Deleted Added
sdiff udiff text old ( 129202 ) new ( 135683 )
full compact
memcpy_xscale.S (129202) memcpy_xscale.S (135683)
1/* $NetBSD: memcpy_xscale.S,v 1.1 2003/10/14 07:51:45 scw Exp $ */
2
3/*
4 * Copyright 2003 Wasabi Systems, Inc.
5 * All rights reserved.
6 *
7 * Written by Steve C. Woodford for Wasabi Systems, Inc.
8 *

--- 22 unchanged lines hidden (view full) ---

31 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
32 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
33 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
34 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
35 * POSSIBILITY OF SUCH DAMAGE.
36 */
37
38#include <machine/asm.h>
1/* $NetBSD: memcpy_xscale.S,v 1.1 2003/10/14 07:51:45 scw Exp $ */
2
3/*
4 * Copyright 2003 Wasabi Systems, Inc.
5 * All rights reserved.
6 *
7 * Written by Steve C. Woodford for Wasabi Systems, Inc.
8 *

--- 22 unchanged lines hidden (view full) ---

31 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
32 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
33 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
34 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
35 * POSSIBILITY OF SUCH DAMAGE.
36 */
37
38#include <machine/asm.h>
39__FBSDID("$FreeBSD: head/lib/libc/arm/string/memcpy_xscale.S 129202 2004-05-14 12:04:31Z cognet $");
39__FBSDID("$FreeBSD: head/lib/libc/arm/string/memcpy_xscale.S 135683 2004-09-23 23:11:32Z cognet $");
40
41/* LINTSTUB: Func: void *memcpy(void *dst, const void *src, size_t len) */
42ENTRY(memcpy)
43 pld [r1]
44 cmp r2, #0x0c
45 ble .Lmemcpy_short /* <= 12 bytes */
46 mov r3, r0 /* We must not clobber r0 */
47

--- 82 unchanged lines hidden (view full) ---

130 strd r8, [r3], #0x08 /* ST:70-77 */
131 subs r2, r2, #0x80
132 strd r4, [r3], #0x08 /* ST:78-7f */
133 bge .Lmemcpy_w_loop128
134
135.Lmemcpy_w_lessthan128:
136 adds r2, r2, #0x80 /* Adjust for extra sub */
137 ldmeqfd sp!, {r4-r9}
40
41/* LINTSTUB: Func: void *memcpy(void *dst, const void *src, size_t len) */
42ENTRY(memcpy)
43 pld [r1]
44 cmp r2, #0x0c
45 ble .Lmemcpy_short /* <= 12 bytes */
46 mov r3, r0 /* We must not clobber r0 */
47

--- 82 unchanged lines hidden (view full) ---

130 strd r8, [r3], #0x08 /* ST:70-77 */
131 subs r2, r2, #0x80
132 strd r4, [r3], #0x08 /* ST:78-7f */
133 bge .Lmemcpy_w_loop128
134
135.Lmemcpy_w_lessthan128:
136 adds r2, r2, #0x80 /* Adjust for extra sub */
137 ldmeqfd sp!, {r4-r9}
138 moveq pc, lr /* Return now if done */
138 bxeq lr /* Return now if done */
139 subs r2, r2, #0x20
140 blt .Lmemcpy_w_lessthan32
141
142 /* Copy 32 bytes at a time */
143.Lmemcpy_w_loop32:
144 ldr r4, [r1], #0x04
145 ldr r5, [r1], #0x04
146 pld [r1, #0x18]

--- 8 unchanged lines hidden (view full) ---

155 strd r8, [r3], #0x08
156 subs r2, r2, #0x20
157 strd r4, [r3], #0x08
158 bge .Lmemcpy_w_loop32
159
160.Lmemcpy_w_lessthan32:
161 adds r2, r2, #0x20 /* Adjust for extra sub */
162 ldmeqfd sp!, {r4-r9}
139 subs r2, r2, #0x20
140 blt .Lmemcpy_w_lessthan32
141
142 /* Copy 32 bytes at a time */
143.Lmemcpy_w_loop32:
144 ldr r4, [r1], #0x04
145 ldr r5, [r1], #0x04
146 pld [r1, #0x18]

--- 8 unchanged lines hidden (view full) ---

155 strd r8, [r3], #0x08
156 subs r2, r2, #0x20
157 strd r4, [r3], #0x08
158 bge .Lmemcpy_w_loop32
159
160.Lmemcpy_w_lessthan32:
161 adds r2, r2, #0x20 /* Adjust for extra sub */
162 ldmeqfd sp!, {r4-r9}
163 moveq pc, lr /* Return now if done */
163 bxeq lr /* Return now if done */
164
165 and r4, r2, #0x18
166 rsbs r4, r4, #0x18
167 addne pc, pc, r4, lsl #1
168 nop
169
170 /* At least 24 bytes remaining */
171 ldr r4, [r1], #0x04

--- 10 unchanged lines hidden (view full) ---

182 /* At least 8 bytes remaining */
183 ldr r4, [r1], #0x04
184 ldr r5, [r1], #0x04
185 subs r2, r2, #0x08
186 strd r4, [r3], #0x08
187
188 /* Less than 8 bytes remaining */
189 ldmfd sp!, {r4-r9}
164
165 and r4, r2, #0x18
166 rsbs r4, r4, #0x18
167 addne pc, pc, r4, lsl #1
168 nop
169
170 /* At least 24 bytes remaining */
171 ldr r4, [r1], #0x04

--- 10 unchanged lines hidden (view full) ---

182 /* At least 8 bytes remaining */
183 ldr r4, [r1], #0x04
184 ldr r5, [r1], #0x04
185 subs r2, r2, #0x08
186 strd r4, [r3], #0x08
187
188 /* Less than 8 bytes remaining */
189 ldmfd sp!, {r4-r9}
190 moveq pc, lr /* Return now if done */
190 bxeq lr /* Return now if done */
191 subs r2, r2, #0x04
192 ldrge ip, [r1], #0x04
193 strge ip, [r3], #0x04
191 subs r2, r2, #0x04
192 ldrge ip, [r1], #0x04
193 strge ip, [r3], #0x04
194 moveq pc, lr /* Return now if done */
194 bxeq lr /* Return now if done */
195 addlt r2, r2, #0x04
196 ldrb ip, [r1], #0x01
197 cmp r2, #0x02
198 ldrgeb r2, [r1], #0x01
199 strb ip, [r3], #0x01
200 ldrgtb ip, [r1]
201 strgeb r2, [r3], #0x01
202 strgtb ip, [r3]
195 addlt r2, r2, #0x04
196 ldrb ip, [r1], #0x01
197 cmp r2, #0x02
198 ldrgeb r2, [r1], #0x01
199 strb ip, [r3], #0x01
200 ldrgtb ip, [r1]
201 strgeb r2, [r3], #0x01
202 strgtb ip, [r3]
203 mov pc, lr
203 bx lr
204
205
206/*
207 * At this point, it has not been possible to word align both buffers.
208 * The destination buffer is word aligned, but the source buffer is not.
209 */
210.Lmemcpy_bad_align:
211 stmfd sp!, {r4-r7}

--- 37 unchanged lines hidden (view full) ---

249 str r6, [r3], #0x04
250 str r7, [r3], #0x04
251.Lmemcpy_bad1:
252 subs r2, r2, #0x10
253 bge .Lmemcpy_bad1_loop16
254
255 adds r2, r2, #0x10
256 ldmeqfd sp!, {r4-r7}
204
205
206/*
207 * At this point, it has not been possible to word align both buffers.
208 * The destination buffer is word aligned, but the source buffer is not.
209 */
210.Lmemcpy_bad_align:
211 stmfd sp!, {r4-r7}

--- 37 unchanged lines hidden (view full) ---

249 str r6, [r3], #0x04
250 str r7, [r3], #0x04
251.Lmemcpy_bad1:
252 subs r2, r2, #0x10
253 bge .Lmemcpy_bad1_loop16
254
255 adds r2, r2, #0x10
256 ldmeqfd sp!, {r4-r7}
257 moveq pc, lr /* Return now if done */
257 bxeq lr /* Return now if done */
258 subs r2, r2, #0x04
259 sublt r1, r1, #0x03
260 blt .Lmemcpy_bad_done
261
262.Lmemcpy_bad1_loop4:
263#ifdef __ARMEB__
264 mov r4, ip, lsl #8
265#else

--- 44 unchanged lines hidden (view full) ---

310 str r6, [r3], #0x04
311 str r7, [r3], #0x04
312.Lmemcpy_bad2:
313 subs r2, r2, #0x10
314 bge .Lmemcpy_bad2_loop16
315
316 adds r2, r2, #0x10
317 ldmeqfd sp!, {r4-r7}
258 subs r2, r2, #0x04
259 sublt r1, r1, #0x03
260 blt .Lmemcpy_bad_done
261
262.Lmemcpy_bad1_loop4:
263#ifdef __ARMEB__
264 mov r4, ip, lsl #8
265#else

--- 44 unchanged lines hidden (view full) ---

310 str r6, [r3], #0x04
311 str r7, [r3], #0x04
312.Lmemcpy_bad2:
313 subs r2, r2, #0x10
314 bge .Lmemcpy_bad2_loop16
315
316 adds r2, r2, #0x10
317 ldmeqfd sp!, {r4-r7}
318 moveq pc, lr /* Return now if done */
318 bxeq lr /* Return now if done */
319 subs r2, r2, #0x04
320 sublt r1, r1, #0x02
321 blt .Lmemcpy_bad_done
322
323.Lmemcpy_bad2_loop4:
324#ifdef __ARMEB__
325 mov r4, ip, lsl #16
326#else

--- 44 unchanged lines hidden (view full) ---

371 str r6, [r3], #0x04
372 str r7, [r3], #0x04
373.Lmemcpy_bad3:
374 subs r2, r2, #0x10
375 bge .Lmemcpy_bad3_loop16
376
377 adds r2, r2, #0x10
378 ldmeqfd sp!, {r4-r7}
319 subs r2, r2, #0x04
320 sublt r1, r1, #0x02
321 blt .Lmemcpy_bad_done
322
323.Lmemcpy_bad2_loop4:
324#ifdef __ARMEB__
325 mov r4, ip, lsl #16
326#else

--- 44 unchanged lines hidden (view full) ---

371 str r6, [r3], #0x04
372 str r7, [r3], #0x04
373.Lmemcpy_bad3:
374 subs r2, r2, #0x10
375 bge .Lmemcpy_bad3_loop16
376
377 adds r2, r2, #0x10
378 ldmeqfd sp!, {r4-r7}
379 moveq pc, lr /* Return now if done */
379 bxeq lr /* Return now if done */
380 subs r2, r2, #0x04
381 sublt r1, r1, #0x01
382 blt .Lmemcpy_bad_done
383
384.Lmemcpy_bad3_loop4:
385#ifdef __ARMEB__
386 mov r4, ip, lsl #24
387#else

--- 8 unchanged lines hidden (view full) ---

396#endif
397 str r4, [r3], #0x04
398 bge .Lmemcpy_bad3_loop4
399 sub r1, r1, #0x01
400
401.Lmemcpy_bad_done:
402 ldmfd sp!, {r4-r7}
403 adds r2, r2, #0x04
380 subs r2, r2, #0x04
381 sublt r1, r1, #0x01
382 blt .Lmemcpy_bad_done
383
384.Lmemcpy_bad3_loop4:
385#ifdef __ARMEB__
386 mov r4, ip, lsl #24
387#else

--- 8 unchanged lines hidden (view full) ---

396#endif
397 str r4, [r3], #0x04
398 bge .Lmemcpy_bad3_loop4
399 sub r1, r1, #0x01
400
401.Lmemcpy_bad_done:
402 ldmfd sp!, {r4-r7}
403 adds r2, r2, #0x04
404 moveq pc, lr
404 bxeq lr
405 ldrb ip, [r1], #0x01
406 cmp r2, #0x02
407 ldrgeb r2, [r1], #0x01
408 strb ip, [r3], #0x01
409 ldrgtb ip, [r1]
410 strgeb r2, [r3], #0x01
411 strgtb ip, [r3]
405 ldrb ip, [r1], #0x01
406 cmp r2, #0x02
407 ldrgeb r2, [r1], #0x01
408 strb ip, [r3], #0x01
409 ldrgtb ip, [r1]
410 strgeb r2, [r3], #0x01
411 strgtb ip, [r3]
412 mov pc, lr
412 bx lr
413
414
415/*
416 * Handle short copies (less than 16 bytes), possibly misaligned.
417 * Some of these are *very* common, thanks to the network stack,
418 * and so are handled specially.
419 */
420.Lmemcpy_short:
421#ifndef _STANDALONE
422 add pc, pc, r2, lsl #2
423 nop
413
414
415/*
416 * Handle short copies (less than 16 bytes), possibly misaligned.
417 * Some of these are *very* common, thanks to the network stack,
418 * and so are handled specially.
419 */
420.Lmemcpy_short:
421#ifndef _STANDALONE
422 add pc, pc, r2, lsl #2
423 nop
424 mov pc, lr /* 0x00 */
424 bx lr /* 0x00 */
425 b .Lmemcpy_bytewise /* 0x01 */
426 b .Lmemcpy_bytewise /* 0x02 */
427 b .Lmemcpy_bytewise /* 0x03 */
428 b .Lmemcpy_4 /* 0x04 */
429 b .Lmemcpy_bytewise /* 0x05 */
430 b .Lmemcpy_6 /* 0x06 */
431 b .Lmemcpy_bytewise /* 0x07 */
432 b .Lmemcpy_8 /* 0x08 */

