udivsi3_i4i.S 10.0 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666
/* Copyright (C) 1994, 1995, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
   2004, 2005, 2006
   Free Software Foundation, Inc.

This file is free software; you can redistribute it and/or modify it
under the terms of the GNU General Public License as published by the
Free Software Foundation; either version 2, or (at your option) any
later version.

In addition to the permissions in the GNU General Public License, the
Free Software Foundation gives you unlimited permission to link the
compiled version of this file into combinations with other programs,
and to distribute those combinations without any restriction coming
from the use of this file.  (The General Public License restrictions
do apply in other respects; for example, they cover modification of
the file, and distribution when not linked into a combine
executable.)

This file is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
General Public License for more details.

You should have received a copy of the GNU General Public License
along with this program; see the file COPYING.  If not, write to
the Free Software Foundation, 51 Franklin Street, Fifth Floor,
Boston, MA 02110-1301, USA.  */

!! libgcc routines for the Renesas / SuperH SH CPUs.
!! Contributed by Steve Chamberlain.
!! sac@cygnus.com

!! ashiftrt_r4_x, ___ashrsi3, ___ashlsi3, ___lshrsi3 routines
!! recoded in assembly by Toshiyasu Morita
!! tm@netcom.com

/* SH2 optimizations for ___ashrsi3, ___ashlsi3, ___lshrsi3 and
   ELF local label prefixes by J"orn Rennecke
   amylaar@cygnus.com  */

/* This code used shld, thus is not suitable for SH1 / SH2.  */

/* Signed / unsigned division without use of FPU, optimized for SH4.
   Uses a lookup table for divisors in the range -128 .. +128, and
   div1 with case distinction for larger divisors in three more ranges.
   The code is lumped together with the table to allow the use of mova.  */
#ifdef CONFIG_CPU_LITTLE_ENDIAN
#define L_LSB 0
#define L_LSWMSB 1
#define L_MSWLSB 2
#else
#define L_LSB 3
#define L_LSWMSB 2
#define L_MSWLSB 1
#endif

	.balign 4
	.global	__udivsi3_i4i
	.global	__udivsi3_i4
	.set	__udivsi3_i4, __udivsi3_i4i
	.type	__udivsi3_i4i, @function
__udivsi3_i4i:
	mov.w c128_w, r1
	div0u
	mov r4,r0
	shlr8 r0
	cmp/hi r1,r5
	extu.w r5,r1
	bf udiv_le128
	cmp/eq r5,r1
	bf udiv_ge64k
	shlr r0
	mov r5,r1
	shll16 r5
	mov.l r4,@-r15
	div1 r5,r0
	mov.l r1,@-r15
	div1 r5,r0
	div1 r5,r0
	bra udiv_25
	div1 r5,r0

div_le128:
	mova div_table_ix,r0
	bra div_le128_2
	mov.b @(r0,r5),r1
udiv_le128:
	mov.l r4,@-r15
	mova div_table_ix,r0
	mov.b @(r0,r5),r1
	mov.l r5,@-r15
div_le128_2:
	mova div_table_inv,r0
	mov.l @(r0,r1),r1
	mov r5,r0
	tst #0xfe,r0
	mova div_table_clz,r0
	dmulu.l r1,r4
	mov.b @(r0,r5),r1
	bt/s div_by_1
	mov r4,r0
	mov.l @r15+,r5
	sts mach,r0
	/* clrt */
	addc r4,r0
	mov.l @r15+,r4
	rotcr r0
	rts
	shld r1,r0

div_by_1_neg:
	neg r4,r0
div_by_1:
	mov.l @r15+,r5
	rts
	mov.l @r15+,r4

div_ge64k:
	bt/s div_r8
	div0u
	shll8 r5
	bra div_ge64k_2
	div1 r5,r0
udiv_ge64k:
	cmp/hi r0,r5
	mov r5,r1
	bt udiv_r8
	shll8 r5
	mov.l r4,@-r15
	div1 r5,r0
	mov.l r1,@-r15
div_ge64k_2:
	div1 r5,r0
	mov.l zero_l,r1
	.rept 4
	div1 r5,r0
	.endr
	mov.l r1,@-r15
	div1 r5,r0
	mov.w m256_w,r1
	div1 r5,r0
	mov.b r0,@(L_LSWMSB,r15)
	xor r4,r0
	and r1,r0
	bra div_ge64k_end
	xor r4,r0
	
div_r8:
	shll16 r4
	bra div_r8_2
	shll8 r4
udiv_r8:
	mov.l r4,@-r15
	shll16 r4
	clrt
	shll8 r4
	mov.l r5,@-r15
div_r8_2:
	rotcl r4
	mov r0,r1
	div1 r5,r1
	mov r4,r0
	rotcl r0
	mov r5,r4
	div1 r5,r1
	.rept 5
	rotcl r0; div1 r5,r1
	.endr
	rotcl r0
	mov.l @r15+,r5
	div1 r4,r1
	mov.l @r15+,r4
	rts
	rotcl r0

