arc: Merge ARCv2 string routines in generic ARC .S files

In cde74b83f9b2 "ARC: remove special CFLAGS/LDFLAGS handling" we
got rid of CONFIG_ARC_CPU_HS which was used to select ARCv2-specific
implementation of optimized string routines. So now ARCv2-tuned
memset/memcpy/strcmp are not used, instead those for ARC700 used for
both ARC700 and ARCHS.

Without uClibc config option we may only tell which CPU type we're
targeting by built-in defines of GCC. I.e. no more conditional file
inclusion in Makefiles. That leaves us only one option - merge both
implementations in 1 file and use ifdefs.

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

6 files changed, 428 insertions, 440 deletions

diff --git a/libc/string/arc/arcv2/memcpy.S b/libc/string/arc/arcv2/memcpy.S
deleted file mode 100644
index ba29e8790..000000000
--- a/libc/string/arc/arcv2/memcpy.S
+++ /dev/null
@@ -1,236 +0,0 @@
-/*
- * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
- *
- * Licensed under the LGPL v2.1 or later, see the file COPYING.LIB in this tarball.
- */
-
-#include <features.h>
-#include <sysdep.h>
-
-#ifdef __LITTLE_ENDIAN__
-# define SHIFT_1(RX,RY,IMM)	asl	RX, RY, IMM	; <<
-# define SHIFT_2(RX,RY,IMM)	lsr	RX, RY, IMM	; >>
-# define MERGE_1(RX,RY,IMM)	asl	RX, RY, IMM
-# define MERGE_2(RX,RY,IMM)
-# define EXTRACT_1(RX,RY,IMM)	and	RX, RY, 0xFFFF
-# define EXTRACT_2(RX,RY,IMM)	lsr	RX, RY, IMM
-#else
-# define SHIFT_1(RX,RY,IMM)	lsr	RX, RY, IMM	; >>
-# define SHIFT_2(RX,RY,IMM)	asl	RX, RY, IMM	; <<
-# define MERGE_1(RX,RY,IMM)	asl	RX, RY, IMM	; <<
-# define MERGE_2(RX,RY,IMM)	asl	RX, RY, IMM	; <<
-# define EXTRACT_1(RX,RY,IMM)	lsr	RX, RY, IMM
-# define EXTRACT_2(RX,RY,IMM)	lsr	RX, RY, 0x08
-#endif
-
-#if defined(__LL64__) || defined(__ARC_LL64__)
-# define PREFETCH_READ(RX)	prefetch [RX, 56]
-# define PREFETCH_WRITE(RX)	prefetchw [RX, 64]
-# define LOADX(DST,RX)		ldd.ab	DST, [RX, 8]
-# define STOREX(SRC,RX)		std.ab	SRC, [RX, 8]
-# define ZOLSHFT		5
-# define ZOLAND			0x1F
-#else
-# define PREFETCH_READ(RX)	prefetch [RX, 28]
-# define PREFETCH_WRITE(RX)	prefetchw [RX, 32]
-# define LOADX(DST,RX)		ld.ab	DST, [RX, 4]
-# define STOREX(SRC,RX)		st.ab	SRC, [RX, 4]
-# define ZOLSHFT		4
-# define ZOLAND			0xF
-#endif
-
-ENTRY(memcpy)
-	prefetch  [r1]		; Prefetch the read location
-	prefetchw [r0]		; Prefetch the write location
-	mov.f	0, r2
-;;; if size is zero
-	jz.d	[blink]
-	mov	r3, r0		; don't clobber ret val
-
-;;; if size <= 8
-	cmp	r2, 8
-	bls.d	@.Lsmallchunk
-	mov.f	lp_count, r2
-
-	and.f	r4, r0, 0x03
-	rsub	lp_count, r4, 4
-	lpnz	@.Laligndestination
-	;; LOOP BEGIN
-	ldb.ab	r5, [r1,1]
-	sub	r2, r2, 1
-	stb.ab	r5, [r3,1]
-.Laligndestination:
-
-;;; Check the alignment of the source
-	and.f	r4, r1, 0x03
-	bnz.d	@.Lsourceunaligned
-
-;;; CASE 0: Both source and destination are 32bit aligned
-;;; Convert len to Dwords, unfold x4