--- 4 unchanged lines hidden (view full) ---

437#endif
438.Lmemcpy_bytewise:
439 mov r3, r0 /* We must not clobber r0 */
440 ldrb ip, [r1], #0x01
4411: subs r2, r2, #0x01
442 strb ip, [r3], #0x01
443 ldrneb ip, [r1], #0x01
444 bne 1b
425 b .Lmemcpy_bytewise /* 0x01 */
426 b .Lmemcpy_bytewise /* 0x02 */
427 b .Lmemcpy_bytewise /* 0x03 */
428 b .Lmemcpy_4 /* 0x04 */
429 b .Lmemcpy_bytewise /* 0x05 */
430 b .Lmemcpy_6 /* 0x06 */
431 b .Lmemcpy_bytewise /* 0x07 */
432 b .Lmemcpy_8 /* 0x08 */

--- 4 unchanged lines hidden (view full) ---

437#endif
438.Lmemcpy_bytewise:
439 mov r3, r0 /* We must not clobber r0 */
440 ldrb ip, [r1], #0x01
4411: subs r2, r2, #0x01
442 strb ip, [r3], #0x01
443 ldrneb ip, [r1], #0x01
444 bne 1b
445 mov pc, lr
445 bx lr
446
447#ifndef _STANDALONE
448/******************************************************************************
449 * Special case for 4 byte copies
450 */
451#define LMEMCPY_4_LOG2 6 /* 64 bytes */
452#define LMEMCPY_4_PAD .align LMEMCPY_4_LOG2
453 LMEMCPY_4_PAD

--- 4 unchanged lines hidden (view full) ---

458 sub r3, pc, #0x14
459 addne pc, r3, r2, lsl #LMEMCPY_4_LOG2
460
461/*
462 * 0000: dst is 32-bit aligned, src is 32-bit aligned
463 */
464 ldr r2, [r1]
465 str r2, [r0]
446
447#ifndef _STANDALONE
448/******************************************************************************
449 * Special case for 4 byte copies
450 */
451#define LMEMCPY_4_LOG2 6 /* 64 bytes */
452#define LMEMCPY_4_PAD .align LMEMCPY_4_LOG2
453 LMEMCPY_4_PAD

--- 4 unchanged lines hidden (view full) ---

458 sub r3, pc, #0x14
459 addne pc, r3, r2, lsl #LMEMCPY_4_LOG2
460
461/*
462 * 0000: dst is 32-bit aligned, src is 32-bit aligned
463 */
464 ldr r2, [r1]
465 str r2, [r0]
466 mov pc, lr
466 bx lr
467 LMEMCPY_4_PAD
468
469/*
470 * 0001: dst is 32-bit aligned, src is 8-bit aligned
471 */
472 ldr r3, [r1, #-1] /* BE:r3 = x012 LE:r3 = 210x */
473 ldr r2, [r1, #3] /* BE:r2 = 3xxx LE:r2 = xxx3 */
474#ifdef __ARMEB__
475 mov r3, r3, lsl #8 /* r3 = 012. */
476 orr r3, r3, r2, lsr #24 /* r3 = 0123 */
477#else
478 mov r3, r3, lsr #8 /* r3 = .210 */
479 orr r3, r3, r2, lsl #24 /* r3 = 3210 */
480#endif
481 str r3, [r0]
467 LMEMCPY_4_PAD
468
469/*
470 * 0001: dst is 32-bit aligned, src is 8-bit aligned
471 */
472 ldr r3, [r1, #-1] /* BE:r3 = x012 LE:r3 = 210x */
473 ldr r2, [r1, #3] /* BE:r2 = 3xxx LE:r2 = xxx3 */
474#ifdef __ARMEB__
475 mov r3, r3, lsl #8 /* r3 = 012. */
476 orr r3, r3, r2, lsr #24 /* r3 = 0123 */
477#else
478 mov r3, r3, lsr #8 /* r3 = .210 */
479 orr r3, r3, r2, lsl #24 /* r3 = 3210 */
480#endif
481 str r3, [r0]
482 mov pc, lr
482 bx lr
483 LMEMCPY_4_PAD
484
485/*
486 * 0010: dst is 32-bit aligned, src is 16-bit aligned
487 */
488#ifdef __ARMEB__
489 ldrh r3, [r1]
490 ldrh r2, [r1, #0x02]
491#else
492 ldrh r3, [r1, #0x02]
493 ldrh r2, [r1]
494#endif
495 orr r3, r2, r3, lsl #16
496 str r3, [r0]
483 LMEMCPY_4_PAD
484
485/*
486 * 0010: dst is 32-bit aligned, src is 16-bit aligned
487 */
488#ifdef __ARMEB__
489 ldrh r3, [r1]
490 ldrh r2, [r1, #0x02]
491#else
492 ldrh r3, [r1, #0x02]
493 ldrh r2, [r1]
494#endif
495 orr r3, r2, r3, lsl #16
496 str r3, [r0]
497 mov pc, lr
497 bx lr
498 LMEMCPY_4_PAD
499
500/*
501 * 0011: dst is 32-bit aligned, src is 8-bit aligned
502 */
503 ldr r3, [r1, #-3] /* BE:r3 = xxx0 LE:r3 = 0xxx */
504 ldr r2, [r1, #1] /* BE:r2 = 123x LE:r2 = x321 */
505#ifdef __ARMEB__
506 mov r3, r3, lsl #24 /* r3 = 0... */
507 orr r3, r3, r2, lsr #8 /* r3 = 0123 */
508#else
509 mov r3, r3, lsr #24 /* r3 = ...0 */
510 orr r3, r3, r2, lsl #8 /* r3 = 3210 */
511#endif
512 str r3, [r0]
498 LMEMCPY_4_PAD
499
500/*
501 * 0011: dst is 32-bit aligned, src is 8-bit aligned
502 */
503 ldr r3, [r1, #-3] /* BE:r3 = xxx0 LE:r3 = 0xxx */
504 ldr r2, [r1, #1] /* BE:r2 = 123x LE:r2 = x321 */
505#ifdef __ARMEB__
506 mov r3, r3, lsl #24 /* r3 = 0... */
507 orr r3, r3, r2, lsr #8 /* r3 = 0123 */
508#else
509 mov r3, r3, lsr #24 /* r3 = ...0 */
510 orr r3, r3, r2, lsl #8 /* r3 = 3210 */
511#endif
512 str r3, [r0]
513 mov pc, lr
513 bx lr
514 LMEMCPY_4_PAD
515
516/*
517 * 0100: dst is 8-bit aligned, src is 32-bit aligned
518 */
519 ldr r2, [r1]
520#ifdef __ARMEB__
521 strb r2, [r0, #0x03]
522 mov r3, r2, lsr #8
523 mov r1, r2, lsr #24
524 strb r1, [r0]
525#else
526 strb r2, [r0]
527 mov r3, r2, lsr #8
528 mov r1, r2, lsr #24
529 strb r1, [r0, #0x03]
530#endif
531 strh r3, [r0, #0x01]
514 LMEMCPY_4_PAD
515
516/*
517 * 0100: dst is 8-bit aligned, src is 32-bit aligned
518 */
519 ldr r2, [r1]
520#ifdef __ARMEB__
521 strb r2, [r0, #0x03]
522 mov r3, r2, lsr #8
523 mov r1, r2, lsr #24
524 strb r1, [r0]
525#else
526 strb r2, [r0]
527 mov r3, r2, lsr #8
528 mov r1, r2, lsr #24
529 strb r1, [r0, #0x03]
530#endif
531 strh r3, [r0, #0x01]
532 mov pc, lr
532 bx lr
533 LMEMCPY_4_PAD
534
535/*
536 * 0101: dst is 8-bit aligned, src is 8-bit aligned
537 */
538 ldrb r2, [r1]
539 ldrh r3, [r1, #0x01]
540 ldrb r1, [r1, #0x03]
541 strb r2, [r0]
542 strh r3, [r0, #0x01]
543 strb r1, [r0, #0x03]
533 LMEMCPY_4_PAD
534
535/*
536 * 0101: dst is 8-bit aligned, src is 8-bit aligned
537 */
538 ldrb r2, [r1]
539 ldrh r3, [r1, #0x01]
540 ldrb r1, [r1, #0x03]
541 strb r2, [r0]
542 strh r3, [r0, #0x01]
543 strb r1, [r0, #0x03]
544 mov pc, lr
544 bx lr
545 LMEMCPY_4_PAD
546
547/*
548 * 0110: dst is 8-bit aligned, src is 16-bit aligned
549 */
550 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */
551 ldrh r3, [r1, #0x02] /* LE:r3 = ..23 LE:r3 = ..32 */
552#ifdef __ARMEB__

--- 4 unchanged lines hidden (view full) ---

557#else
558 strb r2, [r0]
559 mov r2, r2, lsr #8 /* r2 = ...1 */
560 orr r2, r2, r3, lsl #8 /* r2 = .321 */
561 mov r3, r3, lsr #8 /* r3 = ...3 */
562#endif
563 strh r2, [r0, #0x01]
564 strb r3, [r0, #0x03]
545 LMEMCPY_4_PAD
546
547/*
548 * 0110: dst is 8-bit aligned, src is 16-bit aligned
549 */
550 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */
551 ldrh r3, [r1, #0x02] /* LE:r3 = ..23 LE:r3 = ..32 */
552#ifdef __ARMEB__

--- 4 unchanged lines hidden (view full) ---

557#else
558 strb r2, [r0]
559 mov r2, r2, lsr #8 /* r2 = ...1 */
560 orr r2, r2, r3, lsl #8 /* r2 = .321 */
561 mov r3, r3, lsr #8 /* r3 = ...3 */
562#endif
563 strh r2, [r0, #0x01]
564 strb r3, [r0, #0x03]
565 mov pc, lr
565 bx lr
566 LMEMCPY_4_PAD
567
568/*
569 * 0111: dst is 8-bit aligned, src is 8-bit aligned
570 */
571 ldrb r2, [r1]
572 ldrh r3, [r1, #0x01]
573 ldrb r1, [r1, #0x03]
574 strb r2, [r0]
575 strh r3, [r0, #0x01]
576 strb r1, [r0, #0x03]
566 LMEMCPY_4_PAD
567
568/*
569 * 0111: dst is 8-bit aligned, src is 8-bit aligned
570 */
571 ldrb r2, [r1]
572 ldrh r3, [r1, #0x01]
573 ldrb r1, [r1, #0x03]
574 strb r2, [r0]
575 strh r3, [r0, #0x01]
576 strb r1, [r0, #0x03]
577 mov pc, lr
577 bx lr
578 LMEMCPY_4_PAD
579
580/*
581 * 1000: dst is 16-bit aligned, src is 32-bit aligned
582 */
583 ldr r2, [r1]
584#ifdef __ARMEB__
585 strh r2, [r0, #0x02]
586 mov r3, r2, lsr #16
587 strh r3, [r0]
588#else
589 strh r2, [r0]
590 mov r3, r2, lsr #16
591 strh r3, [r0, #0x02]
592#endif
578 LMEMCPY_4_PAD
579
580/*
581 * 1000: dst is 16-bit aligned, src is 32-bit aligned
582 */
583 ldr r2, [r1]
584#ifdef __ARMEB__
585 strh r2, [r0, #0x02]
586 mov r3, r2, lsr #16
587 strh r3, [r0]
588#else
589 strh r2, [r0]
590 mov r3, r2, lsr #16
591 strh r3, [r0, #0x02]
592#endif
593 mov pc, lr
593 bx lr
594 LMEMCPY_4_PAD
595
596/*
597 * 1001: dst is 16-bit aligned, src is 8-bit aligned
598 */
599 ldr r2, [r1, #-1] /* BE:r2 = x012 LE:r2 = 210x */
600 ldr r3, [r1, #3] /* BE:r3 = 3xxx LE:r3 = xxx3 */
601 mov r1, r2, lsr #8 /* BE:r1 = .x01 LE:r1 = .210 */
602 strh r1, [r0]
603#ifdef __ARMEB__
604 mov r2, r2, lsl #8 /* r2 = 012. */
605 orr r2, r2, r3, lsr #24 /* r2 = 0123 */
606#else
607 mov r2, r2, lsr #24 /* r2 = ...2 */
608 orr r2, r2, r3, lsl #8 /* r2 = xx32 */
609#endif
610 strh r2, [r0, #0x02]
594 LMEMCPY_4_PAD
595
596/*
597 * 1001: dst is 16-bit aligned, src is 8-bit aligned
598 */
599 ldr r2, [r1, #-1] /* BE:r2 = x012 LE:r2 = 210x */
600 ldr r3, [r1, #3] /* BE:r3 = 3xxx LE:r3 = xxx3 */
601 mov r1, r2, lsr #8 /* BE:r1 = .x01 LE:r1 = .210 */
602 strh r1, [r0]
603#ifdef __ARMEB__
604 mov r2, r2, lsl #8 /* r2 = 012. */
605 orr r2, r2, r3, lsr #24 /* r2 = 0123 */
606#else
607 mov r2, r2, lsr #24 /* r2 = ...2 */
608 orr r2, r2, r3, lsl #8 /* r2 = xx32 */
609#endif
610 strh r2, [r0, #0x02]
611 mov pc, lr
611 bx lr
612 LMEMCPY_4_PAD
613
614/*
615 * 1010: dst is 16-bit aligned, src is 16-bit aligned
616 */
617 ldrh r2, [r1]
618 ldrh r3, [r1, #0x02]
619 strh r2, [r0]
620 strh r3, [r0, #0x02]
612 LMEMCPY_4_PAD
613
614/*
615 * 1010: dst is 16-bit aligned, src is 16-bit aligned
616 */
617 ldrh r2, [r1]
618 ldrh r3, [r1, #0x02]
619 strh r2, [r0]
620 strh r3, [r0, #0x02]
621 mov pc, lr
621 bx lr
622 LMEMCPY_4_PAD
623
624/*
625 * 1011: dst is 16-bit aligned, src is 8-bit aligned
626 */
627 ldr r3, [r1, #1] /* BE:r3 = 123x LE:r3 = x321 */
628 ldr r2, [r1, #-3] /* BE:r2 = xxx0 LE:r2 = 0xxx */
629 mov r1, r3, lsr #8 /* BE:r1 = .123 LE:r1 = .x32 */
630 strh r1, [r0, #0x02]
631#ifdef __ARMEB__
632 mov r3, r3, lsr #24 /* r3 = ...1 */
633 orr r3, r3, r2, lsl #8 /* r3 = xx01 */
634#else
635 mov r3, r3, lsl #8 /* r3 = 321. */
636 orr r3, r3, r2, lsr #24 /* r3 = 3210 */
637#endif
638 strh r3, [r0]
622 LMEMCPY_4_PAD
623
624/*
625 * 1011: dst is 16-bit aligned, src is 8-bit aligned
626 */
627 ldr r3, [r1, #1] /* BE:r3 = 123x LE:r3 = x321 */
628 ldr r2, [r1, #-3] /* BE:r2 = xxx0 LE:r2 = 0xxx */
629 mov r1, r3, lsr #8 /* BE:r1 = .123 LE:r1 = .x32 */
630 strh r1, [r0, #0x02]
631#ifdef __ARMEB__
632 mov r3, r3, lsr #24 /* r3 = ...1 */
633 orr r3, r3, r2, lsl #8 /* r3 = xx01 */
634#else
635 mov r3, r3, lsl #8 /* r3 = 321. */
636 orr r3, r3, r2, lsr #24 /* r3 = 3210 */
637#endif
638 strh r3, [r0]
639 mov pc, lr
639 bx lr
640 LMEMCPY_4_PAD
641
642/*
643 * 1100: dst is 8-bit aligned, src is 32-bit aligned
644 */
645 ldr r2, [r1] /* BE:r2 = 0123 LE:r2 = 3210 */
646#ifdef __ARMEB__
647 strb r2, [r0, #0x03]
648 mov r3, r2, lsr #8
649 mov r1, r2, lsr #24
650 strh r3, [r0, #0x01]
651 strb r1, [r0]
652#else
653 strb r2, [r0]
654 mov r3, r2, lsr #8
655 mov r1, r2, lsr #24
656 strh r3, [r0, #0x01]
657 strb r1, [r0, #0x03]
658#endif
640 LMEMCPY_4_PAD
641
642/*
643 * 1100: dst is 8-bit aligned, src is 32-bit aligned
644 */
645 ldr r2, [r1] /* BE:r2 = 0123 LE:r2 = 3210 */
646#ifdef __ARMEB__
647 strb r2, [r0, #0x03]
648 mov r3, r2, lsr #8
649 mov r1, r2, lsr #24
650 strh r3, [r0, #0x01]
651 strb r1, [r0]
652#else
653 strb r2, [r0]
654 mov r3, r2, lsr #8
655 mov r1, r2, lsr #24
656 strh r3, [r0, #0x01]
657 strb r1, [r0, #0x03]
658#endif
659 mov pc, lr
659 bx lr
660 LMEMCPY_4_PAD
661
662/*
663 * 1101: dst is 8-bit aligned, src is 8-bit aligned
664 */
665 ldrb r2, [r1]
666 ldrh r3, [r1, #0x01]
667 ldrb r1, [r1, #0x03]
668 strb r2, [r0]
669 strh r3, [r0, #0x01]
670 strb r1, [r0, #0x03]
660 LMEMCPY_4_PAD
661
662/*
663 * 1101: dst is 8-bit aligned, src is 8-bit aligned
664 */
665 ldrb r2, [r1]
666 ldrh r3, [r1, #0x01]
667 ldrb r1, [r1, #0x03]
668 strb r2, [r0]
669 strh r3, [r0, #0x01]
670 strb r1, [r0, #0x03]
671 mov pc, lr
671 bx lr
672 LMEMCPY_4_PAD
673
674/*
675 * 1110: dst is 8-bit aligned, src is 16-bit aligned
676 */
677#ifdef __ARMEB__
678 ldrh r3, [r1, #0x02] /* BE:r3 = ..23 LE:r3 = ..32 */
679 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */

