arc: Get rid of handwritten string routines

U-Boot is a bit special piese of software because it is being
only executed once on power-on as compared to operating system
for example. That's why we don't care much about performance
optimizations instead we're more concerned about size. And up-to-date
compilers might produce much smaller code compared to
performance-optimized routines copy-pasted from the Linux kernel.

Here's an example:
------------------------------->8--------------------------
--- size_asm_strings.txt
+++ size_c_strings.txt
@@ -1,2 +1,2 @@
    text	   data	    bss	    dec	    hex	filename
- 121260	   3784	   3308	 128352	  1f560	u-boot
+ 120448	   3784	   3308	 127540	  1f234	u-boot
------------------------------->8--------------------------

See we were able to shave off ~800 bytes of .text section.

Also usage of string routines implemented in C gives us an ability
to support more HW flavors for free: generated instructions will match
our target as long as correct compiler option is used.

Signed-off-by: Alexey Brodkin <abrodkin@synopsys.com>

arch/arc/include/asm/string.h

@@ -1,27 +1 @@
-/*
- * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. All rights reserved.
- *
- * SPDX-License-Identifier:	GPL-2.0+
- */
 
-#ifndef __ASM_ARC_STRING_H
-#define __ASM_ARC_STRING_H
-
-#define __HAVE_ARCH_MEMSET
-#define __HAVE_ARCH_MEMCPY
-#define __HAVE_ARCH_MEMCMP
-#define __HAVE_ARCH_STRCHR
-#define __HAVE_ARCH_STRCPY
-#define __HAVE_ARCH_STRCMP
-#define __HAVE_ARCH_STRLEN
-
-extern void *memset(void *ptr, int, __kernel_size_t);
-extern void *memcpy(void *, const void *, __kernel_size_t);
-extern void memzero(void *ptr, __kernel_size_t n);
-extern int memcmp(const void *, const void *, __kernel_size_t);
-extern char *strchr(const char *s, int c);
-extern char *strcpy(char *dest, const char *src);
-extern int strcmp(const char *cs, const char *ct);
-extern __kernel_size_t strlen(const char *);
-
-#endif /* __ASM_ARC_STRING_H */

arch/arc/lib/Makefile

@@ -10,13 +10,6 @@ obj-y += cache.o
 obj-y += cpu.o
 obj-y += interrupts.o
 obj-y += relocate.o
-obj-y += strchr-700.o
-obj-y += strcmp.o
-obj-y += strcpy-700.o
-obj-y += strlen.o
-obj-y += memcmp.o
-obj-y += memcpy-700.o
-obj-y += memset.o
 obj-y += reset.o
 obj-y += ints_low.o
 obj-y += init_helpers.o

