mplayer.hg: mp3lib/dct64_3dnow.s annotate

annotate mp3lib/dct64_3dnow.s @ 1271:2864e32cd267

Finished 3dnow optimization (in scalar mode) and minor improvements

author	nick
date	Wed, 04 Jul 2001 09:47:56 +0000
parents	03b7e2955a20
children	3a9699d9e7da

rev	line source
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	1 # This code was taken from http://www.mpg123.org
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	2 # See ChangeLog of mpg123-0.59s-pre.1 for detail
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	3 # Applied to mplayer by Nick Kurshev <nickols_k@mail.ru>
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	4 # Partial 3dnow! optimization by Nick Kurshev
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	5 #
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	6 # TODO: optimize scalar 3dnow! code
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	7 # Warning: Phases 7 & 8 are not tested
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	8 #
1 3b5f5d1c5041 Initial revision arpi_esp parents: diff changeset	9
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	10 .text
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	11
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	12 .align 16
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	13
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	14 .globl dct64_MMX_3dnow
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	15 dct64_MMX_3dnow:
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	16 pushl %ebx
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	17 pushl %esi
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	18 pushl %edi
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	19 subl $256,%esp
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	20 movl 280(%esp),%eax
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	21 leal 128(%esp),%edx
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	22 movl 272(%esp),%esi
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	23 movl 276(%esp),%edi
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	24 movl $costab_mmx,%ebx
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	25 orl %ecx,%ecx
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	26 movl %esp,%ecx
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	27
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	28 /* Phase 1*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	29 movq (%eax), %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	30 movq 8(%eax), %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	31 movq %mm0, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	32 movq %mm4, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	33 movq 120(%eax), %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	34 movq 112(%eax), %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	35 /* n.b.: pswapd*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	36 movq %mm1, %mm2
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	37 movq %mm5, %mm6
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	38 psrlq $32, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	39 psrlq $32, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	40 punpckldq %mm2, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	41 punpckldq %mm6, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	42 /**/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	43 pfadd %mm1, %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	44 pfadd %mm5, %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	45 movq %mm0, (%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	46 movq %mm4, 8(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	47 pfsub %mm1, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	48 pfsub %mm5, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	49 pfmul (%ebx), %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	50 pfmul 8(%ebx), %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	51 movd %mm3, 124(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	52 movd %mm7, 116(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	53 psrlq $32, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	54 psrlq $32, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	55 movd %mm3, 120(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	56 movd %mm7, 112(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	57
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	58 movq 16(%eax), %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	59 movq 24(%eax), %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	60 movq %mm0, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	61 movq %mm4, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	62 movq 104(%eax), %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	63 movq 96(%eax), %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	64 /* n.b.: pswapd*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	65 movq %mm1, %mm2
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	66 movq %mm5, %mm6
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	67 psrlq $32, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	68 psrlq $32, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	69 punpckldq %mm2, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	70 punpckldq %mm6, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	71 /**/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	72 pfadd %mm1, %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	73 pfadd %mm5, %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	74 movq %mm0, 16(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	75 movq %mm4, 24(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	76 pfsub %mm1, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	77 pfsub %mm5, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	78 pfmul 16(%ebx), %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	79 pfmul 24(%ebx), %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	80 movd %mm3, 108(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	81 movd %mm7, 100(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	82 psrlq $32, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	83 psrlq $32, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	84 movd %mm3, 104(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	85 movd %mm7, 96(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	86
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	87 movq 32(%eax), %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	88 movq 40(%eax), %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	89 movq %mm0, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	90 movq %mm4, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	91 movq 88(%eax), %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	92 movq 80(%eax), %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	93 /* n.b.: pswapd*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	94 movq %mm1, %mm2
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	95 movq %mm5, %mm6
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	96 psrlq $32, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	97 psrlq $32, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	98 punpckldq %mm2, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	99 punpckldq %mm6, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	100 /**/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	101 pfadd %mm1, %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	102 pfadd %mm5, %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	103 movq %mm0, 32(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	104 movq %mm4, 40(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	105 pfsub %mm1, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	106 pfsub %mm5, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	107 pfmul 32(%ebx), %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	108 pfmul 40(%ebx), %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	109 movd %mm3, 92(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	110 movd %mm7, 84(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	111 psrlq $32, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	112 psrlq $32, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	113 movd %mm3, 88(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	114 movd %mm7, 80(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	115