--- 8 unchanged lines hidden (view full) ---

688 ldrh r3, [r1, #0x02] /* BE:r3 = ..23 LE:r3 = ..32 */
689 strb r2, [r0]
690 mov r2, r2, lsr #8 /* r2 = ...1 */
691 orr r2, r2, r3, lsl #8 /* r2 = .321 */
692 strh r2, [r0, #0x01]
693 mov r3, r3, lsr #8 /* r3 = ...3 */
694 strb r3, [r0, #0x03]
695#endif
672 LMEMCPY_4_PAD
673
674/*
675 * 1110: dst is 8-bit aligned, src is 16-bit aligned
676 */
677#ifdef __ARMEB__
678 ldrh r3, [r1, #0x02] /* BE:r3 = ..23 LE:r3 = ..32 */
679 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */

--- 8 unchanged lines hidden (view full) ---

688 ldrh r3, [r1, #0x02] /* BE:r3 = ..23 LE:r3 = ..32 */
689 strb r2, [r0]
690 mov r2, r2, lsr #8 /* r2 = ...1 */
691 orr r2, r2, r3, lsl #8 /* r2 = .321 */
692 strh r2, [r0, #0x01]
693 mov r3, r3, lsr #8 /* r3 = ...3 */
694 strb r3, [r0, #0x03]
695#endif
696 mov pc, lr
696 bx lr
697 LMEMCPY_4_PAD
698
699/*
700 * 1111: dst is 8-bit aligned, src is 8-bit aligned
701 */
702 ldrb r2, [r1]
703 ldrh r3, [r1, #0x01]
704 ldrb r1, [r1, #0x03]
705 strb r2, [r0]
706 strh r3, [r0, #0x01]
707 strb r1, [r0, #0x03]
697 LMEMCPY_4_PAD
698
699/*
700 * 1111: dst is 8-bit aligned, src is 8-bit aligned
701 */
702 ldrb r2, [r1]
703 ldrh r3, [r1, #0x01]
704 ldrb r1, [r1, #0x03]
705 strb r2, [r0]
706 strh r3, [r0, #0x01]
707 strb r1, [r0, #0x03]
708 mov pc, lr
708 bx lr
709 LMEMCPY_4_PAD
710
711
712/******************************************************************************
713 * Special case for 6 byte copies
714 */
715#define LMEMCPY_6_LOG2 6 /* 64 bytes */
716#define LMEMCPY_6_PAD .align LMEMCPY_6_LOG2

--- 7 unchanged lines hidden (view full) ---

724
725/*
726 * 0000: dst is 32-bit aligned, src is 32-bit aligned
727 */
728 ldr r2, [r1]
729 ldrh r3, [r1, #0x04]
730 str r2, [r0]
731 strh r3, [r0, #0x04]
709 LMEMCPY_4_PAD
710
711
712/******************************************************************************
713 * Special case for 6 byte copies
714 */
715#define LMEMCPY_6_LOG2 6 /* 64 bytes */
716#define LMEMCPY_6_PAD .align LMEMCPY_6_LOG2

--- 7 unchanged lines hidden (view full) ---

724
725/*
726 * 0000: dst is 32-bit aligned, src is 32-bit aligned
727 */
728 ldr r2, [r1]
729 ldrh r3, [r1, #0x04]
730 str r2, [r0]
731 strh r3, [r0, #0x04]
732 mov pc, lr
732 bx lr
733 LMEMCPY_6_PAD
734
735/*
736 * 0001: dst is 32-bit aligned, src is 8-bit aligned
737 */
738 ldr r2, [r1, #-1] /* BE:r2 = x012 LE:r2 = 210x */
739 ldr r3, [r1, #0x03] /* BE:r3 = 345x LE:r3 = x543 */
740#ifdef __ARMEB__
741 mov r2, r2, lsl #8 /* r2 = 012. */
742 orr r2, r2, r3, lsr #24 /* r2 = 0123 */
743#else
744 mov r2, r2, lsr #8 /* r2 = .210 */
745 orr r2, r2, r3, lsl #24 /* r2 = 3210 */
746#endif
747 mov r3, r3, lsr #8 /* BE:r3 = .345 LE:r3 = .x54 */
748 str r2, [r0]
749 strh r3, [r0, #0x04]
733 LMEMCPY_6_PAD
734
735/*
736 * 0001: dst is 32-bit aligned, src is 8-bit aligned
737 */
738 ldr r2, [r1, #-1] /* BE:r2 = x012 LE:r2 = 210x */
739 ldr r3, [r1, #0x03] /* BE:r3 = 345x LE:r3 = x543 */
740#ifdef __ARMEB__
741 mov r2, r2, lsl #8 /* r2 = 012. */
742 orr r2, r2, r3, lsr #24 /* r2 = 0123 */
743#else
744 mov r2, r2, lsr #8 /* r2 = .210 */
745 orr r2, r2, r3, lsl #24 /* r2 = 3210 */
746#endif
747 mov r3, r3, lsr #8 /* BE:r3 = .345 LE:r3 = .x54 */
748 str r2, [r0]
749 strh r3, [r0, #0x04]
750 mov pc, lr
750 bx lr
751 LMEMCPY_6_PAD
752
753/*
754 * 0010: dst is 32-bit aligned, src is 16-bit aligned
755 */
756 ldr r3, [r1, #0x02] /* BE:r3 = 2345 LE:r3 = 5432 */
757 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */
758#ifdef __ARMEB__
759 mov r1, r3, lsr #16 /* r1 = ..23 */
760 orr r1, r1, r2, lsl #16 /* r1 = 0123 */
761 str r1, [r0]
762 strh r3, [r0, #0x04]
763#else
764 mov r1, r3, lsr #16 /* r1 = ..54 */
765 orr r2, r2, r3, lsl #16 /* r2 = 3210 */
766 str r2, [r0]
767 strh r1, [r0, #0x04]
768#endif
751 LMEMCPY_6_PAD
752
753/*
754 * 0010: dst is 32-bit aligned, src is 16-bit aligned
755 */
756 ldr r3, [r1, #0x02] /* BE:r3 = 2345 LE:r3 = 5432 */
757 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */
758#ifdef __ARMEB__
759 mov r1, r3, lsr #16 /* r1 = ..23 */
760 orr r1, r1, r2, lsl #16 /* r1 = 0123 */
761 str r1, [r0]
762 strh r3, [r0, #0x04]
763#else
764 mov r1, r3, lsr #16 /* r1 = ..54 */
765 orr r2, r2, r3, lsl #16 /* r2 = 3210 */
766 str r2, [r0]
767 strh r1, [r0, #0x04]
768#endif
769 mov pc, lr
769 bx lr
770 LMEMCPY_6_PAD
771
772/*
773 * 0011: dst is 32-bit aligned, src is 8-bit aligned
774 */
775 ldr r2, [r1, #-3] /* BE:r2 = xxx0 LE:r2 = 0xxx */
776 ldr r3, [r1, #1] /* BE:r3 = 1234 LE:r3 = 4321 */
777 ldr r1, [r1, #5] /* BE:r1 = 5xxx LE:r3 = xxx5 */

--- 5 unchanged lines hidden (view full) ---

783#else
784 mov r2, r2, lsr #24 /* r2 = ...0 */
785 orr r2, r2, r3, lsl #8 /* r2 = 3210 */
786 mov r1, r1, lsl #8 /* r1 = xx5. */
787 orr r1, r1, r3, lsr #24 /* r1 = xx54 */
788#endif
789 str r2, [r0]
790 strh r1, [r0, #0x04]
770 LMEMCPY_6_PAD
771
772/*
773 * 0011: dst is 32-bit aligned, src is 8-bit aligned
774 */
775 ldr r2, [r1, #-3] /* BE:r2 = xxx0 LE:r2 = 0xxx */
776 ldr r3, [r1, #1] /* BE:r3 = 1234 LE:r3 = 4321 */
777 ldr r1, [r1, #5] /* BE:r1 = 5xxx LE:r3 = xxx5 */

--- 5 unchanged lines hidden (view full) ---

783#else
784 mov r2, r2, lsr #24 /* r2 = ...0 */
785 orr r2, r2, r3, lsl #8 /* r2 = 3210 */
786 mov r1, r1, lsl #8 /* r1 = xx5. */
787 orr r1, r1, r3, lsr #24 /* r1 = xx54 */
788#endif
789 str r2, [r0]
790 strh r1, [r0, #0x04]
791 mov pc, lr
791 bx lr
792 LMEMCPY_6_PAD
793
794/*
795 * 0100: dst is 8-bit aligned, src is 32-bit aligned
796 */
797 ldr r3, [r1] /* BE:r3 = 0123 LE:r3 = 3210 */
798 ldrh r2, [r1, #0x04] /* BE:r2 = ..45 LE:r2 = ..54 */
799 mov r1, r3, lsr #8 /* BE:r1 = .012 LE:r1 = .321 */

--- 6 unchanged lines hidden (view full) ---

806#else
807 strb r3, [r0]
808 mov r3, r3, lsr #24 /* r3 = ...3 */
809 orr r3, r3, r2, lsl #8 /* r3 = .543 */
810 mov r2, r2, lsr #8 /* r2 = ...5 */
811#endif
812 strh r3, [r0, #0x03]
813 strb r2, [r0, #0x05]
792 LMEMCPY_6_PAD
793
794/*
795 * 0100: dst is 8-bit aligned, src is 32-bit aligned
796 */
797 ldr r3, [r1] /* BE:r3 = 0123 LE:r3 = 3210 */
798 ldrh r2, [r1, #0x04] /* BE:r2 = ..45 LE:r2 = ..54 */
799 mov r1, r3, lsr #8 /* BE:r1 = .012 LE:r1 = .321 */

