| xf.li | bdd93d5 | 2023-05-12 07:10:14 -0700 | [diff] [blame] | 1 | # Alpha 21064 __mpn_rshift -- | 
|  | 2 |  | 
|  | 3 | # Copyright (C) 1994-2016 Free Software Foundation, Inc. | 
|  | 4 |  | 
|  | 5 | # This file is part of the GNU MP Library. | 
|  | 6 |  | 
|  | 7 | # The GNU MP Library is free software; you can redistribute it and/or modify | 
|  | 8 | # it under the terms of the GNU Lesser General Public License as published by | 
|  | 9 | # the Free Software Foundation; either version 2.1 of the License, or (at your | 
|  | 10 | # option) any later version. | 
|  | 11 |  | 
|  | 12 | # The GNU MP Library is distributed in the hope that it will be useful, but | 
|  | 13 | # WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY | 
|  | 14 | # or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public | 
|  | 15 | # License for more details. | 
|  | 16 |  | 
|  | 17 | # You should have received a copy of the GNU Lesser General Public License | 
|  | 18 | # along with the GNU MP Library.  If not, see <http://www.gnu.org/licenses/>. | 
|  | 19 |  | 
|  | 20 |  | 
|  | 21 | # INPUT PARAMETERS | 
|  | 22 | # res_ptr	r16 | 
|  | 23 | # s1_ptr	r17 | 
|  | 24 | # size		r18 | 
|  | 25 | # cnt		r19 | 
|  | 26 |  | 
|  | 27 | # This code runs at 4.8 cycles/limb on the 21064.  With infinite unrolling, | 
|  | 28 | # it would take 4 cycles/limb.  It should be possible to get down to 3 | 
|  | 29 | # cycles/limb since both ldq and stq can be paired with the other used | 
|  | 30 | # instructions.  But there are many restrictions in the 21064 pipeline that | 
|  | 31 | # makes it hard, if not impossible, to get down to 3 cycles/limb: | 
|  | 32 |  | 
|  | 33 | # 1. ldq has a 3 cycle delay, srl and sll have a 2 cycle delay. | 
|  | 34 | # 2. Only aligned instruction pairs can be paired. | 
|  | 35 | # 3. The store buffer or silo might not be able to deal with the bandwidth. | 
|  | 36 |  | 
|  | 37 | .set	noreorder | 
|  | 38 | .set	noat | 
|  | 39 | .text | 
|  | 40 | .align	3 | 
|  | 41 | .globl	__mpn_rshift | 
|  | 42 | .ent	__mpn_rshift | 
|  | 43 | __mpn_rshift: | 
|  | 44 | .frame	$30,0,$26,0 | 
|  | 45 |  | 
|  | 46 | ldq	$4,0($17)	# load first limb | 
|  | 47 | addq	$17,8,$17 | 
|  | 48 | subq	$31,$19,$7 | 
|  | 49 | subq	$18,1,$18 | 
|  | 50 | and	$18,4-1,$20	# number of limbs in first loop | 
|  | 51 | sll	$4,$7,$0	# compute function result | 
|  | 52 |  | 
|  | 53 | beq	$20,.L0 | 
|  | 54 | subq	$18,$20,$18 | 
|  | 55 |  | 
|  | 56 | .align	3 | 
|  | 57 | .Loop0: | 
|  | 58 | ldq	$3,0($17) | 
|  | 59 | addq	$16,8,$16 | 
|  | 60 | addq	$17,8,$17 | 
|  | 61 | subq	$20,1,$20 | 
|  | 62 | srl	$4,$19,$5 | 
|  | 63 | sll	$3,$7,$6 | 
|  | 64 | bis	$3,$3,$4 | 
|  | 65 | bis	$5,$6,$8 | 
|  | 66 | stq	$8,-8($16) | 
|  | 67 | bne	$20,.Loop0 | 
|  | 68 |  | 
|  | 69 | .L0:	beq	$18,.Lend | 
|  | 70 |  | 
|  | 71 | .align	3 | 
|  | 72 | .Loop:	ldq	$3,0($17) | 
|  | 73 | addq	$16,32,$16 | 
|  | 74 | subq	$18,4,$18 | 
|  | 75 | srl	$4,$19,$5 | 
|  | 76 | sll	$3,$7,$6 | 
|  | 77 |  | 
|  | 78 | ldq	$4,8($17) | 
|  | 79 | srl	$3,$19,$1 | 
|  | 80 | bis	$5,$6,$8 | 
|  | 81 | stq	$8,-32($16) | 
|  | 82 | sll	$4,$7,$2 | 
|  | 83 |  | 
|  | 84 | ldq	$3,16($17) | 
|  | 85 | srl	$4,$19,$5 | 
|  | 86 | bis	$1,$2,$8 | 
|  | 87 | stq	$8,-24($16) | 
|  | 88 | sll	$3,$7,$6 | 
|  | 89 |  | 
|  | 90 | ldq	$4,24($17) | 
|  | 91 | srl	$3,$19,$1 | 
|  | 92 | bis	$5,$6,$8 | 
|  | 93 | stq	$8,-16($16) | 
|  | 94 | sll	$4,$7,$2 | 
|  | 95 |  | 
|  | 96 | addq	$17,32,$17 | 
|  | 97 | bis	$1,$2,$8 | 
|  | 98 | stq	$8,-8($16) | 
|  | 99 |  | 
|  | 100 | bgt	$18,.Loop | 
|  | 101 |  | 
|  | 102 | .Lend:	srl	$4,$19,$8 | 
|  | 103 | stq	$8,0($16) | 
|  | 104 | ret	$31,($26),1 | 
|  | 105 | .end	__mpn_rshift |