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	116 movq 48(%eax), %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	117 movq 56(%eax), %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	118 movq %mm0, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	119 movq %mm4, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	120 movq 72(%eax), %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	121 movq 64(%eax), %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	122 /* n.b.: pswapd*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	123 movq %mm1, %mm2
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	124 movq %mm5, %mm6
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	125 psrlq $32, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	126 psrlq $32, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	127 punpckldq %mm2, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	128 punpckldq %mm6, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	129 /**/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	130 pfadd %mm1, %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	131 pfadd %mm5, %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	132 movq %mm0, 48(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	133 movq %mm4, 56(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	134 pfsub %mm1, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	135 pfsub %mm5, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	136 pfmul 48(%ebx), %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	137 pfmul 56(%ebx), %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	138 movd %mm3, 76(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	139 movd %mm7, 68(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	140 psrlq $32, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	141 psrlq $32, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	142 movd %mm3, 72(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	143 movd %mm7, 64(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	144
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	145 /* Phase 2*/
1 3b5f5d1c5041 Initial revision arpi_esp parents: diff changeset	146
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	147 movq (%edx), %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	148 movq 8(%edx), %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	149 movq %mm0, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	150 movq %mm4, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	151 movq 56(%edx), %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	152 movq 48(%edx), %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	153 /* n.b.: pswapd*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	154 movq %mm1, %mm2
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	155 movq %mm5, %mm6
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	156 psrlq $32, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	157 psrlq $32, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	158 punpckldq %mm2, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	159 punpckldq %mm6, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	160 /**/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	161 pfadd %mm1, %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	162 pfadd %mm5, %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	163 movq %mm0, (%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	164 movq %mm4, 8(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	165 pfsub %mm1, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	166 pfsub %mm5, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	167 pfmul 64(%ebx), %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	168 pfmul 72(%ebx), %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	169 movd %mm3, 60(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	170 movd %mm7, 52(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	171 psrlq $32, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	172 psrlq $32, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	173 movd %mm3, 56(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	174 movd %mm7, 48(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	175
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	176 movq 16(%edx), %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	177 movq 24(%edx), %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	178 movq %mm0, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	179 movq %mm4, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	180 movq 40(%edx), %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	181 movq 32(%edx), %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	182 /* n.b.: pswapd*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	183 movq %mm1, %mm2
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	184 movq %mm5, %mm6
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	185 psrlq $32, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	186 psrlq $32, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	187 punpckldq %mm2, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	188 punpckldq %mm6, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	189 /**/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	190 pfadd %mm1, %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	191 pfadd %mm5, %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	192 movq %mm0, 16(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	193 movq %mm4, 24(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	194 pfsub %mm1, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	195 pfsub %mm5, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	196 pfmul 80(%ebx), %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	197 pfmul 88(%ebx), %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	198 movd %mm3, 44(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	199 movd %mm7, 36(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	200 psrlq $32, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	201 psrlq $32, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	202 movd %mm3, 40(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	203 movd %mm7, 32(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	204
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	205 /* Phase 3*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	206
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	207 movq 64(%edx), %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	208 movq 72(%edx), %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	209 movq %mm0, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	210 movq %mm4, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	211 movq 120(%edx), %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	212 movq 112(%edx), %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	213 /* n.b.: pswapd*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	214 movq %mm1, %mm2
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	215 movq %mm5, %mm6
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	216 psrlq $32, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	217 psrlq $32, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	218 punpckldq %mm2, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	219 punpckldq %mm6, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	220 /**/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	221 pfadd %mm1, %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	222 pfadd %mm5, %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	223 movq %mm0, 64(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	224 movq %mm4, 72(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	225 pfsubr %mm1, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	226 pfsubr %mm5, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	227 pfmul 64(%ebx), %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	228 pfmul 72(%ebx), %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	229 movd %mm3, 124(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	230 movd %mm7, 116(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	231 psrlq $32, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	232 psrlq $32, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	233 movd %mm3, 120(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	234 movd %mm7, 112(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	235