	.global	__sdivsi3_i4i
	.global __sdivsi3_i4
	.global	__sdivsi3
	.set	__sdivsi3_i4, __sdivsi3_i4i
	.set	__sdivsi3, __sdivsi3_i4i
	.type	__sdivsi3_i4i, @function
	/* This is link-compatible with a __sdivsi3 call,
	   but we effectively clobber only r1.  */
__sdivsi3_i4i:
	mov.l r4,@-r15
	cmp/pz r5
	mov.w c128_w, r1
	bt/s pos_divisor
	cmp/pz r4
	mov.l r5,@-r15
	neg r5,r5
	bt/s neg_result
	cmp/hi r1,r5
	neg r4,r4
pos_result:
	extu.w r5,r0
	bf div_le128
	cmp/eq r5,r0
	mov r4,r0
	shlr8 r0
	bf/s div_ge64k
	cmp/hi r0,r5
	div0u
	shll16 r5
	div1 r5,r0
	div1 r5,r0
	div1 r5,r0
udiv_25:
	mov.l zero_l,r1
	div1 r5,r0
	div1 r5,r0
	mov.l r1,@-r15
	.rept 3
	div1 r5,r0
	.endr
	mov.b r0,@(L_MSWLSB,r15)
	xtrct r4,r0
	swap.w r0,r0
	.rept 8
	div1 r5,r0
	.endr
	mov.b r0,@(L_LSWMSB,r15)
div_ge64k_end:
	.rept 8
	div1 r5,r0
	.endr
	mov.l @r15+,r4 ! zero-extension and swap using LS unit.
	extu.b r0,r0
	mov.l @r15+,r5
	or r4,r0
	mov.l @r15+,r4
	rts
	rotcl r0

div_le128_neg:
	tst #0xfe,r0
	mova div_table_ix,r0
	mov.b @(r0,r5),r1
	mova div_table_inv,r0
	bt/s div_by_1_neg
	mov.l @(r0,r1),r1
	mova div_table_clz,r0
	dmulu.l r1,r4
	mov.b @(r0,r5),r1
	mov.l @r15+,r5
	sts mach,r0
	/* clrt */
	addc r4,r0
	mov.l @r15+,r4
	rotcr r0
	shld r1,r0
	rts
	neg r0,r0

pos_divisor:
	mov.l r5,@-r15
	bt/s pos_result
	cmp/hi r1,r5
	neg r4,r4
neg_result:
	extu.w r5,r0
	bf div_le128_neg
	cmp/eq r5,r0
	mov r4,r0
	shlr8 r0
	bf/s div_ge64k_neg
	cmp/hi r0,r5
	div0u
	mov.l zero_l,r1
	shll16 r5
	div1 r5,r0
	mov.l r1,@-r15
	.rept 7
	div1 r5,r0
	.endr
	mov.b r0,@(L_MSWLSB,r15)
	xtrct r4,r0
	swap.w r0,r0
	.rept 8
	div1 r5,r0
	.endr
	mov.b r0,@(L_LSWMSB,r15)
div_ge64k_neg_end:
	.rept 8
	div1 r5,r0
	.endr
	mov.l @r15+,r4 ! zero-extension and swap using LS unit.
	extu.b r0,r1
	mov.l @r15+,r5
	or r4,r1
div_r8_neg_end:
	mov.l @r15+,r4
	rotcl r1
	rts
	neg r1,r0

div_ge64k_neg:
	bt/s div_r8_neg
	div0u
	shll8 r5
	mov.l zero_l,r1
	.rept 6
	div1 r5,r0
	.endr
	mov.l r1,@-r15
	div1 r5,r0
	mov.w m256_w,r1
	div1 r5,r0
	mov.b r0,@(L_LSWMSB,r15)
	xor r4,r0
	and r1,r0
	bra div_ge64k_neg_end
	xor r4,r0

c128_w:
	.word 128

div_r8_neg:
	clrt
	shll16 r4
	mov r4,r1
	shll8 r1
	mov r5,r4
	.rept 7
	rotcl r1; div1 r5,r0
	.endr
	mov.l @r15+,r5
	rotcl r1
	bra div_r8_neg_end
	div1 r4,r0

