zlib/intel/adler32vec.s

124 	subl	$140, %esp				// to save %xmm0-%xmm7 into stack, extra 12 to align %esp to 16-byte boundary
160 	// update adler/sum2 according to a new 16-byte vector
163 	movaps		%xmm1, %xmm3			// a copy of the vector, used for unsigned byte in the destination of pmaddubsw
183 	// update adler/sum2 according to a new 32-byte vector
188 	movaps		%xmm1, %xmm3			// a copy of 1st vector, used for unsigned byte in the destination of pmaddubsw
189 	movaps		%xmm7, %xmm2			// a copy of 2nd vector, used for unsigned byte in the destination of pmaddubsw
276 	DO32							// 			update adler/sum2 for a 32-byte input
279 	DO16							//  	update adler/sum2 for a 16-byte input
289 	DO32							//   update adler/sum2 for a 32-byte input
297 	DO16							// update adler/sum2 for a 16-byte input
305 	movzbl	(buf), %edx				// 	new input byte
370 	DO16_nossse3					//			update adler/sum2 for a 16-byte input
383 	DO16_nossse3					// update adler/sum2 for a 16-byte input
392 	.byte	32
393 	.byte	31
394 	.byte	30
395 	.byte	29
396 	.byte	28
397 	.byte	27
398 	.byte	26
399 	.byte	25
400 	.byte	24
401 	.byte	23
402 	.byte	22
403 	.byte	21
404 	.byte	20
405 	.byte	19
406 	.byte	18
407 	.byte	17
408 	.byte	16
409 	.byte	15
410 	.byte	14
411 	.byte	13
412 	.byte	12
413 	.byte	11
414 	.byte	10
415 	.byte	9
416 	.byte	8
417 	.byte	7
418 	.byte	6
419 	.byte	5
420 	.byte	4
421 	.byte	3
422 	.byte	2
423 	.byte	1
488 	subq	$200, %rsp	// allocate for %xmm0-%xmm11 (192 bytes), extra 8 to align %rsp to 16-byte boundary
521 	// update adler/sum2 according to a new 16-byte vector, no ssse3
573 	DO16_nossse3					//			update adler/sum2 for a 16-byte input
586 	DO16_nossse3					// update adler/sum2 for a 16-byte input
594 	movzbq	(buf), %rdx				// 	new input byte
681 	subq	$200, %rsp	// allocate for %xmm0-%xmm11 (192 bytes), extra 8 to align %rsp to 16-byte boundary
706 	// update adler/sum2 according to a new 16-byte vector
709 	movaps		%xmm1, %xmm3			// a copy of the vector, used for unsigned byte in the destination of pmaddubsw
729 	// update adler/sum2 according to a new 32-byte vector
734 	movaps		%xmm1, %xmm3			// a copy of 1st vector, used for unsigned byte in the destination of pmaddubsw
735 	movaps		%xmm7, %xmm2			// a copy of 2nd vector, used for unsigned byte in the destination of pmaddubsw
758 	// update adler/sum2 according to a new 48-byte vector
807 	// update adler/sum2 according to a new 64-byte vector
890 	DO64							// 			update adler/sum2 for a 64-byte input
894 	DO48							//		update adler/sum2 for a 48-byte input
906 	DO64							//   update adler/sum2 for a 64-byte input
913 	DO32							//   update adler/sum2 for a 32-byte input
920 	DO16							// update adler/sum2 for a 16-byte input
928 	movzbq	(buf), %rdx				// 	new input byte
973 	.byte	64
974 	.byte	63
975 	.byte	62
976 	.byte	61
977 	.byte	60
978 	.byte	59
979 	.byte	58
980 	.byte	57
981 	.byte	56
982 	.byte	55
983 	.byte	54
984 	.byte	53
985 	.byte	52
986 	.byte	51
987 	.byte	50
988 	.byte	49
989 	.byte	48
990 	.byte	47
991 	.byte	46
992 	.byte	45
993 	.byte	44
994 	.byte	43
995 	.byte	42
996 	.byte	41
997 	.byte	40
998 	.byte	39
999 	.byte	38
1000 	.byte	37
1001 	.byte	36
1002 	.byte	35
1003 	.byte	34
1004 	.byte	33
1005 	.byte	32
1006 	.byte	31
1007 	.byte	30
1008 	.byte	29
1009 	.byte	28
1010 	.byte	27
1011 	.byte	26
1012 	.byte	25
1013 	.byte	24
1014 	.byte	23
1015 	.byte	22
1016 	.byte	21
1017 	.byte	20
1018 	.byte	19
1019 	.byte	18
1020 	.byte	17
1021 	.byte	16
1022 	.byte	15
1023 	.byte	14
1024 	.byte	13
1025 	.byte	12
1026 	.byte	11
1027 	.byte	10
1028 	.byte	9
1029 	.byte	8
1030 	.byte	7
1031 	.byte	6
1032 	.byte	5
1033 	.byte	4
1034 	.byte	3
1035 	.byte	2
1036 	.byte	1