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	236 movq 80(%edx), %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	237 movq 88(%edx), %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	238 movq %mm0, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	239 movq %mm4, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	240 movq 104(%edx), %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	241 movq 96(%edx), %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	242 /* n.b.: pswapd*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	243 movq %mm1, %mm2
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	244 movq %mm5, %mm6
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	245 psrlq $32, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	246 psrlq $32, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	247 punpckldq %mm2, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	248 punpckldq %mm6, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	249 /**/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	250 pfadd %mm1, %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	251 pfadd %mm5, %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	252 movq %mm0, 80(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	253 movq %mm4, 88(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	254 pfsubr %mm1, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	255 pfsubr %mm5, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	256 pfmul 80(%ebx), %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	257 pfmul 88(%ebx), %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	258 movd %mm3, 108(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	259 movd %mm7, 100(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	260 psrlq $32, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	261 psrlq $32, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	262 movd %mm3, 104(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	263 movd %mm7, 96(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	264
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	265 /* Phase 4*/
1 3b5f5d1c5041 Initial revision arpi_esp parents: diff changeset	266
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	267 movq (%ecx), %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	268 movq 8(%ecx), %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	269 movq %mm0, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	270 movq %mm4, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	271 movq 24(%ecx), %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	272 movq 16(%ecx), %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	273 /* n.b.: pswapd*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	274 movq %mm1, %mm2
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	275 movq %mm5, %mm6
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	276 psrlq $32, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	277 psrlq $32, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	278 punpckldq %mm2, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	279 punpckldq %mm6, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	280 /**/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	281 pfadd %mm1, %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	282 pfadd %mm5, %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	283 movq %mm0, (%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	284 movq %mm4, 8(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	285 pfsub %mm1, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	286 pfsub %mm5, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	287 pfmul 96(%ebx), %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	288 pfmul 104(%ebx), %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	289 movd %mm3, 28(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	290 movd %mm7, 20(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	291 psrlq $32, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	292 psrlq $32, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	293 movd %mm3, 24(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	294 movd %mm7, 16(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	295
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	296 movq 32(%ecx), %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	297 movq 40(%ecx), %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	298 movq %mm0, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	299 movq %mm4, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	300 movq 56(%ecx), %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	301 movq 48(%ecx), %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	302 /* n.b.: pswapd*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	303 movq %mm1, %mm2
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	304 movq %mm5, %mm6
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	305 psrlq $32, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	306 psrlq $32, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	307 punpckldq %mm2, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	308 punpckldq %mm6, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	309 /**/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	310 pfadd %mm1, %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	311 pfadd %mm5, %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	312 movq %mm0, 32(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	313 movq %mm4, 40(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	314 pfsubr %mm1, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	315 pfsubr %mm5, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	316 pfmul 96(%ebx), %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	317 pfmul 104(%ebx), %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	318 movd %mm3, 60(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	319 movd %mm7, 52(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	320 psrlq $32, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	321 psrlq $32, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	322 movd %mm3, 56(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	323 movd %mm7, 48(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	324
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	325 movq 64(%ecx), %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	326 movq 72(%ecx), %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	327 movq %mm0, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	328 movq %mm4, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	329 movq 88(%ecx), %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	330 movq 80(%ecx), %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	331 /* n.b.: pswapd*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	332 movq %mm1, %mm2
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	333 movq %mm5, %mm6