--- 6 unchanged lines hidden (view full) ---

806#else
807 strb r3, [r0]
808 mov r3, r3, lsr #24 /* r3 = ...3 */
809 orr r3, r3, r2, lsl #8 /* r3 = .543 */
810 mov r2, r2, lsr #8 /* r2 = ...5 */
811#endif
812 strh r3, [r0, #0x03]
813 strb r2, [r0, #0x05]
814 mov pc, lr
814 bx lr
815 LMEMCPY_6_PAD
816
817/*
818 * 0101: dst is 8-bit aligned, src is 8-bit aligned
819 */
820 ldrb r2, [r1]
821 ldrh r3, [r1, #0x01]
822 ldrh ip, [r1, #0x03]
823 ldrb r1, [r1, #0x05]
824 strb r2, [r0]
825 strh r3, [r0, #0x01]
826 strh ip, [r0, #0x03]
827 strb r1, [r0, #0x05]
815 LMEMCPY_6_PAD
816
817/*
818 * 0101: dst is 8-bit aligned, src is 8-bit aligned
819 */
820 ldrb r2, [r1]
821 ldrh r3, [r1, #0x01]
822 ldrh ip, [r1, #0x03]
823 ldrb r1, [r1, #0x05]
824 strb r2, [r0]
825 strh r3, [r0, #0x01]
826 strh ip, [r0, #0x03]
827 strb r1, [r0, #0x05]
828 mov pc, lr
828 bx lr
829 LMEMCPY_6_PAD
830
831/*
832 * 0110: dst is 8-bit aligned, src is 16-bit aligned
833 */
834 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */
835 ldr r1, [r1, #0x02] /* BE:r1 = 2345 LE:r1 = 5432 */
836#ifdef __ARMEB__

--- 10 unchanged lines hidden (view full) ---

847 mov r3, r1, lsr #24
848 strb r3, [r0, #0x05]
849 mov r3, r1, lsr #8 /* r3 = .543 */
850 strh r3, [r0, #0x03]
851 mov r3, r2, lsr #8 /* r3 = ...1 */
852 orr r3, r3, r1, lsl #8 /* r3 = 4321 */
853 strh r3, [r0, #0x01]
854#endif
829 LMEMCPY_6_PAD
830
831/*
832 * 0110: dst is 8-bit aligned, src is 16-bit aligned
833 */
834 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */
835 ldr r1, [r1, #0x02] /* BE:r1 = 2345 LE:r1 = 5432 */
836#ifdef __ARMEB__

--- 10 unchanged lines hidden (view full) ---

847 mov r3, r1, lsr #24
848 strb r3, [r0, #0x05]
849 mov r3, r1, lsr #8 /* r3 = .543 */
850 strh r3, [r0, #0x03]
851 mov r3, r2, lsr #8 /* r3 = ...1 */
852 orr r3, r3, r1, lsl #8 /* r3 = 4321 */
853 strh r3, [r0, #0x01]
854#endif
855 mov pc, lr
855 bx lr
856 LMEMCPY_6_PAD
857
858/*
859 * 0111: dst is 8-bit aligned, src is 8-bit aligned
860 */
861 ldrb r2, [r1]
862 ldrh r3, [r1, #0x01]
863 ldrh ip, [r1, #0x03]
864 ldrb r1, [r1, #0x05]
865 strb r2, [r0]
866 strh r3, [r0, #0x01]
867 strh ip, [r0, #0x03]
868 strb r1, [r0, #0x05]
856 LMEMCPY_6_PAD
857
858/*
859 * 0111: dst is 8-bit aligned, src is 8-bit aligned
860 */
861 ldrb r2, [r1]
862 ldrh r3, [r1, #0x01]
863 ldrh ip, [r1, #0x03]
864 ldrb r1, [r1, #0x05]
865 strb r2, [r0]
866 strh r3, [r0, #0x01]
867 strh ip, [r0, #0x03]
868 strb r1, [r0, #0x05]
869 mov pc, lr
869 bx lr
870 LMEMCPY_6_PAD
871
872/*
873 * 1000: dst is 16-bit aligned, src is 32-bit aligned
874 */
875#ifdef __ARMEB__
876 ldr r2, [r1] /* r2 = 0123 */
877 ldrh r3, [r1, #0x04] /* r3 = ..45 */

--- 4 unchanged lines hidden (view full) ---

882#else
883 ldrh r2, [r1, #0x04] /* r2 = ..54 */
884 ldr r3, [r1] /* r3 = 3210 */
885 mov r2, r2, lsl #16 /* r2 = 54.. */
886 orr r2, r2, r3, lsr #16 /* r2 = 5432 */
887 strh r3, [r0]
888 str r2, [r0, #0x02]
889#endif
870 LMEMCPY_6_PAD
871
872/*
873 * 1000: dst is 16-bit aligned, src is 32-bit aligned
874 */
875#ifdef __ARMEB__
876 ldr r2, [r1] /* r2 = 0123 */
877 ldrh r3, [r1, #0x04] /* r3 = ..45 */

--- 4 unchanged lines hidden (view full) ---

882#else
883 ldrh r2, [r1, #0x04] /* r2 = ..54 */
884 ldr r3, [r1] /* r3 = 3210 */
885 mov r2, r2, lsl #16 /* r2 = 54.. */
886 orr r2, r2, r3, lsr #16 /* r2 = 5432 */
887 strh r3, [r0]
888 str r2, [r0, #0x02]
889#endif
890 mov pc, lr
890 bx lr
891 LMEMCPY_6_PAD
892
893/*
894 * 1001: dst is 16-bit aligned, src is 8-bit aligned
895 */
896 ldr r3, [r1, #-1] /* BE:r3 = x012 LE:r3 = 210x */
897 ldr r2, [r1, #3] /* BE:r2 = 345x LE:r2 = x543 */
898 mov r1, r3, lsr #8 /* BE:r1 = .x01 LE:r1 = .210 */
899#ifdef __ARMEB__
900 mov r2, r2, lsr #8 /* r2 = .345 */
901 orr r2, r2, r3, lsl #24 /* r2 = 2345 */
902#else
903 mov r2, r2, lsl #8 /* r2 = 543. */
904 orr r2, r2, r3, lsr #24 /* r2 = 5432 */
905#endif
906 strh r1, [r0]
907 str r2, [r0, #0x02]
891 LMEMCPY_6_PAD
892
893/*
894 * 1001: dst is 16-bit aligned, src is 8-bit aligned
895 */
896 ldr r3, [r1, #-1] /* BE:r3 = x012 LE:r3 = 210x */
897 ldr r2, [r1, #3] /* BE:r2 = 345x LE:r2 = x543 */
898 mov r1, r3, lsr #8 /* BE:r1 = .x01 LE:r1 = .210 */
899#ifdef __ARMEB__
900 mov r2, r2, lsr #8 /* r2 = .345 */
901 orr r2, r2, r3, lsl #24 /* r2 = 2345 */
902#else
903 mov r2, r2, lsl #8 /* r2 = 543. */
904 orr r2, r2, r3, lsr #24 /* r2 = 5432 */
905#endif
906 strh r1, [r0]
907 str r2, [r0, #0x02]
908 mov pc, lr
908 bx lr
909 LMEMCPY_6_PAD
910
911/*
912 * 1010: dst is 16-bit aligned, src is 16-bit aligned
913 */
914 ldrh r2, [r1]
915 ldr r3, [r1, #0x02]
916 strh r2, [r0]
917 str r3, [r0, #0x02]
909 LMEMCPY_6_PAD
910
911/*
912 * 1010: dst is 16-bit aligned, src is 16-bit aligned
913 */
914 ldrh r2, [r1]
915 ldr r3, [r1, #0x02]
916 strh r2, [r0]
917 str r3, [r0, #0x02]
918 mov pc, lr
918 bx lr
919 LMEMCPY_6_PAD
920
921/*
922 * 1011: dst is 16-bit aligned, src is 8-bit aligned
923 */
924 ldrb r3, [r1] /* r3 = ...0 */
925 ldr r2, [r1, #0x01] /* BE:r2 = 1234 LE:r2 = 4321 */
926 ldrb r1, [r1, #0x05] /* r1 = ...5 */
927#ifdef __ARMEB__
928 mov r3, r3, lsl #8 /* r3 = ..0. */
929 orr r3, r3, r2, lsr #24 /* r3 = ..01 */
930 orr r1, r1, r2, lsl #8 /* r1 = 2345 */
931#else
932 orr r3, r3, r2, lsl #8 /* r3 = 3210 */
933 mov r1, r1, lsl #24 /* r1 = 5... */
934 orr r1, r1, r2, lsr #8 /* r1 = 5432 */
935#endif
936 strh r3, [r0]
937 str r1, [r0, #0x02]
919 LMEMCPY_6_PAD
920
921/*
922 * 1011: dst is 16-bit aligned, src is 8-bit aligned
923 */
924 ldrb r3, [r1] /* r3 = ...0 */
925 ldr r2, [r1, #0x01] /* BE:r2 = 1234 LE:r2 = 4321 */
926 ldrb r1, [r1, #0x05] /* r1 = ...5 */
927#ifdef __ARMEB__
928 mov r3, r3, lsl #8 /* r3 = ..0. */
929 orr r3, r3, r2, lsr #24 /* r3 = ..01 */
930 orr r1, r1, r2, lsl #8 /* r1 = 2345 */
931#else
932 orr r3, r3, r2, lsl #8 /* r3 = 3210 */
933 mov r1, r1, lsl #24 /* r1 = 5... */
934 orr r1, r1, r2, lsr #8 /* r1 = 5432 */
935#endif
936 strh r3, [r0]
937 str r1, [r0, #0x02]
938 mov pc, lr
938 bx lr
939 LMEMCPY_6_PAD
940
941/*
942 * 1100: dst is 8-bit aligned, src is 32-bit aligned
943 */
944 ldr r2, [r1] /* BE:r2 = 0123 LE:r2 = 3210 */
945 ldrh r1, [r1, #0x04] /* BE:r1 = ..45 LE:r1 = ..54 */
946#ifdef __ARMEB__

--- 4 unchanged lines hidden (view full) ---

951#else
952 strb r2, [r0]
953 mov r2, r2, lsr #8 /* r2 = .321 */
954 orr r2, r2, r1, lsl #24 /* r2 = 4321 */
955 mov r1, r1, lsr #8 /* r1 = ...5 */
956#endif
957 str r2, [r0, #0x01]
958 strb r1, [r0, #0x05]
939 LMEMCPY_6_PAD
940
941/*
942 * 1100: dst is 8-bit aligned, src is 32-bit aligned
943 */
944 ldr r2, [r1] /* BE:r2 = 0123 LE:r2 = 3210 */
945 ldrh r1, [r1, #0x04] /* BE:r1 = ..45 LE:r1 = ..54 */
946#ifdef __ARMEB__

--- 4 unchanged lines hidden (view full) ---

951#else
952 strb r2, [r0]
953 mov r2, r2, lsr #8 /* r2 = .321 */
954 orr r2, r2, r1, lsl #24 /* r2 = 4321 */
955 mov r1, r1, lsr #8 /* r1 = ...5 */
956#endif
957 str r2, [r0, #0x01]
958 strb r1, [r0, #0x05]
959 mov pc, lr
959 bx lr
960 LMEMCPY_6_PAD
961
962/*
963 * 1101: dst is 8-bit aligned, src is 8-bit aligned
964 */
965 ldrb r2, [r1]
966 ldrh r3, [r1, #0x01]
967 ldrh ip, [r1, #0x03]
968 ldrb r1, [r1, #0x05]
969 strb r2, [r0]
970 strh r3, [r0, #0x01]
971 strh ip, [r0, #0x03]
972 strb r1, [r0, #0x05]
960 LMEMCPY_6_PAD
961
962/*
963 * 1101: dst is 8-bit aligned, src is 8-bit aligned
964 */
965 ldrb r2, [r1]
966 ldrh r3, [r1, #0x01]
967 ldrh ip, [r1, #0x03]
968 ldrb r1, [r1, #0x05]
969 strb r2, [r0]
970 strh r3, [r0, #0x01]
971 strh ip, [r0, #0x03]
972 strb r1, [r0, #0x05]
973 mov pc, lr
973 bx lr
974 LMEMCPY_6_PAD
975
976/*
977 * 1110: dst is 8-bit aligned, src is 16-bit aligned
978 */
979 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */
980 ldr r1, [r1, #0x02] /* BE:r1 = 2345 LE:r1 = 5432 */
981#ifdef __ARMEB__

--- 4 unchanged lines hidden (view full) ---

986#else
987 strb r2, [r0]
988 mov r2, r2, lsr #8 /* r2 = ...1 */
989 orr r2, r2, r1, lsl #8 /* r2 = 4321 */
990 mov r1, r1, lsr #24 /* r1 = ...5 */
991#endif
992 str r2, [r0, #0x01]
993 strb r1, [r0, #0x05]
974 LMEMCPY_6_PAD
975
976/*
977 * 1110: dst is 8-bit aligned, src is 16-bit aligned
978 */
979 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */
980 ldr r1, [r1, #0x02] /* BE:r1 = 2345 LE:r1 = 5432 */
981#ifdef __ARMEB__

