Merge "Update CHANGELOG for Cayuga release" into cayuga
diff --git a/.mailmap b/.mailmap
index 5052f29..2e1d4a9 100644
--- a/.mailmap
+++ b/.mailmap
@@ -2,3 +2,4 @@
Johann Koenig <johannkoenig@google.com>
Tero Rintaluoma <teror@google.com> <tero.rintaluoma@on2.com>
Tom Finegan <tomfinegan@google.com>
+Ralph Giles <giles@xiph.org> <giles@entropywave.com>
diff --git a/AUTHORS b/AUTHORS
index b8fc45e..a93df45 100644
--- a/AUTHORS
+++ b/AUTHORS
@@ -4,8 +4,11 @@
Aaron Watry <awatry@gmail.com>
Adrian Grange <agrange@google.com>
Alex Converse <alex.converse@gmail.com>
+Alexis Ballier <aballier@gentoo.org>
+Alok Ahuja <waveletcoeff@gmail.com>
Andoni Morales Alastruey <ylatuya@gmail.com>
Andres Mejia <mcitadel@gmail.com>
+Aron Rosenberg <arosenberg@logitech.com>
Attila Nagy <attilanagy@google.com>
Fabio Pedretti <fabio.ped@libero.it>
Frank Galligan <fgalligan@google.com>
@@ -22,20 +25,29 @@
Jim Bankoski <jimbankoski@google.com>
Johann Koenig <johannkoenig@google.com>
John Koleszar <jkoleszar@google.com>
+Joshua Bleecher Snyder <josh@treelinelabs.com>
Justin Clift <justin@salasaga.org>
Justin Lebar <justin.lebar@gmail.com>
+Lou Quillio <louquillio@google.com>
Luca Barbato <lu_zero@gentoo.org>
Makoto Kato <makoto.kt@gmail.com>
Martin Ettl <ettl.martin78@googlemail.com>
Michael Kohler <michaelkohler@live.com>
+Mike Hommey <mhommey@mozilla.com>
Mikhal Shemer <mikhal@google.com>
Pascal Massimino <pascal.massimino@gmail.com>
Patrik Westin <patrik.westin@gmail.com>
Paul Wilkins <paulwilkins@google.com>
Pavol Rusnak <stick@gk2.sk>
Philip Jägenstedt <philipj@opera.com>
+Rafael Ávila de Espíndola <rafael.espindola@gmail.com>
+Ralph Giles <giles@xiph.org>
+Ronald S. Bultje <rbultje@google.com>
Scott LaVarnway <slavarnway@google.com>
+Stefan Holmer <holmer@google.com>
+Taekhyun Kim <takim@nvidia.com>
Tero Rintaluoma <teror@google.com>
+Thijs Vermeir <thijsvermeir@gmail.com>
Timothy B. Terriberry <tterribe@xiph.org>
Tom Finegan <tomfinegan@google.com>
Yaowu Xu <yaowu@google.com>
diff --git a/libs.mk b/libs.mk
index 452c3f8..757e068 100644
--- a/libs.mk
+++ b/libs.mk
@@ -180,7 +180,7 @@
else
LIBVPX_OBJS=$(call objs,$(CODEC_SRCS))
OBJS-$(BUILD_LIBVPX) += $(LIBVPX_OBJS)
-LIBS-$(CONFIG_STATIC) += $(BUILD_PFX)libvpx.a $(BUILD_PFX)libvpx_g.a
+LIBS-$(if $(BUILD_LIBVPX),$(CONFIG_STATIC)) += $(BUILD_PFX)libvpx.a $(BUILD_PFX)libvpx_g.a
$(BUILD_PFX)libvpx_g.a: $(LIBVPX_OBJS)
BUILD_LIBVPX_SO := $(if $(BUILD_LIBVPX),$(CONFIG_SHARED))
@@ -272,20 +272,20 @@
#
ifeq ($(filter icc gcc,$(TGT_CC)), $(TGT_CC))
- asm_com_offsets.asm: $(VP8_PREFIX)common/asm_com_offsets.c.S
+ $(BUILD_PFX)asm_com_offsets.asm: $(BUILD_PFX)$(VP8_PREFIX)common/asm_com_offsets.c.S
grep EQU $< | tr -d '$$\#' $(ADS2GAS) > $@
- $(VP8_PREFIX)common/asm_com_offsets.c.S: vp8/common/asm_com_offsets.c
- CLEAN-OBJS += asm_com_offsets.asm $(VP8_PREFIX)common/asm_com_offsets.c.S
+ $(BUILD_PFX)$(VP8_PREFIX)common/asm_com_offsets.c.S: $(VP8_PREFIX)common/asm_com_offsets.c
