| xf.li | bdd93d5 | 2023-05-12 07:10:14 -0700 | [diff] [blame] | 1 | /* Copyright (C) 1996-2016 Free Software Foundation, Inc. | 
|  | 2 | This file is part of the GNU C Library. | 
|  | 3 | Contributed by Richard Henderson <rth@tamu.edu>. | 
|  | 4 |  | 
|  | 5 | The GNU C Library is free software; you can redistribute it and/or | 
|  | 6 | modify it under the terms of the GNU Lesser General Public | 
|  | 7 | License as published by the Free Software Foundation; either | 
|  | 8 | version 2.1 of the License, or (at your option) any later version. | 
|  | 9 |  | 
|  | 10 | The GNU C Library is distributed in the hope that it will be useful, | 
|  | 11 | but WITHOUT ANY WARRANTY; without even the implied warranty of | 
|  | 12 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU | 
|  | 13 | Lesser General Public License for more details. | 
|  | 14 |  | 
|  | 15 | You should have received a copy of the GNU Lesser General Public | 
|  | 16 | License along with the GNU C Library.  If not, see | 
|  | 17 | <http://www.gnu.org/licenses/>.  */ | 
|  | 18 |  | 
|  | 19 | #include "div_libc.h" | 
|  | 20 |  | 
|  | 21 | #undef FRAME | 
|  | 22 | #ifdef __alpha_fix__ | 
|  | 23 | #define FRAME 0 | 
|  | 24 | #else | 
|  | 25 | #define FRAME 16 | 
|  | 26 | #endif | 
|  | 27 |  | 
|  | 28 | #undef X | 
|  | 29 | #undef Y | 
|  | 30 | #define X $17 | 
|  | 31 | #define Y $18 | 
|  | 32 |  | 
|  | 33 | .set noat | 
|  | 34 |  | 
|  | 35 | .align 4 | 
|  | 36 | .globl ldiv | 
|  | 37 | .ent ldiv | 
|  | 38 | ldiv: | 
|  | 39 | .frame sp, FRAME, ra | 
|  | 40 | #if FRAME > 0 | 
|  | 41 | lda	sp, -FRAME(sp) | 
|  | 42 | #endif | 
|  | 43 | #ifdef PROF | 
|  | 44 | .set	macro | 
|  | 45 | ldgp	gp, 0(pv) | 
|  | 46 | lda	AT, _mcount | 
|  | 47 | jsr	AT, (AT), _mcount | 
|  | 48 | .set	nomacro | 
|  | 49 | .prologue 1 | 
|  | 50 | #else | 
|  | 51 | .prologue 0 | 
|  | 52 | #endif | 
|  | 53 |  | 
|  | 54 | beq	Y, $divbyzero | 
|  | 55 | excb | 
|  | 56 | mf_fpcr	$f10 | 
|  | 57 |  | 
|  | 58 | _ITOFT2	X, $f0, 0, Y, $f1, 8 | 
|  | 59 |  | 
|  | 60 | .align	4 | 
|  | 61 | cvtqt	$f0, $f0 | 
|  | 62 | cvtqt	$f1, $f1 | 
|  | 63 | divt/c	$f0, $f1, $f0 | 
|  | 64 | unop | 
|  | 65 |  | 
|  | 66 | /* Check to see if X fit in the double as an exact value.  */ | 
|  | 67 | sll	X, (64-53), AT | 
|  | 68 | sra	AT, (64-53), AT | 
|  | 69 | cmpeq	X, AT, AT | 
|  | 70 | beq	AT, $x_big | 
|  | 71 |  | 
|  | 72 | /* If we get here, we're expecting exact results from the division. | 
|  | 73 | Do nothing else besides convert and clean up.  */ | 
|  | 74 | cvttq/c	$f0, $f0 | 
|  | 75 | excb | 
|  | 76 | mt_fpcr	$f10 | 
|  | 77 | _FTOIT	$f0, $0, 0 | 
|  | 78 |  | 
|  | 79 | $egress: | 
|  | 80 | mulq	$0, Y, $1 | 
|  | 81 | subq	X, $1, $1 | 
|  | 82 |  | 
|  | 83 | stq	$0, 0($16) | 
|  | 84 | stq	$1, 8($16) | 
|  | 85 | mov	$16, $0 | 
|  | 86 |  | 
|  | 87 | #if FRAME > 0 | 
|  | 88 | lda	sp, FRAME(sp) | 
|  | 89 | #endif | 
|  | 90 | ret | 
|  | 91 |  | 
|  | 92 | .align	4 | 
|  | 93 | $x_big: | 
|  | 94 | /* If we get here, X is large enough that we don't expect exact | 
|  | 95 | results, and neither X nor Y got mis-translated for the fp | 
|  | 96 | division.  Our task is to take the fp result, figure out how | 
|  | 97 | far it's off from the correct result and compute a fixup.  */ | 
|  | 98 |  | 
|  | 99 | #define Q	v0		/* quotient */ | 
|  | 100 | #define R	t0		/* remainder */ | 
|  | 101 | #define SY	t1		/* scaled Y */ | 
|  | 102 | #define S	t2		/* scalar */ | 
|  | 103 | #define QY	t3		/* Q*Y */ | 
|  | 104 |  | 
|  | 105 | /* The fixup code below can only handle unsigned values.  */ | 