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	334 psrlq $32, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	335 psrlq $32, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	336 punpckldq %mm2, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	337 punpckldq %mm6, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	338 /**/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	339 pfadd %mm1, %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	340 pfadd %mm5, %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	341 movq %mm0, 64(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	342 movq %mm4, 72(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	343 pfsub %mm1, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	344 pfsub %mm5, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	345 pfmul 96(%ebx), %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	346 pfmul 104(%ebx), %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	347 movd %mm3, 92(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	348 movd %mm7, 84(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	349 psrlq $32, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	350 psrlq $32, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	351 movd %mm3, 88(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	352 movd %mm7, 80(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	353
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	354 movq 96(%ecx), %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	355 movq 104(%ecx), %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	356 movq %mm0, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	357 movq %mm4, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	358 movq 120(%ecx), %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	359 movq 112(%ecx), %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	360 /* n.b.: pswapd*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	361 movq %mm1, %mm2
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	362 movq %mm5, %mm6
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	363 psrlq $32, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	364 psrlq $32, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	365 punpckldq %mm2, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	366 punpckldq %mm6, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	367 /**/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	368 pfadd %mm1, %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	369 pfadd %mm5, %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	370 movq %mm0, 96(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	371 movq %mm4, 104(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	372 pfsubr %mm1, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	373 pfsubr %mm5, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	374 pfmul 96(%ebx), %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	375 pfmul 104(%ebx), %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	376 movd %mm3, 124(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	377 movd %mm7, 116(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	378 psrlq $32, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	379 psrlq $32, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	380 movd %mm3, 120(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	381 movd %mm7, 112(%edx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	382
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	383 /* Phase 5 */
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	384
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	385 movq (%edx), %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	386 movq 16(%edx), %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	387 movq %mm0, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	388 movq %mm4, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	389 movq 8(%edx), %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	390 movq 24(%edx), %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	391 /* n.b.: pswapd*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	392 movq %mm1, %mm2
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	393 movq %mm5, %mm6
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	394 psrlq $32, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	395 psrlq $32, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	396 punpckldq %mm2, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	397 punpckldq %mm6, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	398 /**/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	399 pfadd %mm1, %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	400 pfadd %mm5, %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	401 movq %mm0, (%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	402 movq %mm4, 16(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	403 pfsub %mm1, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	404 pfsubr %mm5, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	405 pfmul 112(%ebx), %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	406 pfmul 112(%ebx), %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	407 movd %mm3, 12(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	408 movd %mm7, 28(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	409 psrlq $32, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	410 psrlq $32, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	411 movd %mm3, 8(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	412 movd %mm7, 24(%ecx)
1 3b5f5d1c5041 Initial revision arpi_esp parents: diff changeset	413
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	414 movq 32(%edx), %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	415 movq 48(%edx), %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	416 movq %mm0, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	417 movq %mm4, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	418 movq 40(%edx), %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	419 movq 56(%edx), %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	420 /* n.b.: pswapd*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	421 movq %mm1, %mm2
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	422 movq %mm5, %mm6
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	423 psrlq $32, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	424 psrlq $32, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	425 punpckldq %mm2, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	426 punpckldq %mm6, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	427 /**/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	428 pfadd %mm1, %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	429 pfadd %mm5, %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	430 movq %mm0, 32(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	431 movq %mm4, 48(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	432 pfsub %mm1, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	433 pfsubr %mm5, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	434 pfmul 112(%ebx), %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	435 pfmul 112(%ebx), %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	436 movd %mm3, 44(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	437 movd %mm7, 60(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	438 psrlq $32, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	439 psrlq $32, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	440 movd %mm3, 40(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	441 movd %mm7, 56(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	442
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	443 movq 64(%edx), %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	444 movq 80(%edx), %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	445 movq %mm0, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	446 movq %mm4, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	447 movq 72(%edx), %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	448 movq 88(%edx), %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	449 /* n.b.: pswapd*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	450 movq %mm1, %mm2
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	451 movq %mm5, %mm6