--- 4 unchanged lines hidden (view full) ---

986#else
987 strb r2, [r0]
988 mov r2, r2, lsr #8 /* r2 = ...1 */
989 orr r2, r2, r1, lsl #8 /* r2 = 4321 */
990 mov r1, r1, lsr #24 /* r1 = ...5 */
991#endif
992 str r2, [r0, #0x01]
993 strb r1, [r0, #0x05]
994 mov pc, lr
994 bx lr
995 LMEMCPY_6_PAD
996
997/*
998 * 1111: dst is 8-bit aligned, src is 8-bit aligned
999 */
1000 ldrb r2, [r1]
1001 ldr r3, [r1, #0x01]
1002 ldrb r1, [r1, #0x05]
1003 strb r2, [r0]
1004 str r3, [r0, #0x01]
1005 strb r1, [r0, #0x05]
995 LMEMCPY_6_PAD
996
997/*
998 * 1111: dst is 8-bit aligned, src is 8-bit aligned
999 */
1000 ldrb r2, [r1]
1001 ldr r3, [r1, #0x01]
1002 ldrb r1, [r1, #0x05]
1003 strb r2, [r0]
1004 str r3, [r0, #0x01]
1005 strb r1, [r0, #0x05]
1006 mov pc, lr
1006 bx lr
1007 LMEMCPY_6_PAD
1008
1009
1010/******************************************************************************
1011 * Special case for 8 byte copies
1012 */
1013#define LMEMCPY_8_LOG2 6 /* 64 bytes */
1014#define LMEMCPY_8_PAD .align LMEMCPY_8_LOG2

--- 7 unchanged lines hidden (view full) ---

1022
1023/*
1024 * 0000: dst is 32-bit aligned, src is 32-bit aligned
1025 */
1026 ldr r2, [r1]
1027 ldr r3, [r1, #0x04]
1028 str r2, [r0]
1029 str r3, [r0, #0x04]
1007 LMEMCPY_6_PAD
1008
1009
1010/******************************************************************************
1011 * Special case for 8 byte copies
1012 */
1013#define LMEMCPY_8_LOG2 6 /* 64 bytes */
1014#define LMEMCPY_8_PAD .align LMEMCPY_8_LOG2

--- 7 unchanged lines hidden (view full) ---

1022
1023/*
1024 * 0000: dst is 32-bit aligned, src is 32-bit aligned
1025 */
1026 ldr r2, [r1]
1027 ldr r3, [r1, #0x04]
1028 str r2, [r0]
1029 str r3, [r0, #0x04]
1030 mov pc, lr
1030 bx lr
1031 LMEMCPY_8_PAD
1032
1033/*
1034 * 0001: dst is 32-bit aligned, src is 8-bit aligned
1035 */
1036 ldr r3, [r1, #-1] /* BE:r3 = x012 LE:r3 = 210x */
1037 ldr r2, [r1, #0x03] /* BE:r2 = 3456 LE:r2 = 6543 */
1038 ldrb r1, [r1, #0x07] /* r1 = ...7 */

--- 4 unchanged lines hidden (view full) ---

1043#else
1044 mov r3, r3, lsr #8 /* r3 = .210 */
1045 orr r3, r3, r2, lsl #24 /* r3 = 3210 */
1046 mov r1, r1, lsl #24 /* r1 = 7... */
1047 orr r2, r1, r2, lsr #8 /* r2 = 7654 */
1048#endif
1049 str r3, [r0]
1050 str r2, [r0, #0x04]
1031 LMEMCPY_8_PAD
1032
1033/*
1034 * 0001: dst is 32-bit aligned, src is 8-bit aligned
1035 */
1036 ldr r3, [r1, #-1] /* BE:r3 = x012 LE:r3 = 210x */
1037 ldr r2, [r1, #0x03] /* BE:r2 = 3456 LE:r2 = 6543 */
1038 ldrb r1, [r1, #0x07] /* r1 = ...7 */

--- 4 unchanged lines hidden (view full) ---

1043#else
1044 mov r3, r3, lsr #8 /* r3 = .210 */
1045 orr r3, r3, r2, lsl #24 /* r3 = 3210 */
1046 mov r1, r1, lsl #24 /* r1 = 7... */
1047 orr r2, r1, r2, lsr #8 /* r2 = 7654 */
1048#endif
1049 str r3, [r0]
1050 str r2, [r0, #0x04]
1051 mov pc, lr
1051 bx lr
1052 LMEMCPY_8_PAD
1053
1054/*
1055 * 0010: dst is 32-bit aligned, src is 16-bit aligned
1056 */
1057 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */
1058 ldr r3, [r1, #0x02] /* BE:r3 = 2345 LE:r3 = 5432 */
1059 ldrh r1, [r1, #0x06] /* BE:r1 = ..67 LE:r1 = ..76 */
1060#ifdef __ARMEB__
1061 mov r2, r2, lsl #16 /* r2 = 01.. */
1062 orr r2, r2, r3, lsr #16 /* r2 = 0123 */
1063 orr r3, r1, r3, lsl #16 /* r3 = 4567 */
1064#else
1065 orr r2, r2, r3, lsl #16 /* r2 = 3210 */
1066 mov r3, r3, lsr #16 /* r3 = ..54 */
1067 orr r3, r3, r1, lsl #16 /* r3 = 7654 */
1068#endif
1069 str r2, [r0]
1070 str r3, [r0, #0x04]
1052 LMEMCPY_8_PAD
1053
1054/*
1055 * 0010: dst is 32-bit aligned, src is 16-bit aligned
1056 */
1057 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */
1058 ldr r3, [r1, #0x02] /* BE:r3 = 2345 LE:r3 = 5432 */
1059 ldrh r1, [r1, #0x06] /* BE:r1 = ..67 LE:r1 = ..76 */
1060#ifdef __ARMEB__
1061 mov r2, r2, lsl #16 /* r2 = 01.. */
1062 orr r2, r2, r3, lsr #16 /* r2 = 0123 */
1063 orr r3, r1, r3, lsl #16 /* r3 = 4567 */
1064#else
1065 orr r2, r2, r3, lsl #16 /* r2 = 3210 */
1066 mov r3, r3, lsr #16 /* r3 = ..54 */
1067 orr r3, r3, r1, lsl #16 /* r3 = 7654 */
1068#endif
1069 str r2, [r0]
1070 str r3, [r0, #0x04]
1071 mov pc, lr
1071 bx lr
1072 LMEMCPY_8_PAD
1073
1074/*
1075 * 0011: dst is 32-bit aligned, src is 8-bit aligned
1076 */
1077 ldrb r3, [r1] /* r3 = ...0 */
1078 ldr r2, [r1, #0x01] /* BE:r2 = 1234 LE:r2 = 4321 */
1079 ldr r1, [r1, #0x05] /* BE:r1 = 567x LE:r1 = x765 */

--- 4 unchanged lines hidden (view full) ---

1084 orr r2, r2, r1, lsr #8 /* r2 = 4567 */
1085#else
1086 orr r3, r3, r2, lsl #8 /* r3 = 3210 */
1087 mov r2, r2, lsr #24 /* r2 = ...4 */
1088 orr r2, r2, r1, lsl #8 /* r2 = 7654 */
1089#endif
1090 str r3, [r0]
1091 str r2, [r0, #0x04]
1072 LMEMCPY_8_PAD
1073
1074/*
1075 * 0011: dst is 32-bit aligned, src is 8-bit aligned
1076 */
1077 ldrb r3, [r1] /* r3 = ...0 */
1078 ldr r2, [r1, #0x01] /* BE:r2 = 1234 LE:r2 = 4321 */
1079 ldr r1, [r1, #0x05] /* BE:r1 = 567x LE:r1 = x765 */

--- 4 unchanged lines hidden (view full) ---

1084 orr r2, r2, r1, lsr #8 /* r2 = 4567 */
1085#else
1086 orr r3, r3, r2, lsl #8 /* r3 = 3210 */
1087 mov r2, r2, lsr #24 /* r2 = ...4 */
1088 orr r2, r2, r1, lsl #8 /* r2 = 7654 */
1089#endif
1090 str r3, [r0]
1091 str r2, [r0, #0x04]
1092 mov pc, lr
1092 bx lr
1093 LMEMCPY_8_PAD
1094
1095/*
1096 * 0100: dst is 8-bit aligned, src is 32-bit aligned
1097 */
1098 ldr r3, [r1] /* BE:r3 = 0123 LE:r3 = 3210 */
1099 ldr r2, [r1, #0x04] /* BE:r2 = 4567 LE:r2 = 7654 */
1100#ifdef __ARMEB__

--- 8 unchanged lines hidden (view full) ---

1109 mov r1, r2, lsr #24 /* r1 = ...7 */
1110 strb r1, [r0, #0x07]
1111 mov r1, r3, lsr #8 /* r1 = .321 */
1112 mov r3, r3, lsr #24 /* r3 = ...3 */
1113 orr r3, r3, r2, lsl #8 /* r3 = 6543 */
1114#endif
1115 strh r1, [r0, #0x01]
1116 str r3, [r0, #0x03]
1093 LMEMCPY_8_PAD
1094
1095/*
1096 * 0100: dst is 8-bit aligned, src is 32-bit aligned
1097 */
1098 ldr r3, [r1] /* BE:r3 = 0123 LE:r3 = 3210 */
1099 ldr r2, [r1, #0x04] /* BE:r2 = 4567 LE:r2 = 7654 */
1100#ifdef __ARMEB__

--- 8 unchanged lines hidden (view full) ---

1109 mov r1, r2, lsr #24 /* r1 = ...7 */
1110 strb r1, [r0, #0x07]
1111 mov r1, r3, lsr #8 /* r1 = .321 */
1112 mov r3, r3, lsr #24 /* r3 = ...3 */
1113 orr r3, r3, r2, lsl #8 /* r3 = 6543 */
1114#endif
1115 strh r1, [r0, #0x01]
1116 str r3, [r0, #0x03]
1117 mov pc, lr
1117 bx lr
1118 LMEMCPY_8_PAD
1119
1120/*
1121 * 0101: dst is 8-bit aligned, src is 8-bit aligned
1122 */
1123 ldrb r2, [r1]
1124 ldrh r3, [r1, #0x01]
1125 ldr ip, [r1, #0x03]
1126 ldrb r1, [r1, #0x07]
1127 strb r2, [r0]
1128 strh r3, [r0, #0x01]
1129 str ip, [r0, #0x03]
1130 strb r1, [r0, #0x07]
1118 LMEMCPY_8_PAD
1119
1120/*
1121 * 0101: dst is 8-bit aligned, src is 8-bit aligned
1122 */
1123 ldrb r2, [r1]
1124 ldrh r3, [r1, #0x01]
1125 ldr ip, [r1, #0x03]
1126 ldrb r1, [r1, #0x07]
1127 strb r2, [r0]
1128 strh r3, [r0, #0x01]
1129 str ip, [r0, #0x03]
1130 strb r1, [r0, #0x07]
1131 mov pc, lr
1131 bx lr
1132 LMEMCPY_8_PAD
1133
1134/*
1135 * 0110: dst is 8-bit aligned, src is 16-bit aligned
1136 */
1137 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */
1138 ldr r3, [r1, #0x02] /* BE:r3 = 2345 LE:r3 = 5432 */
1139 ldrh r1, [r1, #0x06] /* BE:r1 = ..67 LE:r1 = ..76 */

--- 11 unchanged lines hidden (view full) ---

1151 strb ip, [r0, #0x07] /* 7 */
1152 mov ip, r2, lsr #8 /* ip = ...1 */
1153 orr ip, ip, r3, lsl #8 /* ip = 4321 */
1154 mov r3, r3, lsr #8 /* r3 = .543 */
1155 orr r3, r3, r1, lsl #24 /* r3 = 6543 */
1156#endif
1157 strh ip, [r0, #0x01]
1158 str r3, [r0, #0x03]
1132 LMEMCPY_8_PAD
1133
1134/*
1135 * 0110: dst is 8-bit aligned, src is 16-bit aligned
1136 */
1137 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */
1138 ldr r3, [r1, #0x02] /* BE:r3 = 2345 LE:r3 = 5432 */
1139 ldrh r1, [r1, #0x06] /* BE:r1 = ..67 LE:r1 = ..76 */

--- 11 unchanged lines hidden (view full) ---

1151 strb ip, [r0, #0x07] /* 7 */
1152 mov ip, r2, lsr #8 /* ip = ...1 */
1153 orr ip, ip, r3, lsl #8 /* ip = 4321 */
1154 mov r3, r3, lsr #8 /* r3 = .543 */
1155 orr r3, r3, r1, lsl #24 /* r3 = 6543 */
1156#endif
1157 strh ip, [r0, #0x01]
1158 str r3, [r0, #0x03]
1159 mov pc, lr
1159 bx lr
1160 LMEMCPY_8_PAD
1161
1162/*
1163 * 0111: dst is 8-bit aligned, src is 8-bit aligned
1164 */
1165 ldrb r3, [r1] /* r3 = ...0 */
1166 ldr ip, [r1, #0x01] /* BE:ip = 1234 LE:ip = 4321 */
1167 ldrh r2, [r1, #0x05] /* BE:r2 = ..56 LE:r2 = ..65 */

--- 4 unchanged lines hidden (view full) ---

1172 strh r3, [r0, #0x01]
1173 orr r2, r2, ip, lsl #16 /* r2 = 3456 */
1174#else
1175 strh ip, [r0, #0x01]
1176 orr r2, r3, r2, lsl #16 /* r2 = 6543 */
1177#endif
1178 str r2, [r0, #0x03]
1179 strb r1, [r0, #0x07]
1160 LMEMCPY_8_PAD
1161
1162/*
1163 * 0111: dst is 8-bit aligned, src is 8-bit aligned
1164 */
1165 ldrb r3, [r1] /* r3 = ...0 */
1166 ldr ip, [r1, #0x01] /* BE:ip = 1234 LE:ip = 4321 */
1167 ldrh r2, [r1, #0x05] /* BE:r2 = ..56 LE:r2 = ..65 */