+ CLEAN-OBJS += $(BUILD_PFX)asm_com_offsets.asm $(BUILD_PFX)$(VP8_PREFIX)common/asm_com_offsets.c.S
- asm_enc_offsets.asm: $(VP8_PREFIX)encoder/asm_enc_offsets.c.S
+ $(BUILD_PFX)asm_enc_offsets.asm: $(BUILD_PFX)$(VP8_PREFIX)encoder/asm_enc_offsets.c.S
grep EQU $< | tr -d '$$\#' $(ADS2GAS) > $@
- $(VP8_PREFIX)encoder/asm_enc_offsets.c.S: vp8/encoder/asm_enc_offsets.c
- CLEAN-OBJS += asm_enc_offsets.asm $(VP8_PREFIX)encoder/asm_enc_offsets.c.S
+ $(BUILD_PFX)$(VP8_PREFIX)encoder/asm_enc_offsets.c.S: $(VP8_PREFIX)encoder/asm_enc_offsets.c
+ CLEAN-OBJS += $(BUILD_PFX)asm_enc_offsets.asm $(BUILD_PFX)$(VP8_PREFIX)encoder/asm_enc_offsets.c.S
- asm_dec_offsets.asm: $(VP8_PREFIX)decoder/asm_dec_offsets.c.S
+ $(BUILD_PFX)asm_dec_offsets.asm: $(BUILD_PFX)$(VP8_PREFIX)decoder/asm_dec_offsets.c.S
grep EQU $< | tr -d '$$\#' $(ADS2GAS) > $@
- $(VP8_PREFIX)decoder/asm_dec_offsets.c.S: vp8/decoder/asm_dec_offsets.c
- CLEAN-OBJS += asm_dec_offsets.asm $(VP8_PREFIX)decoder/asm_dec_offsets.c.S
+ $(BUILD_PFX)$(VP8_PREFIX)decoder/asm_dec_offsets.c.S: $(VP8_PREFIX)decoder/asm_dec_offsets.c
+ CLEAN-OBJS += $(BUILD_PFX)asm_dec_offsets.asm $(BUILD_PFX)$(VP8_PREFIX)decoder/asm_dec_offsets.c.S
else
ifeq ($(filter rvct,$(TGT_CC)), $(TGT_CC))
asm_com_offsets.asm: obj_int_extract
diff --git a/vp8/common/asm_com_offsets.c b/vp8/common/asm_com_offsets.c
index e167d26..e135a4d 100644
--- a/vp8/common/asm_com_offsets.c
+++ b/vp8/common/asm_com_offsets.c
@@ -9,6 +9,8 @@
*/
+#include "vpx_config.h"
+#include "vpx/vpx_codec.h"
#include "vpx_ports/asm_offsets.h"
#include "vpx_scale/yv12config.h"
@@ -25,8 +27,14 @@
DEFINE(yv12_buffer_config_u_buffer, offsetof(YV12_BUFFER_CONFIG, u_buffer));
DEFINE(yv12_buffer_config_v_buffer, offsetof(YV12_BUFFER_CONFIG, v_buffer));
DEFINE(yv12_buffer_config_border, offsetof(YV12_BUFFER_CONFIG, border));
+DEFINE(VP8BORDERINPIXELS_VAL, VP8BORDERINPIXELS);
END
/* add asserts for any offset that is not supported by assembly code */
/* add asserts for any size that is not supported by assembly code */
+
+#if HAVE_ARMV7
+/* vp8_yv12_extend_frame_borders_neon makes several assumptions based on this */
+ct_assert(VP8BORDERINPIXELS_VAL, VP8BORDERINPIXELS == 32)
+#endif
diff --git a/vp8/encoder/onyx_if.c b/vp8/encoder/onyx_if.c
index 8330203..36a1865 100644
--- a/vp8/encoder/onyx_if.c
+++ b/vp8/encoder/onyx_if.c
@@ -2594,6 +2594,8 @@
cpi->Source = &cpi->scaled_source;
#endif
}
+ else
+ cpi->Source = sd;
}
diff --git a/vpx_scale/arm/neon/vp8_vpxyv12_extendframeborders_neon.asm b/vpx_scale/arm/neon/vp8_vpxyv12_extendframeborders_neon.asm
index b0a3b93..8444b8e 100644
--- a/vpx_scale/arm/neon/vp8_vpxyv12_extendframeborders_neon.asm
+++ b/vpx_scale/arm/neon/vp8_vpxyv12_extendframeborders_neon.asm
@@ -18,42 +18,32 @@
AREA ||.text||, CODE, READONLY, ALIGN=2
;void vp8_yv12_extend_frame_borders_neon (YV12_BUFFER_CONFIG *ybf);
-;Note: this is VP8 function, which has border=32 and 16. Internal y_width and y_height
-; are always multiples of 16.