m256_w:
	.word 0xff00
/* This table has been generated by divtab-sh4.c.  */
	.balign 4
div_table_clz:
	.byte	0
	.byte	1
	.byte	0
	.byte	-1
	.byte	-1
	.byte	-2
	.byte	-2
	.byte	-2
	.byte	-2
	.byte	-3
	.byte	-3
	.byte	-3
	.byte	-3
	.byte	-3
	.byte	-3
	.byte	-3
	.byte	-3
	.byte	-4
	.byte	-4
	.byte	-4
	.byte	-4
	.byte	-4
	.byte	-4
	.byte	-4
	.byte	-4
	.byte	-4
	.byte	-4
	.byte	-4
	.byte	-4
	.byte	-4
	.byte	-4
	.byte	-4
	.byte	-4
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-5
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
	.byte	-6
/* Lookup table translating positive divisor to index into table of
   normalized inverse.  N.B. the '0' entry is also the last entry of the
 previous table, and causes an unaligned access for division by zero.  */
div_table_ix:
	.byte	-6
	.byte	-128
	.byte	-128
	.byte	0
	.byte	-128
	.byte	-64
	.byte	0
	.byte	64
	.byte	-128
	.byte	-96
	.byte	-64
	.byte	-32
	.byte	0
	.byte	32
	.byte	64
	.byte	96
	.byte	-128
	.byte	-112
	.byte	-96
	.byte	-80
	.byte	-64
	.byte	-48
	.byte	-32
	.byte	-16
	.byte	0
	.byte	16
	.byte	32
	.byte	48
	.byte	64
	.byte	80
	.byte	96
	.byte	112
	.byte	-128
	.byte	-120
	.byte	-112
	.byte	-104
	.byte	-96
	.byte	-88
	.byte	-80
	.byte	-72
	.byte	-64
	.byte	-56
	.byte	-48
	.byte	-40
	.byte	-32
	.byte	-24
	.byte	-16
	.byte	-8
	.byte	0
	.byte	8
	.byte	16
	.byte	24
	.byte	32
	.byte	40
	.byte	48
	.byte	56
	.byte	64
	.byte	72
	.byte	80
	.byte	88
	.byte	96
	.byte	104
	.byte	112
	.byte	120
	.byte	-128
	.byte	-124
	.byte	-120
	.byte	-116
	.byte	-112
	.byte	-108
	.byte	-104
	.byte	-100
	.byte	-96
	.byte	-92
	.byte	-88
	.byte	-84
	.byte	-80
	.byte	-76
	.byte	-72
	.byte	-68
	.byte	-64
	.byte	-60
	.byte	-56
	.byte	-52
	.byte	-48
	.byte	-44
	.byte	-40
	.byte	-36
	.byte	-32
	.byte	-28
	.byte	-24
	.byte	-20
	.byte	-16
	.byte	-12
	.byte	-8
	.byte	-4
	.byte	0
	.byte	4
	.byte	8
	.byte	12
	.byte	16
	.byte	20
	.byte	24
	.byte	28
	.byte	32
	.byte	36
	.byte	40
	.byte	44
	.byte	48
	.byte	52
	.byte	56
	.byte	60
	.byte	64
	.byte	68
	.byte	72
	.byte	76
	.byte	80
	.byte	84
	.byte	88
	.byte	92
	.byte	96
	.byte	100
	.byte	104
	.byte	108
	.byte	112
	.byte	116
	.byte	120
	.byte	124
	.byte	-128
/* 1/64 .. 1/127, normalized.  There is an implicit leading 1 in bit 32.  */
	.balign 4
zero_l:
	.long	0x0
	.long	0xF81F81F9
	.long	0xF07C1F08
	.long	0xE9131AC0
	.long	0xE1E1E1E2
	.long	0xDAE6076C
	.long	0xD41D41D5
	.long	0xCD856891
	.long	0xC71C71C8
	.long	0xC0E07039
	.long	0xBACF914D
	.long	0xB4E81B4F
	.long	0xAF286BCB
	.long	0xA98EF607
	.long	0xA41A41A5
	.long	0x9EC8E952
	.long	0x9999999A
	.long	0x948B0FCE
	.long	0x8F9C18FA
	.long	0x8ACB90F7
	.long	0x86186187
	.long	0x81818182
	.long	0x7D05F418
	.long	0x78A4C818
	.long	0x745D1746
	.long	0x702E05C1
	.long	0x6C16C16D
	.long	0x68168169
	.long	0x642C8591
	.long	0x60581606
	.long	0x5C9882BA
	.long	0x58ED2309
div_table_inv:
	.long	0x55555556
	.long	0x51D07EAF
	.long	0x4E5E0A73
	.long	0x4AFD6A06
	.long	0x47AE147B
	.long	0x446F8657
	.long	0x41414142
	.long	0x3E22CBCF
	.long	0x3B13B13C
	.long	0x38138139
	.long	0x3521CFB3
	.long	0x323E34A3
	.long	0x2F684BDB
	.long	0x2C9FB4D9
	.long	0x29E4129F
	.long	0x27350B89
	.long	0x24924925
	.long	0x21FB7813
	.long	0x1F7047DD
	.long	0x1CF06ADB
	.long	0x1A7B9612
	.long	0x18118119
	.long	0x15B1E5F8
	.long	0x135C8114
	.long	0x11111112
	.long	0xECF56BF
	.long	0xC9714FC
	.long	0xA6810A7
	.long	0x8421085
	.long	0x624DD30
	.long	0x4104105
	.long	0x2040811
	/* maximum error: 0.987342 scaled: 0.921875*/