--- 4 unchanged lines hidden (view full) ---

1172 strh r3, [r0, #0x01]
1173 orr r2, r2, ip, lsl #16 /* r2 = 3456 */
1174#else
1175 strh ip, [r0, #0x01]
1176 orr r2, r3, r2, lsl #16 /* r2 = 6543 */
1177#endif
1178 str r2, [r0, #0x03]
1179 strb r1, [r0, #0x07]
1180 mov pc, lr
1180 bx lr
1181 LMEMCPY_8_PAD
1182
1183/*
1184 * 1000: dst is 16-bit aligned, src is 32-bit aligned
1185 */
1186 ldr r2, [r1] /* BE:r2 = 0123 LE:r2 = 3210 */
1187 ldr r3, [r1, #0x04] /* BE:r3 = 4567 LE:r3 = 7654 */
1188 mov r1, r2, lsr #16 /* BE:r1 = ..01 LE:r1 = ..32 */
1189#ifdef __ARMEB__
1190 strh r1, [r0]
1191 mov r1, r3, lsr #16 /* r1 = ..45 */
1192 orr r2, r1 ,r2, lsl #16 /* r2 = 2345 */
1193#else
1194 strh r2, [r0]
1195 orr r2, r1, r3, lsl #16 /* r2 = 5432 */
1196 mov r3, r3, lsr #16 /* r3 = ..76 */
1197#endif
1198 str r2, [r0, #0x02]
1199 strh r3, [r0, #0x06]
1181 LMEMCPY_8_PAD
1182
1183/*
1184 * 1000: dst is 16-bit aligned, src is 32-bit aligned
1185 */
1186 ldr r2, [r1] /* BE:r2 = 0123 LE:r2 = 3210 */
1187 ldr r3, [r1, #0x04] /* BE:r3 = 4567 LE:r3 = 7654 */
1188 mov r1, r2, lsr #16 /* BE:r1 = ..01 LE:r1 = ..32 */
1189#ifdef __ARMEB__
1190 strh r1, [r0]
1191 mov r1, r3, lsr #16 /* r1 = ..45 */
1192 orr r2, r1 ,r2, lsl #16 /* r2 = 2345 */
1193#else
1194 strh r2, [r0]
1195 orr r2, r1, r3, lsl #16 /* r2 = 5432 */
1196 mov r3, r3, lsr #16 /* r3 = ..76 */
1197#endif
1198 str r2, [r0, #0x02]
1199 strh r3, [r0, #0x06]
1200 mov pc, lr
1200 bx lr
1201 LMEMCPY_8_PAD
1202
1203/*
1204 * 1001: dst is 16-bit aligned, src is 8-bit aligned
1205 */
1206 ldr r2, [r1, #-1] /* BE:r2 = x012 LE:r2 = 210x */
1207 ldr r3, [r1, #0x03] /* BE:r3 = 3456 LE:r3 = 6543 */
1208 ldrb ip, [r1, #0x07] /* ip = ...7 */

--- 6 unchanged lines hidden (view full) ---

1215#else
1216 mov r1, r2, lsr #24 /* r1 = ...2 */
1217 orr r1, r1, r3, lsl #8 /* r1 = 5432 */
1218 mov r3, r3, lsr #24 /* r3 = ...6 */
1219 orr r3, r3, ip, lsl #8 /* r3 = ..76 */
1220#endif
1221 str r1, [r0, #0x02]
1222 strh r3, [r0, #0x06]
1201 LMEMCPY_8_PAD
1202
1203/*
1204 * 1001: dst is 16-bit aligned, src is 8-bit aligned
1205 */
1206 ldr r2, [r1, #-1] /* BE:r2 = x012 LE:r2 = 210x */
1207 ldr r3, [r1, #0x03] /* BE:r3 = 3456 LE:r3 = 6543 */
1208 ldrb ip, [r1, #0x07] /* ip = ...7 */

--- 6 unchanged lines hidden (view full) ---

1215#else
1216 mov r1, r2, lsr #24 /* r1 = ...2 */
1217 orr r1, r1, r3, lsl #8 /* r1 = 5432 */
1218 mov r3, r3, lsr #24 /* r3 = ...6 */
1219 orr r3, r3, ip, lsl #8 /* r3 = ..76 */
1220#endif
1221 str r1, [r0, #0x02]
1222 strh r3, [r0, #0x06]
1223 mov pc, lr
1223 bx lr
1224 LMEMCPY_8_PAD
1225
1226/*
1227 * 1010: dst is 16-bit aligned, src is 16-bit aligned
1228 */
1229 ldrh r2, [r1]
1230 ldr ip, [r1, #0x02]
1231 ldrh r3, [r1, #0x06]
1232 strh r2, [r0]
1233 str ip, [r0, #0x02]
1234 strh r3, [r0, #0x06]
1224 LMEMCPY_8_PAD
1225
1226/*
1227 * 1010: dst is 16-bit aligned, src is 16-bit aligned
1228 */
1229 ldrh r2, [r1]
1230 ldr ip, [r1, #0x02]
1231 ldrh r3, [r1, #0x06]
1232 strh r2, [r0]
1233 str ip, [r0, #0x02]
1234 strh r3, [r0, #0x06]
1235 mov pc, lr
1235 bx lr
1236 LMEMCPY_8_PAD
1237
1238/*
1239 * 1011: dst is 16-bit aligned, src is 8-bit aligned
1240 */
1241 ldr r3, [r1, #0x05] /* BE:r3 = 567x LE:r3 = x765 */
1242 ldr r2, [r1, #0x01] /* BE:r2 = 1234 LE:r2 = 4321 */
1243 ldrb ip, [r1] /* ip = ...0 */

--- 6 unchanged lines hidden (view full) ---

1250 orr r2, r2, ip, lsl #8 /* r2 = ..01 */
1251#else
1252 mov r3, r3, lsl #24 /* r3 = 5... */
1253 orr r3, r3, r2, lsr #8 /* r3 = 5432 */
1254 orr r2, ip, r2, lsl #8 /* r2 = 3210 */
1255#endif
1256 str r3, [r0, #0x02]
1257 strh r2, [r0]
1236 LMEMCPY_8_PAD
1237
1238/*
1239 * 1011: dst is 16-bit aligned, src is 8-bit aligned
1240 */
1241 ldr r3, [r1, #0x05] /* BE:r3 = 567x LE:r3 = x765 */
1242 ldr r2, [r1, #0x01] /* BE:r2 = 1234 LE:r2 = 4321 */
1243 ldrb ip, [r1] /* ip = ...0 */

--- 6 unchanged lines hidden (view full) ---

1250 orr r2, r2, ip, lsl #8 /* r2 = ..01 */
1251#else
1252 mov r3, r3, lsl #24 /* r3 = 5... */
1253 orr r3, r3, r2, lsr #8 /* r3 = 5432 */
1254 orr r2, ip, r2, lsl #8 /* r2 = 3210 */
1255#endif
1256 str r3, [r0, #0x02]
1257 strh r2, [r0]
1258 mov pc, lr
1258 bx lr
1259 LMEMCPY_8_PAD
1260
1261/*
1262 * 1100: dst is 8-bit aligned, src is 32-bit aligned
1263 */
1264 ldr r3, [r1, #0x04] /* BE:r3 = 4567 LE:r3 = 7654 */
1265 ldr r2, [r1] /* BE:r2 = 0123 LE:r2 = 3210 */
1266 mov r1, r3, lsr #8 /* BE:r1 = .456 LE:r1 = .765 */

--- 8 unchanged lines hidden (view full) ---

1275#else
1276 strb r2, [r0]
1277 mov r1, r3, lsr #24 /* r1 = ...7 */
1278 strb r1, [r0, #0x07]
1279 mov r2, r2, lsr #8 /* r2 = .321 */
1280 orr r2, r2, r3, lsl #24 /* r2 = 4321 */
1281 str r2, [r0, #0x01]
1282#endif
1259 LMEMCPY_8_PAD
1260
1261/*
1262 * 1100: dst is 8-bit aligned, src is 32-bit aligned
1263 */
1264 ldr r3, [r1, #0x04] /* BE:r3 = 4567 LE:r3 = 7654 */
1265 ldr r2, [r1] /* BE:r2 = 0123 LE:r2 = 3210 */
1266 mov r1, r3, lsr #8 /* BE:r1 = .456 LE:r1 = .765 */

--- 8 unchanged lines hidden (view full) ---

1275#else
1276 strb r2, [r0]
1277 mov r1, r3, lsr #24 /* r1 = ...7 */
1278 strb r1, [r0, #0x07]
1279 mov r2, r2, lsr #8 /* r2 = .321 */
1280 orr r2, r2, r3, lsl #24 /* r2 = 4321 */
1281 str r2, [r0, #0x01]
1282#endif
1283 mov pc, lr
1283 bx lr
1284 LMEMCPY_8_PAD
1285
1286/*
1287 * 1101: dst is 8-bit aligned, src is 8-bit aligned
1288 */
1289 ldrb r3, [r1] /* r3 = ...0 */
1290 ldrh r2, [r1, #0x01] /* BE:r2 = ..12 LE:r2 = ..21 */
1291 ldr ip, [r1, #0x03] /* BE:ip = 3456 LE:ip = 6543 */

--- 4 unchanged lines hidden (view full) ---

1296 strh ip, [r0, #0x05]
1297 orr r2, r3, r2, lsl #16 /* r2 = 1234 */
1298#else
1299 strh r3, [r0, #0x05]
1300 orr r2, r2, ip, lsl #16 /* r2 = 4321 */
1301#endif
1302 str r2, [r0, #0x01]
1303 strb r1, [r0, #0x07]
1284 LMEMCPY_8_PAD
1285
1286/*
1287 * 1101: dst is 8-bit aligned, src is 8-bit aligned
1288 */
1289 ldrb r3, [r1] /* r3 = ...0 */
1290 ldrh r2, [r1, #0x01] /* BE:r2 = ..12 LE:r2 = ..21 */
1291 ldr ip, [r1, #0x03] /* BE:ip = 3456 LE:ip = 6543 */

--- 4 unchanged lines hidden (view full) ---

1296 strh ip, [r0, #0x05]
1297 orr r2, r3, r2, lsl #16 /* r2 = 1234 */
1298#else
1299 strh r3, [r0, #0x05]
1300 orr r2, r2, ip, lsl #16 /* r2 = 4321 */
1301#endif
1302 str r2, [r0, #0x01]
1303 strb r1, [r0, #0x07]
1304 mov pc, lr
1304 bx lr
1305 LMEMCPY_8_PAD
1306
1307/*
1308 * 1110: dst is 8-bit aligned, src is 16-bit aligned
1309 */
1310 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */
1311 ldr r3, [r1, #0x02] /* BE:r3 = 2345 LE:r3 = 5432 */
1312 ldrh r1, [r1, #0x06] /* BE:r1 = ..67 LE:r1 = ..76 */

--- 11 unchanged lines hidden (view full) ---

1324 orr ip, ip, r3, lsl #8 /* ip = 4321 */
1325 mov r2, r1, lsr #8 /* r2 = ...7 */
1326 strb r2, [r0, #0x07]
1327 mov r1, r1, lsl #8 /* r1 = .76. */
1328 orr r1, r1, r3, lsr #24 /* r1 = .765 */
1329#endif
1330 str ip, [r0, #0x01]
1331 strh r1, [r0, #0x05]
1305 LMEMCPY_8_PAD
1306
1307/*
1308 * 1110: dst is 8-bit aligned, src is 16-bit aligned
1309 */
1310 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */
1311 ldr r3, [r1, #0x02] /* BE:r3 = 2345 LE:r3 = 5432 */
1312 ldrh r1, [r1, #0x06] /* BE:r1 = ..67 LE:r1 = ..76 */

--- 11 unchanged lines hidden (view full) ---

1324 orr ip, ip, r3, lsl #8 /* ip = 4321 */
1325 mov r2, r1, lsr #8 /* r2 = ...7 */
1326 strb r2, [r0, #0x07]
1327 mov r1, r1, lsl #8 /* r1 = .76. */
1328 orr r1, r1, r3, lsr #24 /* r1 = .765 */
1329#endif
1330 str ip, [r0, #0x01]
1331 strh r1, [r0, #0x05]
1332 mov pc, lr
1332 bx lr
1333 LMEMCPY_8_PAD
1334
1335/*
1336 * 1111: dst is 8-bit aligned, src is 8-bit aligned
1337 */
1338 ldrb r2, [r1]
1339 ldr ip, [r1, #0x01]
1340 ldrh r3, [r1, #0x05]
1341 ldrb r1, [r1, #0x07]
1342 strb r2, [r0]
1343 str ip, [r0, #0x01]
1344 strh r3, [r0, #0x05]
1345 strb r1, [r0, #0x07]
1333 LMEMCPY_8_PAD
1334
1335/*
1336 * 1111: dst is 8-bit aligned, src is 8-bit aligned
1337 */
1338 ldrb r2, [r1]
1339 ldr ip, [r1, #0x01]
1340 ldrh r3, [r1, #0x05]
1341 ldrb r1, [r1, #0x07]
1342 strb r2, [r0]
1343 str ip, [r0, #0x01]
1344 strh r3, [r0, #0x05]
1345 strb r1, [r0, #0x07]
1346 mov pc, lr
1346 bx lr
1347 LMEMCPY_8_PAD
1348
1349/******************************************************************************
1350 * Special case for 12 byte copies
1351 */
1352#define LMEMCPY_C_LOG2 7 /* 128 bytes */
1353#define LMEMCPY_C_PAD .align LMEMCPY_C_LOG2
1354 LMEMCPY_C_PAD