+; we depend on VP8BORDERINPIXELS being 32
|vp8_yv12_extend_frame_borders_neon| PROC
push {r4 - r10, lr}
vpush {d8 - d15}
- ;Not need to load y_width, since: y_width = y_stride - 2*border
- ldr r3, [r0, #yv12_buffer_config_border]
- ldr r1, [r0, #yv12_buffer_config_y_buffer] ;srcptr1
- ldr r4, [r0, #yv12_buffer_config_y_height]
- ldr lr, [r0, #yv12_buffer_config_y_stride]
+ ; Border = 32
+ ldr r3, [r0, #yv12_buffer_config_y_width] ; plane_width
+ ldr r1, [r0, #yv12_buffer_config_y_buffer] ; src_ptr1
+ ldr r4, [r0, #yv12_buffer_config_y_height] ; plane_height
+ ldr lr, [r0, #yv12_buffer_config_y_stride] ; plane_stride
- cmp r3, #16
- beq b16_extend_frame_borders
+; Border copy for Y plane
+; copy the left and right most columns out
+ add r6, r1, r3 ; dest_ptr2 = src_ptr2 + 1 (src_ptr1 + plane_width)
+ sub r2, r6, #1 ; src_ptr2 = src_ptr1 + plane_width - 1
+ sub r5, r1, #32 ; dest_ptr1 = src_ptr1 - Border
-;=======================
-b32_extend_frame_borders
-;border = 32
-;=======================
-;Border copy for Y plane
-;copy the left and right most columns out
- sub r5, r1, r3 ;destptr1
- add r6, r1, lr
- sub r6, r6, r3, lsl #1 ;destptr2
- sub r2, r6, #1 ;srcptr2
-
- ;Do four rows at one time
- mov r12, r4, lsr #2
+ mov r12, r4, lsr #2 ; plane_height / 4
copy_left_right_y
vld1.8 {d0[], d1[]}, [r1], lr
vld1.8 {d4[], d5[]}, [r2], lr
vld1.8 {d8[], d9[]}, [r1], lr
vld1.8 {d12[], d13[]}, [r2], lr
- vld1.8 {d16[], d17[]}, [r1], lr
+ vld1.8 {d16[], d17[]}, [r1], lr
vld1.8 {d20[], d21[]}, [r2], lr
vld1.8 {d24[], d25[]}, [r1], lr
vld1.8 {d28[], d29[]}, [r2], lr
@@ -81,15 +71,16 @@
bne copy_left_right_y
;Now copy the top and bottom source lines into each line of the respective borders
- ldr r7, [r0, #yv12_buffer_config_y_buffer] ;srcptr1
- mul r8, r3, lr
+ ldr r1, [r0, #yv12_buffer_config_y_buffer] ; y_buffer
+ mul r8, r4, lr ; plane_height * plane_stride
- mov r12, lr, lsr #7
+ ; copy width is plane_stride
+ mov r12, lr, lsr #7 ; plane_stride / 128
- sub r6, r1, r3 ;destptr2
- sub r2, r6, lr ;srcptr2
- sub r1, r7, r3 ;srcptr1
- sub r5, r1, r8 ;destptr1
+ sub r1, r1, #32 ; src_ptr1 = y_buffer - Border
+ add r6, r1, r8 ; dest_ptr2 = src_ptr2 - plane_stride (src_ptr1 + (plane_height * plane_stride))
+ sub r2, r6, lr ; src_ptr2 = src_ptr1 + (plane_height * plane_stride) - plane_stride
+ sub r5, r1, lr, asl #5 ; dest_ptr1 = src_ptr1 - (Border * plane_stride)
copy_top_bottom_y
vld1.8 {q0, q1}, [r1]!