arch/arc/lib/memcmp.S

@@ -1,123 +0,0 @@
-/*
- * Copyright (C) 2004, 2007-2010, 2011-2014 Synopsys, Inc. All rights reserved.
- *
- * SPDX-License-Identifier:	GPL-2.0+
- */
-
-#ifdef __LITTLE_ENDIAN__
-#define WORD2 r2
-#define SHIFT r3
-#else /* __BIG_ENDIAN__ */
-#define WORD2 r3
-#define SHIFT r2
-#endif /* _ENDIAN__ */
-
-.global memcmp
-.align 4
-memcmp:
-	or	%r12, %r0, %r1
-	asl_s	%r12, %r12, 30
-	sub	%r3, %r2, 1
-	brls	%r2, %r12, .Lbytewise
-	ld	%r4, [%r0, 0]
-	ld	%r5, [%r1, 0]
-	lsr.f	%lp_count, %r3, 3
-	lpne	.Loop_end
-	ld_s	WORD2, [%r0, 4]
-	ld_s	%r12, [%r1, 4]
-	brne	%r4, %r5, .Leven
-	ld.a	%r4, [%r0, 8]
-	ld.a	%r5, [%r1, 8]
-	brne	WORD2, %r12, .Lodd
-	nop
-.Loop_end:
-	asl_s	SHIFT, SHIFT, 3
-	bhs_s	.Last_cmp
-	brne	%r4, %r5, .Leven
-	ld	%r4, [%r0, 4]
-	ld	%r5, [%r1, 4]
-#ifdef __LITTLE_ENDIAN__
-	nop_s
-	/* one more load latency cycle */
-.Last_cmp:
-	xor	%r0, %r4, %r5
-	bset	%r0, %r0, SHIFT
-	sub_s	%r1, %r0, 1
-	bic_s	%r1, %r1, %r0
-	norm	%r1, %r1
-	b.d	.Leven_cmp
-	and	%r1, %r1, 24
-.Leven:
-	xor	%r0, %r4, %r5
-	sub_s	%r1, %r0, 1
-	bic_s	%r1, %r1, %r0
-	norm	%r1, %r1
-	/* slow track insn */
-	and	%r1, %r1, 24
-.Leven_cmp:
-	asl	%r2, %r4, %r1
-	asl	%r12, %r5, %r1
-	lsr_s	%r2, %r2, 1
-	lsr_s	%r12, %r12, 1
-	j_s.d	[%blink]
-	sub	%r0, %r2, %r12
-	.balign	4
-.Lodd:
-	xor	%r0, WORD2, %r12
-	sub_s	%r1, %r0, 1
-	bic_s	%r1, %r1, %r0
-	norm	%r1, %r1
-	/* slow track insn */
-	and	%r1, %r1, 24
-	asl_s	%r2, %r2, %r1
-	asl_s	%r12, %r12, %r1
-	lsr_s	%r2, %r2, 1
-	lsr_s	%r12, %r12, 1
-	j_s.d	[%blink]
-	sub	%r0, %r2, %r12
-#else /* __BIG_ENDIAN__ */
-.Last_cmp:
-	neg_s	SHIFT, SHIFT
-	lsr	%r4, %r4, SHIFT
-	lsr	%r5, %r5, SHIFT
-	/* slow track insn */
-.Leven:
-	sub.f	%r0, %r4, %r5
-	mov.ne	%r0, 1
-	j_s.d	[%blink]
-	bset.cs	%r0, %r0, 31
-.Lodd:
-	cmp_s	WORD2, %r12
-
-	mov_s	%r0, 1
-	j_s.d	[%blink]
-	bset.cs	%r0, %r0, 31
-#endif /* _ENDIAN__ */
-	.balign	4
-.Lbytewise:
-	breq	%r2, 0, .Lnil
-	ldb	%r4, [%r0, 0]
-	ldb	%r5, [%r1, 0]
-	lsr.f	%lp_count, %r3
-	lpne	.Lbyte_end
-	ldb_s	%r3, [%r0, 1]
-	ldb	%r12, [%r1, 1]
-	brne	%r4, %r5, .Lbyte_even
-	ldb.a	%r4, [%r0, 2]
-	ldb.a	%r5, [%r1, 2]
-	brne	%r3, %r12, .Lbyte_odd
-	nop
-.Lbyte_end:
-	bcc	.Lbyte_even
-	brne	%r4, %r5, .Lbyte_even
-	ldb_s	%r3, [%r0, 1]
-	ldb_s	%r12, [%r1, 1]
-.Lbyte_odd:
-	j_s.d	[%blink]
-	sub	%r0, %r3, %r12
-.Lbyte_even:
-	j_s.d	[%blink]
-	sub	%r0, %r4, %r5
-.Lnil:
-	j_s.d	[%blink]
-	mov	%r0, 0

arch/arc/lib/memcpy-700.S

@@ -1,63 +0,0 @@
-/*
- * Copyright (C) 2004, 2007-2010, 2011-2014 Synopsys, Inc. All rights reserved.
- *
- * SPDX-License-Identifier:	GPL-2.0+
- */
-
-.global memcpy
-.align 4
-memcpy:
-	or	%r3, %r0, %r1
-	asl_s	%r3, %r3, 30
-	mov_s	%r5, %r0
-	brls.d	%r2, %r3, .Lcopy_bytewise
-	sub.f	%r3, %r2, 1
-	ld_s	%r12, [%r1, 0]
-	asr.f	%lp_count, %r3, 3
-	bbit0.d	%r3, 2, .Lnox4
-	bmsk_s	%r2, %r2, 1
-	st.ab	%r12, [%r5, 4]
-	ld.a	%r12, [%r1, 4]
-.Lnox4:
-	lppnz	.Lendloop
-	ld_s	%r3, [%r1, 4]
-	st.ab	%r12, [%r5, 4]
-	ld.a	%r12, [%r1, 8]
-	st.ab	%r3, [%r5, 4]
-.Lendloop:
-	breq	%r2, 0, .Last_store
-	ld	%r3, [%r5, 0]
-#ifdef __LITTLE_ENDIAN__
-	add3	%r2, -1, %r2
-	/* uses long immediate */
-	xor_s	%r12, %r12, %r3
-	bmsk	%r12, %r12, %r2
-	xor_s	%r12, %r12, %r3
-#else /* __BIG_ENDIAN__ */
-	sub3	%r2, 31, %r2
-	/* uses long immediate */
-	xor_s	%r3, %r3, %r12
-	bmsk	%r3, %r3, %r2
-	xor_s	%r12, %r12, %r3
-#endif /* _ENDIAN__ */
-.Last_store:
-	j_s.d	[%blink]
-	st	%r12, [%r5, 0]
-
-	.balign	4
-.Lcopy_bytewise:
-	jcs	[%blink]
-	ldb_s	%r12, [%r1, 0]
-	lsr.f	%lp_count, %r3
-	bhs_s	.Lnox1
-	stb.ab	%r12, [%r5, 1]
-	ldb.a	%r12, [%r1, 1]
-.Lnox1:
-	lppnz	.Lendbloop
-	ldb_s	%r3, [%r1, 1]
-	stb.ab	%r12, [%r5, 1]
-	ldb.a	%r12, [%r1, 2]
-	stb.ab	%r3, [%r5, 1]
-.Lendbloop:
-	j_s.d	[%blink]
-	stb	%r12, [%r5, 0]

arch/arc/lib/memset.S

@@ -1,62 +0,0 @@
-/*
- * Copyright (C) 2004, 2007-2010, 2011-2014 Synopsys, Inc. All rights reserved.
- *
- * SPDX-License-Identifier:	GPL-2.0+
- */
-
-#define SMALL	7 /* Must be at least 6 to deal with alignment/loop issues.  */
-
-.global memset
-.align 4
-memset:
-	mov_s	%r4, %r0
-	or	%r12, %r0, %r2
-	bmsk.f	%r12, %r12, 1
-	extb_s	%r1, %r1
-	asl	%r3, %r1, 8
-	beq.d	.Laligned
-	or_s	%r1, %r1, %r3
-	brls	%r2, SMALL, .Ltiny
-	add	%r3, %r2, %r0
-	stb	%r1, [%r3, -1]
-	bclr_s	%r3, %r3, 0
-	stw	%r1, [%r3, -2]
-	bmsk.f	%r12, %r0, 1
-	add_s	%r2, %r2, %r12
-	sub.ne	%r2, %r2, 4
-	stb.ab	%r1, [%r4, 1]
-	and	%r4, %r4, -2
-	stw.ab	%r1, [%r4, 2]
-	and	%r4, %r4, -4
-
-	.balign	4
-.Laligned:
-	asl	%r3, %r1, 16
-	lsr.f	%lp_count, %r2, 2
-	or_s	%r1, %r1, %r3
-	lpne	.Loop_end
-	st.ab	%r1, [%r4, 4]
-.Loop_end:
-	j_s	[%blink]
-
-	.balign	4
-.Ltiny:
-	mov.f	%lp_count, %r2
-	lpne	.Ltiny_end
-	stb.ab	%r1, [%r4, 1]
-.Ltiny_end:
-	j_s	[%blink]
-
-/*
- * memzero: @r0 = mem, @r1 = size_t
- * memset:  @r0 = mem, @r1 = char, @r2 = size_t
- */
-
-.global memzero
-.align 4
-memzero:
-	/* adjust bzero args to memset args */
-	mov	%r2, %r1
-	mov	%r1, 0
-	/* tail call so need to tinker with blink */
-	b	memset

arch/arc/lib/strchr-700.S

@@ -1,141 +0,0 @@
-/*
- * Copyright (C) 2004, 2007-2010, 2011-2014 Synopsys, Inc. All rights reserved.
- *
- * SPDX-License-Identifier:	GPL-2.0+
- */
-
-/*
- * ARC700 has a relatively long pipeline and branch prediction, so we want
- * to avoid branches that are hard to predict.  On the other hand, the
- * presence of the norm instruction makes it easier to operate on whole
- * words branch-free.
- */
-
-.global strchr
-.align 4
-strchr:
-	extb_s	%r1, %r1
-	asl	%r5, %r1, 8
-	bmsk	%r2, %r0, 1
-	or	%r5, %r5, %r1
-	mov_s	%r3, 0x01010101
-	breq.d	%r2, %r0, .Laligned
-	asl	%r4, %r5, 16
-	sub_s	%r0, %r0, %r2
-	asl	%r7, %r2, 3
-	ld_s	%r2, [%r0]
-#ifdef __LITTLE_ENDIAN__
-	asl	%r7, %r3, %r7
-#else /* __BIG_ENDIAN__ */
-	lsr	%r7, %r3, %r7
-#endif /* _ENDIAN__ */
-	or	%r5, %r5, %r4
-	ror	%r4, %r3
-	sub	%r12, %r2, %r7
-	bic_s	%r12, %r12, %r2
-	and	%r12, %r12, %r4
-	brne.d	%r12, 0, .Lfound0_ua
-	xor	%r6, %r2, %r5
-	ld.a	%r2, [%r0, 4]
-	sub	%r12, %r6, %r7
-	bic	%r12, %r12, %r6
-#ifdef __LITTLE_ENDIAN__
-	and	%r7, %r12, %r4
-	/* For speed, we want this branch to be unaligned. */
-	breq	%r7, 0, .Loop
-	/* Likewise this one */
-	b	.Lfound_char
-#else /* __BIG_ENDIAN__ */
-	and	%r12, %r12, %r4
-	/* For speed, we want this branch to be unaligned. */
-	breq	%r12, 0, .Loop
-	lsr_s	%r12, %r12, 7
-	bic 	%r2, %r7, %r6
-	b.d	.Lfound_char_b
-	and_s	%r2, %r2, %r12
-#endif /* _ENDIAN__ */
-	/* We require this code address to be unaligned for speed...  */
-.Laligned:
-	ld_s	%r2, [%r0]
-	or	%r5, %r5, %r4
-	ror	%r4, %r3
-	/* ... so that this code address is aligned, for itself and ...  */
-.Loop:
-	sub	%r12, %r2, %r3
-	bic_s	%r12, %r12, %r2
-	and	%r12, %r12, %r4
-	brne.d	%r12, 0, .Lfound0
-	xor	%r6, %r2, %r5
-	ld.a	%r2, [%r0, 4]
-	sub	%r12, %r6, %r3
-	bic	%r12, %r12, %r6
-	and	%r7, %r12, %r4
-	breq	%r7, 0, .Loop
-	/*
-	 *... so that this branch is unaligned.
-	 * Found searched-for character.
-	 * r0 has already advanced to next word.
-	 */
-#ifdef __LITTLE_ENDIAN__
-	/*
-	 * We only need the information about the first matching byte
-	 * (i.e. the least significant matching byte) to be exact,
-	 * hence there is no problem with carry effects.
-	 */
-.Lfound_char:
-	sub	%r3, %r7, 1
-	bic	%r3, %r3, %r7
-	norm	%r2, %r3
-	sub_s	%r0, %r0, 1
-	asr_s	%r2, %r2, 3
-	j.d	[%blink]
-	sub_s	%r0, %r0, %r2
-
-	.balign	4
-.Lfound0_ua:
-	mov	%r3, %r7
-.Lfound0:
-	sub	%r3, %r6, %r3
-	bic	%r3, %r3, %r6
-	and	%r2, %r3, %r4
-	or_s	%r12, %r12, %r2
-	sub_s	%r3, %r12, 1
-	bic_s	%r3, %r3, %r12
-	norm	%r3, %r3
-	add_s	%r0, %r0, 3
-	asr_s	%r12, %r3, 3
-	asl.f	0, %r2, %r3
-	sub_s	%r0, %r0, %r12
-	j_s.d	[%blink]
-	mov.pl	%r0, 0
-#else /* __BIG_ENDIAN__ */
-.Lfound_char:
-	lsr	%r7, %r7, 7
-
-	bic	%r2, %r7, %r6
-.Lfound_char_b:
-	norm	%r2, %r2
-	sub_s	%r0, %r0, 4
-	asr_s	%r2, %r2, 3
-	j.d	[%blink]
-	add_s	%r0, %r0, %r2
-
-.Lfound0_ua:
-	mov_s	%r3, %r7
-.Lfound0:
-	asl_s	%r2, %r2, 7
-	or	%r7, %r6, %r4
-	bic_s	%r12, %r12, %r2
-	sub	%r2, %r7, %r3
-	or	%r2, %r2, %r6
-	bic	%r12, %r2, %r12
-	bic.f	%r3, %r4, %r12
-	norm	%r3, %r3
-
-	add.pl	%r3, %r3, 1
-	asr_s	%r12, %r3, 3
-	asl.f	0, %r2, %r3
-	add_s	%r0, %r0, %r12
-	j_s.d	[%blink]
-	mov.mi	%r0, 0
-#endif /* _ENDIAN__ */

arch/arc/lib/strcmp.S

@@ -1,97 +0,0 @@
-/*
- * Copyright (C) 2004, 2007-2010, 2011-2014 Synopsys, Inc. All rights reserved.
- *
- * SPDX-License-Identifier:	GPL-2.0+
- */
-
-/*
- * This is optimized primarily for the ARC700.
- * It would be possible to speed up the loops by one cycle / word
- * respective one cycle / byte by forcing double source 1 alignment, unrolling
- * by a factor of two, and speculatively loading the second word / byte of
- * source 1; however, that would increase the overhead for loop setup / finish,
- * and strcmp might often terminate early.
- */
-
-.global strcmp
-.align 4
-strcmp:
-	or	%r2, %r0, %r1
-	bmsk_s	%r2, %r2, 1
-	brne	%r2, 0, .Lcharloop
-	mov_s	%r12, 0x01010101
-	ror	%r5, %r12
-.Lwordloop:
-	ld.ab	%r2, [%r0, 4]
-	ld.ab	%r3, [%r1, 4]
-	nop_s
-	sub	%r4, %r2, %r12
-	bic	%r4, %r4, %r2
-	and	%r4, %r4, %r5
-	brne	%r4, 0, .Lfound0
-	breq	%r2 ,%r3, .Lwordloop
-#ifdef	__LITTLE_ENDIAN__
-	xor	%r0, %r2, %r3	/* mask for difference */
-	sub_s	%r1, %r0, 1
-	bic_s	%r0, %r0, %r1	/* mask for least significant difference bit */
-	sub	%r1, %r5, %r0
-	xor	%r0, %r5, %r1	/* mask for least significant difference byte */
-	and_s	%r2, %r2, %r0
-	and_s	%r3, %r3, %r0
-#endif /* _ENDIAN__ */
-	cmp_s	%r2, %r3
-	mov_s	%r0, 1
-	j_s.d	[%blink]
-	bset.lo	%r0, %r0, 31
-
-	.balign	4
-#ifdef __LITTLE_ENDIAN__
-.Lfound0:
-	xor	%r0, %r2, %r3	/* mask for difference */
-	or	%r0, %r0, %r4	/* or in zero indicator */
-	sub_s	%r1, %r0, 1
-	bic_s	%r0, %r0, %r1	/* mask for least significant difference bit */
-	sub	%r1, %r5, %r0
-	xor	%r0, %r5, %r1	/* mask for least significant difference byte */
-	and_s	%r2, %r2, %r0
-	and_s	%r3, %r3, %r0
-	sub.f	%r0, %r2, %r3
-	mov.hi	%r0, 1
-	j_s.d	[%blink]
-	bset.lo	%r0, %r0, 31
-#else /* __BIG_ENDIAN__ */
-	/*
-	 * The zero-detection above can mis-detect 0x01 bytes as zeroes
-	 * because of carry-propagateion from a lower significant zero byte.
-	 * We can compensate for this by checking that bit0 is zero.
-	 * This compensation is not necessary in the step where we
-	 * get a low estimate for r2, because in any affected bytes
-	 * we already have 0x00 or 0x01, which will remain unchanged
-	 * when bit 7 is cleared.
-	 */
-	.balign	4
-.Lfound0:
-	lsr	%r0, %r4, 8
-	lsr_s	%r1, %r2
-	bic_s	%r2, %r2, %r0	/* get low estimate for r2 and get ... */
-	bic_s	%r0, %r0, %r1	/* <this is the adjusted mask for zeros> */
-	or_s	%r3, %r3, %r0	/* ... high estimate r3 so that r2 > r3 will */
-	cmp_s	%r3, %r2	/* ... be independent of trailing garbage */
-	or_s	%r2, %r2, %r0	/* likewise for r3 > r2 */
-	bic_s	%r3, %r3, %r0
-	rlc	%r0, 0		/* r0 := r2 > r3 ? 1 : 0 */
-	cmp_s	%r2, %r3
-	j_s.d	[%blink]
-	bset.lo	%r0, %r0, 31
-#endif /* _ENDIAN__ */
-
-	.balign	4
-.Lcharloop:
-	ldb.ab	%r2,[%r0,1]
-	ldb.ab	%r3,[%r1,1]
-	nop_s
-	breq	%r2, 0, .Lcmpend
-	breq	%r2, %r3, .Lcharloop
-.Lcmpend:
-	j_s.d	[%blink]
-	sub	%r0, %r2, %r3

arch/arc/lib/strcpy-700.S

@@ -1,67 +0,0 @@
-/*
- * Copyright (C) 2004, 2007-2010, 2011-2014 Synopsys, Inc. All rights reserved.
- *
- * SPDX-License-Identifier:	GPL-2.0+
- */
-
-/*
- * If dst and src are 4 byte aligned, copy 8 bytes at a time.
- * If the src is 4, but not 8 byte aligned, we first read 4 bytes to get
- * it 8 byte aligned.  Thus, we can do a little read-ahead, without
- * dereferencing a cache line that we should not touch.
- * Note that short and long instructions have been scheduled to avoid
- * branch stalls.
- * The beq_s to r3z could be made unaligned & long to avoid a stall
- * there, but it is not likely to be taken often, and it would also be likely
- * to cost an unaligned mispredict at the next call.
- */
-
-.global strcpy
-.align 4
-strcpy:
-	or	%r2, %r0, %r1
-	bmsk_s	%r2, %r2, 1
-	brne.d	%r2, 0, charloop
-	mov_s	%r10, %r0
-	ld_s	%r3, [%r1, 0]
-	mov	%r8, 0x01010101
-	bbit0.d	%r1, 2, loop_start
-	ror	%r12, %r8
-	sub	%r2, %r3, %r8
-	bic_s	%r2, %r2, %r3
-	tst_s	%r2,%r12
-	bne	r3z
-	mov_s	%r4,%r3
-	.balign 4
-loop:
-	ld.a	%r3, [%r1, 4]
-	st.ab	%r4, [%r10, 4]
-loop_start:
-	ld.a	%r4, [%r1, 4]
-	sub	%r2, %r3, %r8
-	bic_s	%r2, %r2, %r3
-	tst_s	%r2, %r12
-	bne_s	r3z
-	st.ab	%r3, [%r10, 4]
-	sub	%r2, %r4, %r8
-	bic	%r2, %r2, %r4
-	tst	%r2, %r12
-	beq	loop
-	mov_s	%r3, %r4
-#ifdef __LITTLE_ENDIAN__
-r3z:	bmsk.f	%r1, %r3, 7
-	lsr_s	%r3, %r3, 8
-#else /* __BIG_ENDIAN__ */
-r3z:	lsr.f	%r1, %r3, 24
-	asl_s	%r3, %r3, 8
-#endif /* _ENDIAN__ */
-	bne.d	r3z
-	stb.ab	%r1, [%r10, 1]
-	j_s	[%blink]
-
-	.balign	4
-charloop:
-	ldb.ab	%r3, [%r1, 1]
-	brne.d	%r3, 0, charloop
-	stb.ab	%r3, [%r10, 1]
-	j	[%blink]