--- 8 unchanged lines hidden (view full) ---

1363 * 0000: dst is 32-bit aligned, src is 32-bit aligned
1364 */
1365 ldr r2, [r1]
1366 ldr r3, [r1, #0x04]
1367 ldr r1, [r1, #0x08]
1368 str r2, [r0]
1369 str r3, [r0, #0x04]
1370 str r1, [r0, #0x08]
1347 LMEMCPY_8_PAD
1348
1349/******************************************************************************
1350 * Special case for 12 byte copies
1351 */
1352#define LMEMCPY_C_LOG2 7 /* 128 bytes */
1353#define LMEMCPY_C_PAD .align LMEMCPY_C_LOG2
1354 LMEMCPY_C_PAD

--- 8 unchanged lines hidden (view full) ---

1363 * 0000: dst is 32-bit aligned, src is 32-bit aligned
1364 */
1365 ldr r2, [r1]
1366 ldr r3, [r1, #0x04]
1367 ldr r1, [r1, #0x08]
1368 str r2, [r0]
1369 str r3, [r0, #0x04]
1370 str r1, [r0, #0x08]
1371 mov pc, lr
1371 bx lr
1372 LMEMCPY_C_PAD
1373
1374/*
1375 * 0001: dst is 32-bit aligned, src is 8-bit aligned
1376 */
1377 ldrb r2, [r1, #0xb] /* r2 = ...B */
1378 ldr ip, [r1, #0x07] /* BE:ip = 789A LE:ip = A987 */
1379 ldr r3, [r1, #0x03] /* BE:r3 = 3456 LE:r3 = 6543 */

--- 11 unchanged lines hidden (view full) ---

1391 str r2, [r0, #0x08]
1392 mov r2, ip, lsl #24 /* r2 = 7... */
1393 orr r2, r2, r3, lsr #8 /* r2 = 7654 */
1394 mov r1, r1, lsr #8 /* r1 = .210 */
1395 orr r1, r1, r3, lsl #24 /* r1 = 3210 */
1396#endif
1397 str r2, [r0, #0x04]
1398 str r1, [r0]
1372 LMEMCPY_C_PAD
1373
1374/*
1375 * 0001: dst is 32-bit aligned, src is 8-bit aligned
1376 */
1377 ldrb r2, [r1, #0xb] /* r2 = ...B */
1378 ldr ip, [r1, #0x07] /* BE:ip = 789A LE:ip = A987 */
1379 ldr r3, [r1, #0x03] /* BE:r3 = 3456 LE:r3 = 6543 */

--- 11 unchanged lines hidden (view full) ---

1391 str r2, [r0, #0x08]
1392 mov r2, ip, lsl #24 /* r2 = 7... */
1393 orr r2, r2, r3, lsr #8 /* r2 = 7654 */
1394 mov r1, r1, lsr #8 /* r1 = .210 */
1395 orr r1, r1, r3, lsl #24 /* r1 = 3210 */
1396#endif
1397 str r2, [r0, #0x04]
1398 str r1, [r0]
1399 mov pc, lr
1399 bx lr
1400 LMEMCPY_C_PAD
1401
1402/*
1403 * 0010: dst is 32-bit aligned, src is 16-bit aligned
1404 */
1405 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */
1406 ldr r3, [r1, #0x02] /* BE:r3 = 2345 LE:r3 = 5432 */
1407 ldr ip, [r1, #0x06] /* BE:ip = 6789 LE:ip = 9876 */

--- 10 unchanged lines hidden (view full) ---

1418 str r2, [r0]
1419 mov r3, r3, lsr #16 /* r3 = ..54 */
1420 orr r3, r3, ip, lsl #16 /* r3 = 7654 */
1421 mov r1, r1, lsl #16 /* r1 = BA.. */
1422 orr r1, r1, ip, lsr #16 /* r1 = BA98 */
1423#endif
1424 str r3, [r0, #0x04]
1425 str r1, [r0, #0x08]
1400 LMEMCPY_C_PAD
1401
1402/*
1403 * 0010: dst is 32-bit aligned, src is 16-bit aligned
1404 */
1405 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */
1406 ldr r3, [r1, #0x02] /* BE:r3 = 2345 LE:r3 = 5432 */
1407 ldr ip, [r1, #0x06] /* BE:ip = 6789 LE:ip = 9876 */

--- 10 unchanged lines hidden (view full) ---

1418 str r2, [r0]
1419 mov r3, r3, lsr #16 /* r3 = ..54 */
1420 orr r3, r3, ip, lsl #16 /* r3 = 7654 */
1421 mov r1, r1, lsl #16 /* r1 = BA.. */
1422 orr r1, r1, ip, lsr #16 /* r1 = BA98 */
1423#endif
1424 str r3, [r0, #0x04]
1425 str r1, [r0, #0x08]
1426 mov pc, lr
1426 bx lr
1427 LMEMCPY_C_PAD
1428
1429/*
1430 * 0011: dst is 32-bit aligned, src is 8-bit aligned
1431 */
1432 ldrb r2, [r1] /* r2 = ...0 */
1433 ldr r3, [r1, #0x01] /* BE:r3 = 1234 LE:r3 = 4321 */
1434 ldr ip, [r1, #0x05] /* BE:ip = 5678 LE:ip = 8765 */

--- 11 unchanged lines hidden (view full) ---

1446 str r2, [r0]
1447 mov r3, r3, lsr #24 /* r3 = ...4 */
1448 orr r3, r3, ip, lsl #8 /* r3 = 7654 */
1449 mov r1, r1, lsl #8 /* r1 = BA9. */
1450 orr r1, r1, ip, lsr #24 /* r1 = BA98 */
1451#endif
1452 str r3, [r0, #0x04]
1453 str r1, [r0, #0x08]
1427 LMEMCPY_C_PAD
1428
1429/*
1430 * 0011: dst is 32-bit aligned, src is 8-bit aligned
1431 */
1432 ldrb r2, [r1] /* r2 = ...0 */
1433 ldr r3, [r1, #0x01] /* BE:r3 = 1234 LE:r3 = 4321 */
1434 ldr ip, [r1, #0x05] /* BE:ip = 5678 LE:ip = 8765 */

--- 11 unchanged lines hidden (view full) ---

1446 str r2, [r0]
1447 mov r3, r3, lsr #24 /* r3 = ...4 */
1448 orr r3, r3, ip, lsl #8 /* r3 = 7654 */
1449 mov r1, r1, lsl #8 /* r1 = BA9. */
1450 orr r1, r1, ip, lsr #24 /* r1 = BA98 */
1451#endif
1452 str r3, [r0, #0x04]
1453 str r1, [r0, #0x08]
1454 mov pc, lr
1454 bx lr
1455 LMEMCPY_C_PAD
1456
1457/*
1458 * 0100: dst is 8-bit aligned (byte 1), src is 32-bit aligned
1459 */
1460 ldr r2, [r1] /* BE:r2 = 0123 LE:r2 = 3210 */
1461 ldr r3, [r1, #0x04] /* BE:r3 = 4567 LE:r3 = 7654 */
1462 ldr ip, [r1, #0x08] /* BE:ip = 89AB LE:ip = BA98 */

--- 12 unchanged lines hidden (view full) ---

1475 orr r2, r1, r3, lsl #8 /* r1 = 6543 */
1476 mov r1, r3, lsr #24 /* r1 = ...7 */
1477 orr r1, r1, ip, lsl #8 /* r1 = A987 */
1478 mov ip, ip, lsr #24 /* ip = ...B */
1479#endif
1480 str r2, [r0, #0x03]
1481 str r1, [r0, #0x07]
1482 strb ip, [r0, #0x0b]
1455 LMEMCPY_C_PAD
1456
1457/*
1458 * 0100: dst is 8-bit aligned (byte 1), src is 32-bit aligned
1459 */
1460 ldr r2, [r1] /* BE:r2 = 0123 LE:r2 = 3210 */
1461 ldr r3, [r1, #0x04] /* BE:r3 = 4567 LE:r3 = 7654 */
1462 ldr ip, [r1, #0x08] /* BE:ip = 89AB LE:ip = BA98 */

--- 12 unchanged lines hidden (view full) ---

1475 orr r2, r1, r3, lsl #8 /* r1 = 6543 */
1476 mov r1, r3, lsr #24 /* r1 = ...7 */
1477 orr r1, r1, ip, lsl #8 /* r1 = A987 */
1478 mov ip, ip, lsr #24 /* ip = ...B */
1479#endif
1480 str r2, [r0, #0x03]
1481 str r1, [r0, #0x07]
1482 strb ip, [r0, #0x0b]
1483 mov pc, lr
1483 bx lr
1484 LMEMCPY_C_PAD
1485
1486/*
1487 * 0101: dst is 8-bit aligned (byte 1), src is 8-bit aligned (byte 1)
1488 */
1489 ldrb r2, [r1]
1490 ldrh r3, [r1, #0x01]
1491 ldr ip, [r1, #0x03]
1492 strb r2, [r0]
1493 ldr r2, [r1, #0x07]
1494 ldrb r1, [r1, #0x0b]
1495 strh r3, [r0, #0x01]
1496 str ip, [r0, #0x03]
1497 str r2, [r0, #0x07]
1498 strb r1, [r0, #0x0b]
1484 LMEMCPY_C_PAD
1485
1486/*
1487 * 0101: dst is 8-bit aligned (byte 1), src is 8-bit aligned (byte 1)
1488 */
1489 ldrb r2, [r1]
1490 ldrh r3, [r1, #0x01]
1491 ldr ip, [r1, #0x03]
1492 strb r2, [r0]
1493 ldr r2, [r1, #0x07]
1494 ldrb r1, [r1, #0x0b]
1495 strh r3, [r0, #0x01]
1496 str ip, [r0, #0x03]
1497 str r2, [r0, #0x07]
1498 strb r1, [r0, #0x0b]
1499 mov pc, lr
1499 bx lr
1500 LMEMCPY_C_PAD
1501
1502/*
1503 * 0110: dst is 8-bit aligned (byte 1), src is 16-bit aligned
1504 */
1505 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */
1506 ldr r3, [r1, #0x02] /* BE:r3 = 2345 LE:r3 = 5432 */
1507 ldr ip, [r1, #0x06] /* BE:ip = 6789 LE:ip = 9876 */

--- 17 unchanged lines hidden (view full) ---

1525 orr r3, r2, ip, lsl #24 /* r3 = 6543 */
1526 mov r2, ip, lsr #8 /* r2 = .987 */
1527 orr r2, r2, r1, lsl #24 /* r2 = A987 */
1528 mov r1, r1, lsr #8 /* r1 = ...B */
1529#endif
1530 str r3, [r0, #0x03]
1531 str r2, [r0, #0x07]
1532 strb r1, [r0, #0x0b]
1500 LMEMCPY_C_PAD
1501
1502/*
1503 * 0110: dst is 8-bit aligned (byte 1), src is 16-bit aligned
1504 */
1505 ldrh r2, [r1] /* BE:r2 = ..01 LE:r2 = ..10 */
1506 ldr r3, [r1, #0x02] /* BE:r3 = 2345 LE:r3 = 5432 */
1507 ldr ip, [r1, #0x06] /* BE:ip = 6789 LE:ip = 9876 */

--- 17 unchanged lines hidden (view full) ---

1525 orr r3, r2, ip, lsl #24 /* r3 = 6543 */
1526 mov r2, ip, lsr #8 /* r2 = .987 */
1527 orr r2, r2, r1, lsl #24 /* r2 = A987 */
1528 mov r1, r1, lsr #8 /* r1 = ...B */
1529#endif
1530 str r3, [r0, #0x03]
1531 str r2, [r0, #0x07]
1532 strb r1, [r0, #0x0b]
1533 mov pc, lr
1533 bx lr
1534 LMEMCPY_C_PAD
1535
1536/*
1537 * 0111: dst is 8-bit aligned (byte 1), src is 8-bit aligned (byte 3)
1538 */
1539 ldrb r2, [r1]
1540 ldr r3, [r1, #0x01] /* BE:r3 = 1234 LE:r3 = 4321 */
1541 ldr ip, [r1, #0x05] /* BE:ip = 5678 LE:ip = 8765 */

--- 13 unchanged lines hidden (view full) ---

1555 orr r3, r3, ip, lsl #16 /* r3 = 6543 */
1556 mov ip, ip, lsr #16 /* ip = ..87 */
1557 orr ip, ip, r1, lsl #16 /* ip = A987 */
1558 mov r1, r1, lsr #16 /* r1 = ..xB */
1559#endif
1560 str r3, [r0, #0x03]
1561 str ip, [r0, #0x07]
1562 strb r1, [r0, #0x0b]
1534 LMEMCPY_C_PAD
1535
1536/*
1537 * 0111: dst is 8-bit aligned (byte 1), src is 8-bit aligned (byte 3)
1538 */
1539 ldrb r2, [r1]
1540 ldr r3, [r1, #0x01] /* BE:r3 = 1234 LE:r3 = 4321 */
1541 ldr ip, [r1, #0x05] /* BE:ip = 5678 LE:ip = 8765 */

--- 13 unchanged lines hidden (view full) ---

1555 orr r3, r3, ip, lsl #16 /* r3 = 6543 */
1556 mov ip, ip, lsr #16 /* ip = ..87 */
1557 orr ip, ip, r1, lsl #16 /* ip = A987 */
1558 mov r1, r1, lsr #16 /* r1 = ..xB */
1559#endif
1560 str r3, [r0, #0x03]
1561 str ip, [r0, #0x07]
1562 strb r1, [r0, #0x0b]
1563 mov pc, lr
1563 bx lr
1564 LMEMCPY_C_PAD
1565
1566/*
1567 * 1000: dst is 16-bit aligned, src is 32-bit aligned
1568 */
1569 ldr ip, [r1] /* BE:ip = 0123 LE:ip = 3210 */
1570 ldr r3, [r1, #0x04] /* BE:r3 = 4567 LE:r3 = 7654 */
1571 ldr r2, [r1, #0x08] /* BE:r2 = 89AB LE:r2 = BA98 */

