Update libvpx snapshot to v0.9.7-p1 (Cayuga).

source/libvpx/vp8/encoder/arm/armv6/vp8_variance_halfpixvar16x16_h_armv6.asm

 ;
 ;  Copyright (c) 2011 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.
 ;
 
 
     EXPORT  |vp8_variance_halfpixvar16x16_h_armv6|
 
     ARM
     REQUIRE8
     PRESERVE8
 
     AREA ||.text||, CODE, READONLY, ALIGN=2
 
 ; r0    unsigned char *src_ptr
 ; r1    int source_stride
 ; r2    unsigned char *ref_ptr
 ; r3    int  recon_stride
 ; stack unsigned int *sse
 |vp8_variance_halfpixvar16x16_h_armv6| PROC
 
     stmfd   sp!, {r4-r12, lr}
+
+    pld     [r0, r1, lsl #0]
+    pld     [r2, r3, lsl #0]
+
     mov     r8, #0              ; initialize sum = 0
     ldr     r10, c80808080
     mov     r11, #0             ; initialize sse = 0
     mov     r12, #16            ; set loop counter to 16 (=block height)
     mov     lr, #0              ; constant zero
 loop
     ; 1st 4 pixels
     ldr     r4, [r0, #0]        ; load 4 src pixels
     ldr     r6, [r0, #1]        ; load 4 src pixels with 1 byte offset
     ldr     r5, [r2, #0]        ; load 4 ref pixels
 
     ; bilinear interpolation
     mvn     r6, r6
     uhsub8  r4, r4, r6
     eor     r4, r4, r10
 
     usub8   r6, r4, r5          ; calculate difference
+    pld     [r0, r1, lsl #1]
     sel     r7, r6, lr          ; select bytes with positive difference
     usub8   r6, r5, r4          ; calculate difference with reversed operands
+    pld     [r2, r3, lsl #1]
     sel     r6, r6, lr          ; select bytes with negative difference
 
     ; calculate partial sums
     usad8   r4, r7, lr          ; calculate sum of positive differences
     usad8   r5, r6, lr          ; calculate sum of negative differences
     orr     r6, r6, r7          ; differences of all 4 pixels
     ; calculate total sum
     adds    r8, r8, r4          ; add positive differences to sum
     subs    r8, r8, r5          ; substract negative differences from sum
 
@@ skipping 110 matching lines @@
 
     ldmfd   sp!, {r4-r12, pc}
 
     ENDP
 
 c80808080
     DCD     0x80808080
 
     END