|  | 106 | or	X, Y, AT | 
|  | 107 | mov	$31, t5 | 
|  | 108 | blt	AT, $fix_sign_in | 
|  | 109 | $fix_sign_in_ret1: | 
|  | 110 | cvttq/c	$f0, $f0 | 
|  | 111 |  | 
|  | 112 | _FTOIT	$f0, Q, 8 | 
|  | 113 | $fix_sign_in_ret2: | 
|  | 114 | mulq	Q, Y, QY | 
|  | 115 | excb | 
|  | 116 | mt_fpcr	$f10 | 
|  | 117 |  | 
|  | 118 | .align	4 | 
|  | 119 | subq	QY, X, R | 
|  | 120 | mov	Y, SY | 
|  | 121 | mov	1, S | 
|  | 122 | bgt	R, $q_high | 
|  | 123 |  | 
|  | 124 | $q_high_ret: | 
|  | 125 | subq	X, QY, R | 
|  | 126 | mov	Y, SY | 
|  | 127 | mov	1, S | 
|  | 128 | bgt	R, $q_low | 
|  | 129 |  | 
|  | 130 | $q_low_ret: | 
|  | 131 | negq	Q, t4 | 
|  | 132 | cmovlbs	t5, t4, Q | 
|  | 133 | br	$egress | 
|  | 134 |  | 
|  | 135 | .align	4 | 
|  | 136 | /* The quotient that we computed was too large.  We need to reduce | 
|  | 137 | it by S such that Y*S >= R.  Obviously the closer we get to the | 
|  | 138 | correct value the better, but overshooting high is ok, as we'll | 
|  | 139 | fix that up later.  */ | 
|  | 140 | 0: | 
|  | 141 | addq	SY, SY, SY | 
|  | 142 | addq	S, S, S | 
|  | 143 | $q_high: | 
|  | 144 | cmpult	SY, R, AT | 
|  | 145 | bne	AT, 0b | 
|  | 146 |  | 
|  | 147 | subq	Q, S, Q | 
|  | 148 | unop | 
|  | 149 | subq	QY, SY, QY | 
|  | 150 | br	$q_high_ret | 
|  | 151 |  | 
|  | 152 | .align	4 | 
|  | 153 | /* The quotient that we computed was too small.  Divide Y by the | 
|  | 154 | current remainder (R) and add that to the existing quotient (Q). | 
|  | 155 | The expectation, of course, is that R is much smaller than X.  */ | 
|  | 156 | /* Begin with a shift-up loop.  Compute S such that Y*S >= R.  We | 
|  | 157 | already have a copy of Y in SY and the value 1 in S.  */ | 
|  | 158 | 0: | 
|  | 159 | addq	SY, SY, SY | 
|  | 160 | addq	S, S, S | 
|  | 161 | $q_low: | 
|  | 162 | cmpult	SY, R, AT | 
|  | 163 | bne	AT, 0b | 
|  | 164 |  | 
|  | 165 | /* Shift-down and subtract loop.  Each iteration compares our scaled | 
|  | 166 | Y (SY) with the remainder (R); if SY <= R then X is divisible by | 
|  | 167 | Y's scalar (S) so add it to the quotient (Q).  */ | 
|  | 168 | 2:	addq	Q, S, t3 | 
|  | 169 | srl	S, 1, S | 
|  | 170 | cmpule	SY, R, AT | 
|  | 171 | subq	R, SY, t4 | 
|  | 172 |  | 
|  | 173 | cmovne	AT, t3, Q | 
|  | 174 | cmovne	AT, t4, R | 
|  | 175 | srl	SY, 1, SY | 
|  | 176 | bne	S, 2b | 
|  | 177 |  | 
|  | 178 | br	$q_low_ret | 
|  | 179 |  | 
|  | 180 | .align	4 | 
|  | 181 | $fix_sign_in: | 
|  | 182 | /* If we got here, then X|Y is negative.  Need to adjust everything | 
|  | 183 | such that we're doing unsigned division in the fixup loop.  */ | 
|  | 184 | /* T5 is true if result should be negative.  */ | 
|  | 185 | xor	X, Y, AT | 
|  | 186 | cmplt	AT, 0, t5 | 
|  | 187 | cmplt	X, 0, AT | 
|  | 188 | negq	X, t0 | 
|  | 189 |  | 
|  | 190 | cmovne	AT, t0, X | 
|  | 191 | cmplt	Y, 0, AT | 
|  | 192 | negq	Y, t0 | 
|  | 193 |  | 
|  | 194 | cmovne	AT, t0, Y | 
|  | 195 | blbc	t5, $fix_sign_in_ret1 | 
|  | 196 |  | 
|  | 197 | cvttq/c	$f0, $f0 | 
|  | 198 | _FTOIT	$f0, Q, 8 | 
|  | 199 | .align	3 | 
|  | 200 | negq	Q, Q | 
|  | 201 | br	$fix_sign_in_ret2 | 
|  | 202 |  | 
|  | 203 | $divbyzero: | 
|  | 204 | mov	a0, v0 | 
|  | 205 | lda	a0, GEN_INTDIV | 
|  | 206 | call_pal PAL_gentrap | 
|  | 207 | stq	zero, 0(v0) | 
|  | 208 | stq	zero, 8(v0) | 
|  | 209 |  | 
|  | 210 | #if FRAME > 0 | 
|  | 211 | lda	sp, FRAME(sp) | 
|  | 212 | #endif | 
|  | 213 | ret | 
|  | 214 |  | 
|  | 215 | .end	ldiv | 
|  | 216 |  | 
|  | 217 | weak_alias (ldiv, lldiv) | 
|  | 218 | weak_alias (ldiv, imaxdiv) |