--- 9 unchanged lines hidden (view full) ---

1581 orr r1, r1, r3, lsl #16 /* r1 = 5432 */
1582 mov r3, r3, lsr #16 /* r3 = ..76 */
1583 orr r3, r3, r2, lsl #16 /* r3 = 9876 */
1584 mov r2, r2, lsr #16 /* r2 = ..BA */
1585#endif
1586 str r1, [r0, #0x02]
1587 str r3, [r0, #0x06]
1588 strh r2, [r0, #0x0a]
1564 LMEMCPY_C_PAD
1565
1566/*
1567 * 1000: dst is 16-bit aligned, src is 32-bit aligned
1568 */
1569 ldr ip, [r1] /* BE:ip = 0123 LE:ip = 3210 */
1570 ldr r3, [r1, #0x04] /* BE:r3 = 4567 LE:r3 = 7654 */
1571 ldr r2, [r1, #0x08] /* BE:r2 = 89AB LE:r2 = BA98 */

--- 9 unchanged lines hidden (view full) ---

1581 orr r1, r1, r3, lsl #16 /* r1 = 5432 */
1582 mov r3, r3, lsr #16 /* r3 = ..76 */
1583 orr r3, r3, r2, lsl #16 /* r3 = 9876 */
1584 mov r2, r2, lsr #16 /* r2 = ..BA */
1585#endif
1586 str r1, [r0, #0x02]
1587 str r3, [r0, #0x06]
1588 strh r2, [r0, #0x0a]
1589 mov pc, lr
1589 bx lr
1590 LMEMCPY_C_PAD
1591
1592/*
1593 * 1001: dst is 16-bit aligned, src is 8-bit aligned (byte 1)
1594 */
1595 ldr r2, [r1, #-1] /* BE:r2 = x012 LE:r2 = 210x */
1596 ldr r3, [r1, #0x03] /* BE:r3 = 3456 LE:r3 = 6543 */
1597 mov ip, r2, lsr #8 /* BE:ip = .x01 LE:ip = .210 */

--- 12 unchanged lines hidden (view full) ---

1610 mov r3, r3, lsr #24 /* r3 = ...6 */
1611 orr r3, r3, ip, lsl #8 /* r3 = 9876 */
1612 mov r1, r1, lsl #8 /* r1 = ..B. */
1613 orr r1, r1, ip, lsr #24 /* r1 = ..BA */
1614#endif
1615 str r2, [r0, #0x02]
1616 str r3, [r0, #0x06]
1617 strh r1, [r0, #0x0a]
1590 LMEMCPY_C_PAD
1591
1592/*
1593 * 1001: dst is 16-bit aligned, src is 8-bit aligned (byte 1)
1594 */
1595 ldr r2, [r1, #-1] /* BE:r2 = x012 LE:r2 = 210x */
1596 ldr r3, [r1, #0x03] /* BE:r3 = 3456 LE:r3 = 6543 */
1597 mov ip, r2, lsr #8 /* BE:ip = .x01 LE:ip = .210 */

--- 12 unchanged lines hidden (view full) ---

1610 mov r3, r3, lsr #24 /* r3 = ...6 */
1611 orr r3, r3, ip, lsl #8 /* r3 = 9876 */
1612 mov r1, r1, lsl #8 /* r1 = ..B. */
1613 orr r1, r1, ip, lsr #24 /* r1 = ..BA */
1614#endif
1615 str r2, [r0, #0x02]
1616 str r3, [r0, #0x06]
1617 strh r1, [r0, #0x0a]
1618 mov pc, lr
1618 bx lr
1619 LMEMCPY_C_PAD
1620
1621/*
1622 * 1010: dst is 16-bit aligned, src is 16-bit aligned
1623 */
1624 ldrh r2, [r1]
1625 ldr r3, [r1, #0x02]
1626 ldr ip, [r1, #0x06]
1627 ldrh r1, [r1, #0x0a]
1628 strh r2, [r0]
1629 str r3, [r0, #0x02]
1630 str ip, [r0, #0x06]
1631 strh r1, [r0, #0x0a]
1619 LMEMCPY_C_PAD
1620
1621/*
1622 * 1010: dst is 16-bit aligned, src is 16-bit aligned
1623 */
1624 ldrh r2, [r1]
1625 ldr r3, [r1, #0x02]
1626 ldr ip, [r1, #0x06]
1627 ldrh r1, [r1, #0x0a]
1628 strh r2, [r0]
1629 str r3, [r0, #0x02]
1630 str ip, [r0, #0x06]
1631 strh r1, [r0, #0x0a]
1632 mov pc, lr
1632 bx lr
1633 LMEMCPY_C_PAD
1634
1635/*
1636 * 1011: dst is 16-bit aligned, src is 8-bit aligned (byte 3)
1637 */
1638 ldr r2, [r1, #0x09] /* BE:r2 = 9ABx LE:r2 = xBA9 */
1639 ldr r3, [r1, #0x05] /* BE:r3 = 5678 LE:r3 = 8765 */
1640 mov ip, r2, lsr #8 /* BE:ip = .9AB LE:ip = .xBA */

--- 12 unchanged lines hidden (view full) ---

1653 orr r2, r2, r3, lsr #8 /* r2 = 9876 */
1654 mov r3, r3, lsl #24 /* r3 = 5... */
1655 orr r3, r3, ip, lsr #8 /* r3 = 5432 */
1656 orr r1, r1, ip, lsl #8 /* r1 = 3210 */
1657#endif
1658 str r2, [r0, #0x06]
1659 str r3, [r0, #0x02]
1660 strh r1, [r0]
1633 LMEMCPY_C_PAD
1634
1635/*
1636 * 1011: dst is 16-bit aligned, src is 8-bit aligned (byte 3)
1637 */
1638 ldr r2, [r1, #0x09] /* BE:r2 = 9ABx LE:r2 = xBA9 */
1639 ldr r3, [r1, #0x05] /* BE:r3 = 5678 LE:r3 = 8765 */
1640 mov ip, r2, lsr #8 /* BE:ip = .9AB LE:ip = .xBA */

--- 12 unchanged lines hidden (view full) ---

1653 orr r2, r2, r3, lsr #8 /* r2 = 9876 */
1654 mov r3, r3, lsl #24 /* r3 = 5... */
1655 orr r3, r3, ip, lsr #8 /* r3 = 5432 */
1656 orr r1, r1, ip, lsl #8 /* r1 = 3210 */
1657#endif
1658 str r2, [r0, #0x06]
1659 str r3, [r0, #0x02]
1660 strh r1, [r0]
1661 mov pc, lr
1661 bx lr
1662 LMEMCPY_C_PAD
1663
1664/*
1665 * 1100: dst is 8-bit aligned (byte 3), src is 32-bit aligned
1666 */
1667 ldr r2, [r1] /* BE:r2 = 0123 LE:r2 = 3210 */
1668 ldr ip, [r1, #0x04] /* BE:ip = 4567 LE:ip = 7654 */
1669 ldr r1, [r1, #0x08] /* BE:r1 = 89AB LE:r1 = BA98 */

--- 17 unchanged lines hidden (view full) ---

1687 mov r3, ip, lsr #8 /* r3 = .765 */
1688 orr r3, r3, r1, lsl #24 /* r3 = 8765 */
1689 str r3, [r0, #0x05]
1690 mov r1, r1, lsr #8 /* r1 = .BA9 */
1691 strh r1, [r0, #0x09]
1692 mov r1, r1, lsr #16 /* r1 = ...B */
1693 strb r1, [r0, #0x0b]
1694#endif
1662 LMEMCPY_C_PAD
1663
1664/*
1665 * 1100: dst is 8-bit aligned (byte 3), src is 32-bit aligned
1666 */
1667 ldr r2, [r1] /* BE:r2 = 0123 LE:r2 = 3210 */
1668 ldr ip, [r1, #0x04] /* BE:ip = 4567 LE:ip = 7654 */
1669 ldr r1, [r1, #0x08] /* BE:r1 = 89AB LE:r1 = BA98 */

--- 17 unchanged lines hidden (view full) ---

1687 mov r3, ip, lsr #8 /* r3 = .765 */
1688 orr r3, r3, r1, lsl #24 /* r3 = 8765 */
1689 str r3, [r0, #0x05]
1690 mov r1, r1, lsr #8 /* r1 = .BA9 */
1691 strh r1, [r0, #0x09]
1692 mov r1, r1, lsr #16 /* r1 = ...B */
1693 strb r1, [r0, #0x0b]
1694#endif
1695 mov pc, lr
1695 bx lr
1696 LMEMCPY_C_PAD
1697
1698/*
1699 * 1101: dst is 8-bit aligned (byte 3), src is 8-bit aligned (byte 1)
1700 */
1701 ldrb r2, [r1, #0x0b] /* r2 = ...B */
1702 ldr r3, [r1, #0x07] /* BE:r3 = 789A LE:r3 = A987 */
1703 ldr ip, [r1, #0x03] /* BE:ip = 3456 LE:ip = 6543 */

--- 13 unchanged lines hidden (view full) ---

1717 orr r3, r3, ip, lsr #16 /* r3 = 8765 */
1718 mov ip, ip, lsl #16 /* ip = 43.. */
1719 orr ip, ip, r1, lsr #16 /* ip = 4321 */
1720 mov r1, r1, lsr #8 /* r1 = .210 */
1721#endif
1722 str r3, [r0, #0x05]
1723 str ip, [r0, #0x01]
1724 strb r1, [r0]
1696 LMEMCPY_C_PAD
1697
1698/*
1699 * 1101: dst is 8-bit aligned (byte 3), src is 8-bit aligned (byte 1)
1700 */
1701 ldrb r2, [r1, #0x0b] /* r2 = ...B */
1702 ldr r3, [r1, #0x07] /* BE:r3 = 789A LE:r3 = A987 */
1703 ldr ip, [r1, #0x03] /* BE:ip = 3456 LE:ip = 6543 */

--- 13 unchanged lines hidden (view full) ---

1717 orr r3, r3, ip, lsr #16 /* r3 = 8765 */
1718 mov ip, ip, lsl #16 /* ip = 43.. */
1719 orr ip, ip, r1, lsr #16 /* ip = 4321 */
1720 mov r1, r1, lsr #8 /* r1 = .210 */
1721#endif
1722 str r3, [r0, #0x05]
1723 str ip, [r0, #0x01]
1724 strb r1, [r0]
1725 mov pc, lr
1725 bx lr
1726 LMEMCPY_C_PAD
1727
1728/*
1729 * 1110: dst is 8-bit aligned (byte 3), src is 16-bit aligned
1730 */
1731#ifdef __ARMEB__
1732 ldrh r2, [r1, #0x0a] /* r2 = ..AB */
1733 ldr ip, [r1, #0x06] /* ip = 6789 */

--- 24 unchanged lines hidden (view full) ---

1758 mov ip, ip, lsr #24 /* ip = ...9 */
1759 orr ip, ip, r1, lsl #8 /* ip = .BA9 */
1760 mov r1, r1, lsr #8 /* r1 = ...B */
1761 str r2, [r0, #0x01]
1762 str r3, [r0, #0x05]
1763 strh ip, [r0, #0x09]
1764 strb r1, [r0, #0x0b]
1765#endif
1726 LMEMCPY_C_PAD
1727
1728/*
1729 * 1110: dst is 8-bit aligned (byte 3), src is 16-bit aligned
1730 */
1731#ifdef __ARMEB__
1732 ldrh r2, [r1, #0x0a] /* r2 = ..AB */
1733 ldr ip, [r1, #0x06] /* ip = 6789 */

--- 24 unchanged lines hidden (view full) ---

1758 mov ip, ip, lsr #24 /* ip = ...9 */
1759 orr ip, ip, r1, lsl #8 /* ip = .BA9 */
1760 mov r1, r1, lsr #8 /* r1 = ...B */
1761 str r2, [r0, #0x01]
1762 str r3, [r0, #0x05]
1763 strh ip, [r0, #0x09]
1764 strb r1, [r0, #0x0b]
1765#endif
1766 mov pc, lr
1766 bx lr
1767 LMEMCPY_C_PAD
1768
1769/*
1770 * 1111: dst is 8-bit aligned (byte 3), src is 8-bit aligned (byte 3)
1771 */
1772 ldrb r2, [r1]
1773 ldr r3, [r1, #0x01]
1774 ldr ip, [r1, #0x05]
1775 strb r2, [r0]
1776 ldrh r2, [r1, #0x09]
1777 ldrb r1, [r1, #0x0b]
1778 str r3, [r0, #0x01]
1779 str ip, [r0, #0x05]
1780 strh r2, [r0, #0x09]
1781 strb r1, [r0, #0x0b]
1767 LMEMCPY_C_PAD
1768
1769/*
1770 * 1111: dst is 8-bit aligned (byte 3), src is 8-bit aligned (byte 3)
1771 */
1772 ldrb r2, [r1]
1773 ldr r3, [r1, #0x01]
1774 ldr ip, [r1, #0x05]
1775 strb r2, [r0]
1776 ldrh r2, [r1, #0x09]
1777 ldrb r1, [r1, #0x0b]
1778 str r3, [r0, #0x01]
1779 str ip, [r0, #0x05]
1780 strh r2, [r0, #0x09]
1781 strb r1, [r0, #0x0b]
1782 mov pc, lr
1782 bx lr
1783#endif /* !_STANDALONE */
1783#endif /* !_STANDALONE */