Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Contribute to GitLab
Sign in / Register
Toggle navigation
F
ffmpeg.wasm-core
Project
Project
Details
Activity
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
Linshizhi
ffmpeg.wasm-core
Commits
994c3550
Commit
994c3550
authored
Jun 02, 2011
by
Loren Merritt
Committed by
Ronald S. Bultje
Jun 02, 2011
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
2x faster h264_idct_add8_10.
Signed-off-by:
Ronald S. Bultje
<
rsbultje@gmail.com
>
parent
cc9947ff
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
21 additions
and
34 deletions
+21
-34
h264_idct_10bit.asm
libavcodec/x86/h264_idct_10bit.asm
+21
-34
No files found.
libavcodec/x86/h264_idct_10bit.asm
View file @
994c3550
...
...
@@ -249,16 +249,17 @@ IDCT8_DC_ADD avx
jmp
.
skipadd%2
%endmacro
%assign
last_block
16
%macro
ADD16_OP_INTRA
3
cmp
word
[
r4
+
%3
]
,
0
jnz
.
ac%2
mov
r
6
d
,
dword
[
r2
+
0
]
or
r
6
d
,
dword
[
r2
+
64
]
mov
r
5
d
,
dword
[
r2
+
0
]
or
r
5
d
,
dword
[
r2
+
64
]
jz
.
skipblock%2
mov
r5d
,
dword
[
r1
+
(
%2
+
0
)
*
4
]
call
idct_dc_add_
%1
.
skipblock%2:
%if
%2
<
15
%if
%2
<
last_block
-
2
add
r2
,
128
%endif
.
skipadd%2:
...
...
@@ -302,47 +303,33 @@ INIT_AVX
IDCT_ADD16INTRA_10
avx
%endif
%assign
last_block
24
;-----------------------------------------------------------------------------
; h264_idct_add8(pixel **dst, const int *block_offset, dctcoef *block, int stride, const uint8_t nnzc[6*8])
;-----------------------------------------------------------------------------
%macro
IDCT_ADD8
1
cglobal
h264_idct_add8_10_
%1
,
5
,
7
mov
r5
,
16
add
r2
,
1024
%ifdef
PIC
lea
r11
,
[
scan8_mem
]
%endif
%ifdef
ARCH_X86_64
mov
r10
,
r0
%endif
.
nextblock
:
movzx
r6
,
byte
[
scan8
+
r5
]
movzx
r6
,
byte
[
r4
+
r6
]
or
r6d
,
dword
[r2]
test
r6
,
r6
jz
.
skipblock
%ifdef
ARCH_X86_64
mov
r0d
,
dword
[
r1
+
r5
*
4
]
add
r0
,
[r10]
%else
mov
r0
,
r0m
add
r2
,
1024
mov
r0
,
[r0]
add
r0
,
dword
[
r1
+
r5
*
4
]
%endif
IDCT4_ADD_10
r0
,
r2
,
r3
.
skipblock
:
inc
r5
add
r2
,
64
test
r5
,
3
jnz
.
nextblock
ADD16_OP_INTRA
%1
,
16
,
1
+
1
*
8
ADD16_OP_INTRA
%1
,
18
,
1
+
2
*
8
%ifdef
ARCH_X86_64
add
r10
,
gprsize
mov
r0
,
[
r10
+
gprsize
]
%else
add
r0mp
,
gprsize
mov
r0
,
r0m
mov
r0
,
[
r0
+
gprsize
]
%endif
test
r5
,
4
jnz
.
nextblock
ADD16_OP_INTRA
%1
,
20
,
1
+
4
*
8
ADD16_OP_INTRA
%1
,
22
,
1
+
5
*
8
REP_RET
AC
%1
,
16
AC
%1
,
18
AC
%1
,
20
AC
%1
,
22
%endmacro
; IDCT_ADD8
INIT_XMM
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment