libvpx: Pull from upstream

source/libvpx/vp9/common/x86/vp9_mfqe_sse2.asm

 ;
-;  Copyright (c) 2012 The WebM project authors. All Rights Reserved.
+;  Copyright (c) 2015 The WebM project authors. All Rights Reserved.
 ;
 ;  Use of this source code is governed by a BSD-style license
 ;  that can be found in the LICENSE file in the root of the source
 ;  tree. An additional intellectual property rights grant can be found
 ;  in the file PATENTS.  All contributing project authors may
 ;  be found in the AUTHORS file in the root of the source tree.
 ;
 
-
+;  This file is a duplicate of mfqe_sse2.asm in VP8.
+;  TODO(jackychen): Find a way to fix the duplicate.
 %include "vpx_ports/x86_abi_support.asm"
 
-;void vp8_filter_by_weight16x16_sse2
+;void vp9_filter_by_weight16x16_sse2
 ;(
 ;    unsigned char *src,
 ;    int            src_stride,
 ;    unsigned char *dst,
 ;    int            dst_stride,
 ;    int            src_weight
 ;)
-global sym(vp8_filter_by_weight16x16_sse2) PRIVATE
-sym(vp8_filter_by_weight16x16_sse2):
+global sym(vp9_filter_by_weight16x16_sse2) PRIVATE
+sym(vp9_filter_by_weight16x16_sse2):
     push        rbp
     mov         rbp, rsp
     SHADOW_ARGS_TO_STACK 5
     SAVE_XMM 6
     GET_GOT     rbx
     push        rsi
     push        rdi
     ; end prolog
 
     movd        xmm0, arg(4)                ; src_weight
@@ skipping 48 matching lines @@
     ; begin epilog
     pop         rdi
     pop         rsi
     RESTORE_GOT
     RESTORE_XMM
     UNSHADOW_ARGS
     pop         rbp
 
     ret
 
-;void vp8_filter_by_weight8x8_sse2
+;void vp9_filter_by_weight8x8_sse2
 ;(
 ;    unsigned char *src,
 ;    int            src_stride,
 ;    unsigned char *dst,
 ;    int            dst_stride,
 ;    int            src_weight
 ;)
-global sym(vp8_filter_by_weight8x8_sse2) PRIVATE
-sym(vp8_filter_by_weight8x8_sse2):
+global sym(vp9_filter_by_weight8x8_sse2) PRIVATE
+sym(vp9_filter_by_weight8x8_sse2):
     push        rbp
     mov         rbp, rsp
     SHADOW_ARGS_TO_STACK 5
     GET_GOT     rbx
     push        rsi
     push        rdi
     ; end prolog
 
     movd        xmm0, arg(4)                ; src_weight
     pshuflw     xmm0, xmm0, 0x0             ; replicate to all low words
@@ skipping 37 matching lines @@
 
     ; begin epilog
     pop         rdi
     pop         rsi
     RESTORE_GOT
     UNSHADOW_ARGS
     pop         rbp
 
     ret
 
-;void vp8_variance_and_sad_16x16_sse2 | arg
+;void vp9_variance_and_sad_16x16_sse2 | arg
 ;(
 ;    unsigned char *src1,          0
 ;    int            stride1,       1
 ;    unsigned char *src2,          2
 ;    int            stride2,       3
 ;    unsigned int  *variance,      4
 ;    unsigned int  *sad,           5
 ;)
-global sym(vp8_variance_and_sad_16x16_sse2) PRIVATE
-sym(vp8_variance_and_sad_16x16_sse2):
+global sym(vp9_variance_and_sad_16x16_sse2) PRIVATE
+sym(vp9_variance_and_sad_16x16_sse2):
     push        rbp
     mov         rbp, rsp
     SHADOW_ARGS_TO_STACK 6
     GET_GOT     rbx
     push        rsi
     push        rdi
     ; end prolog
 
     mov         rax,        arg(0)          ; src1
     mov         rcx,        arg(1)          ; stride1
@@ skipping 97 matching lines @@
     dq  0, 128
 %else
     dq  128, 0
 %endif
 align 16
 tMFQE: ; 1 << MFQE_PRECISION
     times 8 dw 0x10
 align 16
 tMFQE_round: ; 1 << (MFQE_PRECISION - 1)
     times 8 dw 0x08
-