_DEBUG 0
-#define CONFIG_MSVS 0
 #define CONFIG_MULTITHREAD 1
+#define CONFIG_NORMAL_TILE_MODE 0
 #define CONFIG_OS_SUPPORT 1
 #define CONFIG_PIC 0
 #define CONFIG_RD_DEBUG 0
+#define CONFIG_REDUCED_ENCODER_BORDER 0
 #define CONFIG_RUNTIME_CPU_DETECT 1
 #define CONFIG_SHARED 0
+#define CONFIG_SHARP_SETTINGS 0
 #define CONFIG_SIZE_LIMIT 0
 #define CONFIG_SPATIAL_RESAMPLING 1
 #define CONFIG_STATIC 1

media/libaom/config/win/mingw32/config/aom_dsp_rtcd.h

@@ -28,6 +28,7 @@ RTCD_EXTERN void (*aom_blend_a64_hmask)(uint8_t *dst, uint32_t dst_stride, const
 
 void aom_blend_a64_mask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 void aom_blend_a64_mask_sse4_1(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
+void aom_blend_a64_mask_avx2(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 RTCD_EXTERN void (*aom_blend_a64_mask)(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 
 void aom_blend_a64_vmask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int w, int h);
@@ -1230,6 +1231,7 @@ RTCD_EXTERN void (*aom_highbd_v_predictor_8x8)(uint16_t *dst, ptrdiff_t y_stride
 
 void aom_lowbd_blend_a64_d16_mask_c(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 void aom_lowbd_blend_a64_d16_mask_sse4_1(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
+void aom_lowbd_blend_a64_d16_mask_avx2(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 RTCD_EXTERN void (*aom_lowbd_blend_a64_d16_mask)(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 
 void aom_lpf_horizontal_14_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);
@@ -1725,6 +1727,7 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_SSE4_1) aom_blend_a64_hmask = aom_blend_a64_hmask_sse4_1;
     aom_blend_a64_mask = aom_blend_a64_mask_c;
     if (flags & HAS_SSE4_1) aom_blend_a64_mask = aom_blend_a64_mask_sse4_1;
+    if (flags & HAS_AVX2) aom_blend_a64_mask = aom_blend_a64_mask_avx2;
     aom_blend_a64_vmask = aom_blend_a64_vmask_c;
     if (flags & HAS_SSE4_1) aom_blend_a64_vmask = aom_blend_a64_vmask_sse4_1;
     aom_convolve8_horiz = aom_convolve8_horiz_c;
@@ -2125,6 +2128,7 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_SSE2) aom_highbd_v_predictor_8x8 = aom_highbd_v_predictor_8x8_sse2;
     aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_c;
     if (flags & HAS_SSE4_1) aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_sse4_1;
+    if (flags & HAS_AVX2) aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_avx2;
     aom_lpf_horizontal_14 = aom_lpf_horizontal_14_c;
     if (flags & HAS_SSE2) aom_lpf_horizontal_14 = aom_lpf_horizontal_14_sse2;
     aom_lpf_horizontal_14_dual = aom_lpf_horizontal_14_dual_c;

media/libaom/config/win/mingw32/config/av1_rtcd.h

@@ -1,6 +1,6 @@
 // This file is generated. Do not edit.
-#ifndef AOM_RTCD_H_
-#define AOM_RTCD_H_
+#ifndef AV1_RTCD_H_
+#define AV1_RTCD_H_
 
 #ifdef RTCD_C
 #define RTCD_EXTERN
@@ -58,10 +58,12 @@ RTCD_EXTERN void (*apply_selfguided_restoration)(const uint8_t *dat, int width,
 
 void av1_build_compound_diffwtd_mask_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 void av1_build_compound_diffwtd_mask_sse4_1(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
+void av1_build_compound_diffwtd_mask_avx2(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 RTCD_EXTERN void (*av1_build_compound_diffwtd_mask)(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 
 void av1_build_compound_diffwtd_mask_d16_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 void av1_build_compound_diffwtd_mask_d16_sse4_1(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
+void av1_build_compound_diffwtd_mask_d16_avx2(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 RTCD_EXTERN void (*av1_build_compound_diffwtd_mask_d16)(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 
 void av1_build_compound_diffwtd_mask_highbd_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w, int bd);
@@ -170,6 +172,36 @@ void av1_highbd_dr_prediction_z2_c(uint16_t *dst, ptrdiff_t stride, int bw, int
 void av1_highbd_dr_prediction_z3_c(uint16_t *dst, ptrdiff_t stride, int bw, int bh, const uint16_t *above, const uint16_t *left, int upsample_left, int dx, int dy, int bd);
 #define av1_highbd_dr_prediction_z3 av1_highbd_dr_prediction_z3_c
 
+void av1_highbd_inv_txfm_add_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_avx2(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_16x16_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_16x16_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_16x16)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_16x8_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_16x8_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_16x8)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_32x32_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_32x32_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_32x32_avx2(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_32x32)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_4x4_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_4x4_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_4x4)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_8x16_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_8x16_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_8x16)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_8x8_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_8x8_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_8x8)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
 void av1_highbd_iwht4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, int bd);
 #define av1_highbd_iwht4x4_16_add av1_highbd_iwht4x4_16_add_c
 
@@ -206,8 +238,7 @@ void av1_highbd_wiener_convolve_add_src_avx2(const uint8_t *src, ptrdiff_t src_s
 RTCD_EXTERN void (*av1_highbd_wiener_convolve_add_src)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, const ConvolveParams *conv_params, int bps);
 
 void av1_inv_txfm2d_add_16x16_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_16x16_sse4_1(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_16x16)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_16x16 av1_inv_txfm2d_add_16x16_c
 
 void av1_inv_txfm2d_add_16x32_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_16x32 av1_inv_txfm2d_add_16x32_c
@@ -225,8 +256,7 @@ void av1_inv_txfm2d_add_32x16_c(const int32_t *input, uint16_t *output, int stri
 #define av1_inv_txfm2d_add_32x16 av1_inv_txfm2d_add_32x16_c
 
 void av1_inv_txfm2d_add_32x32_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_32x32_avx2(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_32x32)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_32x32 av1_inv_txfm2d_add_32x32_c
 
 void av1_inv_txfm2d_add_32x64_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_32x64 av1_inv_txfm2d_add_32x64_c
@@ -251,8 +281,7 @@ void av1_inv_txfm2d_add_64x32_c(const int32_t *input, uint16_t *output, int stri
 #define av1_inv_txfm2d_add_64x32 av1_inv_txfm2d_add_64x32_c
 
 void av1_inv_txfm2d_add_64x64_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_64x64_sse4_1(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_64x64)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_64x64 av1_inv_txfm2d_add_64x64_c
 
 void av1_inv_txfm2d_add_8x16_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_8x16 av1_inv_txfm2d_add_8x16_c
@@ -292,18 +321,18 @@ void av1_jnt_convolve_y_sse2(const uint8_t *src, int src_stride, uint8_t *dst, i
 void av1_jnt_convolve_y_avx2(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams *filter_params_x, const InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params);
 RTCD_EXTERN void (*av1_jnt_convolve_y)(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams *filter_params_x, const InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params);
 
-void av1_selfguided_restoration_c(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-void av1_selfguided_restoration_sse4_1(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-void av1_selfguided_restoration_avx2(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-RTCD_EXTERN void (*av1_selfguided_restoration)(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_c(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_sse4_1(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_avx2(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+RTCD_EXTERN int (*av1_selfguided_restoration)(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
 
 void av1_upsample_intra_edge_c(uint8_t *p, int sz);
 void av1_upsample_intra_edge_sse4_1(uint8_t *p, int sz);
@@ -395,7 +424,7 @@ cfl_subtract_average_fn get_subtract_average_fn_sse2(TX_SIZE tx_size);
 cfl_subtract_average_fn get_subtract_average_fn_avx2(TX_SIZE tx_size);
 RTCD_EXTERN cfl_subtract_average_fn (*get_subtract_average_fn)(TX_SIZE tx_size);
 
-void aom_rtcd(void);
+void av1_rtcd(void);
 
 #ifdef RTCD_C
 #include "aom_ports/x86.h"
@@ -410,8 +439,10 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_AVX2) apply_selfguided_restoration = apply_selfguided_restoration_avx2;
     av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_c;
     if (flags & HAS_SSE4_1) av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_sse4_1;
+    if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_avx2;
     av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_c;
     if (flags & HAS_SSE4_1) av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_sse4_1;
+    if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_avx2;
     av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_c;
     if (flags & HAS_SSSE3) av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_ssse3;
     if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_avx2;
@@ -453,6 +484,22 @@ static void setup_rtcd_internal(void)
     av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_c;
     if (flags & HAS_SSSE3) av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_ssse3;
     if (flags & HAS_AVX2) av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_avx2;
+    av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_sse4_1;
+    if (flags & HAS_AVX2) av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_avx2;
+    av1_highbd_inv_txfm_add_16x16 = av1_highbd_inv_txfm_add_16x16_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_16x16 = av1_highbd_inv_txfm_add_16x16_sse4_1;
+    av1_highbd_inv_txfm_add_16x8 = av1_highbd_inv_txfm_add_16x8_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_16x8 = av1_highbd_inv_txfm_add_16x8_sse4_1;
+    av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_sse4_1;
+    if (flags & HAS_AVX2) av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_avx2;
+    av1_highbd_inv_txfm_add_4x4 = av1_highbd_inv_txfm_add_4x4_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_4x4 = av1_highbd_inv_txfm_add_4x4_sse4_1;
+    av1_highbd_inv_txfm_add_8x16 = av1_highbd_inv_txfm_add_8x16_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_8x16 = av1_highbd_inv_txfm_add_8x16_sse4_1;
+    av1_highbd_inv_txfm_add_8x8 = av1_highbd_inv_txfm_add_8x8_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_8x8 = av1_highbd_inv_txfm_add_8x8_sse4_1;
     av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_c;
     if (flags & HAS_SSE4_1) av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_sse4_1;
     if (flags & HAS_AVX2) av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_avx2;
@@ -470,14 +517,8 @@ static void setup_rtcd_internal(void)
     av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_c;
     if (flags & HAS_SSSE3) av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_ssse3;
     if (flags & HAS_AVX2) av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_avx2;
-    av1_inv_txfm2d_add_16x16 = av1_inv_txfm2d_add_16x16_c;
-    if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_16x16 = av1_inv_txfm2d_add_16x16_sse4_1;
-    av1_inv_txfm2d_add_32x32 = av1_inv_txfm2d_add_32x32_c;
-    if (flags & HAS_AVX2) av1_inv_txfm2d_add_32x32 = av1_inv_txfm2d_add_32x32_avx2;
     av1_inv_txfm2d_add_4x4 = av1_inv_txfm2d_add_4x4_c;
     if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_4x4 = av1_inv_txfm2d_add_4x4_sse4_1;
-    av1_inv_txfm2d_add_64x64 = av1_inv_txfm2d_add_64x64_c;
-    if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_64x64 = av1_inv_txfm2d_add_64x64_sse4_1;
     av1_inv_txfm2d_add_8x8 = av1_inv_txfm2d_add_8x8_c;
     if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_8x8 = av1_inv_txfm2d_add_8x8_sse4_1;
     av1_inv_txfm_add = av1_inv_txfm_add_c;

media/libaom/config/win/mingw64/config/aom_config.asm

@@ -14,6 +14,7 @@ ARCH_MIPS equ 0
 ARCH_PPC equ 0
 ARCH_X86 equ 0
 ARCH_X86_64 equ 1
+CONFIG_2PASS_PARTITION_SEARCH_LVL equ 1
 CONFIG_ACCOUNTING equ 0
 CONFIG_ANALYZER equ 0
 CONFIG_AV1_DECODER equ 1
@@ -21,30 +22,35 @@ CONFIG_AV1_ENCODER equ 0
 CONFIG_BIG_ENDIAN equ 0
 CONFIG_BITSTREAM_DEBUG equ 0
 CONFIG_COEFFICIENT_RANGE_CHECKING equ 0
-CONFIG_COLLECT_INTER_MODE_RD_STATS equ 1
+CONFIG_COLLECT_INTER_MODE_RD_STATS equ 0
 CONFIG_COLLECT_RD_STATS equ 0
 CONFIG_DEBUG equ 0
-CONFIG_DENOISE equ 0
-CONFIG_DIST_8X8 equ 1
+CONFIG_DENOISE equ 1
+CONFIG_DIST_8X8 equ 0
 CONFIG_ENTROPY_STATS equ 0
 CONFIG_FILEOPTIONS equ 1
+CONFIG_FIX_GF_LENGTH equ 1
 CONFIG_FP_MB_STATS equ 0
 CONFIG_GCC equ 1
 CONFIG_GCOV equ 0
+CONFIG_GLOBAL_MOTION_SEARCH equ 1
 CONFIG_GPROF equ 0
 CONFIG_INSPECTION equ 0
 CONFIG_INTERNAL_STATS equ 0
 CONFIG_INTER_STATS_ONLY equ 0
 CONFIG_LIBYUV equ 0
-CONFIG_LOWBITDEPTH equ 0
+CONFIG_LOWBITDEPTH equ 1
+CONFIG_MAX_DECODE_PROFILE equ 2
 CONFIG_MISMATCH_DEBUG equ 0
-CONFIG_MSVS equ 0
 CONFIG_MULTITHREAD equ 1
+CONFIG_NORMAL_TILE_MODE equ 0
 CONFIG_OS_SUPPORT equ 1
 CONFIG_PIC equ 0
 CONFIG_RD_DEBUG equ 0
+CONFIG_REDUCED_ENCODER_BORDER equ 0
 CONFIG_RUNTIME_CPU_DETECT equ 1
 CONFIG_SHARED equ 0
+CONFIG_SHARP_SETTINGS equ 0
 CONFIG_SIZE_LIMIT equ 0
 CONFIG_SPATIAL_RESAMPLING equ 1
 CONFIG_STATIC equ 1

media/libaom/config/win/mingw64/config/aom_config.h

@@ -16,6 +16,7 @@
 #define ARCH_PPC 0
 #define ARCH_X86 0
 #define ARCH_X86_64 1
+#define CONFIG_2PASS_PARTITION_SEARCH_LVL 1
 #define CONFIG_ACCOUNTING 0
 #define CONFIG_ANALYZER 0
 #define CONFIG_AV1_DECODER 1
@@ -23,30 +24,35 @@
 #define CONFIG_BIG_ENDIAN 0
 #define CONFIG_BITSTREAM_DEBUG 0
 #define CONFIG_COEFFICIENT_RANGE_CHECKING 0
-#define CONFIG_COLLECT_INTER_MODE_RD_STATS 1
+#define CONFIG_COLLECT_INTER_MODE_RD_STATS 0
 #define CONFIG_COLLECT_RD_STATS 0
 #define CONFIG_DEBUG 0
-#define CONFIG_DENOISE 0
-#define CONFIG_DIST_8X8 1
+#define CONFIG_DENOISE 1
+#define CONFIG_DIST_8X8 0
 #define CONFIG_ENTROPY_STATS 0
 #define CONFIG_FILEOPTIONS 1
+#define CONFIG_FIX_GF_LENGTH 1
 #define CONFIG_FP_MB_STATS 0
 #define CONFIG_GCC 1
 #define CONFIG_GCOV 0
+#define CONFIG_GLOBAL_MOTION_SEARCH 1
 #define CONFIG_GPROF 0
 #define CONFIG_INSPECTION 0
 #define CONFIG_INTERNAL_STATS 0
 #define CONFIG_INTER_STATS_ONLY 0
 #define CONFIG_LIBYUV 0
-#define CONFIG_LOWBITDEPTH 0
+#define CONFIG_LOWBITDEPTH 1
+#define CONFIG_MAX_DECODE_PROFILE 2
 #define CONFIG_MISMATCH_DEBUG 0
-#define CONFIG_MSVS 0
 #define CONFIG_MULTITHREAD 1
+#define CONFIG_NORMAL_TILE_MODE 0
 #define CONFIG_OS_SUPPORT 1
 #define CONFIG_PIC 0
 #define CONFIG_RD_DEBUG 0
+#define CONFIG_REDUCED_ENCODER_BORDER 0
 #define CONFIG_RUNTIME_CPU_DETECT 1
 #define CONFIG_SHARED 0
+#define CONFIG_SHARP_SETTINGS 0
 #define CONFIG_SIZE_LIMIT 0
 #define CONFIG_SPATIAL_RESAMPLING 1
 #define CONFIG_STATIC 1

media/libaom/config/win/mingw64/config/aom_dsp_rtcd.h

@@ -28,6 +28,7 @@ RTCD_EXTERN void (*aom_blend_a64_hmask)(uint8_t *dst, uint32_t dst_stride, const
 
 void aom_blend_a64_mask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 void aom_blend_a64_mask_sse4_1(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
+void aom_blend_a64_mask_avx2(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 RTCD_EXTERN void (*aom_blend_a64_mask)(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 
 void aom_blend_a64_vmask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int w, int h);
@@ -1232,6 +1233,7 @@ void aom_highbd_v_predictor_8x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const ui
 
 void aom_lowbd_blend_a64_d16_mask_c(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 void aom_lowbd_blend_a64_d16_mask_sse4_1(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
+void aom_lowbd_blend_a64_d16_mask_avx2(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 RTCD_EXTERN void (*aom_lowbd_blend_a64_d16_mask)(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 
 void aom_lpf_horizontal_14_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);
@@ -1727,6 +1729,7 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_SSE4_1) aom_blend_a64_hmask = aom_blend_a64_hmask_sse4_1;
     aom_blend_a64_mask = aom_blend_a64_mask_c;
     if (flags & HAS_SSE4_1) aom_blend_a64_mask = aom_blend_a64_mask_sse4_1;
+    if (flags & HAS_AVX2) aom_blend_a64_mask = aom_blend_a64_mask_avx2;
     aom_blend_a64_vmask = aom_blend_a64_vmask_c;
     if (flags & HAS_SSE4_1) aom_blend_a64_vmask = aom_blend_a64_vmask_sse4_1;
     aom_convolve8_horiz = aom_convolve8_horiz_sse2;
@@ -1811,6 +1814,7 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_AVX2) aom_highbd_lpf_vertical_8_dual = aom_highbd_lpf_vertical_8_dual_avx2;
     aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_c;
     if (flags & HAS_SSE4_1) aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_sse4_1;
+    if (flags & HAS_AVX2) aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_avx2;
     aom_paeth_predictor_16x16 = aom_paeth_predictor_16x16_c;
     if (flags & HAS_SSSE3) aom_paeth_predictor_16x16 = aom_paeth_predictor_16x16_ssse3;
     if (flags & HAS_AVX2) aom_paeth_predictor_16x16 = aom_paeth_predictor_16x16_avx2;

media/libaom/config/win/mingw64/config/av1_rtcd.h

@@ -1,6 +1,6 @@
 // This file is generated. Do not edit.
-#ifndef AOM_RTCD_H_
-#define AOM_RTCD_H_
+#ifndef AV1_RTCD_H_
+#define AV1_RTCD_H_
 