@@ -101,7 +92,7 @@
vld1.8 {q6, q7}, [r1]!
vld1.8 {q14, q15}, [r2]!
- mov r7, r3
+ mov r7, #32 ; Border
top_bottom_32
subs r7, r7, #1
@@ -115,44 +106,41 @@
vst1.8 {q6, q7}, [r5]!
vst1.8 {q14, q15}, [r6]!
- add r5, r5, lr
- sub r5, r5, #128
- add r6, r6, lr
- sub r6, r6, #128
+ add r5, r5, lr ; dest_ptr1 += plane_stride
+ sub r5, r5, #128 ; dest_ptr1 -= 128
+ add r6, r6, lr ; dest_ptr2 += plane_stride
+ sub r6, r6, #128 ; dest_ptr2 -= 128
bne top_bottom_32
- sub r5, r1, r8
- add r6, r2, lr
+ sub r5, r1, lr, asl #5 ; src_ptr1 - (Border* plane_stride)
+ add r6, r2, lr ; src_ptr2 + plane_stride
subs r12, r12, #1
bne copy_top_bottom_y
- mov r7, lr, lsr #4 ;check to see if extra copy is needed
+ mov r7, lr, lsr #4 ; check to see if extra copy is needed
ands r7, r7, #0x7
bne extra_top_bottom_y
end_of_border_copy_y
;Border copy for U, V planes
- ldr r1, [r0, #yv12_buffer_config_u_buffer] ;srcptr1
- mov lr, lr, lsr #1 ;uv_stride
- mov r3, r3, lsr #1 ;border
- mov r4, r4, lsr #1 ;uv_height
- mov r8, r8, lsr #2
+; Border = 16
+ ldr r7, [r0, #yv12_buffer_config_u_buffer] ; src_ptr1
+ ldr lr, [r0, #yv12_buffer_config_uv_stride] ; plane_stride
+ ldr r3, [r0, #yv12_buffer_config_uv_width] ; plane_width
+ ldr r4, [r0, #yv12_buffer_config_uv_height] ; plane_height
mov r10, #2
;copy the left and right most columns out
border_copy_uv
- sub r5, r1, r3 ;destptr1
- add r6, r1, lr
- sub r6, r6, r3, lsl #1 ;destptr2
- sub r2, r6, #1 ;srcptr2
+ mov r1, r7 ; src_ptr1 needs to be saved for second half of loop
+ sub r5, r1, #16 ; dest_ptr1 = src_ptr1 - Border
+ add r6, r1, r3 ; dest_ptr2 = src_ptr2 + 1 (src_ptr1 + plane_width)
+ sub r2, r6, #1 ; src_ptr2 = src_ptr1 + plane_width - 1
- mov r7, r1
-
- ;Do eight rows at one time
- mov r12, r4, lsr #3
+ mov r12, r4, lsr #3 ; plane_height / 8
copy_left_right_uv
vld1.8 {d0[], d1[]}, [r1], lr
@@ -167,7 +155,7 @@
vld1.8 {d18[], d19[]}, [r2], lr
vld1.8 {d20[], d21[]}, [r1], lr
vld1.8 {d22[], d23[]}, [r2], lr
- vld1.8 {d24[], d25[]}, [r1], lr
+ vld1.8 {d24[], d25[]}, [r1], lr
vld1.8 {d26[], d27[]}, [r2], lr
vld1.8 {d28[], d29[]}, [r1], lr
vld1.8 {d30[], d31[]}, [r2], lr
@@ -194,12 +182,14 @@
bne copy_left_right_uv
;Now copy the top and bottom source lines into each line of the respective borders
- mov r12, lr, lsr #6
+ mov r1, r7
+ mul r8, r4, lr ; plane_height * plane_stride
+ mov r12, lr, lsr #6 ; plane_stride / 64
- sub r6, r1, r3 ;destptr2
- sub r2, r6, lr ;srcptr2
- sub r1, r7, r3 ;srcptr1
- sub r5, r1, r8 ;destptr1
+ sub r1, r1, #16 ; src_ptr1 = u_buffer - Border
+ add r6, r1, r8 ; dest_ptr2 = src_ptr2 + plane_stride (src_ptr1 + (plane_height * plane_stride)
+ sub r2, r6, lr ; src_ptr2 = src_ptr1 + (plane_height * plane_stride) - plane_stride
+ sub r5, r1, lr, asl #4 ; dest_ptr1 = src_ptr1 - (Border * plane_stride)
copy_top_bottom_uv
vld1.8 {q0, q1}, [r1]!