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	452 psrlq $32, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	453 psrlq $32, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	454 punpckldq %mm2, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	455 punpckldq %mm6, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	456 /**/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	457 pfadd %mm1, %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	458 pfadd %mm5, %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	459 movq %mm0, 64(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	460 movq %mm4, 80(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	461 pfsub %mm1, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	462 pfsubr %mm5, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	463 pfmul 112(%ebx), %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	464 pfmul 112(%ebx), %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	465 movd %mm3, 76(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	466 movd %mm7, 92(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	467 psrlq $32, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	468 psrlq $32, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	469 movd %mm3, 72(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	470 movd %mm7, 88(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	471
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	472 movq 96(%edx), %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	473 movq 112(%edx), %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	474 movq %mm0, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	475 movq %mm4, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	476 movq 104(%edx), %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	477 movq 120(%edx), %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	478 /* n.b.: pswapd*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	479 movq %mm1, %mm2
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	480 movq %mm5, %mm6
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	481 psrlq $32, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	482 psrlq $32, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	483 punpckldq %mm2, %mm1
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	484 punpckldq %mm6, %mm5
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	485 /**/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	486 pfadd %mm1, %mm0
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	487 pfadd %mm5, %mm4
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	488 movq %mm0, 96(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	489 movq %mm4, 112(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	490 pfsub %mm1, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	491 pfsubr %mm5, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	492 pfmul 112(%ebx), %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	493 pfmul 112(%ebx), %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	494 movd %mm3, 108(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	495 movd %mm7, 124(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	496 psrlq $32, %mm3
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	497 psrlq $32, %mm7
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	498 movd %mm3, 104(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	499 movd %mm7, 120(%ecx)
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	500
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	501 /* Phase 6. This is the end of easy road. */
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	502 /* Code below is coded in scalar mode. Should be optimized */
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	503
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	504 movd 32(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	505 pfadd 36(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	506 movd %mm0, 32(%edx)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	507
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	508 movd 32(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	509 pfsub 36(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	510 pfmul 120(%ebx),%mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	511 movd %mm0, 36(%edx)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	512
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	513 movd 44(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	514 pfsub 40(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	515 pfmul 120(%ebx),%mm0
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	516
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	517 movd %mm0, 44(%edx)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	518 pfadd 40(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	519 pfadd 44(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	520 movd %mm0, 40(%edx)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	521
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	522 movd 48(%ecx), %mm3
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	523 pfsub 52(%ecx), %mm3
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	524 pfmul 120(%ebx), %mm3
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	525
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	526 movd 60(%ecx), %mm2
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	527 pfsub 56(%ecx), %mm2
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	528 pfmul 120(%ebx), %mm2
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	529 movq %mm2, %mm1
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	530
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	531 pfadd 56(%ecx), %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	532 pfadd 60(%ecx), %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	533 movq %mm1, %mm0
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	534
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	535 pfadd 48(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	536 pfadd 52(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	537 movd %mm0, 48(%edx)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	538 pfadd %mm3, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	539 movd %mm1, 56(%edx)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	540 movd %mm2, 60(%edx)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	541 pfadd %mm3, %mm2
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	542 movd %mm2, 52(%edx)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	543
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	544 /---/
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	545 movd 64(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	546 pfadd 68(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	547 movd %mm0, 64(%edx)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	548
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	549 movd 64(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	550 pfsub 68(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	551 pfmul 120(%ebx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	552 movd %mm0, 68(%edx)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	553
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	554 movd 76(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	555 pfsub 72(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	556 pfmul 120(%ebx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	557 movd %mm0, 76(%edx)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	558 pfadd 72(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	559 pfadd 76(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	560 movd %mm0, 72(%edx)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	561
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	562 movd 92(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	563 pfsub 88(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	564 pfmul 120(%ebx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	565 movd %mm0, 92(%edx)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	566 pfadd 92(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	567 pfadd 88(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	568 movq %mm0, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	569
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	570 pfadd 80(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	571 pfadd 84(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	572 movd %mm0, 80(%edx)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	573
