RepoMirrors
/
ffmpeg
mirror of https://git.ffmpeg.org/ffmpeg.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

avcodec/x86: allow future 8-bit simple idct to use slightly different coefficients

This commit is contained in:
James Darnley 2017-06-12 12:32:57 +01:00
parent 9d11fedd11
commit 8221c71703
3 changed files with 50 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
libavcodec/x86/proresdsp.asm
View File

@ -33,14 +33,14 @@ cextern pw_1
cextern pw_4
cextern pw_1019
; Below are defined in simple_idct10.asm built from selecting idctdsp
cextern w4_plus_w2
cextern w4_min_w2
cextern w4_plus_w6
cextern w4_min_w6
cextern w1_plus_w3
cextern w3_min_w1
cextern w7_plus_w3
cextern w3_min_w7
cextern w4_plus_w2_hi
cextern w4_min_w2_hi
cextern w4_plus_w6_hi
cextern w4_min_w6_hi
cextern w1_plus_w3_hi
cextern w3_min_w1_hi
cextern w7_plus_w3_hi
cextern w3_min_w7_hi
cextern w1_plus_w5
cextern w5_min_w1
cextern w5_plus_w7
@ -50,6 +50,8 @@ cextern w7_min_w5
SECTION .text
define_constants _hi
%macro idct_fn 0
cglobal prores_idct_put_10, 4, 4, 15, pixels, lsize, block, qmat
IDCT_FN pw_1, 15, pw_88, 18, "put", pw_4, pw_1019, r3

29
libavcodec/x86/simple_idct10.asm
View File

@ -46,28 +46,41 @@ times 4 dw %2, %3
%define W2sh2 21407 ; W2 = 85627 = 21407<<2 - 1
%define W3sh2 19265 ; W3 = 77062 = 19265<<2 + 2
%define W4sh2 16384 ; W4 = 65535 = 16384<<2 - 1
%define W3sh2_lo 19266
%define W4sh2_lo 16383
%define W5sh2 12873 ; W5 = 51491 = 12873<<2 - 1
%define W6sh2 8867 ; W6 = 35468 = 8867<<2
%define W7sh2 4520 ; W7 = 18081 = 4520<<2 + 1
CONST_DEC w4_plus_w2, W4sh2, +W2sh2
CONST_DEC w4_min_w2, W4sh2, -W2sh2
CONST_DEC w4_plus_w6, W4sh2, +W6sh2
CONST_DEC w4_min_w6, W4sh2, -W6sh2
CONST_DEC w1_plus_w3, W1sh2, +W3sh2
CONST_DEC w3_min_w1, W3sh2, -W1sh2
CONST_DEC w7_plus_w3, W7sh2, +W3sh2
CONST_DEC w3_min_w7, W3sh2, -W7sh2
CONST_DEC w4_plus_w2_hi, W4sh2, +W2sh2
CONST_DEC w4_min_w2_hi, W4sh2, -W2sh2
CONST_DEC w4_plus_w6_hi, W4sh2, +W6sh2
CONST_DEC w4_min_w6_hi, W4sh2, -W6sh2
CONST_DEC w1_plus_w3_hi, W1sh2, +W3sh2
CONST_DEC w3_min_w1_hi, W3sh2, -W1sh2
CONST_DEC w7_plus_w3_hi, W7sh2, +W3sh2
CONST_DEC w3_min_w7_hi, W3sh2, -W7sh2
CONST_DEC w1_plus_w5, W1sh2, +W5sh2
CONST_DEC w5_min_w1, W5sh2, -W1sh2
CONST_DEC w5_plus_w7, W5sh2, +W7sh2
CONST_DEC w7_min_w5, W7sh2, -W5sh2
CONST_DEC w4_plus_w2_lo, W4sh2_lo, +W2sh2
CONST_DEC w4_min_w2_lo, W4sh2_lo, -W2sh2
CONST_DEC w4_plus_w6_lo, W4sh2_lo, +W6sh2
CONST_DEC w4_min_w6_lo, W4sh2_lo, -W6sh2
CONST_DEC w1_plus_w3_lo, W1sh2, +W3sh2_lo
CONST_DEC w3_min_w1_lo, W3sh2_lo, -W1sh2
CONST_DEC w7_plus_w3_lo, W7sh2, +W3sh2_lo
CONST_DEC w3_min_w7_lo, W3sh2_lo, -W7sh2
%include "libavcodec/x86/simple_idct10_template.asm"
SECTION .text
%macro idct_fn 0
define_constants _hi
cglobal simple_idct10, 1, 1, 16, block
IDCT_FN "", 12, "", 19, "store"
RET

19
libavcodec/x86/simple_idct10_template.asm
View File

@ -26,6 +26,25 @@
%if ARCH_X86_64
%macro define_constants 1
%undef w4_plus_w2
%undef w4_min_w2
%undef w4_plus_w6
%undef w4_min_w6
%undef w1_plus_w3
%undef w3_min_w1
%undef w7_plus_w3
%undef w3_min_w7
%define w4_plus_w2 w4_plus_w2%1
%define w4_min_w2 w4_min_w2%1
%define w4_plus_w6 w4_plus_w6%1
%define w4_min_w6 w4_min_w6%1
%define w1_plus_w3 w1_plus_w3%1
%define w3_min_w1 w3_min_w1%1
%define w7_plus_w3 w7_plus_w3%1
%define w3_min_w7 w3_min_w7%1
%endmacro
; interleave data while maintaining source
; %1=type, %2=dstlo, %3=dsthi, %4=src, %5=interleave
%macro SBUTTERFLY3 5