@@ -207,7 +197,7 @@
vld1.8 {q2, q3}, [r1]!
vld1.8 {q10, q11}, [r2]!
- mov r7, r3
+ mov r7, #16 ; Border
top_bottom_16
subs r7, r7, #1
@@ -217,38 +207,37 @@
vst1.8 {q2, q3}, [r5]!
vst1.8 {q10, q11}, [r6]!
- add r5, r5, lr
+ add r5, r5, lr ; dest_ptr1 += plane_stride
sub r5, r5, #64
- add r6, r6, lr
+ add r6, r6, lr ; dest_ptr2 += plane_stride
sub r6, r6, #64
bne top_bottom_16
- sub r5, r1, r8
- add r6, r2, lr
+ sub r5, r1, lr, asl #4 ; dest_ptr1 = src_ptr1 - (Border * plane_stride)
+ add r6, r2, lr ; dest_ptr2 = src_ptr2 + plane_stride
subs r12, r12, #1
bne copy_top_bottom_uv
- mov r7, lr, lsr #3 ;check to see if extra copy is needed
+ mov r7, lr, lsr #3 ; check to see if extra copy is needed
ands r7, r7, #0x7
bne extra_top_bottom_uv
end_of_border_copy_uv
subs r10, r10, #1
- ldrne r1, [r0, #yv12_buffer_config_v_buffer] ;srcptr1
+ ldrne r7, [r0, #yv12_buffer_config_v_buffer] ; src_ptr1
bne border_copy_uv
vpop {d8 - d15}
pop {r4 - r10, pc}
;;;;;;;;;;;;;;;;;;;;;;
-;extra copy part for Y
extra_top_bottom_y
vld1.8 {q0}, [r1]!
vld1.8 {q2}, [r2]!
- mov r9, r3, lsr #3
+ mov r9, #4 ; 32 >> 3
extra_top_bottom_32
subs r9, r9, #1
@@ -271,19 +260,18 @@
vst1.8 {q2}, [r6], lr
bne extra_top_bottom_32
- sub r5, r1, r8
- add r6, r2, lr
+ sub r5, r1, lr, asl #5 ; src_ptr1 - (Border * plane_stride)
+ add r6, r2, lr ; src_ptr2 + plane_stride
subs r7, r7, #1
bne extra_top_bottom_y
b end_of_border_copy_y
-;extra copy part for UV
extra_top_bottom_uv
vld1.8 {d0}, [r1]!
vld1.8 {d8}, [r2]!
- mov r9, r3, lsr #3
+ mov r9, #2 ; 16 >> 3
extra_top_bottom_16
subs r9, r9, #1
@@ -306,283 +294,12 @@
vst1.8 {d8}, [r6], lr
bne extra_top_bottom_16
- sub r5, r1, r8
- add r6, r2, lr
+ sub r5, r1, lr, asl #4 ; src_ptr1 - (Border * plane_stride)
+ add r6, r2, lr ; src_ptr2 + plane_stride
subs r7, r7, #1
bne extra_top_bottom_uv
b end_of_border_copy_uv
-
-;=======================
-b16_extend_frame_borders
-;border = 16
-;=======================
-;Border copy for Y plane
-;copy the left and right most columns out
- sub r5, r1, r3 ;destptr1
- add r6, r1, lr
- sub r6, r6, r3, lsl #1 ;destptr2
- sub r2, r6, #1 ;srcptr2
-
- ;Do four rows at one time
- mov r12, r4, lsr #2
-
-copy_left_right_y_b16
- vld1.8 {d0[], d1[]}, [r1], lr
- vld1.8 {d4[], d5[]}, [r2], lr
- vld1.8 {d8[], d9[]}, [r1], lr
- vld1.8 {d12[], d13[]}, [r2], lr
- vld1.8 {d16[], d17[]}, [r1], lr
- vld1.8 {d20[], d21[]}, [r2], lr
- vld1.8 {d24[], d25[]}, [r1], lr
- vld1.8 {d28[], d29[]}, [r2], lr
-
- subs r12, r12, #1
-
- vst1.8 {q0}, [r5], lr
- vst1.8 {q2}, [r6], lr
- vst1.8 {q4}, [r5], lr
- vst1.8 {q6}, [r6], lr
- vst1.8 {q8}, [r5], lr
- vst1.8 {q10}, [r6], lr
- vst1.8 {q12}, [r5], lr
- vst1.8 {q14}, [r6], lr
-
- bne copy_left_right_y_b16
-
-;Now copy the top and bottom source lines into each line of the respective borders
- ldr r7, [r0, #yv12_buffer_config_y_buffer] ;srcptr1
- mul r8, r3, lr
-
- mov r12, lr, lsr #7
-
- sub r6, r1, r3 ;destptr2
- sub r2, r6, lr ;srcptr2
- sub r1, r7, r3 ;srcptr1
- sub r5, r1, r8 ;destptr1
-
-copy_top_bottom_y_b16
- vld1.8 {q0, q1}, [r1]!
- vld1.8 {q8, q9}, [r2]!
- vld1.8 {q2, q3}, [r1]!
- vld1.8 {q10, q11}, [r2]!
- vld1.8 {q4, q5}, [r1]!
- vld1.8 {q12, q13}, [r2]!
- vld1.8 {q6, q7}, [r1]!
- vld1.8 {q14, q15}, [r2]!
-
- mov r7, r3
-
-top_bottom_16_b16
- subs r7, r7, #1
-
- vst1.8 {q0, q1}, [r5]!
- vst1.8 {q8, q9}, [r6]!
- vst1.8 {q2, q3}, [r5]!
- vst1.8 {q10, q11}, [r6]!
- vst1.8 {q4, q5}, [r5]!
- vst1.8 {q12, q13}, [r6]!
- vst1.8 {q6, q7}, [r5]!
- vst1.8 {q14, q15}, [r6]!
-
- add r5, r5, lr
- sub r5, r5, #128
- add r6, r6, lr
- sub r6, r6, #128
-
- bne top_bottom_16_b16
-
- sub r5, r1, r8
- add r6, r2, lr
-
- subs r12, r12, #1
- bne copy_top_bottom_y_b16
-
- mov r7, lr, lsr #4 ;check to see if extra copy is needed
- ands r7, r7, #0x7
- bne extra_top_bottom_y_b16
-end_of_border_copy_y_b16
-
-;Border copy for U, V planes
- ldr r1, [r0, #yv12_buffer_config_u_buffer] ;srcptr1
- mov lr, lr, lsr #1 ;uv_stride
- mov r3, r3, lsr #1 ;border
- mov r4, r4, lsr #1 ;uv_height
- mov r8, r8, lsr #2
-
- mov r10, #2
-
-;copy the left and right most columns out
-border_copy_uv_b16
- sub r5, r1, r3 ;destptr1
- add r6, r1, lr
- sub r6, r6, r3, lsl #1 ;destptr2
- sub r2, r6, #1 ;srcptr2
-
- mov r7, r1
-
- ;Do eight rows at one time
- mov r12, r4, lsr #3
-
-copy_left_right_uv_b16
- vld1.8 {d0[]}, [r1], lr
- vld1.8 {d2[]}, [r2], lr
- vld1.8 {d4[]}, [r1], lr
- vld1.8 {d6[]}, [r2], lr
- vld1.8 {d8[]}, [r1], lr
- vld1.8 {d10[]}, [r2], lr
- vld1.8 {d12[]}, [r1], lr
- vld1.8 {d14[]}, [r2], lr
- vld1.8 {d16[]}, [r1], lr
- vld1.8 {d18[]}, [r2], lr
- vld1.8 {d20[]}, [r1], lr
- vld1.8 {d22[]}, [r2], lr
- vld1.8 {d24[]}, [r1], lr
- vld1.8 {d26[]}, [r2], lr
- vld1.8 {d28[]}, [r1], lr
- vld1.8 {d30[]}, [r2], lr
-
- subs r12, r12, #1
-
- vst1.8 {d0}, [r5], lr
- vst1.8 {d2}, [r6], lr
- vst1.8 {d4}, [r5], lr
- vst1.8 {d6}, [r6], lr
- vst1.8 {d8}, [r5], lr
- vst1.8 {d10}, [r6], lr
- vst1.8 {d12}, [r5], lr
- vst1.8 {d14}, [r6], lr
- vst1.8 {d16}, [r5], lr
- vst1.8 {d18}, [r6], lr
- vst1.8 {d20}, [r5], lr
- vst1.8 {d22}, [r6], lr
- vst1.8 {d24}, [r5], lr
- vst1.8 {d26}, [r6], lr
- vst1.8 {d28}, [r5], lr
- vst1.8 {d30}, [r6], lr
-
- bne copy_left_right_uv_b16
-
-;Now copy the top and bottom source lines into each line of the respective borders
- mov r12, lr, lsr #6
-
- sub r6, r1, r3 ;destptr2
- sub r2, r6, lr ;srcptr2
- sub r1, r7, r3 ;srcptr1
- sub r5, r1, r8 ;destptr1
-
-copy_top_bottom_uv_b16
- vld1.8 {q0, q1}, [r1]!