 #ifdef RTCD_C
 #define RTCD_EXTERN
@@ -58,10 +58,12 @@ RTCD_EXTERN void (*apply_selfguided_restoration)(const uint8_t *dat, int width,
 
 void av1_build_compound_diffwtd_mask_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 void av1_build_compound_diffwtd_mask_sse4_1(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
+void av1_build_compound_diffwtd_mask_avx2(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 RTCD_EXTERN void (*av1_build_compound_diffwtd_mask)(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 
 void av1_build_compound_diffwtd_mask_d16_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 void av1_build_compound_diffwtd_mask_d16_sse4_1(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
+void av1_build_compound_diffwtd_mask_d16_avx2(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 RTCD_EXTERN void (*av1_build_compound_diffwtd_mask_d16)(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 
 void av1_build_compound_diffwtd_mask_highbd_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w, int bd);
@@ -173,6 +175,36 @@ void av1_highbd_dr_prediction_z2_c(uint16_t *dst, ptrdiff_t stride, int bw, int
 void av1_highbd_dr_prediction_z3_c(uint16_t *dst, ptrdiff_t stride, int bw, int bh, const uint16_t *above, const uint16_t *left, int upsample_left, int dx, int dy, int bd);
 #define av1_highbd_dr_prediction_z3 av1_highbd_dr_prediction_z3_c
 
+void av1_highbd_inv_txfm_add_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_avx2(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_16x16_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_16x16_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_16x16)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_16x8_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_16x8_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_16x8)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_32x32_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_32x32_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_32x32_avx2(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_32x32)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_4x4_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_4x4_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_4x4)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_8x16_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_8x16_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_8x16)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_8x8_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_8x8_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_8x8)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
 void av1_highbd_iwht4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, int bd);
 #define av1_highbd_iwht4x4_16_add av1_highbd_iwht4x4_16_add_c
 
@@ -209,8 +241,7 @@ void av1_highbd_wiener_convolve_add_src_avx2(const uint8_t *src, ptrdiff_t src_s
 RTCD_EXTERN void (*av1_highbd_wiener_convolve_add_src)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, const ConvolveParams *conv_params, int bps);
 
 void av1_inv_txfm2d_add_16x16_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_16x16_sse4_1(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_16x16)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_16x16 av1_inv_txfm2d_add_16x16_c
 
 void av1_inv_txfm2d_add_16x32_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_16x32 av1_inv_txfm2d_add_16x32_c
@@ -228,8 +259,7 @@ void av1_inv_txfm2d_add_32x16_c(const int32_t *input, uint16_t *output, int stri
 #define av1_inv_txfm2d_add_32x16 av1_inv_txfm2d_add_32x16_c
 
 void av1_inv_txfm2d_add_32x32_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_32x32_avx2(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_32x32)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_32x32 av1_inv_txfm2d_add_32x32_c
 
 void av1_inv_txfm2d_add_32x64_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_32x64 av1_inv_txfm2d_add_32x64_c
@@ -254,8 +284,7 @@ void av1_inv_txfm2d_add_64x32_c(const int32_t *input, uint16_t *output, int stri
 #define av1_inv_txfm2d_add_64x32 av1_inv_txfm2d_add_64x32_c
 
 void av1_inv_txfm2d_add_64x64_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_64x64_sse4_1(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_64x64)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_64x64 av1_inv_txfm2d_add_64x64_c
 
 void av1_inv_txfm2d_add_8x16_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_8x16 av1_inv_txfm2d_add_8x16_c
@@ -295,18 +324,18 @@ void av1_jnt_convolve_y_sse2(const uint8_t *src, int src_stride, uint8_t *dst, i
 void av1_jnt_convolve_y_avx2(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams *filter_params_x, const InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params);
 RTCD_EXTERN void (*av1_jnt_convolve_y)(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams *filter_params_x, const InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params);
 
-void av1_selfguided_restoration_c(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-void av1_selfguided_restoration_sse4_1(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-void av1_selfguided_restoration_avx2(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-RTCD_EXTERN void (*av1_selfguided_restoration)(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_c(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_sse4_1(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_avx2(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+RTCD_EXTERN int (*av1_selfguided_restoration)(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
 
 void av1_upsample_intra_edge_c(uint8_t *p, int sz);
 void av1_upsample_intra_edge_sse4_1(uint8_t *p, int sz);
@@ -398,7 +427,7 @@ cfl_subtract_average_fn get_subtract_average_fn_sse2(TX_SIZE tx_size);
 cfl_subtract_average_fn get_subtract_average_fn_avx2(TX_SIZE tx_size);
 RTCD_EXTERN cfl_subtract_average_fn (*get_subtract_average_fn)(TX_SIZE tx_size);
 
-void aom_rtcd(void);
+void av1_rtcd(void);
 
 #ifdef RTCD_C
 #include "aom_ports/x86.h"
@@ -413,8 +442,10 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_AVX2) apply_selfguided_restoration = apply_selfguided_restoration_avx2;
     av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_c;
     if (flags & HAS_SSE4_1) av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_sse4_1;
+    if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_avx2;
     av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_c;
     if (flags & HAS_SSE4_1) av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_sse4_1;
+    if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_avx2;
     av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_c;
     if (flags & HAS_SSSE3) av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_ssse3;
     if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_avx2;
@@ -451,6 +482,22 @@ static void setup_rtcd_internal(void)
     av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_c;
     if (flags & HAS_SSSE3) av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_ssse3;
     if (flags & HAS_AVX2) av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_avx2;
+    av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_sse4_1;
+    if (flags & HAS_AVX2) av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_avx2;
+    av1_highbd_inv_txfm_add_16x16 = av1_highbd_inv_txfm_add_16x16_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_16x16 = av1_highbd_inv_txfm_add_16x16_sse4_1;
+    av1_highbd_inv_txfm_add_16x8 = av1_highbd_inv_txfm_add_16x8_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_16x8 = av1_highbd_inv_txfm_add_16x8_sse4_1;
+    av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_sse4_1;
+    if (flags & HAS_AVX2) av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_avx2;
+    av1_highbd_inv_txfm_add_4x4 = av1_highbd_inv_txfm_add_4x4_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_4x4 = av1_highbd_inv_txfm_add_4x4_sse4_1;
+    av1_highbd_inv_txfm_add_8x16 = av1_highbd_inv_txfm_add_8x16_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_8x16 = av1_highbd_inv_txfm_add_8x16_sse4_1;
+    av1_highbd_inv_txfm_add_8x8 = av1_highbd_inv_txfm_add_8x8_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_8x8 = av1_highbd_inv_txfm_add_8x8_sse4_1;
     av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_c;
     if (flags & HAS_SSE4_1) av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_sse4_1;
     if (flags & HAS_AVX2) av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_avx2;
@@ -468,14 +515,8 @@ static void setup_rtcd_internal(void)
     av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_c;
     if (flags & HAS_SSSE3) av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_ssse3;
     if (flags & HAS_AVX2) av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_avx2;
-    av1_inv_txfm2d_add_16x16 = av1_inv_txfm2d_add_16x16_c;
-    if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_16x16 = av1_inv_txfm2d_add_16x16_sse4_1;
-    av1_inv_txfm2d_add_32x32 = av1_inv_txfm2d_add_32x32_c;
-    if (flags & HAS_AVX2) av1_inv_txfm2d_add_32x32 = av1_inv_txfm2d_add_32x32_avx2;
     av1_inv_txfm2d_add_4x4 = av1_inv_txfm2d_add_4x4_c;
     if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_4x4 = av1_inv_txfm2d_add_4x4_sse4_1;
-    av1_inv_txfm2d_add_64x64 = av1_inv_txfm2d_add_64x64_c;
-    if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_64x64 = av1_inv_txfm2d_add_64x64_sse4_1;
     av1_inv_txfm2d_add_8x8 = av1_inv_txfm2d_add_8x8_c;
     if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_8x8 = av1_inv_txfm2d_add_8x8_sse4_1;
     av1_inv_txfm_add = av1_inv_txfm_add_c;

media/libaom/config/win/x64/config/aom_config.asm

@@ -14,6 +14,7 @@ ARCH_MIPS equ 0
 ARCH_PPC equ 0
 ARCH_X86 equ 0
 ARCH_X86_64 equ 1
+CONFIG_2PASS_PARTITION_SEARCH_LVL equ 1
 CONFIG_ACCOUNTING equ 0
 CONFIG_ANALYZER equ 0
 CONFIG_AV1_DECODER equ 1
@@ -21,30 +22,35 @@ CONFIG_AV1_ENCODER equ 0
 CONFIG_BIG_ENDIAN equ 0
 CONFIG_BITSTREAM_DEBUG equ 0
 CONFIG_COEFFICIENT_RANGE_CHECKING equ 0
-CONFIG_COLLECT_INTER_MODE_RD_STATS equ 1
+CONFIG_COLLECT_INTER_MODE_RD_STATS equ 0
 CONFIG_COLLECT_RD_STATS equ 0
 CONFIG_DEBUG equ 0
-CONFIG_DENOISE equ 0
-CONFIG_DIST_8X8 equ 1
+CONFIG_DENOISE equ 1
+CONFIG_DIST_8X8 equ 0
 CONFIG_ENTROPY_STATS equ 0
 CONFIG_FILEOPTIONS equ 1
+CONFIG_FIX_GF_LENGTH equ 1
 CONFIG_FP_MB_STATS equ 0
 CONFIG_GCC equ 1
 CONFIG_GCOV equ 0
+CONFIG_GLOBAL_MOTION_SEARCH equ 1
 CONFIG_GPROF equ 0
 CONFIG_INSPECTION equ 0
 CONFIG_INTERNAL_STATS equ 0
 CONFIG_INTER_STATS_ONLY equ 0
 CONFIG_LIBYUV equ 0
-CONFIG_LOWBITDEPTH equ 0
+CONFIG_LOWBITDEPTH equ 1
+CONFIG_MAX_DECODE_PROFILE equ 2
 CONFIG_MISMATCH_DEBUG equ 0
-CONFIG_MSVS equ 1
 CONFIG_MULTITHREAD equ 1
+CONFIG_NORMAL_TILE_MODE equ 0
 CONFIG_OS_SUPPORT equ 1
 CONFIG_PIC equ 0
 CONFIG_RD_DEBUG equ 0
+CONFIG_REDUCED_ENCODER_BORDER equ 0
 CONFIG_RUNTIME_CPU_DETECT equ 1
 CONFIG_SHARED equ 0
+CONFIG_SHARP_SETTINGS equ 0
 CONFIG_SIZE_LIMIT equ 0
 CONFIG_SPATIAL_RESAMPLING equ 1
 CONFIG_STATIC equ 1

media/libaom/config/win/x64/config/aom_config.h

@@ -16,6 +16,7 @@
 #define ARCH_PPC 0
 #define ARCH_X86 0
 #define ARCH_X86_64 1
+#define CONFIG_2PASS_PARTITION_SEARCH_LVL 1
 #define CONFIG_ACCOUNTING 0
 #define CONFIG_ANALYZER 0
 #define CONFIG_AV1_DECODER 1
@@ -23,30 +24,35 @@
 #define CONFIG_BIG_ENDIAN 0
 #define CONFIG_BITSTREAM_DEBUG 0
 #define CONFIG_COEFFICIENT_RANGE_CHECKING 0
-#define CONFIG_COLLECT_INTER_MODE_RD_STATS 1
+#define CONFIG_COLLECT_INTER_MODE_RD_STATS 0
 #define CONFIG_COLLECT_RD_STATS 0
 #define CONFIG_DEBUG 0
-#define CONFIG_DENOISE 0
-#define CONFIG_DIST_8X8 1
+#define CONFIG_DENOISE 1
+#define CONFIG_DIST_8X8 0
 #define CONFIG_ENTROPY_STATS 0
 #define CONFIG_FILEOPTIONS 1
+#define CONFIG_FIX_GF_LENGTH 1
 #define CONFIG_FP_MB_STATS 0
 #define CONFIG_GCC 1
 #define CONFIG_GCOV 0
+#define CONFIG_GLOBAL_MOTION_SEARCH 1
 #define CONFIG_GPROF 0
 #define CONFIG_INSPECTION 0
 #define CONFIG_INTERNAL_STATS 0
 #define CONFIG_INTER_STATS_ONLY 0
 #define CONFIG_LIBYUV 0
-#define CONFIG_LOWBITDEPTH 0
+#define CONFIG_LOWBITDEPTH 1
+#define CONFIG_MAX_DECODE_PROFILE 2
 #define CONFIG_MISMATCH_DEBUG 0
-#define CONFIG_MSVS 1
 #define CONFIG_MULTITHREAD 1
+#define CONFIG_NORMAL_TILE_MODE 0
 #define CONFIG_OS_SUPPORT 1
 #define CONFIG_PIC 0
 #define CONFIG_RD_DEBUG 0
+#define CONFIG_REDUCED_ENCODER_BORDER 0
 #define CONFIG_RUNTIME_CPU_DETECT 1
 #define CONFIG_SHARED 0
+#define CONFIG_SHARP_SETTINGS 0
 #define CONFIG_SIZE_LIMIT 0
 #define CONFIG_SPATIAL_RESAMPLING 1
 #define CONFIG_STATIC 1

media/libaom/config/win/x64/config/aom_dsp_rtcd.h

@@ -28,6 +28,7 @@ RTCD_EXTERN void (*aom_blend_a64_hmask)(uint8_t *dst, uint32_t dst_stride, const
 
 void aom_blend_a64_mask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 void aom_blend_a64_mask_sse4_1(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
+void aom_blend_a64_mask_avx2(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 RTCD_EXTERN void (*aom_blend_a64_mask)(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby);
 
 void aom_blend_a64_vmask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int w, int h);
@@ -1232,6 +1233,7 @@ void aom_highbd_v_predictor_8x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const ui
 
 void aom_lowbd_blend_a64_d16_mask_c(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 void aom_lowbd_blend_a64_d16_mask_sse4_1(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
+void aom_lowbd_blend_a64_d16_mask_avx2(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 RTCD_EXTERN void (*aom_lowbd_blend_a64_d16_mask)(uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params);
 
 void aom_lpf_horizontal_14_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh);
@@ -1727,6 +1729,7 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_SSE4_1) aom_blend_a64_hmask = aom_blend_a64_hmask_sse4_1;
     aom_blend_a64_mask = aom_blend_a64_mask_c;
     if (flags & HAS_SSE4_1) aom_blend_a64_mask = aom_blend_a64_mask_sse4_1;
+    if (flags & HAS_AVX2) aom_blend_a64_mask = aom_blend_a64_mask_avx2;
     aom_blend_a64_vmask = aom_blend_a64_vmask_c;
     if (flags & HAS_SSE4_1) aom_blend_a64_vmask = aom_blend_a64_vmask_sse4_1;
     aom_convolve8_horiz = aom_convolve8_horiz_sse2;
@@ -1811,6 +1814,7 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_AVX2) aom_highbd_lpf_vertical_8_dual = aom_highbd_lpf_vertical_8_dual_avx2;
     aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_c;
     if (flags & HAS_SSE4_1) aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_sse4_1;
+    if (flags & HAS_AVX2) aom_lowbd_blend_a64_d16_mask = aom_lowbd_blend_a64_d16_mask_avx2;
     aom_paeth_predictor_16x16 = aom_paeth_predictor_16x16_c;
     if (flags & HAS_SSSE3) aom_paeth_predictor_16x16 = aom_paeth_predictor_16x16_ssse3;
     if (flags & HAS_AVX2) aom_paeth_predictor_16x16 = aom_paeth_predictor_16x16_avx2;

media/libaom/config/win/x64/config/av1_rtcd.h

@@ -1,6 +1,6 @@
 // This file is generated. Do not edit.
-#ifndef AOM_RTCD_H_
-#define AOM_RTCD_H_
+#ifndef AV1_RTCD_H_
+#define AV1_RTCD_H_
 
 #ifdef RTCD_C
 #define RTCD_EXTERN
@@ -58,10 +58,12 @@ RTCD_EXTERN void (*apply_selfguided_restoration)(const uint8_t *dat, int width,
 
 void av1_build_compound_diffwtd_mask_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 void av1_build_compound_diffwtd_mask_sse4_1(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
+void av1_build_compound_diffwtd_mask_avx2(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 RTCD_EXTERN void (*av1_build_compound_diffwtd_mask)(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w);
 
 void av1_build_compound_diffwtd_mask_d16_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 void av1_build_compound_diffwtd_mask_d16_sse4_1(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
+void av1_build_compound_diffwtd_mask_d16_avx2(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 RTCD_EXTERN void (*av1_build_compound_diffwtd_mask_d16)(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const CONV_BUF_TYPE *src0, int src0_stride, const CONV_BUF_TYPE *src1, int src1_stride, int h, int w, ConvolveParams *conv_params, int bd);
 
 void av1_build_compound_diffwtd_mask_highbd_c(uint8_t *mask, DIFFWTD_MASK_TYPE mask_type, const uint8_t *src0, int src0_stride, const uint8_t *src1, int src1_stride, int h, int w, int bd);
@@ -173,6 +175,36 @@ void av1_highbd_dr_prediction_z2_c(uint16_t *dst, ptrdiff_t stride, int bw, int
 void av1_highbd_dr_prediction_z3_c(uint16_t *dst, ptrdiff_t stride, int bw, int bh, const uint16_t *above, const uint16_t *left, int upsample_left, int dx, int dy, int bd);
 #define av1_highbd_dr_prediction_z3 av1_highbd_dr_prediction_z3_c
 
+void av1_highbd_inv_txfm_add_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_avx2(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_16x16_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_16x16_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_16x16)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_16x8_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_16x8_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_16x8)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_32x32_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_32x32_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_32x32_avx2(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_32x32)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_4x4_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_4x4_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_4x4)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_8x16_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_8x16_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_8x16)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
+void av1_highbd_inv_txfm_add_8x8_c(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+void av1_highbd_inv_txfm_add_8x8_sse4_1(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+RTCD_EXTERN void (*av1_highbd_inv_txfm_add_8x8)(const tran_low_t *dqcoeff, uint8_t *dst, int stride, const TxfmParam *txfm_param);
+
 void av1_highbd_iwht4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, int bd);
 #define av1_highbd_iwht4x4_16_add av1_highbd_iwht4x4_16_add_c
 
@@ -209,8 +241,7 @@ void av1_highbd_wiener_convolve_add_src_avx2(const uint8_t *src, ptrdiff_t src_s
 RTCD_EXTERN void (*av1_highbd_wiener_convolve_add_src)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, const ConvolveParams *conv_params, int bps);
 
 void av1_inv_txfm2d_add_16x16_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_16x16_sse4_1(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_16x16)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_16x16 av1_inv_txfm2d_add_16x16_c
 
 void av1_inv_txfm2d_add_16x32_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_16x32 av1_inv_txfm2d_add_16x32_c
@@ -228,8 +259,7 @@ void av1_inv_txfm2d_add_32x16_c(const int32_t *input, uint16_t *output, int stri
 #define av1_inv_txfm2d_add_32x16 av1_inv_txfm2d_add_32x16_c
 
 void av1_inv_txfm2d_add_32x32_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_32x32_avx2(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_32x32)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_32x32 av1_inv_txfm2d_add_32x32_c
 
 void av1_inv_txfm2d_add_32x64_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_32x64 av1_inv_txfm2d_add_32x64_c
@@ -254,8 +284,7 @@ void av1_inv_txfm2d_add_64x32_c(const int32_t *input, uint16_t *output, int stri
 #define av1_inv_txfm2d_add_64x32 av1_inv_txfm2d_add_64x32_c
 
 void av1_inv_txfm2d_add_64x64_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-void av1_inv_txfm2d_add_64x64_sse4_1(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
-RTCD_EXTERN void (*av1_inv_txfm2d_add_64x64)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
+#define av1_inv_txfm2d_add_64x64 av1_inv_txfm2d_add_64x64_c
 
 void av1_inv_txfm2d_add_8x16_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd);
 #define av1_inv_txfm2d_add_8x16 av1_inv_txfm2d_add_8x16_c
@@ -295,18 +324,18 @@ void av1_jnt_convolve_y_sse2(const uint8_t *src, int src_stride, uint8_t *dst, i
 void av1_jnt_convolve_y_avx2(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams *filter_params_x, const InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params);
 RTCD_EXTERN void (*av1_jnt_convolve_y)(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams *filter_params_x, const InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params);
 