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	574 movd 80(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	575 pfsub 84(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	576 pfmul 120(%ebx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	577 pfadd %mm0, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	578 pfadd 92(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	579 movd %mm0, 84(%edx)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	580 movd %mm1, 88(%edx)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	581
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	582 movd 96(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	583 pfadd 100(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	584 movd %mm0, 96(%edx)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	585
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	586 movd 96(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	587 pfsub 100(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	588 pfmul 120(%ebx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	589 movd %mm0, 100(%edx)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	590
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	591 movd 108(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	592 pfsub 104(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	593 pfmul 120(%ebx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	594 movd %mm0, 108(%edx)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	595 pfadd 104(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	596 pfadd 108(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	597 movd %mm0, 104(%edx)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	598
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	599 movd 124(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	600 pfsub 120(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	601 pfmul 120(%ebx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	602 movd %mm0, 124(%edx)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	603 pfadd 120(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	604 pfadd 124(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	605 movq %mm0, %mm1
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	606
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	607 pfadd 112(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	608 pfadd 116(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	609 movd %mm0, 112(%edx)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	610
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	611 movd 112(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	612 pfsub 116(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	613 pfmul 120(%ebx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	614 pfadd %mm0,%mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	615 pfadd 124(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	616 movd %mm0, 116(%edx)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	617 movd %mm1, 120(%edx)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	618
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	619 jnz .L01
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	620
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	621 /* Phase 7*/
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	622 /* Code below is coded in scalar mode. Should be optimized */
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	623
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	624 movd (%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	625 pfadd 4(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	626 movd %mm0, 1024(%esi)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	627
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	628 movd (%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	629 pfsub 4(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	630 pfmul 120(%ebx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	631 movd %mm0, (%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	632 movd %mm0, (%edi)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	633
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	634 movd 12(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	635 pfsub 8(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	636 pfmul 120(%ebx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	637 movd %mm0, 512(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	638 pfadd 12(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	639 pfadd 8(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	640 movd %mm0, 512(%esi)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	641
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	642 movd 16(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	643 pfsub 20(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	644 pfmul 120(%ebx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	645 movq %mm0, %mm3
1 3b5f5d1c5041 Initial revision arpi_esp parents: diff changeset	646
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	647 movd 28(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	648 pfsub 24(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	649 pfmul 120(%ebx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	650 movd %mm0, 768(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	651 movq %mm0, %mm2
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	652
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	653 pfadd 24(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	654 pfadd 28(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	655 movq %mm0, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	656
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	657 pfadd 16(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	658 pfadd 20(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	659 movd %mm0, 768(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	660 pfadd %mm3, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	661 movd %mm1, 256(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	662 pfadd %mm3, %mm2
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	663 movd %mm2, 256(%edi)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	664
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	665 /* Phase 8*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	666
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	667 movq 32(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	668 movq 48(%edx), %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	669 pfadd 48(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	670 pfadd 40(%edx), %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	671 movd %mm0, 896(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	672 movd %mm1, 640(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	673 psrlq $32, %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	674 psrlq $32, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	675 movd %mm0, 128(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	676 movd %mm1, 384(%edi)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	677
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	678 movd 40(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	679 pfadd 56(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	680 movd %mm0, 384(%esi)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	681
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	682 movd 56(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	683 pfadd 36(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	684 movd %mm0, 128(%esi)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	685
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	686 movd 60(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	687 movd %mm0, 896(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	688 pfadd 44(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	689 movd %mm0, 640(%edi)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	690
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	691 movq 96(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	692 movq 112(%edx), %mm2