arch/arc/lib/strlen.S

@@ -1,80 +0,0 @@
-/*
- * Copyright (C) 2004, 2007-2010, 2011-2014 Synopsys, Inc. All rights reserved.
- *
- * SPDX-License-Identifier:	GPL-2.0+
- */
-
-.global strlen
-.align 4
-strlen:
-	or	%r3, %r0, 7
-	ld	%r2, [%r3, -7]
-	ld.a	%r6, [%r3, -3]
-	mov	%r4, 0x01010101
-	/* uses long immediate */
-#ifdef __LITTLE_ENDIAN__
-	asl_s	%r1, %r0, 3
-	btst_s	%r0, 2
-	asl	%r7, %r4, %r1
-	ror	%r5, %r4
-	sub	%r1, %r2, %r7
-	bic_s	%r1, %r1, %r2
-	mov.eq	%r7, %r4
-	sub	%r12, %r6, %r7
-	bic	%r12, %r12, %r6
-	or.eq	%r12, %r12, %r1
-	and	%r12, %r12, %r5
-	brne	%r12, 0, .Learly_end
-#else /* __BIG_ENDIAN__ */
-	ror	%r5, %r4
-	btst_s	%r0, 2
-	mov_s	%r1, 31
-	sub3	%r7, %r1, %r0
-	sub	%r1, %r2, %r4
-	bic_s	%r1, %r1, %r2
-	bmsk	%r1, %r1, %r7
-	sub	%r12, %r6, %r4
-	bic	%r12, %r12, %r6
-	bmsk.ne	%r12, %r12, %r7
-	or.eq	%r12, %r12, %r1
-	and	%r12, %r12, %r5
-	brne	%r12, 0, .Learly_end
-#endif /* _ENDIAN__ */
-
-.Loop:
-	ld_s	%r2, [%r3, 4]
-	ld.a	%r6, [%r3, 8]
-	/* stall for load result */
-	sub	%r1, %r2, %r4
-	bic_s	%r1, %r1, %r2
-	sub	%r12, %r6, %r4
-	bic	%r12, %r12, %r6
-	or	%r12, %r12, %r1
-	and	%r12, %r12, %r5
-	breq	%r12, 0, .Loop
-.Lend:
-	and.f	%r1, %r1, %r5
-	sub.ne	%r3, %r3, 4
-	mov.eq	%r1, %r12
-#ifdef __LITTLE_ENDIAN__
-	sub_s	%r2, %r1, 1
-	bic_s	%r2, %r2, %r1
-	norm	%r1, %r2
-	sub_s	%r0, %r0, 3
-	lsr_s	%r1, %r1, 3
-	sub	%r0, %r3, %r0
-	j_s.d	[%blink]
-	sub	%r0, %r0, %r1
-#else /* __BIG_ENDIAN__ */
-	lsr_s	%r1, %r1, 7
-	mov.eq	%r2, %r6
-	bic_s	%r1, %r1, %r2
-	norm	%r1, %r1
-	sub	%r0, %r3, %r0
-	lsr_s	%r1, %r1, 3
-	j_s.d	[%blink]
-	add	%r0, %r0, %r1
-#endif /* _ENDIAN */
-.Learly_end:
-	b.d	.Lend
-	sub_s.ne %r1, %r1, %r1