-void av1_selfguided_restoration_c(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-void av1_selfguided_restoration_sse4_1(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-void av1_selfguided_restoration_avx2(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
-RTCD_EXTERN void (*av1_selfguided_restoration)(const uint8_t *dgd8, int width, int height,
-                                  int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
-                                  int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_c(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_sse4_1(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+int av1_selfguided_restoration_avx2(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
+RTCD_EXTERN int (*av1_selfguided_restoration)(const uint8_t *dgd8, int width, int height,
+                                 int dgd_stride, int32_t *flt0, int32_t *flt1, int flt_stride,
+                                 int sgr_params_idx, int bit_depth, int highbd);
 
 void av1_upsample_intra_edge_c(uint8_t *p, int sz);
 void av1_upsample_intra_edge_sse4_1(uint8_t *p, int sz);
@@ -398,7 +427,7 @@ cfl_subtract_average_fn get_subtract_average_fn_sse2(TX_SIZE tx_size);
 cfl_subtract_average_fn get_subtract_average_fn_avx2(TX_SIZE tx_size);
 RTCD_EXTERN cfl_subtract_average_fn (*get_subtract_average_fn)(TX_SIZE tx_size);
 
-void aom_rtcd(void);
+void av1_rtcd(void);
 
 #ifdef RTCD_C
 #include "aom_ports/x86.h"
@@ -413,8 +442,10 @@ static void setup_rtcd_internal(void)
     if (flags & HAS_AVX2) apply_selfguided_restoration = apply_selfguided_restoration_avx2;
     av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_c;
     if (flags & HAS_SSE4_1) av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_sse4_1;
+    if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask = av1_build_compound_diffwtd_mask_avx2;
     av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_c;
     if (flags & HAS_SSE4_1) av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_sse4_1;
+    if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask_d16 = av1_build_compound_diffwtd_mask_d16_avx2;
     av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_c;
     if (flags & HAS_SSSE3) av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_ssse3;
     if (flags & HAS_AVX2) av1_build_compound_diffwtd_mask_highbd = av1_build_compound_diffwtd_mask_highbd_avx2;
@@ -451,6 +482,22 @@ static void setup_rtcd_internal(void)
     av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_c;
     if (flags & HAS_SSSE3) av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_ssse3;
     if (flags & HAS_AVX2) av1_highbd_convolve_y_sr = av1_highbd_convolve_y_sr_avx2;
+    av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_sse4_1;
+    if (flags & HAS_AVX2) av1_highbd_inv_txfm_add = av1_highbd_inv_txfm_add_avx2;
+    av1_highbd_inv_txfm_add_16x16 = av1_highbd_inv_txfm_add_16x16_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_16x16 = av1_highbd_inv_txfm_add_16x16_sse4_1;
+    av1_highbd_inv_txfm_add_16x8 = av1_highbd_inv_txfm_add_16x8_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_16x8 = av1_highbd_inv_txfm_add_16x8_sse4_1;
+    av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_sse4_1;
+    if (flags & HAS_AVX2) av1_highbd_inv_txfm_add_32x32 = av1_highbd_inv_txfm_add_32x32_avx2;
+    av1_highbd_inv_txfm_add_4x4 = av1_highbd_inv_txfm_add_4x4_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_4x4 = av1_highbd_inv_txfm_add_4x4_sse4_1;
+    av1_highbd_inv_txfm_add_8x16 = av1_highbd_inv_txfm_add_8x16_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_8x16 = av1_highbd_inv_txfm_add_8x16_sse4_1;
+    av1_highbd_inv_txfm_add_8x8 = av1_highbd_inv_txfm_add_8x8_c;
+    if (flags & HAS_SSE4_1) av1_highbd_inv_txfm_add_8x8 = av1_highbd_inv_txfm_add_8x8_sse4_1;
     av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_c;
     if (flags & HAS_SSE4_1) av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_sse4_1;
     if (flags & HAS_AVX2) av1_highbd_jnt_convolve_2d = av1_highbd_jnt_convolve_2d_avx2;
@@ -468,14 +515,8 @@ static void setup_rtcd_internal(void)
     av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_c;
     if (flags & HAS_SSSE3) av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_ssse3;
     if (flags & HAS_AVX2) av1_highbd_wiener_convolve_add_src = av1_highbd_wiener_convolve_add_src_avx2;
-    av1_inv_txfm2d_add_16x16 = av1_inv_txfm2d_add_16x16_c;
-    if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_16x16 = av1_inv_txfm2d_add_16x16_sse4_1;
-    av1_inv_txfm2d_add_32x32 = av1_inv_txfm2d_add_32x32_c;
-    if (flags & HAS_AVX2) av1_inv_txfm2d_add_32x32 = av1_inv_txfm2d_add_32x32_avx2;
     av1_inv_txfm2d_add_4x4 = av1_inv_txfm2d_add_4x4_c;
     if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_4x4 = av1_inv_txfm2d_add_4x4_sse4_1;
-    av1_inv_txfm2d_add_64x64 = av1_inv_txfm2d_add_64x64_c;
-    if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_64x64 = av1_inv_txfm2d_add_64x64_sse4_1;
     av1_inv_txfm2d_add_8x8 = av1_inv_txfm2d_add_8x8_c;
     if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_8x8 = av1_inv_txfm2d_add_8x8_sse4_1;
     av1_inv_txfm_add = av1_inv_txfm_add_c;

media/libaom/sources.mozbuild

@@ -36,6 +36,7 @@ files = {
     '../../third_party/aom/aom_dsp/arm/subtract_neon.c',
     '../../third_party/aom/aom_dsp/binary_codes_reader.c',
     '../../third_party/aom/aom_dsp/bitreader_buffer.c',
+    '../../third_party/aom/aom_dsp/bitwriter_buffer.c',
     '../../third_party/aom/aom_dsp/blend_a64_hmask.c',
     '../../third_party/aom/aom_dsp/blend_a64_mask.c',
     '../../third_party/aom/aom_dsp/blend_a64_vmask.c',
@@ -67,6 +68,7 @@ files = {
     '../../third_party/aom/av1/common/arm/jnt_convolve_neon.c',
     '../../third_party/aom/av1/common/arm/reconinter_neon.c',
     '../../third_party/aom/av1/common/arm/selfguided_neon.c',
+    '../../third_party/aom/av1/common/arm/warp_plane_neon.c',
     '../../third_party/aom/av1/common/arm/wiener_convolve_neon.c',
     '../../third_party/aom/av1/common/av1_inv_txfm1d.c',
     '../../third_party/aom/av1/common/av1_inv_txfm2d.c',
@@ -86,6 +88,7 @@ files = {
     '../../third_party/aom/av1/common/frame_buffers.c',
     '../../third_party/aom/av1/common/idct.c',
     '../../third_party/aom/av1/common/mvref_common.c',
+    '../../third_party/aom/av1/common/obu_util.c',
     '../../third_party/aom/av1/common/odintrin.c',
     '../../third_party/aom/av1/common/pred_common.c',
     '../../third_party/aom/av1/common/quant_common.c',
@@ -139,6 +142,7 @@ files = {
     '../../third_party/aom/aom_dsp/aom_dsp_rtcd.c',
     '../../third_party/aom/aom_dsp/binary_codes_reader.c',
     '../../third_party/aom/aom_dsp/bitreader_buffer.c',
+    '../../third_party/aom/aom_dsp/bitwriter_buffer.c',
     '../../third_party/aom/aom_dsp/blend_a64_hmask.c',
     '../../third_party/aom/aom_dsp/blend_a64_mask.c',
     '../../third_party/aom/aom_dsp/blend_a64_vmask.c',
@@ -177,6 +181,7 @@ files = {
     '../../third_party/aom/av1/common/frame_buffers.c',
     '../../third_party/aom/av1/common/idct.c',
     '../../third_party/aom/av1/common/mvref_common.c',
+    '../../third_party/aom/av1/common/obu_util.c',
     '../../third_party/aom/av1/common/odintrin.c',
     '../../third_party/aom/av1/common/pred_common.c',
     '../../third_party/aom/av1/common/quant_common.c',
@@ -229,6 +234,7 @@ files = {
     '../../third_party/aom/aom_dsp/aom_dsp_rtcd.c',
     '../../third_party/aom/aom_dsp/binary_codes_reader.c',
     '../../third_party/aom/aom_dsp/bitreader_buffer.c',
+    '../../third_party/aom/aom_dsp/bitwriter_buffer.c',
     '../../third_party/aom/aom_dsp/blend_a64_hmask.c',
     '../../third_party/aom/aom_dsp/blend_a64_mask.c',
     '../../third_party/aom/aom_dsp/blend_a64_vmask.c',
@@ -251,6 +257,7 @@ files = {
     '../../third_party/aom/aom_dsp/x86/aom_subpixel_bilinear_sse2.asm',
     '../../third_party/aom/aom_dsp/x86/aom_subpixel_bilinear_ssse3.asm',
     '../../third_party/aom/aom_dsp/x86/blend_a64_hmask_sse4.c',
+    '../../third_party/aom/aom_dsp/x86/blend_a64_mask_avx2.c',
     '../../third_party/aom/aom_dsp/x86/blend_a64_mask_sse4.c',
     '../../third_party/aom/aom_dsp/x86/blend_a64_vmask_sse4.c',
     '../../third_party/aom/aom_dsp/x86/fft_avx2.c',
@@ -300,6 +307,7 @@ files = {
     '../../third_party/aom/av1/common/frame_buffers.c',
     '../../third_party/aom/av1/common/idct.c',
     '../../third_party/aom/av1/common/mvref_common.c',
+    '../../third_party/aom/av1/common/obu_util.c',
     '../../third_party/aom/av1/common/odintrin.c',
     '../../third_party/aom/av1/common/pred_common.c',
     '../../third_party/aom/av1/common/quant_common.c',
@@ -389,6 +397,7 @@ files = {
     '../../third_party/aom/aom_dsp/aom_dsp_rtcd.c',
     '../../third_party/aom/aom_dsp/binary_codes_reader.c',
     '../../third_party/aom/aom_dsp/bitreader_buffer.c',
+    '../../third_party/aom/aom_dsp/bitwriter_buffer.c',
     '../../third_party/aom/aom_dsp/blend_a64_hmask.c',
     '../../third_party/aom/aom_dsp/blend_a64_mask.c',
     '../../third_party/aom/aom_dsp/blend_a64_vmask.c',
@@ -411,6 +420,7 @@ files = {
     '../../third_party/aom/aom_dsp/x86/aom_subpixel_bilinear_sse2.asm',
     '../../third_party/aom/aom_dsp/x86/aom_subpixel_bilinear_ssse3.asm',
     '../../third_party/aom/aom_dsp/x86/blend_a64_hmask_sse4.c',
+    '../../third_party/aom/aom_dsp/x86/blend_a64_mask_avx2.c',
     '../../third_party/aom/aom_dsp/x86/blend_a64_mask_sse4.c',
     '../../third_party/aom/aom_dsp/x86/blend_a64_vmask_sse4.c',
     '../../third_party/aom/aom_dsp/x86/fft_avx2.c',
@@ -459,6 +469,7 @@ files = {
     '../../third_party/aom/av1/common/frame_buffers.c',
     '../../third_party/aom/av1/common/idct.c',
     '../../third_party/aom/av1/common/mvref_common.c',
+    '../../third_party/aom/av1/common/obu_util.c',
     '../../third_party/aom/av1/common/odintrin.c',
     '../../third_party/aom/av1/common/pred_common.c',
     '../../third_party/aom/av1/common/quant_common.c',

third_party/aom/CMakeLists.txt

@@ -18,45 +18,6 @@ if(NOT EMSCRIPTEN)
   endif()
 endif()
 
-option(ENABLE_CCACHE "Enable ccache support." OFF)
-option(ENABLE_DECODE_PERF_TESTS "Enables decoder performance tests" OFF)
-option(ENABLE_DISTCC "Enable distcc support." OFF)
-option(ENABLE_DOCS "Enable documentation generation (doxygen required)." ON)
-option(ENABLE_ENCODE_PERF_TESTS "Enables encoder performance tests" OFF)
-option(ENABLE_EXAMPLES "Enables build of example code." ON)
-option(ENABLE_GOMA "Enable goma support." OFF)
-option(ENABLE_IDE_TEST_HOSTING
-       "Enables running tests within IDEs like Visual Studio and Xcode." OFF)
-option(ENABLE_NASM "Use nasm instead of yasm for x86 assembly." OFF)
-option(ENABLE_TESTDATA "Enables unit test data download targets." ON)
-option(ENABLE_TESTS "Enables unit tests." ON)
-option(ENABLE_TOOLS "Enable applications in tools sub directory." ON)
-option(ENABLE_WERROR "Converts warnings to errors at compile time." OFF)
-
-# ARM assembly/intrinsics flags.
-option(ENABLE_NEON "Enables NEON optimizations on ARM targets." ON)
-
-# MIPS assembly/intrinsics flags.
-option(ENABLE_DSPR2 "Enables DSPR2 optimizations on MIPS targets." OFF)
-option(ENABLE_MSA "Enables MSA optimizations on MIPS targets." OFF)
-
-# VSX intrinsics flags.
-option(ENABLE_VSX "Enables VSX optimizations on PowerPC targets." ON)
-
-# x86/x86_64 assembly/intrinsics flags.
-option(ENABLE_MMX "Enables MMX optimizations on x86/x86_64 targets." ON)
-option(ENABLE_SSE "Enables SSE optimizations on x86/x86_64 targets." ON)
-option(ENABLE_SSE2 "Enables SSE2 optimizations on x86/x86_64 targets." ON)
-option(ENABLE_SSE3 "Enables SSE3 optimizations on x86/x86_64 targets." ON)
-option(ENABLE_SSSE3 "Enables SSSE3 optimizations on x86/x86_64 targets." ON)
-option(ENABLE_SSE4_1 "Enables SSE4_1 optimizations on x86/x86_64 targets." ON)
-option(ENABLE_SSE4_2 "Enables SSE4_2 optimizations on x86/x86_64 targets." ON)
-option(ENABLE_AVX "Enables AVX optimizations on x86/x86_64 targets." ON)
-option(ENABLE_AVX2 "Enables AVX2 optimizations on x86/x86_64 targets." ON)
-
-# $BUILD_SHARED_LIBS is a CMake built-in-- it's listed here for visibility.
-option(BUILD_SHARED_LIBS "CMake should generate a shared library build." OFF)
-
 project(AOM C CXX)
 
 set(AOM_ROOT "${CMAKE_CURRENT_SOURCE_DIR}")
@@ -95,7 +56,7 @@ list(APPEND AOM_RTCD_SOURCES
             "${AOM_ROOT}/aom_scale/aom_scale_rtcd.c"
             "${AOM_ROOT}/av1/common/av1_rtcd_defs.pl"
             "${AOM_ROOT}/av1/common/av1_rtcd.c"
-            "${AOM_ROOT}/build/make/rtcd.pl")
+            "${AOM_ROOT}/build/cmake/rtcd.pl")
 
 list(APPEND AOM_LIBWEBM_SOURCES
             "${AOM_ROOT}/third_party/libwebm/common/hdr_util.cc"
@@ -161,12 +122,19 @@ list(APPEND AOM_SOURCES
             "${AOM_ROOT}/aom/src/aom_image.c"
             "${AOM_ROOT}/aom/src/aom_integer.c")
 
-list(APPEND AOM_COMMON_APP_UTIL_SOURCES "${AOM_ROOT}/common/args.c"
-            "${AOM_ROOT}/common/args.h" "${AOM_ROOT}/common/md5_utils.c"
+list(APPEND AOM_COMMON_APP_UTIL_SOURCES
+            "${AOM_ROOT}/common/args.c"
+            "${AOM_ROOT}/common/args.h"
+            "${AOM_ROOT}/common/av1_config.c"
+            "${AOM_ROOT}/common/av1_config.h"
+            "${AOM_ROOT}/common/md5_utils.c"
             "${AOM_ROOT}/common/md5_utils.h"
             "${AOM_ROOT}/common/tools_common.c"
             "${AOM_ROOT}/common/tools_common.h"
-            "${AOM_ROOT}/common/video_common.h" "${AOM_ROOT}/common/y4menc.c"
+            "${AOM_ROOT}/common/video_common.h"
+            "${AOM_ROOT}/common/rawenc.c"
+            "${AOM_ROOT}/common/rawenc.h"
+            "${AOM_ROOT}/common/y4menc.c"
             "${AOM_ROOT}/common/y4menc.h")
 
 list(APPEND AOM_DECODER_APP_UTIL_SOURCES "${AOM_ROOT}/common/ivfdec.c"
@@ -255,10 +223,10 @@ add_rtcd_build_step("${AOM_ROOT}/av1/common/av1_rtcd_defs.pl"
 add_library(aom_rtcd OBJECT ${AOM_RTCD_SOURCES})
 add_dependencies(aom_rtcd aom_version)
 
-if (ENABLE_EXAMPLES)
-add_library(aom_encoder_stats OBJECT ${AOM_ENCODER_STATS_SOURCES})
-endif ()
-
+if(ENABLE_EXAMPLES)
+  add_library(aom_encoder_stats OBJECT ${AOM_ENCODER_STATS_SOURCES})
+  set(AOM_LIB_TARGETS ${AOM_LIB_TARGETS} aom_encoder_stats)
+endif()
 add_library(aom ${AOM_SOURCES} $<TARGET_OBJECTS:aom_rtcd>)
 
 if(NOT MSVC AND NOT APPLE)
@@ -288,8 +256,8 @@ endforeach()
 # aom_common_app_util library must define this function. This is a convenience
 # to allow omission of the function from applications that might want to use
 # other pieces of the util support without defining usage_exit().
-file(WRITE "${AOM_CONFIG_DIR}/usage_exit.c" "void usage_exit(void) {}")
-file(WRITE "${AOM_CONFIG_DIR}/usage_exit.cc"
+file(WRITE "${AOM_GEN_SRC_DIR}/usage_exit.c" "void usage_exit(void) {}")
+file(WRITE "${AOM_GEN_SRC_DIR}/usage_exit.cc"
            "extern \"C\" void usage_exit(void) {}")
 
 #
@@ -349,6 +317,8 @@ if(CONFIG_AV1_DECODER AND ENABLE_EXAMPLES)
       add_preproc_definition(_POSIX_SOURCE)
       append_link_flag_to_target("inspect" "-s TOTAL_MEMORY=402653184")
       append_link_flag_to_target("inspect" "-s MODULARIZE=1")
+      append_link_flag_to_target(
+        "inspect" "-s \'EXTRA_EXPORTED_RUNTIME_METHODS=[\"UTF8ToString\"]\'")
       append_link_flag_to_target("inspect"
                                  "-s EXPORT_NAME=\"\'DecoderModule\'\"")
       append_link_flag_to_target("inspect" "--memory-init-file 0")
@@ -407,7 +377,7 @@ if(CONFIG_AV1_ENCODER)
       # TODO(tomfinegan): Sort out why a simple link command with
       # aom_entropy_optimizer.c won't work on macos, but dragging in all the
       # helper machinery allows the link to succeed.
-      add_executable(aom_entropy_optimizer "${AOM_CONFIG_DIR}/usage_exit.c"
+      add_executable(aom_entropy_optimizer "${AOM_GEN_SRC_DIR}/usage_exit.c"
                      "${AOM_ROOT}/tools/aom_entropy_optimizer.c"
                      $<TARGET_OBJECTS:aom_common_app_util>
                      $<TARGET_OBJECTS:aom_encoder_app_util>)
@@ -434,7 +404,7 @@ endif()
 if(ENABLE_TOOLS)
   if(CONFIG_AV1_DECODER)
     require_cxx_flag_nomsvc("-std=c++11" NO)
-    add_executable(dump_obu "${AOM_CONFIG_DIR}/usage_exit.cc"
+    add_executable(dump_obu "${AOM_GEN_SRC_DIR}/usage_exit.cc"
                    "${AOM_ROOT}/tools/dump_obu.cc"
                    "${AOM_ROOT}/tools/obu_parser.cc"
                    "${AOM_ROOT}/tools/obu_parser.h"
@@ -555,9 +525,7 @@ endif()
 
 if(HAVE_PTHREAD_H AND CONFIG_MULTITHREAD)
   find_package(Threads)
-  foreach(app_target ${AOM_APP_TARGETS})
-    target_link_libraries(${app_target} ${AOM_LIB_LINK_TYPE} Threads::Threads)
-  endforeach()
+  target_link_libraries(aom ${AOM_LIB_LINK_TYPE} Threads::Threads)
 endif()
 
 if(XCODE)

third_party/aom/README.md

@@ -414,6 +414,16 @@ First, add the new test data file to the `aom-test-data` bucket of the
 `aomedia-testing` project on Google Cloud Platform. You may need to ask someone
 with the necessary access permissions to do this for you.
 
+NOTE: When a new test data file is added to the `aom-test-data` bucket, its
+"Public access" is initially "Not public". We need to change its
+"Public access" to "Public" by using the following
+[`gsutil`](https://cloud.google.com/storage/docs/gsutil_install) command:
+~~~
+    $ gsutil acl ch -g all:R gs://aom-test-data/test-data-file-name
+~~~
+This command grants the `AllUsers` group READ access to the file named
+"test-data-file-name" in the `aom-test-data` bucket.
+
 Once the new test data file has been added to `aom-test-data`, create a CL to
 add the name of the new test data file to `test/test_data_util.cmake` and add
 the SHA1 checksum of the new test data file to `test/test-data.sha1`. (The SHA1

third_party/aom/aom/aom.h

@@ -28,8 +28,8 @@
 /*!\file
  * \brief Provides controls common to both the AOM encoder and decoder.
  */
-#ifndef AOM_AOM_H_
-#define AOM_AOM_H_
+#ifndef AOM_AOM_AOM_H_
+#define AOM_AOM_AOM_H_
 
 #include "aom/aom_codec.h"
 #include "aom/aom_image.h"
@@ -144,4 +144,4 @@ AOM_CTRL_USE_TYPE(AV1_COPY_NEW_FRAME_IMAGE, aom_image_t *)
 }  // extern "C"
 #endif
 
-#endif  // AOM_AOM_H_
+#endif  // AOM_AOM_AOM_H_

third_party/aom/aom/aom_codec.h

@@ -33,11 +33,11 @@
  *       }
  *     </pre>
  *
- * Once initialized, the instance is manged using other functions from
+ * Once initialized, the instance is managed using other functions from
  * the aom_codec_* family.
  */
-#ifndef AOM_AOM_CODEC_H_
-#define AOM_AOM_CODEC_H_
+#ifndef AOM_AOM_AOM_CODEC_H_
+#define AOM_AOM_AOM_CODEC_H_
 
 #ifdef __cplusplus
 extern "C" {
@@ -259,12 +259,6 @@ typedef enum aom_superblock_size {
  *
  */
 int aom_codec_version(void);
-#define AOM_VERSION_MAJOR(v) \
-  ((v >> 16) & 0xff) /**< extract major from packed version */
-#define AOM_VERSION_MINOR(v) \
-  ((v >> 8) & 0xff) /**< extract minor from packed version */
-#define AOM_VERSION_PATCH(v) \
-  ((v >> 0) & 0xff) /**< extract patch from packed version */
 
 /*!\brief Return the version major number */
 #define aom_codec_version_major() ((aom_codec_version() >> 16) & 0xff)
@@ -526,4 +520,4 @@ typedef struct cfg_options {
 #ifdef __cplusplus
 }
 #endif
-#endif  // AOM_AOM_CODEC_H_
+#endif  // AOM_AOM_AOM_CODEC_H_

third_party/aom/aom/aom_decoder.h

@@ -8,8 +8,8 @@
  * Media Patent License 1.0 was not distributed with this source code in the
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
-#ifndef AOM_AOM_DECODER_H_
-#define AOM_AOM_DECODER_H_
+#ifndef AOM_AOM_AOM_DECODER_H_
+#define AOM_AOM_AOM_DECODER_H_
 
 /*!\defgroup decoder Decoder Algorithm Interface
  * \ingroup codec
@@ -361,4 +361,4 @@ aom_codec_err_t aom_codec_set_frame_buffer_functions(
 #ifdef __cplusplus
 }
 #endif
-#endif  // AOM_AOM_DECODER_H_
+#endif  // AOM_AOM_AOM_DECODER_H_

third_party/aom/aom/aom_encoder.h

@@ -8,8 +8,8 @@
  * Media Patent License 1.0 was not distributed with this source code in the
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
-#ifndef AOM_AOM_ENCODER_H_
-#define AOM_AOM_ENCODER_H_
+#ifndef AOM_AOM_AOM_ENCODER_H_
+#define AOM_AOM_AOM_ENCODER_H_
 
 /*!\defgroup encoder Encoder Algorithm Interface
  * \ingroup codec
@@ -54,13 +54,6 @@ extern "C" {
  */
 #define AOM_CODEC_CAP_PSNR 0x10000 /**< Can issue PSNR packets */
 
-/*! Can output one partition at a time. Each partition is returned in its
- *  own AOM_CODEC_CX_FRAME_PKT, with the FRAME_IS_FRAGMENT flag set for
- *  every partition but the last. In this mode all frames are always
- *  returned partition by partition.
- */
-#define AOM_CODEC_CAP_OUTPUT_PARTITION 0x20000
-
 /*! Can support input images at greater than 8 bitdepth.
  */
 #define AOM_CODEC_CAP_HIGHBITDEPTH 0x40000
@@ -74,7 +67,6 @@ extern "C" {
  */
 #define AOM_CODEC_USE_PSNR 0x10000 /**< Calculate PSNR on each frame */
 /*!\brief Make the encoder output one  partition at a time. */
-#define AOM_CODEC_USE_OUTPUT_PARTITION 0x20000
 #define AOM_CODEC_USE_HIGHBITDEPTH 0x40000 /**< Use high bitdepth */
 
 /*!\brief Generic fixed size buffer structure
@@ -119,11 +111,6 @@ typedef uint32_t aom_codec_frame_flags_t;
 typedef uint32_t aom_codec_er_flags_t;
 /*!\brief Improve resiliency against losses of whole frames */
 #define AOM_ERROR_RESILIENT_DEFAULT 0x1
-/*!\brief The frame partitions are independently decodable by the bool decoder,
- * meaning that partitions can be decoded even though earlier partitions have
- * been lost. Note that intra prediction is still done over the partition
- * boundary. */
-#define AOM_ERROR_RESILIENT_PARTITIONS 0x2
 
 /*!\brief Encoder output packet variants
  *
@@ -849,13 +836,25 @@ aom_codec_err_t aom_codec_enc_config_set(aom_codec_ctx_t *ctx,
 /*!\brief Get global stream headers
  *
  * Retrieves a stream level global header packet, if supported by the codec.
+ * Calls to this function should be deferred until all configuration information
+ * has been passed to libaom. Otherwise the global header data may be
+ * invalidated by additional configuration changes.
+ *
+ * The AV1 implementation of this function returns an OBU. The OBU returned is
+ * in Low Overhead Bitstream Format. Specifically, the obu_has_size_field bit is
+ * set, and the buffer contains the obu_size field for the returned OBU.
  *
  * \param[in]    ctx     Pointer to this instance's context
  *
  * \retval NULL
- *     Encoder does not support global header
+ *     Encoder does not support global header, or an error occurred while
+ *     generating the global header.
+ *
  * \retval Non-NULL
- *     Pointer to buffer containing global header packet
+ *     Pointer to buffer containing global header packet. The caller owns the
+ *     memory associated with this buffer, and must free the 'buf' member of the
+ *     aom_fixed_buf_t as well as the aom_fixed_buf_t pointer. Memory returned
+ *     must be freed via call to free().
  */
 aom_fixed_buf_t *aom_codec_get_global_headers(aom_codec_ctx_t *ctx);
 
@@ -979,4 +978,4 @@ const aom_image_t *aom_codec_get_preview_frame(aom_codec_ctx_t *ctx);
 #ifdef __cplusplus
 }
 #endif
-#endif  // AOM_AOM_ENCODER_H_
+#endif  // AOM_AOM_AOM_ENCODER_H_

third_party/aom/aom/aom_frame_buffer.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_AOM_FRAME_BUFFER_H_
-#define AOM_AOM_FRAME_BUFFER_H_
+#ifndef AOM_AOM_AOM_FRAME_BUFFER_H_
+#define AOM_AOM_AOM_FRAME_BUFFER_H_
 
 /*!\file
  * \brief Describes the decoder external frame buffer interface.
@@ -81,4 +81,4 @@ typedef int (*aom_release_frame_buffer_cb_fn_t)(void *priv,
 }  // extern "C"
 #endif
 
-#endif  // AOM_AOM_FRAME_BUFFER_H_
+#endif  // AOM_AOM_AOM_FRAME_BUFFER_H_

third_party/aom/aom/aom_image.h

@@ -13,8 +13,8 @@
  * \brief Describes the aom image descriptor and associated operations
  *
  */
-#ifndef AOM_AOM_IMAGE_H_
-#define AOM_AOM_IMAGE_H_
+#ifndef AOM_AOM_AOM_IMAGE_H_
+#define AOM_AOM_AOM_IMAGE_H_
 
 #ifdef __cplusplus
 extern "C" {
@@ -328,4 +328,4 @@ int aom_img_plane_height(const aom_image_t *img, int plane);
 }  // extern "C"
 #endif
 
-#endif  // AOM_AOM_IMAGE_H_
+#endif  // AOM_AOM_AOM_IMAGE_H_

third_party/aom/aom/aom_integer.h

@@ -8,8 +8,8 @@
  * Media Patent License 1.0 was not distributed with this source code in the
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
-#ifndef AOM_AOM_INTEGER_H_
-#define AOM_AOM_INTEGER_H_
+#ifndef AOM_AOM_AOM_INTEGER_H_
+#define AOM_AOM_AOM_INTEGER_H_
 
 /* get ptrdiff_t, size_t, wchar_t, NULL */
 #include <stddef.h>
@@ -103,4 +103,4 @@ int aom_uleb_encode_fixed_size(uint64_t value, size_t available,
 }  // extern "C"
 #endif  // __cplusplus
 
-#endif  // AOM_AOM_INTEGER_H_
+#endif  // AOM_AOM_AOM_INTEGER_H_

third_party/aom/aom/aomcx.h

@@ -8,8 +8,8 @@
  * Media Patent License 1.0 was not distributed with this source code in the
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
-#ifndef AOM_AOMCX_H_
-#define AOM_AOMCX_H_
+#ifndef AOM_AOM_AOMCX_H_
+#define AOM_AOM_AOMCX_H_
 
 /*!\defgroup aom_encoder AOMedia AOM/AV1 Encoder
  * \ingroup aom
@@ -181,10 +181,6 @@ enum aome_enc_control_id {
    */
   AOME_SET_CPUUSED = 13,
 
-  /*!\brief Speed features for codec development
-   */
-  AOME_SET_DEVSF,
-
   /*!\brief Codec control function to enable automatic set and use alf frames.
    */
   AOME_SET_ENABLEAUTOALTREF,
@@ -286,14 +282,19 @@ enum aome_enc_control_id {
    */
   AV1E_SET_LOSSLESS = AV1E_SET_GF_CBR_BOOST_PCT + 2,
 
+  /** control function to enable the row based multi-threading of encoder. A
+   * value that is equal to 1 indicates that row based multi-threading is
+   * enabled.
+   */
+  AV1E_SET_ROW_MT,
+
   /*!\brief Codec control function to set number of tile columns.
    *
    * In encoding and decoding, AV1 allows an input image frame be partitioned
-   * into separated vertical tile columns, which can be encoded or decoded
+   * into separate vertical tile columns, which can be encoded or decoded
    * independently. This enables easy implementation of parallel encoding and
-   * decoding. This control requests the encoder to use column tiles in
-   * encoding an input frame, with number of tile columns (in Log2 unit) as
-   * the parameter:
+   * decoding. The parameter for this control describes the number of tile
+   * columns (in log2 units), which has a valid range of [0, 6]:
    *             0 = 1 tile column
    *             1 = 2 tile columns
    *             2 = 4 tile columns
@@ -310,16 +311,14 @@ enum aome_enc_control_id {
   /*!\brief Codec control function to set number of tile rows.
    *
    * In encoding and decoding, AV1 allows an input image frame be partitioned
-   * into separated horizontal tile rows. Tile rows are encoded or decoded
-   * sequentially. Even though encoding/decoding of later tile rows depends on
-   * earlier ones, this allows the encoder to output data packets for tile rows
-   * prior to completely processing all tile rows in a frame, thereby reducing
-   * the latency in processing between input and output. The parameter
-   * for this control describes the number of tile rows, which has a valid
-   * range [0, 2]:
+   * into separate horizontal tile rows, which can be encoded or decoded
+   * independently. The parameter for this control describes the number of tile
+   * rows (in log2 units), which has a valid range of [0, 6]:
    *            0 = 1 tile row
    *            1 = 2 tile rows
    *            2 = 4 tile rows
+   *            .....
+   *            n = 2**n tile rows
    *
    * By default, the value is 0, i.e. one single row tile for entire image.
    */
@@ -860,6 +859,12 @@ enum aome_enc_control_id {
 
   /*!\brief Sets the denoisers block size */
   AV1E_SET_DENOISE_BLOCK_SIZE,
+
+  /*!\brief Sets the chroma subsampling x value */
+  AV1E_SET_CHROMA_SUBSAMPLING_X,
+
+  /*!\brief Sets the chroma subsampling y value */
+  AV1E_SET_CHROMA_SUBSAMPLING_Y,
 };
 
 /*!\brief aom 1-D scaling mode
@@ -993,6 +998,9 @@ AOM_CTRL_USE_TYPE(AOME_SET_TUNING, int) /* aom_tune_metric */
 AOM_CTRL_USE_TYPE(AOME_SET_CQ_LEVEL, unsigned int)
 #define AOM_CTRL_AOME_SET_CQ_LEVEL
 
+AOM_CTRL_USE_TYPE(AV1E_SET_ROW_MT, int)
+#define AOM_CTRL_AV1E_SET_ROW_MT
+
 AOM_CTRL_USE_TYPE(AV1E_SET_TILE_COLUMNS, int)
 #define AOM_CTRL_AV1E_SET_TILE_COLUMNS
 AOM_CTRL_USE_TYPE(AV1E_SET_TILE_ROWS, int)
@@ -1137,10 +1145,6 @@ AOM_CTRL_USE_TYPE(AV1E_GET_ACTIVEMAP, aom_active_map_t *)
 AOM_CTRL_USE_TYPE(AV1E_SET_COLOR_RANGE, int)
 #define AOM_CTRL_AV1E_SET_COLOR_RANGE
 
-/*!\brief
- *
- * TODO(rbultje) : add support of the control in ffmpeg
- */
 #define AOM_CTRL_AV1E_SET_RENDER_SIZE
 AOM_CTRL_USE_TYPE(AV1E_SET_RENDER_SIZE, int *)
 
@@ -1179,10 +1183,16 @@ AOM_CTRL_USE_TYPE(AV1E_SET_DENOISE_BLOCK_SIZE, unsigned int);
 #define AOM_CTRL_AV1E_SET_DENOISE_BLOCK_SIZE
 #endif
 
+AOM_CTRL_USE_TYPE(AV1E_SET_CHROMA_SUBSAMPLING_X, unsigned int)
+#define AOM_CTRL_AV1E_SET_CHROMA_SUBSAMPLING_X
+
+AOM_CTRL_USE_TYPE(AV1E_SET_CHROMA_SUBSAMPLING_Y, unsigned int)
+#define AOM_CTRL_AV1E_SET_CHROMA_SUBSAMPLING_Y
+
 /*!\endcond */
 /*! @} - end defgroup aom_encoder */
 #ifdef __cplusplus
 }  // extern "C"
 #endif
 
-#endif  // AOM_AOMCX_H_
+#endif  // AOM_AOM_AOMCX_H_

third_party/aom/aom/aomdx.h

@@ -18,8 +18,8 @@
  * \brief Provides definitions for using AOM or AV1 within the aom Decoder
  *        interface.
  */
-#ifndef AOM_AOMDX_H_
-#define AOM_AOMDX_H_
+#ifndef AOM_AOM_AOMDX_H_
+#define AOM_AOM_AOMDX_H_
 
 #ifdef __cplusplus
 extern "C" {
@@ -227,6 +227,12 @@ enum aom_dec_control_id {
    */
   AV1_SET_INSPECTION_CALLBACK,
 
+  /** control function to set the skip film grain flag. Valid values are
+   * integers. The decoder will skip the film grain when its value is set to
+   * nonzero. The default value is 0.
+   */
+  AV1D_SET_SKIP_FILM_GRAIN,
+
   AOM_DECODER_CTRL_ID_MAX,
 };
 
@@ -276,6 +282,8 @@ AOM_CTRL_USE_TYPE(AV1D_EXT_TILE_DEBUG, unsigned int)
 #define AOM_CTRL_AV1D_EXT_TILE_DEBUG
 AOM_CTRL_USE_TYPE(AV1D_SET_ROW_MT, unsigned int)
 #define AOM_CTRL_AV1D_SET_ROW_MT
+AOM_CTRL_USE_TYPE(AV1D_SET_SKIP_FILM_GRAIN, int)
+#define AOM_CTRL_AV1D_SET_SKIP_FILM_GRAIN
 AOM_CTRL_USE_TYPE(AV1D_SET_IS_ANNEXB, unsigned int)
 #define AOM_CTRL_AV1D_SET_IS_ANNEXB
 AOM_CTRL_USE_TYPE(AV1D_SET_OPERATING_POINT, int)
@@ -291,4 +299,4 @@ AOM_CTRL_USE_TYPE(AV1_SET_INSPECTION_CALLBACK, aom_inspect_init *)
 }  // extern "C"
 #endif
 
-#endif  // AOM_AOMDX_H_
+#endif  // AOM_AOM_AOMDX_H_

third_party/aom/aom/exports_com

@@ -10,14 +10,23 @@ text aom_codec_version
 text aom_codec_version_extra_str
 text aom_codec_version_str
 text aom_img_alloc
+text aom_img_alloc_with_border
 text aom_img_flip
 text aom_img_free
-text aom_img_plane_width
 text aom_img_plane_height
+text aom_img_plane_width
 text aom_img_set_rect
 text aom_img_wrap
-text aom_img_alloc_with_border
+text aom_malloc
+text aom_rb_bytes_read
+text aom_rb_read_bit
+text aom_rb_read_literal
+text aom_rb_read_uvlc
 text aom_uleb_decode
 text aom_uleb_encode
 text aom_uleb_encode_fixed_size
 text aom_uleb_size_in_bytes
+text aom_wb_bytes_written
+text aom_wb_write_bit
+text aom_wb_write_literal
+text aom_wb_write_unsigned_literal

third_party/aom/aom/exports_dec

@@ -6,3 +6,5 @@ text aom_codec_peek_stream_info
 text aom_codec_register_put_frame_cb
 text aom_codec_register_put_slice_cb
 text aom_codec_set_frame_buffer_functions
+text aom_obu_type_to_string
+text aom_read_obu_header

third_party/aom/aom/exports_enc

@@ -7,3 +7,12 @@ text aom_codec_get_cx_data
 text aom_codec_get_global_headers
 text aom_codec_get_preview_frame
 text aom_codec_set_cx_data_buf
+text aom_film_grain_table_append
+text aom_film_grain_table_free
+text aom_film_grain_table_write
+text aom_flat_block_finder_init
+text aom_flat_block_finder_run
+text aom_noise_model_init
+text aom_noise_model_get_grain_parameters
+text aom_noise_model_save_latest
+text aom_noise_model_update

third_party/aom/aom/exports_test

@@ -0,0 +1,2 @@
+text aom_dsp_rtcd
+text aom_scale_rtcd

third_party/aom/aom/internal/aom_codec_internal.h

@@ -38,11 +38,11 @@
  *       }
  *     </pre>
  *
- * Once initialized, the instance is manged using other functions from
+ * Once initialized, the instance is managed using other functions from
  * the aom_codec_* family.
  */
-#ifndef AOM_INTERNAL_AOM_CODEC_INTERNAL_H_
-#define AOM_INTERNAL_AOM_CODEC_INTERNAL_H_
+#ifndef AOM_AOM_INTERNAL_AOM_CODEC_INTERNAL_H_
+#define AOM_AOM_INTERNAL_AOM_CODEC_INTERNAL_H_
 #include "../aom_decoder.h"
 #include "../aom_encoder.h"
 #include <stdarg.h>
@@ -438,4 +438,4 @@ void aom_merge_corrupted_flag(int *corrupted, int value);
 }  // extern "C"
 #endif
 
-#endif  // AOM_INTERNAL_AOM_CODEC_INTERNAL_H_
+#endif  // AOM_AOM_INTERNAL_AOM_CODEC_INTERNAL_H_

third_party/aom/aom/src/aom_decoder.c

@@ -101,9 +101,7 @@ aom_codec_err_t aom_codec_decode(aom_codec_ctx_t *ctx, const uint8_t *data,
                                  size_t data_sz, void *user_priv) {
   aom_codec_err_t res;
 
-  /* Sanity checks */
-  /* NULL data ptr allowed if data_sz is 0 too */
-  if (!ctx || (!data && data_sz) || (data && !data_sz))
+  if (!ctx)
     res = AOM_CODEC_INVALID_PARAM;
   else if (!ctx->iface || !ctx->priv)
     res = AOM_CODEC_ERROR;

third_party/aom/aom/src/aom_encoder.c

@@ -16,7 +16,9 @@
 #include "config/aom_config.h"
 
 #if HAVE_FEXCEPT
+#ifndef _GNU_SOURCE
 #define _GNU_SOURCE
+#endif
 #include <fenv.h>
 #endif
 
@@ -46,9 +48,6 @@ aom_codec_err_t aom_codec_enc_init_ver(aom_codec_ctx_t *ctx,
     res = AOM_CODEC_INCAPABLE;
   else if ((flags & AOM_CODEC_USE_PSNR) && !(iface->caps & AOM_CODEC_CAP_PSNR))
     res = AOM_CODEC_INCAPABLE;
-  else if ((flags & AOM_CODEC_USE_OUTPUT_PARTITION) &&
-           !(iface->caps & AOM_CODEC_CAP_OUTPUT_PARTITION))
-    res = AOM_CODEC_INCAPABLE;
   else {
     ctx->iface = iface;
     ctx->name = iface->name;
@@ -81,9 +80,6 @@ aom_codec_err_t aom_codec_enc_init_multi_ver(
     res = AOM_CODEC_INCAPABLE;
   else if ((flags & AOM_CODEC_USE_PSNR) && !(iface->caps & AOM_CODEC_CAP_PSNR))
     res = AOM_CODEC_INCAPABLE;
-  else if ((flags & AOM_CODEC_USE_OUTPUT_PARTITION) &&
-           !(iface->caps & AOM_CODEC_CAP_OUTPUT_PARTITION))
-    res = AOM_CODEC_INCAPABLE;
   else {
     int i;
     void *mem_loc = NULL;

third_party/aom/aom_dsp/aom_convolve.c

@@ -16,7 +16,6 @@
 #include "config/aom_dsp_rtcd.h"
 
 #include "aom/aom_integer.h"
-#include "aom_dsp/aom_convolve.h"
 #include "aom_dsp/aom_dsp_common.h"
 #include "aom_dsp/aom_filter.h"
 #include "aom_ports/mem.h"

third_party/aom/aom_dsp/aom_convolve.h

@@ -1,56 +0,0 @@
-/*
- * Copyright (c) 2016, Alliance for Open Media. All rights reserved
- *
- * This source code is subject to the terms of the BSD 2 Clause License and
- * the Alliance for Open Media Patent License 1.0. If the BSD 2 Clause License
- * was not distributed with this source code in the LICENSE file, you can
- * obtain it at www.aomedia.org/license/software. If the Alliance for Open
- * Media Patent License 1.0 was not distributed with this source code in the
- * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
- */
-#ifndef AOM_DSP_AOM_CONVOLVE_H_
-#define AOM_DSP_AOM_CONVOLVE_H_
-
-#include "config/aom_config.h"
-
-#include "aom/aom_integer.h"
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-// Note: Fixed size intermediate buffers, place limits on parameters
-// of some functions. 2d filtering proceeds in 2 steps:
-//   (1) Interpolate horizontally into an intermediate buffer, temp.
-//   (2) Interpolate temp vertically to derive the sub-pixel result.
-// Deriving the maximum number of rows in the temp buffer (135):
-// --Smallest scaling factor is x1/2 ==> y_step_q4 = 32 (Normative).
-// --Largest block size is 64x64 pixels.
-// --64 rows in the downscaled frame span a distance of (64 - 1) * 32 in the
-//   original frame (in 1/16th pixel units).
-// --Must round-up because block may be located at sub-pixel position.
-// --Require an additional SUBPEL_TAPS rows for the 8-tap filter tails.
-// --((64 - 1) * 32 + 15) >> 4 + 8 = 135.
-// TODO(wtc): Update the above comment to explain the value 263 used in aom.
-#define MAX_EXT_SIZE 263
-
-#define EXTRAPREC_BITS 2
-#define EXTRAPREC_CLAMP_LIMIT(bd) (1 << ((bd) + 1 + EXTRAPREC_BITS))
-
-typedef void (*convolve_fn_t)(const uint8_t *src, ptrdiff_t src_stride,
-                              uint8_t *dst, ptrdiff_t dst_stride,
-                              const int16_t *filter_x, int x_step_q4,
-                              const int16_t *filter_y, int y_step_q4, int w,
-                              int h);
-
-typedef void (*highbd_convolve_fn_t)(const uint8_t *src, ptrdiff_t src_stride,
-                                     uint8_t *dst, ptrdiff_t dst_stride,
-                                     const int16_t *filter_x, int x_step_q4,
-                                     const int16_t *filter_y, int y_step_q4,
-                                     int w, int h, int bd);
-
-#ifdef __cplusplus
-}  // extern "C"
-#endif
-
-#endif  // AOM_DSP_AOM_CONVOLVE_H_

third_party/aom/aom_dsp/aom_dsp.cmake

@@ -15,11 +15,14 @@ set(AOM_AOM_DSP_AOM_DSP_CMAKE_ 1)
 
 list(APPEND AOM_DSP_COMMON_SOURCES
             "${AOM_ROOT}/aom_dsp/aom_convolve.c"
-            "${AOM_ROOT}/aom_dsp/aom_convolve.h"
             "${AOM_ROOT}/aom_dsp/aom_dsp_common.h"
             "${AOM_ROOT}/aom_dsp/aom_filter.h"
             "${AOM_ROOT}/aom_dsp/aom_simd.h"
             "${AOM_ROOT}/aom_dsp/aom_simd_inline.h"
+            "${AOM_ROOT}/aom_dsp/bitreader_buffer.c"
+            "${AOM_ROOT}/aom_dsp/bitreader_buffer.h"
+            "${AOM_ROOT}/aom_dsp/bitwriter_buffer.c"
+            "${AOM_ROOT}/aom_dsp/bitwriter_buffer.h"
             "${AOM_ROOT}/aom_dsp/blend.h"
             "${AOM_ROOT}/aom_dsp/blend_a64_hmask.c"
             "${AOM_ROOT}/aom_dsp/blend_a64_mask.c"
@@ -64,7 +67,8 @@ list(APPEND AOM_DSP_COMMON_INTRIN_SSE2
             "${AOM_ROOT}/aom_dsp/x86/lpf_common_sse2.h"
             "${AOM_ROOT}/aom_dsp/x86/mem_sse2.h"
             "${AOM_ROOT}/aom_dsp/x86/transpose_sse2.h"
-            "${AOM_ROOT}/aom_dsp/x86/txfm_common_sse2.h")
+            "${AOM_ROOT}/aom_dsp/x86/txfm_common_sse2.h"
+            "${AOM_ROOT}/aom_dsp/x86/sum_squares_sse2.h")
 
 list(APPEND AOM_DSP_COMMON_ASM_SSSE3
             "${AOM_ROOT}/aom_dsp/x86/aom_subpixel_8t_ssse3.asm"
@@ -76,6 +80,7 @@ list(APPEND AOM_DSP_COMMON_INTRIN_SSSE3
             "${AOM_ROOT}/aom_dsp/x86/intrapred_ssse3.c")
 
 list(APPEND AOM_DSP_COMMON_INTRIN_SSE4_1
+            "${AOM_ROOT}/aom_dsp/x86/blend_mask_sse4.h"
             "${AOM_ROOT}/aom_dsp/x86/blend_a64_hmask_sse4.c"
             "${AOM_ROOT}/aom_dsp/x86/blend_a64_mask_sse4.c"
             "${AOM_ROOT}/aom_dsp/x86/blend_a64_vmask_sse4.c")
@@ -88,7 +93,8 @@ list(APPEND AOM_DSP_COMMON_INTRIN_AVX2
             "${AOM_ROOT}/aom_dsp/x86/fft_avx2.c"
             "${AOM_ROOT}/aom_dsp/x86/highbd_convolve_avx2.c"
             "${AOM_ROOT}/aom_dsp/x86/highbd_loopfilter_avx2.c"
-            "${AOM_ROOT}/aom_dsp/x86/intrapred_avx2.c")
+            "${AOM_ROOT}/aom_dsp/x86/intrapred_avx2.c"
+            "${AOM_ROOT}/aom_dsp/x86/blend_a64_mask_avx2.c")
 
 list(APPEND AOM_DSP_COMMON_INTRIN_NEON
             "${AOM_ROOT}/aom_dsp/arm/fwd_txfm_neon.c"
@@ -125,12 +131,9 @@ if(CONFIG_AV1_DECODER)
               "${AOM_ROOT}/aom_dsp/binary_codes_reader.c"
               "${AOM_ROOT}/aom_dsp/binary_codes_reader.h"
               "${AOM_ROOT}/aom_dsp/bitreader.h"
-              "${AOM_ROOT}/aom_dsp/bitreader_buffer.c"
-              "${AOM_ROOT}/aom_dsp/bitreader_buffer.h"
               "${AOM_ROOT}/aom_dsp/daalaboolreader.c"
               "${AOM_ROOT}/aom_dsp/daalaboolreader.h"
-              "${AOM_ROOT}/aom_dsp/entdec.c"
-              "${AOM_ROOT}/aom_dsp/entdec.h"
+              "${AOM_ROOT}/aom_dsp/entdec.c" "${AOM_ROOT}/aom_dsp/entdec.h"
               "${AOM_ROOT}/aom_dsp/grain_synthesis.c"
               "${AOM_ROOT}/aom_dsp/grain_synthesis.h")
 endif()
@@ -140,8 +143,6 @@ if(CONFIG_AV1_ENCODER)
               "${AOM_ROOT}/aom_dsp/binary_codes_writer.c"
               "${AOM_ROOT}/aom_dsp/binary_codes_writer.h"
               "${AOM_ROOT}/aom_dsp/bitwriter.h"
-              "${AOM_ROOT}/aom_dsp/bitwriter_buffer.c"
-              "${AOM_ROOT}/aom_dsp/bitwriter_buffer.h"
               "${AOM_ROOT}/aom_dsp/daalaboolwriter.c"
               "${AOM_ROOT}/aom_dsp/daalaboolwriter.h"
               "${AOM_ROOT}/aom_dsp/entenc.c"
@@ -158,13 +159,13 @@ if(CONFIG_AV1_ENCODER)
               "${AOM_ROOT}/aom_dsp/quantize.c"
               "${AOM_ROOT}/aom_dsp/quantize.h"
               "${AOM_ROOT}/aom_dsp/sad.c"
+              "${AOM_ROOT}/aom_dsp/sse.c"
               "${AOM_ROOT}/aom_dsp/sad_av1.c"
               "${AOM_ROOT}/aom_dsp/sum_squares.c"
               "${AOM_ROOT}/aom_dsp/variance.c"
               "${AOM_ROOT}/aom_dsp/variance.h")
 
   list(APPEND AOM_DSP_ENCODER_ASM_SSE2
-              "${AOM_ROOT}/aom_dsp/x86/halfpix_variance_impl_sse2.asm"
               "${AOM_ROOT}/aom_dsp/x86/highbd_sad4d_sse2.asm"
               "${AOM_ROOT}/aom_dsp/x86/highbd_sad_sse2.asm"
               "${AOM_ROOT}/aom_dsp/x86/highbd_subpel_variance_impl_sse2.asm"
@@ -178,11 +179,11 @@ if(CONFIG_AV1_ENCODER)
               "${AOM_ROOT}/aom_dsp/x86/fwd_txfm_impl_sse2.h"
               "${AOM_ROOT}/aom_dsp/x86/fwd_txfm_sse2.c"
               "${AOM_ROOT}/aom_dsp/x86/fwd_txfm_sse2.h"
-              "${AOM_ROOT}/aom_dsp/x86/halfpix_variance_sse2.c"
               "${AOM_ROOT}/aom_dsp/x86/highbd_quantize_intrin_sse2.c"
               "${AOM_ROOT}/aom_dsp/x86/highbd_subtract_sse2.c"
               "${AOM_ROOT}/aom_dsp/x86/highbd_variance_sse2.c"
               "${AOM_ROOT}/aom_dsp/x86/quantize_sse2.c"
+              "${AOM_ROOT}/aom_dsp/x86/quantize_x86.h"
               "${AOM_ROOT}/aom_dsp/x86/sum_squares_sse2.c"
               "${AOM_ROOT}/aom_dsp/x86/variance_sse2.c")
 
@@ -199,8 +200,12 @@ if(CONFIG_AV1_ENCODER)
               "${AOM_ROOT}/aom_dsp/x86/sad_highbd_avx2.c"
               "${AOM_ROOT}/aom_dsp/x86/sad_impl_avx2.c"
               "${AOM_ROOT}/aom_dsp/x86/variance_avx2.c"
+              "${AOM_ROOT}/aom_dsp/x86/highbd_variance_avx2.c"
+              "${AOM_ROOT}/aom_dsp/x86/sse_avx2.c"
               "${AOM_ROOT}/aom_dsp/x86/variance_impl_avx2.c"
-              "${AOM_ROOT}/aom_dsp/x86/obmc_sad_avx2.c")
+              "${AOM_ROOT}/aom_dsp/x86/obmc_sad_avx2.c"
+              "${AOM_ROOT}/aom_dsp/x86/obmc_variance_avx2.c"
+              "${AOM_ROOT}/aom_dsp/x86/sum_squares_avx2.c")
 
   list(APPEND AOM_DSP_ENCODER_ASM_SSSE3_X86_64
               "${AOM_ROOT}/aom_dsp/x86/quantize_ssse3_x86_64.asm")
@@ -219,6 +224,7 @@ if(CONFIG_AV1_ENCODER)
 
   list(APPEND AOM_DSP_ENCODER_INTRIN_SSE4_1
               "${AOM_ROOT}/aom_dsp/x86/highbd_variance_sse4.c"
+              "${AOM_ROOT}/aom_dsp/x86/sse_sse4.c"
               "${AOM_ROOT}/aom_dsp/x86/obmc_sad_sse4.c"
               "${AOM_ROOT}/aom_dsp/x86/obmc_variance_sse4.c")
 

third_party/aom/aom_dsp/aom_dsp_common.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_AOM_DSP_COMMON_H_
-#define AOM_DSP_AOM_DSP_COMMON_H_
+#ifndef AOM_AOM_DSP_AOM_DSP_COMMON_H_
+#define AOM_AOM_DSP_AOM_DSP_COMMON_H_
 
 #include "config/aom_config.h"
 
@@ -95,4 +95,4 @@ static INLINE unsigned int negative_to_zero(int value) {
 }  // extern "C"
 #endif
 
-#endif  // AOM_DSP_AOM_DSP_COMMON_H_
+#endif  // AOM_AOM_DSP_AOM_DSP_COMMON_H_

third_party/aom/aom_dsp/aom_dsp_rtcd_defs.pl

@@ -519,23 +519,23 @@ if (aom_config("CONFIG_AV1_ENCODER") eq "yes"){
 # Quantization
 #
 if (aom_config("CONFIG_AV1_ENCODER") eq "yes") {
-  add_proto qw/void aom_quantize_b/, "const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan";
+  add_proto qw/void aom_quantize_b/, "const tran_low_t *coeff_ptr, intptr_t n_coeffs, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan";
   specialize qw/aom_quantize_b sse2/, "$ssse3_x86_64", "$avx_x86_64";
 
-  add_proto qw/void aom_quantize_b_32x32/, "const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan";
+  add_proto qw/void aom_quantize_b_32x32/, "const tran_low_t *coeff_ptr, intptr_t n_coeffs, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan";
   specialize qw/aom_quantize_b_32x32/, "$ssse3_x86_64", "$avx_x86_64";
 
-  add_proto qw/void aom_quantize_b_64x64/, "const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan";
+  add_proto qw/void aom_quantize_b_64x64/, "const tran_low_t *coeff_ptr, intptr_t n_coeffs, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan";
 }  # CONFIG_AV1_ENCODER
 
 if (aom_config("CONFIG_AV1_ENCODER") eq "yes") {
-  add_proto qw/void aom_highbd_quantize_b/, "const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan";
+  add_proto qw/void aom_highbd_quantize_b/, "const tran_low_t *coeff_ptr, intptr_t n_coeffs, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan";
   specialize qw/aom_highbd_quantize_b sse2 avx2/;
 
-  add_proto qw/void aom_highbd_quantize_b_32x32/, "const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan";
+  add_proto qw/void aom_highbd_quantize_b_32x32/, "const tran_low_t *coeff_ptr, intptr_t n_coeffs, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan";
   specialize qw/aom_highbd_quantize_b_32x32 sse2/;
 
-  add_proto qw/void aom_highbd_quantize_b_64x64/, "const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan";
+  add_proto qw/void aom_highbd_quantize_b_64x64/, "const tran_low_t *coeff_ptr, intptr_t n_coeffs, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan";
 