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	693 movq 104(%edx), %mm4
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	694 pfadd 112(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	695 pfadd 104(%edx), %mm2
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	696 pfadd 120(%edx), %mm4
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	697 movq %mm0, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	698 movq %mm2, %mm3
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	699 movq %mm4, %mm5
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	700 pfadd 64(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	701 pfadd 80(%edx), %mm2
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	702 pfadd 72(%edx), %mm4
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	703 movd %mm0, 960(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	704 movd %mm2, 704(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	705 movd %mm4, 448(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	706 psrlq $32, %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	707 psrlq $32, %mm2
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	708 psrlq $32, %mm4
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	709 movd %mm0, 64(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	710 movd %mm2, 320(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	711 movd %mm4, 576(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	712 pfadd 80(%edx), %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	713 pfadd 72(%edx), %mm3
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	714 pfadd 88(%edx), %mm5
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	715 movd %mm1, 832(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	716 movd %mm3, 576(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	717 movd %mm5, 320(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	718 psrlq $32, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	719 psrlq $32, %mm3
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	720 psrlq $32, %mm5
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	721 movd %mm1, 192(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	722 movd %mm3, 448(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	723 movd %mm5, 704(%edi)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	724
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	725 movd 120(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	726 pfadd 100(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	727 movq %mm0, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	728 pfadd 88(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	729 movd %mm0, 192(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	730 pfadd 68(%edx), %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	731 movd %mm1, 64(%esi)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	732
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	733 movd 124(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	734 movd %mm0, 960(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	735 pfadd 92(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	736 movd %mm0, 832(%edi)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	737
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	738 jmp .L_bye
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	739 .L01:
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	740 /* Phase 9*/
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	741 movd (%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	742 pfadd 4(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	743 pf2id %mm0, %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	744 movd %mm0, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	745 movw %ax, 512(%esi)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	746
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	747 movd (%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	748 pfsub 4(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	749 pfmul 120(%ebx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	750 pf2id %mm0, %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	751 movd %mm0, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	752 movw %ax, (%esi)
1 3b5f5d1c5041 Initial revision arpi_esp parents: diff changeset	753
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	754 movd 12(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	755 pfsub 8(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	756 pfmul 120(%ebx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	757 pf2id %mm0, %mm7
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	758 movd %mm7, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	759 movw %ax, 256(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	760 pfadd 12(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	761 pfadd 8(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	762 pf2id %mm0, %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	763 movd %mm0, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	764 movw %ax, 256(%esi)
1 3b5f5d1c5041 Initial revision arpi_esp parents: diff changeset	765
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	766 movd 16(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	767 pfsub 20(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	768 pfmul 120(%ebx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	769 movq %mm0, %mm3
1 3b5f5d1c5041 Initial revision arpi_esp parents: diff changeset	770
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	771 movd 28(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	772 pfsub 24(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	773 pfmul 120(%ebx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	774 pf2id %mm0, %mm7
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	775 movd %mm7, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	776 movw %ax, 384(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	777 movq %mm0, %mm2
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	778
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	779 pfadd 24(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	780 pfadd 28(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	781 movq %mm0, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	782 pfadd 16(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	783 pfadd 20(%ecx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	784 pf2id %mm0, %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	785 movd %mm0, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	786 movw %ax, 384(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	787 pfadd %mm3, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	788 pf2id %mm1, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	789 movd %mm1, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	790 movw %ax, 128(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	791 pfadd %mm3, %mm2
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	792 pf2id %mm2, %mm2
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	793 movd %mm2, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	794 movw %ax, 128(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	795
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	796
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	797 /* Phase 10*/
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	798
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	799 movq 32(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	800 movq 48(%edx), %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	801 pfadd 48(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	802 pfadd 40(%edx), %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	803 pf2id %mm0, %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	804 pf2id %mm1, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	805 movd %mm0, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	806 movd %mm1, %ecx