- vld1.8 {q8, q9}, [r2]!
- vld1.8 {q2, q3}, [r1]!
- vld1.8 {q10, q11}, [r2]!
-
- mov r7, r3
-
-top_bottom_8_b16
- subs r7, r7, #1
-
- vst1.8 {q0, q1}, [r5]!
- vst1.8 {q8, q9}, [r6]!
- vst1.8 {q2, q3}, [r5]!
- vst1.8 {q10, q11}, [r6]!
-
- add r5, r5, lr
- sub r5, r5, #64
- add r6, r6, lr
- sub r6, r6, #64
-
- bne top_bottom_8_b16
-
- sub r5, r1, r8
- add r6, r2, lr
-
- subs r12, r12, #1
- bne copy_top_bottom_uv_b16
-
- mov r7, lr, lsr #3 ;check to see if extra copy is needed
- ands r7, r7, #0x7
- bne extra_top_bottom_uv_b16
-
-end_of_border_copy_uv_b16
- subs r10, r10, #1
- ldrne r1, [r0, #yv12_buffer_config_v_buffer] ;srcptr1
- bne border_copy_uv_b16
-
- vpop {d8-d15}
- pop {r4 - r10, pc}
-
-;;;;;;;;;;;;;;;;;;;;;;
-;extra copy part for Y
-extra_top_bottom_y_b16
- vld1.8 {q0}, [r1]!
- vld1.8 {q2}, [r2]!
-
- mov r9, r3, lsr #3
-
-extra_top_bottom_16_b16
- subs r9, r9, #1
-
- vst1.8 {q0}, [r5], lr
- vst1.8 {q2}, [r6], lr
- vst1.8 {q0}, [r5], lr
- vst1.8 {q2}, [r6], lr
- vst1.8 {q0}, [r5], lr
- vst1.8 {q2}, [r6], lr
- vst1.8 {q0}, [r5], lr
- vst1.8 {q2}, [r6], lr
- vst1.8 {q0}, [r5], lr
- vst1.8 {q2}, [r6], lr
- vst1.8 {q0}, [r5], lr
- vst1.8 {q2}, [r6], lr
- vst1.8 {q0}, [r5], lr
- vst1.8 {q2}, [r6], lr
- vst1.8 {q0}, [r5], lr
- vst1.8 {q2}, [r6], lr
- bne extra_top_bottom_16_b16
-
- sub r5, r1, r8
- add r6, r2, lr
- subs r7, r7, #1
- bne extra_top_bottom_y_b16
-
- b end_of_border_copy_y_b16
-
-;extra copy part for UV
-extra_top_bottom_uv_b16
- vld1.8 {d0}, [r1]!
- vld1.8 {d8}, [r2]!
-
- mov r9, r3, lsr #3
-
-extra_top_bottom_8_b16
- subs r9, r9, #1
-
- vst1.8 {d0}, [r5], lr
- vst1.8 {d8}, [r6], lr
- vst1.8 {d0}, [r5], lr
- vst1.8 {d8}, [r6], lr
- vst1.8 {d0}, [r5], lr
- vst1.8 {d8}, [r6], lr
- vst1.8 {d0}, [r5], lr
- vst1.8 {d8}, [r6], lr
- vst1.8 {d0}, [r5], lr
- vst1.8 {d8}, [r6], lr
- vst1.8 {d0}, [r5], lr
- vst1.8 {d8}, [r6], lr
- vst1.8 {d0}, [r5], lr
- vst1.8 {d8}, [r6], lr
- vst1.8 {d0}, [r5], lr
- vst1.8 {d8}, [r6], lr
- bne extra_top_bottom_8_b16
-
- sub r5, r1, r8
- add r6, r2, lr
- subs r7, r7, #1
- bne extra_top_bottom_uv_b16
-
- b end_of_border_copy_uv_b16
-
ENDP
END