 }  # CONFIG_AV1_ENCODER
 
@@ -543,12 +543,12 @@ if (aom_config("CONFIG_AV1_ENCODER") eq "yes") {
 # Alpha blending with mask
 #
 add_proto qw/void aom_lowbd_blend_a64_d16_mask/, "uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params";
-specialize qw/aom_lowbd_blend_a64_d16_mask sse4_1 neon/;
+specialize qw/aom_lowbd_blend_a64_d16_mask sse4_1 avx2 neon/;
 add_proto qw/void aom_highbd_blend_a64_d16_mask/, "uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0, uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby, ConvolveParams *conv_params, const int bd";
 add_proto qw/void aom_blend_a64_mask/, "uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int w, int h, int subx, int suby";
 add_proto qw/void aom_blend_a64_hmask/, "uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int w, int h";
 add_proto qw/void aom_blend_a64_vmask/, "uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int w, int h";
-specialize "aom_blend_a64_mask", qw/sse4_1/;
+specialize "aom_blend_a64_mask", qw/sse4_1 avx2/;
 specialize "aom_blend_a64_hmask", qw/sse4_1 neon/;
 specialize "aom_blend_a64_vmask", qw/sse4_1 neon/;
 
@@ -569,15 +569,22 @@ if (aom_config("CONFIG_AV1_ENCODER") eq "yes") {
   add_proto qw/void aom_highbd_subtract_block/, "int rows, int cols, int16_t *diff_ptr, ptrdiff_t diff_stride, const uint8_t *src_ptr, ptrdiff_t src_stride, const uint8_t *pred_ptr, ptrdiff_t pred_stride, int bd";
   specialize qw/aom_highbd_subtract_block sse2/;
 
+  add_proto qw/int64_t/, "aom_sse", "const uint8_t *a, int a_stride, const uint8_t *b,int b_stride, int width, int height";
+  specialize qw/aom_sse  sse4_1 avx2/;
+
+  add_proto qw/int64_t/, "aom_highbd_sse", "const uint8_t *a8, int a_stride, const uint8_t *b8,int b_stride, int width, int height";
+  specialize qw/aom_highbd_sse  sse4_1 avx2/;
+
   if (aom_config("CONFIG_AV1_ENCODER") eq "yes") {
     #
     # Sum of Squares
     #
     add_proto qw/uint64_t aom_sum_squares_2d_i16/, "const int16_t *src, int stride, int width, int height";
-    specialize qw/aom_sum_squares_2d_i16 sse2/;
+    specialize qw/aom_sum_squares_2d_i16 sse2 avx2/;
 
     add_proto qw/uint64_t aom_sum_squares_i16/, "const int16_t *src, uint32_t N";
     specialize qw/aom_sum_squares_i16 sse2/;
+
   }
 
 
@@ -830,7 +837,6 @@ if (aom_config("CONFIG_AV1_ENCODER") eq "yes") {
   specialize qw/aom_highbd_sad16x64x4d sse2/;
   specialize qw/aom_highbd_sad64x16x4d sse2/;
 
-
   #
   # Structured Similarity (SSIM)
   #
@@ -888,36 +894,43 @@ if (aom_config("CONFIG_AV1_ENCODER") eq "yes") {
   #
   add_proto qw/void aom_upsampled_pred/, "MACROBLOCKD *xd, const struct AV1Common *const cm, int mi_row, int mi_col,
                                           const MV *const mv, uint8_t *comp_pred, int width, int height, int subpel_x_q3,
-                                          int subpel_y_q3, const uint8_t *ref, int ref_stride";
+                                          int subpel_y_q3, const uint8_t *ref, int ref_stride, int subpel_search";
   specialize qw/aom_upsampled_pred sse2/;
 
   add_proto qw/void aom_comp_avg_upsampled_pred/, "MACROBLOCKD *xd, const struct AV1Common *const cm, int mi_row, int mi_col,
                                                    const MV *const mv, uint8_t *comp_pred, const uint8_t *pred, int width,
                                                    int height, int subpel_x_q3, int subpel_y_q3, const uint8_t *ref,
-                                                   int ref_stride";
+                                                   int ref_stride, int subpel_search";
   specialize qw/aom_comp_avg_upsampled_pred sse2/;
 
   add_proto qw/void aom_jnt_comp_avg_upsampled_pred/, "MACROBLOCKD *xd, const struct AV1Common *const cm, int mi_row, int mi_col,
                                                        const MV *const mv, uint8_t *comp_pred, const uint8_t *pred, int width,
                                                        int height, int subpel_x_q3, int subpel_y_q3, const uint8_t *ref,
-                                                       int ref_stride, const JNT_COMP_PARAMS *jcp_param";
+                                                       int ref_stride, const JNT_COMP_PARAMS *jcp_param, int subpel_search";
   specialize qw/aom_jnt_comp_avg_upsampled_pred ssse3/;
 
+  add_proto qw/void aom_comp_mask_upsampled_pred/, "MACROBLOCKD *xd, const struct AV1Common *const cm, int mi_row, int mi_col,
+                                                       const MV *const mv, uint8_t *comp_pred, const uint8_t *pred, int width,
+                                                       int height, int subpel_x_q3, int subpel_y_q3, const uint8_t *ref,
+                                                       int ref_stride, const uint8_t *mask, int mask_stride, int invert_mask,
+                                                       int subpel_search";
+  specialize qw/aom_comp_mask_upsampled_pred sse2/;
+
 
   add_proto qw/void aom_highbd_upsampled_pred/, "MACROBLOCKD *xd, const struct AV1Common *const cm, int mi_row, int mi_col,
-                                                 const MV *const mv, uint16_t *comp_pred, int width, int height, int subpel_x_q3,
-                                                 int subpel_y_q3, const uint8_t *ref8, int ref_stride, int bd";
+                                                 const MV *const mv, uint8_t *comp_pred8, int width, int height, int subpel_x_q3,
+                                                 int subpel_y_q3, const uint8_t *ref8, int ref_stride, int bd, int subpel_search";
   specialize qw/aom_highbd_upsampled_pred sse2/;
 
   add_proto qw/void aom_highbd_comp_avg_upsampled_pred/, "MACROBLOCKD *xd, const struct AV1Common *const cm, int mi_row, int mi_col,
-                                                          const MV *const mv, uint16_t *comp_pred, const uint8_t *pred8, int width,
-                                                          int height, int subpel_x_q3, int subpel_y_q3, const uint8_t *ref8, int ref_stride, int bd";
+                                                          const MV *const mv, uint8_t *comp_pred8, const uint8_t *pred8, int width,
+                                                          int height, int subpel_x_q3, int subpel_y_q3, const uint8_t *ref8, int ref_stride, int bd, int subpel_search";
   specialize qw/aom_highbd_comp_avg_upsampled_pred sse2/;
 
   add_proto qw/void aom_highbd_jnt_comp_avg_upsampled_pred/, "MACROBLOCKD *xd, const struct AV1Common *const cm, int mi_row, int mi_col,
-                                                              const MV *const mv, uint16_t *comp_pred, const uint8_t *pred8, int width,
+                                                              const MV *const mv, uint8_t *comp_pred8, const uint8_t *pred8, int width,
                                                               int height, int subpel_x_q3, int subpel_y_q3, const uint8_t *ref8,
-                                                              int ref_stride, int bd, const JNT_COMP_PARAMS *jcp_param";
+                                                              int ref_stride, int bd, const JNT_COMP_PARAMS *jcp_param, int subpel_search";
   specialize qw/aom_highbd_jnt_comp_avg_upsampled_pred sse2/;
 
 
@@ -1101,7 +1114,7 @@ if (aom_config("CONFIG_AV1_ENCODER") eq "yes") {
     ($w, $h) = @$_;
     add_proto qw/unsigned int/, "aom_obmc_variance${w}x${h}", "const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse";
     add_proto qw/unsigned int/, "aom_obmc_sub_pixel_variance${w}x${h}", "const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse";
-    specialize "aom_obmc_variance${w}x${h}", q/sse4_1/;
+    specialize "aom_obmc_variance${w}x${h}", qw/sse4_1 avx2/;
     specialize "aom_obmc_sub_pixel_variance${w}x${h}", q/sse4_1/;
   }
 
@@ -1154,17 +1167,6 @@ if (aom_config("CONFIG_AV1_ENCODER") eq "yes") {
 
   add_proto qw/uint32_t aom_sub_pixel_avg_variance4x4/, "const uint8_t *src_ptr, int source_stride, int xoffset, int  yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred";
   specialize qw/aom_sub_pixel_avg_variance4x4 msa sse2 ssse3/;
-  #
-  # Specialty Subpixel
-  #
-  add_proto qw/uint32_t aom_variance_halfpixvar16x16_h/, "const unsigned char *src_ptr, int source_stride, const unsigned char *ref_ptr, int  ref_stride, uint32_t *sse";
-  specialize qw/aom_variance_halfpixvar16x16_h sse2/;
-
-  add_proto qw/uint32_t aom_variance_halfpixvar16x16_v/, "const unsigned char *src_ptr, int source_stride, const unsigned char *ref_ptr, int  ref_stride, uint32_t *sse";
-  specialize qw/aom_variance_halfpixvar16x16_v sse2/;
-
-  add_proto qw/uint32_t aom_variance_halfpixvar16x16_hv/, "const unsigned char *src_ptr, int source_stride, const unsigned char *ref_ptr, int  ref_stride, uint32_t *sse";
-  specialize qw/aom_variance_halfpixvar16x16_hv sse2/;
 
   #
   # Comp Avg
@@ -1174,6 +1176,14 @@ if (aom_config("CONFIG_AV1_ENCODER") eq "yes") {
   add_proto qw/void aom_jnt_comp_avg_pred/, "uint8_t *comp_pred, const uint8_t *pred, int width, int height, const uint8_t *ref, int ref_stride, const JNT_COMP_PARAMS *jcp_param";
   specialize qw/aom_jnt_comp_avg_pred ssse3/;
 
+    add_proto qw/unsigned int aom_highbd_12_variance128x128/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
+    specialize qw/aom_highbd_12_variance128x128 sse2/;
+
+	add_proto qw/unsigned int aom_highbd_12_variance128x64/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
+    specialize qw/aom_highbd_12_variance128x64 sse2/;
+
+	add_proto qw/unsigned int aom_highbd_12_variance64x128/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
+    specialize qw/aom_highbd_12_variance64x128 sse2/;
 
     add_proto qw/unsigned int aom_highbd_12_variance64x64/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
     specialize qw/aom_highbd_12_variance64x64 sse2/;
@@ -1209,40 +1219,58 @@ if (aom_config("CONFIG_AV1_ENCODER") eq "yes") {
     add_proto qw/unsigned int aom_highbd_12_variance4x8/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
     add_proto qw/unsigned int aom_highbd_12_variance4x4/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
 
+	add_proto qw/unsigned int aom_highbd_10_variance128x128/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
+    specialize qw/aom_highbd_10_variance128x128 sse2 avx2/;
+
+	add_proto qw/unsigned int aom_highbd_10_variance128x64/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
+    specialize qw/aom_highbd_10_variance128x64 sse2 avx2/;
+
+	add_proto qw/unsigned int aom_highbd_10_variance64x128/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
+    specialize qw/aom_highbd_10_variance64x128 sse2 avx2/;
+
     add_proto qw/unsigned int aom_highbd_10_variance64x64/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
-    specialize qw/aom_highbd_10_variance64x64 sse2/;
+    specialize qw/aom_highbd_10_variance64x64 sse2 avx2/;
 
     add_proto qw/unsigned int aom_highbd_10_variance64x32/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
-    specialize qw/aom_highbd_10_variance64x32 sse2/;
+    specialize qw/aom_highbd_10_variance64x32 sse2 avx2/;
 
     add_proto qw/unsigned int aom_highbd_10_variance32x64/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
-    specialize qw/aom_highbd_10_variance32x64 sse2/;
+    specialize qw/aom_highbd_10_variance32x64 sse2 avx2/;
 
     add_proto qw/unsigned int aom_highbd_10_variance32x32/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
-    specialize qw/aom_highbd_10_variance32x32 sse2/;
+    specialize qw/aom_highbd_10_variance32x32 sse2 avx2/;
 
     add_proto qw/unsigned int aom_highbd_10_variance32x16/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
-    specialize qw/aom_highbd_10_variance32x16 sse2/;
+    specialize qw/aom_highbd_10_variance32x16 sse2 avx2/;
 
     add_proto qw/unsigned int aom_highbd_10_variance16x32/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
-    specialize qw/aom_highbd_10_variance16x32 sse2/;
+    specialize qw/aom_highbd_10_variance16x32 sse2 avx2/;
 
     add_proto qw/unsigned int aom_highbd_10_variance16x16/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
-    specialize qw/aom_highbd_10_variance16x16 sse2/;
+    specialize qw/aom_highbd_10_variance16x16 sse2 avx2/;
 
     add_proto qw/unsigned int aom_highbd_10_variance16x8/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
-    specialize qw/aom_highbd_10_variance16x8 sse2/;
+    specialize qw/aom_highbd_10_variance16x8 sse2 avx2/;
 
     add_proto qw/unsigned int aom_highbd_10_variance8x16/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
-    specialize qw/aom_highbd_10_variance8x16 sse2/;
+    specialize qw/aom_highbd_10_variance8x16 sse2 avx2/;
 
     add_proto qw/unsigned int aom_highbd_10_variance8x8/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
-    specialize qw/aom_highbd_10_variance8x8 sse2/;
+    specialize qw/aom_highbd_10_variance8x8 sse2 avx2/;
 
     add_proto qw/unsigned int aom_highbd_10_variance8x4/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
     add_proto qw/unsigned int aom_highbd_10_variance4x8/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
     add_proto qw/unsigned int aom_highbd_10_variance4x4/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
 
+	add_proto qw/unsigned int aom_highbd_8_variance128x128/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
+    specialize qw/aom_highbd_8_variance128x128 sse2/;
+
+	add_proto qw/unsigned int aom_highbd_8_variance128x64/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
+    specialize qw/aom_highbd_8_variance128x64 sse2/;
+
+	add_proto qw/unsigned int aom_highbd_8_variance64x128/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
+    specialize qw/aom_highbd_8_variance64x128 sse2/;
+
     add_proto qw/unsigned int aom_highbd_8_variance64x64/, "const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse";
     specialize qw/aom_highbd_8_variance64x64 sse2/;
 
@@ -1310,9 +1338,9 @@ if (aom_config("CONFIG_AV1_ENCODER") eq "yes") {
     add_proto qw/unsigned int aom_highbd_12_mse8x8/, "const uint8_t *src_ptr, int  source_stride, const uint8_t *ref_ptr, int  recon_stride, unsigned int *sse";
     specialize qw/aom_highbd_12_mse8x8 sse2/;
 
-    add_proto qw/void aom_highbd_comp_avg_pred/, "uint16_t *comp_pred, const uint8_t *pred8, int width, int height, const uint8_t *ref8, int ref_stride";
+    add_proto qw/void aom_highbd_comp_avg_pred/, "uint8_t *comp_pred8, const uint8_t *pred8, int width, int height, const uint8_t *ref8, int ref_stride";
 
-    add_proto qw/void aom_highbd_jnt_comp_avg_pred/, "uint16_t *comp_pred, const uint8_t *pred8, int width, int height, const uint8_t *ref8, int ref_stride, const JNT_COMP_PARAMS *jcp_param";
+    add_proto qw/void aom_highbd_jnt_comp_avg_pred/, "uint8_t *comp_pred8, const uint8_t *pred8, int width, int height, const uint8_t *ref8, int ref_stride, const JNT_COMP_PARAMS *jcp_param";
     specialize qw/aom_highbd_jnt_comp_avg_pred sse2/;
 
     #
@@ -1539,8 +1567,8 @@ if (aom_config("CONFIG_AV1_ENCODER") eq "yes") {
   add_proto qw/void aom_comp_mask_pred/, "uint8_t *comp_pred, const uint8_t *pred, int width, int height, const uint8_t *ref, int ref_stride, const uint8_t *mask, int mask_stride, int invert_mask";
   specialize qw/aom_comp_mask_pred ssse3 avx2/;
 
-  add_proto qw/void aom_highbd_comp_mask_pred/, "uint16_t *comp_pred, const uint8_t *pred8, int width, int height, const uint8_t *ref8, int ref_stride, const uint8_t *mask, int mask_stride, int invert_mask";
-  specialize qw/aom_highbd_comp_mask_pred avx2/;
+  add_proto qw/void aom_highbd_comp_mask_pred/, "uint8_t *comp_pred, const uint8_t *pred8, int width, int height, const uint8_t *ref8, int ref_stride, const uint8_t *mask, int mask_stride, int invert_mask";
+  specialize qw/aom_highbd_comp_mask_pred sse2 avx2/;
 
 }  # CONFIG_AV1_ENCODER
 

third_party/aom/aom_dsp/aom_filter.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_AOM_FILTER_H_
-#define AOM_DSP_AOM_FILTER_H_
+#ifndef AOM_AOM_DSP_AOM_FILTER_H_
+#define AOM_AOM_DSP_AOM_FILTER_H_
 
 #include "aom/aom_integer.h"
 
@@ -53,4 +53,4 @@ static const uint8_t bilinear_filters_2t[BIL_SUBPEL_SHIFTS][2] = {
 }  // extern "C"
 #endif
 
-#endif  // AOM_DSP_AOM_FILTER_H_
+#endif  // AOM_AOM_DSP_AOM_FILTER_H_

third_party/aom/aom_dsp/aom_simd.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_AOM_AOM_SIMD_H_
-#define AOM_DSP_AOM_AOM_SIMD_H_
+#ifndef AOM_AOM_DSP_AOM_SIMD_H_
+#define AOM_AOM_DSP_AOM_SIMD_H_
 
 #include <stdint.h>
 
@@ -35,4 +35,4 @@
 #include "simd/v256_intrinsics.h"
 #endif
 
-#endif  // AOM_DSP_AOM_AOM_SIMD_H_
+#endif  // AOM_AOM_DSP_AOM_SIMD_H_

third_party/aom/aom_dsp/aom_simd_inline.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_AOM_SIMD_INLINE_H_
-#define AOM_DSP_AOM_SIMD_INLINE_H_
+#ifndef AOM_AOM_DSP_AOM_SIMD_INLINE_H_
+#define AOM_AOM_DSP_AOM_SIMD_INLINE_H_
 
 #include "aom/aom_integer.h"
 
@@ -18,4 +18,4 @@
 #define SIMD_INLINE static AOM_FORCE_INLINE
 #endif
 
-#endif  // AOM_DSP_AOM_SIMD_INLINE_H_
+#endif  // AOM_AOM_DSP_AOM_SIMD_INLINE_H_

third_party/aom/aom_dsp/arm/blend_a64_mask_neon.c

@@ -86,7 +86,8 @@ static INLINE void blend_4x4(uint8_t *dst, uint32_t dst_stride,
                              const int16x8_t vec_round_bits) {
   int16x8_t src0_0, src0_1;
   int16x8_t src1_0, src1_1;
-  uint64x2_t tu0, tu1, tu2, tu3;
+  uint64x2_t tu0 = vdupq_n_u64(0), tu1 = vdupq_n_u64(0), tu2 = vdupq_n_u64(0),
+             tu3 = vdupq_n_u64(0);
   int16x8_t mask0_1, mask2_3;
   int16x8_t res0, res1;
 
@@ -154,7 +155,8 @@ void aom_lowbd_blend_a64_d16_mask_neon(
   assert(IS_POWER_OF_TWO(w));
 
   uint8x8_t s0, s1, s2, s3;
-  uint32x2_t tu0, tu1, tu2, tu3;
+  uint32x2_t tu0 = vdup_n_u32(0), tu1 = vdup_n_u32(0), tu2 = vdup_n_u32(0),
+             tu3 = vdup_n_u32(0);
   uint8x16_t t0, t1, t2, t3, t4, t5, t6, t7;
   int16x8_t mask0, mask1, mask2, mask3;
   int16x8_t mask4, mask5, mask6, mask7;

third_party/aom/aom_dsp/arm/subpel_variance_neon.c

@@ -17,13 +17,9 @@
 #include "aom_ports/mem.h"
 #include "aom/aom_integer.h"
 