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	807 movw %ax, 448(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	808 movw %cx, 320(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	809 psrlq $32, %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	810 psrlq $32, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	811 movd %mm0, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	812 movd %mm1, %ecx
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	813 movw %ax, 64(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	814 movw %cx, 192(%edi)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	815
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	816 movd 40(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	817 pfadd 56(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	818 pf2id %mm0, %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	819 movd %mm0, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	820 movw %ax, 192(%esi)
1 3b5f5d1c5041 Initial revision arpi_esp parents: diff changeset	821
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	822 movd 56(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	823 pfadd 36(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	824 pf2id %mm0, %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	825 movd %mm0, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	826 movw %ax, 64(%esi)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	827
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	828 movd 60(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	829 pf2id %mm0, %mm7
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	830 movd %mm7, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	831 movw %ax, 448(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	832 pfadd 44(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	833 pf2id %mm0, %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	834 movd %mm0, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	835 movw %ax, 320(%edi)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	836
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	837 movq 96(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	838 movq 112(%edx), %mm2
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	839 movq 104(%edx), %mm4
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	840 pfadd 112(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	841 pfadd 104(%edx), %mm2
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	842 pfadd 120(%edx), %mm4
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	843 movq %mm0, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	844 movq %mm2, %mm3
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	845 movq %mm4, %mm5
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	846 pfadd 64(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	847 pfadd 80(%edx), %mm2
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	848 pfadd 72(%edx), %mm4
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	849 pf2id %mm0, %mm7
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	850 pf2id %mm2, %mm6
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	851 pf2id %mm4, %mm4
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	852 movd %mm7, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	853 movd %mm6, %ecx
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	854 movd %mm4, %ebx
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	855 movw %ax, 480(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	856 movw %cx, 352(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	857 movw %bx, 224(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	858 psrlq $32, %mm7
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	859 psrlq $32, %mm6
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	860 psrlq $32, %mm4
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	861 movd %mm7, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	862 movd %mm6, %ecx
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	863 movd %mm4, %ebx
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	864 movw %ax, 32(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	865 movw %cx, 160(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	866 movw %bx, 288(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	867 pfadd 80(%edx), %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	868 pfadd 72(%edx), %mm3
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	869 pfadd 88(%edx), %mm5
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	870 pf2id %mm1, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	871 pf2id %mm3, %mm3
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	872 pf2id %mm5, %mm5
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	873 movd %mm1, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	874 movd %mm3, %ecx
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	875 movd %mm5, %ebx
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	876 movw %ax, 416(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	877 movw %cx, 288(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	878 movw %bx, 160(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	879 psrlq $32, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	880 psrlq $32, %mm3
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	881 psrlq $32, %mm5
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	882 movd %mm1, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	883 movd %mm3, %ecx
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	884 movd %mm5, %ebx
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	885 movw %ax, 96(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	886 movw %cx, 224(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	887 movw %bx, 352(%edi)
1 3b5f5d1c5041 Initial revision arpi_esp parents: diff changeset	888
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	889 movd 120(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	890 pfadd 100(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	891 movq %mm0, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	892 pfadd 88(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	893 pf2id %mm0, %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	894 movd %mm0, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	895 movw %ax, 96(%esi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	896 pfadd 68(%edx), %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	897 pf2id %mm1, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	898 movd %mm1, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	899 movw %ax, 32(%esi)
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	900
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	901 movq 124(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	902 pf2id %mm0, %mm1
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	903 movd %mm1, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	904 movw %ax, 480(%edi)
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	905 pfadd 92(%edx), %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	906 pf2id %mm0, %mm0
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	907 movd %mm0, %eax
2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	908 movw %ax, 416(%edi)
1 3b5f5d1c5041 Initial revision arpi_esp parents: diff changeset	909
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	910 movsw
1 3b5f5d1c5041 Initial revision arpi_esp parents: diff changeset	911
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	912 .L_bye:
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	913 addl $256,%esp
1271 2864e32cd267 Finished 3dnow optimization (in scalar mode) and minor improvements nick parents: 1245 diff changeset	914 femms
1245 03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	915 popl %edi
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	916 popl %esi
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	917 popl %ebx
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	918 ret
03b7e2955a20 Added newest MMX-optimized decore which speedups decoding at least on 13% for any cpu. nick parents: 1 diff changeset	919
1 3b5f5d1c5041 Initial revision arpi_esp parents: diff changeset	920

Mercurial > mplayer.hg

annotate mp3lib/dct64_3dnow.s @ 1271:2864e32cd267