+#include "aom_dsp/aom_filter.h"
 #include "aom_dsp/variance.h"
 
-static const uint8_t bilinear_filters[8][2] = {
-  { 128, 0 }, { 112, 16 }, { 96, 32 }, { 80, 48 },
-  { 64, 64 }, { 48, 80 },  { 32, 96 }, { 16, 112 },
-};
-
 static void var_filter_block2d_bil_w8(const uint8_t *src_ptr,
                                       uint8_t *output_ptr,
                                       unsigned int src_pixels_per_line,
@@ -83,9 +79,9 @@ unsigned int aom_sub_pixel_variance8x8_neon(const uint8_t *src, int src_stride,
   DECLARE_ALIGNED(16, uint8_t, fdata3[9 * 8]);
 
   var_filter_block2d_bil_w8(src, fdata3, src_stride, 1, 9, 8,
-                            bilinear_filters[xoffset]);
+                            bilinear_filters_2t[xoffset]);
   var_filter_block2d_bil_w8(fdata3, temp2, 8, 8, 8, 8,
-                            bilinear_filters[yoffset]);
+                            bilinear_filters_2t[yoffset]);
   return aom_variance8x8_neon(temp2, 8, dst, dst_stride, sse);
 }
 
@@ -98,9 +94,9 @@ unsigned int aom_sub_pixel_variance16x16_neon(const uint8_t *src,
   DECLARE_ALIGNED(16, uint8_t, fdata3[17 * 16]);
 
   var_filter_block2d_bil_w16(src, fdata3, src_stride, 1, 17, 16,
-                             bilinear_filters[xoffset]);
+                             bilinear_filters_2t[xoffset]);
   var_filter_block2d_bil_w16(fdata3, temp2, 16, 16, 16, 16,
-                             bilinear_filters[yoffset]);
+                             bilinear_filters_2t[yoffset]);
   return aom_variance16x16_neon(temp2, 16, dst, dst_stride, sse);
 }
 
@@ -113,9 +109,9 @@ unsigned int aom_sub_pixel_variance32x32_neon(const uint8_t *src,
   DECLARE_ALIGNED(16, uint8_t, fdata3[33 * 32]);
 
   var_filter_block2d_bil_w16(src, fdata3, src_stride, 1, 33, 32,
-                             bilinear_filters[xoffset]);
+                             bilinear_filters_2t[xoffset]);
   var_filter_block2d_bil_w16(fdata3, temp2, 32, 32, 32, 32,
-                             bilinear_filters[yoffset]);
+                             bilinear_filters_2t[yoffset]);
   return aom_variance32x32_neon(temp2, 32, dst, dst_stride, sse);
 }
 
@@ -128,8 +124,8 @@ unsigned int aom_sub_pixel_variance64x64_neon(const uint8_t *src,
   DECLARE_ALIGNED(16, uint8_t, fdata3[65 * 64]);
 
   var_filter_block2d_bil_w16(src, fdata3, src_stride, 1, 65, 64,
-                             bilinear_filters[xoffset]);
+                             bilinear_filters_2t[xoffset]);
   var_filter_block2d_bil_w16(fdata3, temp2, 64, 64, 64, 64,
-                             bilinear_filters[yoffset]);
+                             bilinear_filters_2t[yoffset]);
   return aom_variance64x64_neon(temp2, 64, dst, dst_stride, sse);
 }

third_party/aom/aom_dsp/binary_codes_reader.c

@@ -36,7 +36,7 @@ static uint16_t inv_recenter_finite_nonneg(uint16_t n, uint16_t r, uint16_t v) {
 uint16_t aom_read_primitive_quniform_(aom_reader *r,
                                       uint16_t n ACCT_STR_PARAM) {
   if (n <= 1) return 0;
-  const int l = get_msb(n - 1) + 1;
+  const int l = get_msb(n) + 1;
   const int m = (1 << l) - n;
   const int v = aom_read_literal(r, l - 1, ACCT_STR_NAME);
   return v < m ? v : (v << 1) - m + aom_read_bit(r, ACCT_STR_NAME);
@@ -45,7 +45,7 @@ uint16_t aom_read_primitive_quniform_(aom_reader *r,
 static uint16_t aom_rb_read_primitive_quniform(struct aom_read_bit_buffer *rb,
                                                uint16_t n) {
   if (n <= 1) return 0;
-  const int l = get_msb(n - 1) + 1;
+  const int l = get_msb(n) + 1;
   const int m = (1 << l) - n;
   const int v = aom_rb_read_literal(rb, l - 1);
   return v < m ? v : (v << 1) - m + aom_rb_read_bit(rb);
@@ -121,13 +121,3 @@ int16_t aom_rb_read_signed_primitive_refsubexpfin(
   const uint16_t scaled_n = (n << 1) - 1;
   return aom_rb_read_primitive_refsubexpfin(rb, scaled_n, k, ref) - n + 1;
 }
-
-uint32_t aom_rb_read_uvlc(struct aom_read_bit_buffer *rb) {
-  int leading_zeros = 0;
-  while (!aom_rb_read_bit(rb)) ++leading_zeros;
-  // Maximum 32 bits.
-  if (leading_zeros >= 32) return UINT32_MAX;
-  const uint32_t base = (1u << leading_zeros) - 1;
-  const uint32_t value = aom_rb_read_literal(rb, leading_zeros);
-  return base + value;
-}

third_party/aom/aom_dsp/binary_codes_reader.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_BINARY_CODES_READER_H_
-#define AOM_DSP_BINARY_CODES_READER_H_
+#ifndef AOM_AOM_DSP_BINARY_CODES_READER_H_
+#define AOM_AOM_DSP_BINARY_CODES_READER_H_
 
 #ifdef __cplusplus
 extern "C" {
@@ -40,10 +40,8 @@ uint16_t aom_read_primitive_refsubexpfin_(aom_reader *r, uint16_t n, uint16_t k,
 int16_t aom_rb_read_signed_primitive_refsubexpfin(
     struct aom_read_bit_buffer *rb, uint16_t n, uint16_t k, int16_t ref);
 
-uint32_t aom_rb_read_uvlc(struct aom_read_bit_buffer *rb);
-
 #ifdef __cplusplus
 }  // extern "C"
 #endif
 
-#endif  // AOM_DSP_BINARY_CODES_READER_H_
+#endif  // AOM_AOM_DSP_BINARY_CODES_READER_H_

third_party/aom/aom_dsp/binary_codes_writer.c

@@ -59,7 +59,7 @@ int aom_count_primitive_symmetric(int16_t v, unsigned int abs_bits) {
 // Encodes a value v in [0, n-1] quasi-uniformly
 void aom_write_primitive_quniform(aom_writer *w, uint16_t n, uint16_t v) {
   if (n <= 1) return;
-  const int l = get_msb(n - 1) + 1;
+  const int l = get_msb(n) + 1;
   const int m = (1 << l) - n;
   if (v < m) {
     aom_write_literal(w, v, l - 1);
@@ -72,7 +72,7 @@ void aom_write_primitive_quniform(aom_writer *w, uint16_t n, uint16_t v) {
 static void aom_wb_write_primitive_quniform(struct aom_write_bit_buffer *wb,
                                             uint16_t n, uint16_t v) {
   if (n <= 1) return;
-  const int l = get_msb(n - 1) + 1;
+  const int l = get_msb(n) + 1;
   const int m = (1 << l) - n;
   if (v < m) {
     aom_wb_write_literal(wb, v, l - 1);
@@ -84,7 +84,7 @@ static void aom_wb_write_primitive_quniform(struct aom_write_bit_buffer *wb,
 
 int aom_count_primitive_quniform(uint16_t n, uint16_t v) {
   if (n <= 1) return 0;
-  const int l = get_msb(n - 1) + 1;
+  const int l = get_msb(n) + 1;
   const int m = (1 << l) - n;
   return v < m ? l - 1 : l;
 }
@@ -208,15 +208,3 @@ int aom_count_signed_primitive_refsubexpfin(uint16_t n, uint16_t k, int16_t ref,
   const uint16_t scaled_n = (n << 1) - 1;
   return aom_count_primitive_refsubexpfin(scaled_n, k, ref, v);
 }
-
-void aom_wb_write_uvlc(struct aom_write_bit_buffer *wb, uint32_t v) {
-  int64_t shift_val = ++v;
-  int leading_zeroes = 1;
-
-  assert(shift_val > 0);
-
-  while (shift_val >>= 1) leading_zeroes += 2;
-
-  aom_wb_write_literal(wb, 0, leading_zeroes >> 1);
-  aom_wb_write_unsigned_literal(wb, v, (leading_zeroes + 1) >> 1);
-}

third_party/aom/aom_dsp/binary_codes_writer.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_BINARY_CODES_WRITER_H_
-#define AOM_DSP_BINARY_CODES_WRITER_H_
+#ifndef AOM_AOM_DSP_BINARY_CODES_WRITER_H_
+#define AOM_AOM_DSP_BINARY_CODES_WRITER_H_
 
 #ifdef __cplusplus
 extern "C" {
@@ -61,9 +61,8 @@ int aom_count_primitive_refsubexpfin(uint16_t n, uint16_t k, uint16_t ref,
                                      uint16_t v);
 int aom_count_signed_primitive_refsubexpfin(uint16_t n, uint16_t k, int16_t ref,
                                             int16_t v);
-void aom_wb_write_uvlc(struct aom_write_bit_buffer *wb, uint32_t v);
 #ifdef __cplusplus
 }  // extern "C"
 #endif
 
-#endif  // AOM_DSP_BINARY_CODES_WRITER_H_
+#endif  // AOM_AOM_DSP_BINARY_CODES_WRITER_H_

third_party/aom/aom_dsp/bitreader.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_BITREADER_H_
-#define AOM_DSP_BITREADER_H_
+#ifndef AOM_AOM_DSP_BITREADER_H_
+#define AOM_AOM_DSP_BITREADER_H_
 
 #include <assert.h>
 #include <limits.h>
@@ -69,6 +69,12 @@ static INLINE int aom_reader_has_error(aom_reader *r) {
   return aom_daala_reader_has_error(r);
 }
 
+// Returns true if the bit reader has tried to decode more data from the buffer
+// than was actually provided.
+static INLINE int aom_reader_has_overflowed(const aom_reader *r) {
+  return aom_daala_reader_has_overflowed(r);
+}
+
 // Returns the position in the bit reader in bits.
 static INLINE uint32_t aom_reader_tell(const aom_reader *r) {
   return aom_daala_reader_tell(r);
@@ -151,4 +157,4 @@ static INLINE int aom_read_symbol_(aom_reader *r, aom_cdf_prob *cdf,
 }  // extern "C"
 #endif
 
-#endif  // AOM_DSP_BITREADER_H_
+#endif  // AOM_AOM_DSP_BITREADER_H_

third_party/aom/aom_dsp/bitreader_buffer.c

@@ -55,3 +55,13 @@ int aom_rb_read_inv_signed_literal(struct aom_read_bit_buffer *rb, int bits) {
   const unsigned value = (unsigned)aom_rb_read_literal(rb, bits + 1) << nbits;
   return ((int)value) >> nbits;
 }
+
+uint32_t aom_rb_read_uvlc(struct aom_read_bit_buffer *rb) {
+  int leading_zeros = 0;
+  while (!aom_rb_read_bit(rb)) ++leading_zeros;
+  // Maximum 32 bits.
+  if (leading_zeros >= 32) return UINT32_MAX;
+  const uint32_t base = (1u << leading_zeros) - 1;
+  const uint32_t value = aom_rb_read_literal(rb, leading_zeros);
+  return base + value;
+}

third_party/aom/aom_dsp/bitreader_buffer.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_BITREADER_BUFFER_H_
-#define AOM_DSP_BITREADER_BUFFER_H_
+#ifndef AOM_AOM_DSP_BITREADER_BUFFER_H_
+#define AOM_AOM_DSP_BITREADER_BUFFER_H_
 
 #include <limits.h>
 
@@ -41,8 +41,10 @@ uint32_t aom_rb_read_unsigned_literal(struct aom_read_bit_buffer *rb, int bits);
 
 int aom_rb_read_inv_signed_literal(struct aom_read_bit_buffer *rb, int bits);
 
+uint32_t aom_rb_read_uvlc(struct aom_read_bit_buffer *rb);
+
 #ifdef __cplusplus
 }  // extern "C"
 #endif
 
-#endif  // AOM_DSP_BITREADER_BUFFER_H_
+#endif  // AOM_AOM_DSP_BITREADER_BUFFER_H_

third_party/aom/aom_dsp/bitwriter.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_BITWRITER_H_
-#define AOM_DSP_BITWRITER_H_
+#ifndef AOM_AOM_DSP_BITWRITER_H_
+#define AOM_AOM_DSP_BITWRITER_H_
 
 #include <assert.h>
 
@@ -86,4 +86,4 @@ static INLINE void aom_write_symbol(aom_writer *w, int symb, aom_cdf_prob *cdf,
 }  // extern "C"
 #endif
 
-#endif  // AOM_DSP_BITWRITER_H_
+#endif  // AOM_AOM_DSP_BITWRITER_H_

third_party/aom/aom_dsp/bitwriter_buffer.c

@@ -73,3 +73,15 @@ void aom_wb_write_inv_signed_literal(struct aom_write_bit_buffer *wb, int data,
                                      int bits) {
   aom_wb_write_literal(wb, data, bits + 1);
 }
+
+void aom_wb_write_uvlc(struct aom_write_bit_buffer *wb, uint32_t v) {
+  int64_t shift_val = ++v;
+  int leading_zeroes = 1;
+
+  assert(shift_val > 0);
+
+  while (shift_val >>= 1) leading_zeroes += 2;
+
+  aom_wb_write_literal(wb, 0, leading_zeroes >> 1);
+  aom_wb_write_unsigned_literal(wb, v, (leading_zeroes + 1) >> 1);
+}

third_party/aom/aom_dsp/bitwriter_buffer.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_BITWRITER_BUFFER_H_
-#define AOM_DSP_BITWRITER_BUFFER_H_
+#ifndef AOM_AOM_DSP_BITWRITER_BUFFER_H_
+#define AOM_AOM_DSP_BITWRITER_BUFFER_H_
 
 #include "aom/aom_integer.h"
 
@@ -42,8 +42,10 @@ void aom_wb_overwrite_literal(struct aom_write_bit_buffer *wb, int data,
 void aom_wb_write_inv_signed_literal(struct aom_write_bit_buffer *wb, int data,
                                      int bits);
 
+void aom_wb_write_uvlc(struct aom_write_bit_buffer *wb, uint32_t v);
+
 #ifdef __cplusplus
 }  // extern "C"
 #endif
 
-#endif  // AOM_DSP_BITWRITER_BUFFER_H_
+#endif  // AOM_AOM_DSP_BITWRITER_BUFFER_H_

third_party/aom/aom_dsp/blend.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_BLEND_H_
-#define AOM_DSP_BLEND_H_
+#ifndef AOM_AOM_DSP_BLEND_H_
+#define AOM_AOM_DSP_BLEND_H_
 
 #include "aom_ports/mem.h"
 
@@ -42,4 +42,4 @@
 #define DIFF_FACTOR_LOG2 4
 #define DIFF_FACTOR (1 << DIFF_FACTOR_LOG2)
 
-#endif  // AOM_DSP_BLEND_H_
+#endif  // AOM_AOM_DSP_BLEND_H_

third_party/aom/aom_dsp/buf_ans.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_BUF_ANS_H_
-#define AOM_DSP_BUF_ANS_H_
+#ifndef AOM_AOM_DSP_BUF_ANS_H_
+#define AOM_AOM_DSP_BUF_ANS_H_
 // Buffered forward ANS writer.
 // Symbols are written to the writer in forward (decode) order and serialized
 // backwards due to ANS's stack like behavior.
@@ -133,4 +133,4 @@ static INLINE int buf_ans_write_end(struct BufAnsCoder *const c) {
 #ifdef __cplusplus
 }  // extern "C"
 #endif  // __cplusplus
-#endif  // AOM_DSP_BUF_ANS_H_
+#endif  // AOM_AOM_DSP_BUF_ANS_H_

third_party/aom/aom_dsp/daalaboolreader.c

@@ -39,3 +39,9 @@ uint32_t aom_daala_reader_tell(const daala_reader *r) {
 uint32_t aom_daala_reader_tell_frac(const daala_reader *r) {
   return od_ec_dec_tell_frac(&r->ec);
 }
+
+int aom_daala_reader_has_overflowed(const daala_reader *r) {
+  const uint32_t tell_bits = aom_daala_reader_tell(r);
+  const uint32_t tell_bytes = (tell_bits + 7) >> 3;
+  return ((ptrdiff_t)tell_bytes > r->buffer_end - r->buffer);
+}

third_party/aom/aom_dsp/daalaboolreader.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_DAALABOOLREADER_H_
-#define AOM_DSP_DAALABOOLREADER_H_
+#ifndef AOM_AOM_DSP_DAALABOOLREADER_H_
+#define AOM_AOM_DSP_DAALABOOLREADER_H_
 
 #include "aom/aom_integer.h"
 #include "aom_dsp/entdec.h"
@@ -44,6 +44,9 @@ const uint8_t *aom_daala_reader_find_begin(daala_reader *r);
 const uint8_t *aom_daala_reader_find_end(daala_reader *r);
 uint32_t aom_daala_reader_tell(const daala_reader *r);
 uint32_t aom_daala_reader_tell_frac(const daala_reader *r);
+// Returns true if the reader has tried to decode more data from the buffer
+// than was actually provided.
+int aom_daala_reader_has_overflowed(const daala_reader *r);
 
 static INLINE int aom_daala_read(daala_reader *r, int prob) {
   int bit;
@@ -154,4 +157,4 @@ static INLINE int daala_read_symbol(daala_reader *r, const aom_cdf_prob *cdf,
 }  // extern "C"
 #endif
 
-#endif
+#endif  // AOM_AOM_DSP_DAALABOOLREADER_H_

third_party/aom/aom_dsp/daalaboolwriter.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_DAALABOOLWRITER_H_
-#define AOM_DSP_DAALABOOLWRITER_H_
+#ifndef AOM_AOM_DSP_DAALABOOLWRITER_H_
+#define AOM_AOM_DSP_DAALABOOLWRITER_H_
 
 #include <stdio.h>
 
@@ -75,4 +75,4 @@ static INLINE void daala_write_symbol(daala_writer *w, int symb,
 }  // extern "C"
 #endif
 
-#endif
+#endif  // AOM_AOM_DSP_DAALABOOLWRITER_H_

third_party/aom/aom_dsp/entcode.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_ENTCODE_H_
-#define AOM_DSP_ENTCODE_H_
+#ifndef AOM_AOM_DSP_ENTCODE_H_
+#define AOM_AOM_DSP_ENTCODE_H_
 
 #include <limits.h>
 #include <stddef.h>
@@ -37,4 +37,4 @@ typedef uint32_t od_ec_window;
 OD_WARN_UNUSED_RESULT uint32_t od_ec_tell_frac(uint32_t nbits_total,
                                                uint32_t rng);
 
-#endif  // AOM_DSP_ENTCODE_H_
+#endif  // AOM_AOM_DSP_ENTCODE_H_

third_party/aom/aom_dsp/entdec.c

@@ -112,6 +112,7 @@ static int od_ec_dec_normalize(od_ec_dec *dec, od_ec_window dif, unsigned rng,
                                int ret) {
   int d;
   assert(rng <= 65535U);
+  // The number of leading zeros in the 16-bit binary representation of rng.
   d = 16 - OD_ILOG_NZ(rng);
   dec->cnt -= d;
   /*This is equivalent to shifting in 1's instead of 0's.*/

third_party/aom/aom_dsp/entdec.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#if !defined(_entdec_H)
-#define _entdec_H (1)
+#ifndef AOM_AOM_DSP_ENTDEC_H_
+#define AOM_AOM_DSP_ENTDEC_H_
 #include <limits.h>
 #include "aom_dsp/entcode.h"
 
@@ -80,4 +80,4 @@ OD_WARN_UNUSED_RESULT uint32_t od_ec_dec_tell_frac(const od_ec_dec *dec)
 }  // extern "C"
 #endif
 
-#endif
+#endif  // AOM_AOM_DSP_ENTDEC_H_

third_party/aom/aom_dsp/entenc.c

@@ -60,6 +60,7 @@ static void od_ec_enc_normalize(od_ec_enc *enc, od_ec_window low,
   int s;
   c = enc->cnt;
   assert(rng <= 65535U);
+  // The number of leading zeros in the 16-bit binary representation of rng.
   d = 16 - OD_ILOG_NZ(rng);
   s = c + d;
   /*TODO: Right now we flush every time we have at least one byte available.

third_party/aom/aom_dsp/entenc.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#if !defined(_entenc_H)
-#define _entenc_H (1)
+#ifndef AOM_AOM_DSP_ENTENC_H_
+#define AOM_AOM_DSP_ENTENC_H_
 #include <stddef.h>
 #include "aom_dsp/entcode.h"
 
@@ -82,4 +82,4 @@ void od_ec_enc_rollback(od_ec_enc *dst, const od_ec_enc *src);
 }  // extern "C"
 #endif
 
-#endif
+#endif  // AOM_AOM_DSP_ENTENC_H_

third_party/aom/aom_dsp/fft_common.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_FFT_COMMON_H_
-#define AOM_DSP_FFT_COMMON_H_
+#ifndef AOM_AOM_DSP_FFT_COMMON_H_
+#define AOM_AOM_DSP_FFT_COMMON_H_
 
 #ifdef __cplusplus
 extern "C" {
@@ -1047,4 +1047,4 @@ void aom_ifft_2d_gen(const float *input, float *temp, float *output, int n,
           add(w93[0], sub(mul(kWeight5, w157[0]), mul(kWeight6, w157[1]))));   \
   }
 
-#endif  // AOM_DSP_FFT_COMMON_H_
+#endif  // AOM_AOM_DSP_FFT_COMMON_H_

third_party/aom/aom_dsp/grain_synthesis.c

@@ -396,14 +396,15 @@ static void init_random_generator(int luma_line, uint16_t seed) {
   random_register ^= ((luma_num * 173 + 105) & 255);
 }
 
-static void generate_luma_grain_block(
+// Return 0 for success, -1 for failure
+static int generate_luma_grain_block(
     const aom_film_grain_t *params, int **pred_pos_luma, int *luma_grain_block,
     int luma_block_size_y, int luma_block_size_x, int luma_grain_stride,
     int left_pad, int top_pad, int right_pad, int bottom_pad) {
   if (params->num_y_points == 0) {
     memset(luma_grain_block, 0,
            sizeof(*luma_grain_block) * luma_block_size_y * luma_grain_stride);
-    return;
+    return 0;
   }
 
   int bit_depth = params->bit_depth;
@@ -433,9 +434,11 @@ static void generate_luma_grain_block(
                     ((wsum + rounding_offset) >> params->ar_coeff_shift),
                 grain_min, grain_max);
     }
+  return 0;
 }
 
-static void generate_chroma_grain_blocks(
+// Return 0 for success, -1 for failure
+static int generate_chroma_grain_blocks(
     const aom_film_grain_t *params,
     //                                  int** pred_pos_luma,
     int **pred_pos_chroma, int *luma_grain_block, int *cb_grain_block,
@@ -510,10 +513,11 @@ static void generate_chroma_grain_blocks(
           wsum_cb = wsum_cb + params->ar_coeffs_cb[pos] * av_luma;
           wsum_cr = wsum_cr + params->ar_coeffs_cr[pos] * av_luma;
         } else {
-          printf(
+          fprintf(
+              stderr,
               "Grain synthesis: prediction between two chroma components is "
               "not supported!");
-          exit(1);
+          return -1;
         }
       }
       if (params->num_cb_points || params->chroma_scaling_from_luma)
@@ -527,6 +531,7 @@ static void generate_chroma_grain_blocks(
                       ((wsum_cr + rounding_offset) >> params->ar_coeff_shift),
                   grain_min, grain_max);
     }
+  return 0;
 }
 
 static void init_scaling_function(const int scaling_points[][2], int num_points,
@@ -910,8 +915,8 @@ static void hor_boundary_overlap(int *top_block, int top_stride,
   }
 }
 
-void av1_add_film_grain(const aom_film_grain_t *params, const aom_image_t *src,
-                        aom_image_t *dst) {
+int av1_add_film_grain(const aom_film_grain_t *params, const aom_image_t *src,
+                       aom_image_t *dst) {
   uint8_t *luma, *cb, *cr;
   int height, width, luma_stride, chroma_stride;
   int use_high_bit_depth = 0;
@@ -953,8 +958,8 @@ void av1_add_film_grain(const aom_film_grain_t *params, const aom_image_t *src,
       chroma_subsamp_y = 0;
       break;
     default:  // unknown input format
-      printf("Film grain error: input format is not supported!");
-      exit(1);
+      fprintf(stderr, "Film grain error: input format is not supported!");
+      return -1;
   }
 
   assert(params->bit_depth == src->bit_depth);
@@ -1011,17 +1016,16 @@ void av1_add_film_grain(const aom_film_grain_t *params, const aom_image_t *src,
   luma_stride = dst->stride[AOM_PLANE_Y] >> use_high_bit_depth;
   chroma_stride = dst->stride[AOM_PLANE_U] >> use_high_bit_depth;
 
-  av1_add_film_grain_run(params, luma, cb, cr, height, width, luma_stride,
-                         chroma_stride, use_high_bit_depth, chroma_subsamp_y,
-                         chroma_subsamp_x, mc_identity);
-  return;
+  return av1_add_film_grain_run(
+      params, luma, cb, cr, height, width, luma_stride, chroma_stride,
+      use_high_bit_depth, chroma_subsamp_y, chroma_subsamp_x, mc_identity);
 }
 
-void av1_add_film_grain_run(const aom_film_grain_t *params, uint8_t *luma,
-                            uint8_t *cb, uint8_t *cr, int height, int width,
-                            int luma_stride, int chroma_stride,
-                            int use_high_bit_depth, int chroma_subsamp_y,
-                            int chroma_subsamp_x, int mc_identity) {
+int av1_add_film_grain_run(const aom_film_grain_t *params, uint8_t *luma,
+                           uint8_t *cb, uint8_t *cr, int height, int width,
+                           int luma_stride, int chroma_stride,
+                           int use_high_bit_depth, int chroma_subsamp_y,
+                           int chroma_subsamp_x, int mc_identity) {
   int **pred_pos_luma;
   int **pred_pos_chroma;
   int *luma_grain_block;
@@ -1085,18 +1089,20 @@ void av1_add_film_grain_run(const aom_film_grain_t *params, uint8_t *luma,
               chroma_block_size_y * chroma_block_size_x, chroma_subsamp_y,
               chroma_subsamp_x);
 
-  generate_luma_grain_block(params, pred_pos_luma, luma_grain_block,
-                            luma_block_size_y, luma_block_size_x,
-                            luma_grain_stride, left_pad, top_pad, right_pad,
-                            bottom_pad);
+  if (generate_luma_grain_block(params, pred_pos_luma, luma_grain_block,
+                                luma_block_size_y, luma_block_size_x,
+                                luma_grain_stride, left_pad, top_pad, right_pad,
+                                bottom_pad))
+    return -1;
 
-  generate_chroma_grain_blocks(
-      params,
-      //                               pred_pos_luma,
-      pred_pos_chroma, luma_grain_block, cb_grain_block, cr_grain_block,
-      luma_grain_stride, chroma_block_size_y, chroma_block_size_x,
-      chroma_grain_stride, left_pad, top_pad, right_pad, bottom_pad,
-      chroma_subsamp_y, chroma_subsamp_x);
+  if (generate_chroma_grain_blocks(
+          params,
+          //                               pred_pos_luma,
+          pred_pos_chroma, luma_grain_block, cb_grain_block, cr_grain_block,
+          luma_grain_stride, chroma_block_size_y, chroma_block_size_x,
+          chroma_grain_stride, left_pad, top_pad, right_pad, bottom_pad,
+          chroma_subsamp_y, chroma_subsamp_x))
+    return -1;
 
   init_scaling_function(params->scaling_points_y, params->num_y_points,
                         scaling_lut_y);
@@ -1399,4 +1405,5 @@ void av1_add_film_grain_run(const aom_film_grain_t *params, uint8_t *luma,
   dealloc_arrays(params, &pred_pos_luma, &pred_pos_chroma, &luma_grain_block,
                  &cb_grain_block, &cr_grain_block, &y_line_buf, &cb_line_buf,
                  &cr_line_buf, &y_col_buf, &cb_col_buf, &cr_col_buf);
+  return 0;
 }

third_party/aom/aom_dsp/grain_synthesis.h

@@ -13,8 +13,8 @@
  * \brief Describes film grain parameters and film grain synthesis
  *
  */
-#ifndef AOM_AOM_GRAIN_SYNTHESIS_H_
-#define AOM_AOM_GRAIN_SYNTHESIS_H_
+#ifndef AOM_AOM_DSP_GRAIN_SYNTHESIS_H_
+#define AOM_AOM_DSP_GRAIN_SYNTHESIS_H_
 
 #ifdef __cplusplus
 extern "C" {
@@ -85,6 +85,8 @@ typedef struct {
  *
  * Add film grain to an image
  *
+ * Returns 0 for success, -1 for failure
+ *
  * \param[in]    grain_params     Grain parameters
  * \param[in]    luma             luma plane
  * \param[in]    cb               cb plane
@@ -94,25 +96,27 @@ typedef struct {
  * \param[in]    luma_stride      luma plane stride
  * \param[in]    chroma_stride    chroma plane stride
  */
-void av1_add_film_grain_run(const aom_film_grain_t *grain_params, uint8_t *luma,
-                            uint8_t *cb, uint8_t *cr, int height, int width,
-                            int luma_stride, int chroma_stride,
-                            int use_high_bit_depth, int chroma_subsamp_y,
-                            int chroma_subsamp_x, int mc_identity);
+int av1_add_film_grain_run(const aom_film_grain_t *grain_params, uint8_t *luma,
+                           uint8_t *cb, uint8_t *cr, int height, int width,
+                           int luma_stride, int chroma_stride,
+                           int use_high_bit_depth, int chroma_subsamp_y,
+                           int chroma_subsamp_x, int mc_identity);
 
 /*!\brief Add film grain
  *
  * Add film grain to an image
  *
+ * Returns 0 for success, -1 for failure
+ *
  * \param[in]    grain_params     Grain parameters
  * \param[in]    src              Source image
  * \param[out]   dst              Resulting image with grain
  */
-void av1_add_film_grain(const aom_film_grain_t *grain_params,
-                        const aom_image_t *src, aom_image_t *dst);
+int av1_add_film_grain(const aom_film_grain_t *grain_params,
+                       const aom_image_t *src, aom_image_t *dst);
 
 #ifdef __cplusplus
 }  // extern "C"
 #endif
 
-#endif  // AOM_AOM_GRAIN_SYNTHESIS_H_
+#endif  // AOM_AOM_DSP_GRAIN_SYNTHESIS_H_

third_party/aom/aom_dsp/grain_table.h

@@ -99,4 +99,4 @@ void aom_film_grain_table_free(aom_film_grain_table_t *t);
 }
 #endif
 
-#endif
+#endif  // AOM_AOM_DSP_GRAIN_TABLE_H_

third_party/aom/aom_dsp/intrapred_common.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef _AOM_DSP_INTRAPRED_COMMON_H
-#define _AOM_DSP_INTRAPRED_COMMON_H
+#ifndef AOM_AOM_DSP_INTRAPRED_COMMON_H_
+#define AOM_AOM_DSP_INTRAPRED_COMMON_H_
 
 #include "config/aom_config.h"
 
@@ -44,4 +44,4 @@ static const uint8_t sm_weight_arrays[2 * MAX_BLOCK_DIM] = {
 };
 /* clang-format on */
 
-#endif  // _AOM_DSP_INTRAPRED_COMMON_H
+#endif  // AOM_AOM_DSP_INTRAPRED_COMMON_H_

third_party/aom/aom_dsp/mips/aom_convolve_msa.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_MIPS_AOM_CONVOLVE_MSA_H_
-#define AOM_DSP_MIPS_AOM_CONVOLVE_MSA_H_
+#ifndef AOM_AOM_DSP_MIPS_AOM_CONVOLVE_MSA_H_
+#define AOM_AOM_DSP_MIPS_AOM_CONVOLVE_MSA_H_
 
 #include "aom_dsp/mips/macros_msa.h"
 #include "aom_dsp/aom_filter.h"
@@ -76,4 +76,4 @@ extern const uint8_t mc_filt_mask_arr[16 * 3];
                 res7_m, out0, out1, out2, out3);                             \
   }
 
-#endif /* AOM_DSP_MIPS_AOM_CONVOLVE_MSA_H_ */
+#endif  // AOM_AOM_DSP_MIPS_AOM_CONVOLVE_MSA_H_

third_party/aom/aom_dsp/mips/common_dspr2.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_COMMON_MIPS_DSPR2_H_
-#define AOM_COMMON_MIPS_DSPR2_H_
+#ifndef AOM_AOM_DSP_MIPS_COMMON_DSPR2_H_
+#define AOM_AOM_DSP_MIPS_COMMON_DSPR2_H_
 
 #include <assert.h>
 
@@ -48,4 +48,4 @@ static INLINE void prefetch_store_streamed(unsigned char *dst) {
 }  // extern "C"
 #endif
 
-#endif  // AOM_COMMON_MIPS_DSPR2_H_
+#endif  // AOM_AOM_DSP_MIPS_COMMON_DSPR2_H_

third_party/aom/aom_dsp/mips/convolve2_horiz_dspr2.c

@@ -15,7 +15,6 @@
 #include "config/aom_dsp_rtcd.h"
 
 #include "aom_dsp/mips/convolve_common_dspr2.h"
-#include "aom_dsp/aom_convolve.h"
 #include "aom_dsp/aom_dsp_common.h"
 #include "aom_ports/mem.h"
 

third_party/aom/aom_dsp/mips/convolve2_vert_dspr2.c

@@ -15,7 +15,6 @@
 #include "config/aom_dsp_rtcd.h"
 
 #include "aom_dsp/mips/convolve_common_dspr2.h"
-#include "aom_dsp/aom_convolve.h"
 #include "aom_dsp/aom_dsp_common.h"
 #include "aom_ports/mem.h"
 

third_party/aom/aom_dsp/mips/convolve_common_dspr2.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_MIPS_AOM_COMMON_DSPR2_H_
-#define AOM_DSP_MIPS_AOM_COMMON_DSPR2_H_
+#ifndef AOM_AOM_DSP_MIPS_CONVOLVE_COMMON_DSPR2_H_
+#define AOM_AOM_DSP_MIPS_CONVOLVE_COMMON_DSPR2_H_
 
 #include <assert.h>
 
@@ -45,4 +45,4 @@ void aom_convolve2_vert_dspr2(const uint8_t *src, ptrdiff_t src_stride,
 }  // extern "C"
 #endif
 
-#endif  // AOM_DSP_MIPS_AOM_COMMON_DSPR2_H_
+#endif  // AOM_AOM_DSP_MIPS_CONVOLVE_COMMON_DSPR2_H_

third_party/aom/aom_dsp/mips/loopfilter_filters_dspr2.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_MIPS_LOOPFILTER_FILTERS_DSPR2_H_
-#define AOM_DSP_MIPS_LOOPFILTER_FILTERS_DSPR2_H_
+#ifndef AOM_AOM_DSP_MIPS_LOOPFILTER_FILTERS_DSPR2_H_
+#define AOM_AOM_DSP_MIPS_LOOPFILTER_FILTERS_DSPR2_H_
 
 #include <stdlib.h>
 
@@ -733,4 +733,4 @@ static INLINE void wide_mbfilter_dspr2(
 }  // extern "C"
 #endif
 
-#endif  // AOM_DSP_MIPS_LOOPFILTER_FILTERS_DSPR2_H_
+#endif  // AOM_AOM_DSP_MIPS_LOOPFILTER_FILTERS_DSPR2_H_

third_party/aom/aom_dsp/mips/loopfilter_macros_dspr2.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_MIPS_LOOPFILTER_MACROS_DSPR2_H_
-#define AOM_DSP_MIPS_LOOPFILTER_MACROS_DSPR2_H_
+#ifndef AOM_AOM_DSP_MIPS_LOOPFILTER_MACROS_DSPR2_H_
+#define AOM_AOM_DSP_MIPS_LOOPFILTER_MACROS_DSPR2_H_
 
 #include <stdlib.h>
 
@@ -434,4 +434,4 @@ extern "C" {
 }  // extern "C"
 #endif
 
-#endif  // AOM_DSP_MIPS_LOOPFILTER_MACROS_DSPR2_H_
+#endif  // AOM_AOM_DSP_MIPS_LOOPFILTER_MACROS_DSPR2_H_

third_party/aom/aom_dsp/mips/loopfilter_masks_dspr2.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_MIPS_LOOPFILTER_MASKS_DSPR2_H_
-#define AOM_DSP_MIPS_LOOPFILTER_MASKS_DSPR2_H_
+#ifndef AOM_AOM_DSP_MIPS_LOOPFILTER_MASKS_DSPR2_H_
+#define AOM_AOM_DSP_MIPS_LOOPFILTER_MASKS_DSPR2_H_
 
 #include <stdlib.h>
 
@@ -354,4 +354,4 @@ static INLINE void flatmask5(uint32_t p4, uint32_t p3, uint32_t p2, uint32_t p1,
 }  // extern "C"
 #endif
 
-#endif  // AOM_DSP_MIPS_LOOPFILTER_MASKS_DSPR2_H_
+#endif  // AOM_AOM_DSP_MIPS_LOOPFILTER_MASKS_DSPR2_H_

third_party/aom/aom_dsp/mips/loopfilter_msa.h

@@ -9,8 +9,8 @@
  * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
  */
 
-#ifndef AOM_DSP_LOOPFILTER_MSA_H_
-#define AOM_DSP_LOOPFILTER_MSA_H_
+#ifndef AOM_AOM_DSP_MIPS_LOOPFILTER_MSA_H_
+#define AOM_AOM_DSP_MIPS_LOOPFILTER_MSA_H_
 
 #include "aom_dsp/mips/macros_msa.h"
 
@@ -248,4 +248,4 @@
     mask_out = limit_in < (v16u8)mask_out;                                   \
     mask_out = __msa_xori_b(mask_out, 0xff);                                 \
   }
-#endif /* AOM_DSP_LOOPFILTER_MSA_H_ */
+#endif  // AOM_AOM_DSP_MIPS_LOOPFILTER_MSA_H_