-	lsr.f	lp_count, r2, ZOLSHFT
-	lpnz	@.Lcopy32_64bytes
-	;; LOOP START
-	LOADX (r6, r1)
-	PREFETCH_READ (r1)
-	PREFETCH_WRITE (r3)
-	LOADX (r8, r1)
-	LOADX (r10, r1)
-	LOADX (r4, r1)
-	STOREX (r6, r3)
-	STOREX (r8, r3)
-	STOREX (r10, r3)
-	STOREX (r4, r3)
-.Lcopy32_64bytes:
-
-	and.f	lp_count, r2, ZOLAND ;Last remaining 31 bytes
-.Lsmallchunk:
-	lpnz	@.Lcopyremainingbytes
-	;; LOOP START
-	ldb.ab	r5, [r1,1]
-	stb.ab	r5, [r3,1]
-.Lcopyremainingbytes:
-
-	j	[blink]
-;;; END CASE 0
-
-.Lsourceunaligned:
-	cmp	r4, 2
-	beq.d	@.LunalignedOffby2
-	sub	r2, r2, 1
-
-	bhi.d	@.LunalignedOffby3
-	ldb.ab	r5, [r1, 1]
-
-;;; CASE 1: The source is unaligned, off by 1
-	;; Hence I need to read 1 byte for a 16bit alignment
-	;; and 2bytes to reach 32bit alignment
-	ldh.ab	r6, [r1, 2]
-	sub	r2, r2, 2
-	;; Convert to words, unfold x2
-	lsr.f	lp_count, r2, 3
-	MERGE_1 (r6, r6, 8)
-	MERGE_2 (r5, r5, 24)
-	or	r5, r5, r6
-
-	;; Both src and dst are aligned
-	lpnz	@.Lcopy8bytes_1
-	;; LOOP START
-	ld.ab	r6, [r1, 4]
-	prefetch [r1, 28]	;Prefetch the next read location
-	ld.ab	r8, [r1,4]
-	prefetchw [r3, 32]	;Prefetch the next write location
-
-	SHIFT_1	(r7, r6, 24)
-	or	r7, r7, r5
-	SHIFT_2	(r5, r6, 8)
-
-	SHIFT_1	(r9, r8, 24)
-	or	r9, r9, r5
-	SHIFT_2	(r5, r8, 8)
-
-	st.ab	r7, [r3, 4]
-	st.ab	r9, [r3, 4]
-.Lcopy8bytes_1:
-
-	;; Write back the remaining 16bits
-	EXTRACT_1 (r6, r5, 16)
-	sth.ab	r6, [r3, 2]
-	;; Write back the remaining 8bits
-	EXTRACT_2 (r5, r5, 16)
-	stb.ab	r5, [r3, 1]
-
-	and.f	lp_count, r2, 0x07 ;Last 8bytes
-	lpnz	@.Lcopybytewise_1
-	;; LOOP START
-	ldb.ab	r6, [r1,1]
-	stb.ab	r6, [r3,1]
-.Lcopybytewise_1:
-	j	[blink]
-
-.LunalignedOffby2:
-;;; CASE 2: The source is unaligned, off by 2
-	ldh.ab	r5, [r1, 2]
-	sub	r2, r2, 1
-
-	;; Both src and dst are aligned
-	;; Convert to words, unfold x2
-	lsr.f	lp_count, r2, 3
-#ifdef __BIG_ENDIAN__
-	asl.nz	r5, r5, 16
-#endif
-	lpnz	@.Lcopy8bytes_2
-	;; LOOP START
-	ld.ab	r6, [r1, 4]
-	prefetch [r1, 28]	;Prefetch the next read location
-	ld.ab	r8, [r1,4]
-	prefetchw [r3, 32]	;Prefetch the next write location
-
-	SHIFT_1	(r7, r6, 16)
-	or	r7, r7, r5
-	SHIFT_2	(r5, r6, 16)
-
-	SHIFT_1	(r9, r8, 16)
-	or	r9, r9, r5
-	SHIFT_2	(r5, r8, 16)
-
-	st.ab	r7, [r3, 4]
-	st.ab	r9, [r3, 4]
-.Lcopy8bytes_2:
-
-#ifdef __BIG_ENDIAN__
-	lsr.nz	r5, r5, 16
-#endif
-	sth.ab	r5, [r3, 2]
-
-	and.f	lp_count, r2, 0x07 ;Last 8bytes
-	lpnz	@.Lcopybytewise_2
-	;; LOOP START
-	ldb.ab	r6, [r1,1]
-	stb.ab	r6, [r3,1]
-.Lcopybytewise_2:
-	j	[blink]
-
-.LunalignedOffby3:
-;;; CASE 3: The source is unaligned, off by 3
-;;; Hence, I need to read 1byte for achieve the 32bit alignment
-
-	;; Both src and dst are aligned
-	;; Convert to words, unfold x2
-	lsr.f	lp_count, r2, 3
-#ifdef __BIG_ENDIAN__
-	asl.ne	r5, r5, 24
-#endif
-	lpnz	@.Lcopy8bytes_3
-	;; LOOP START
-	ld.ab	r6, [r1, 4]
-	prefetch [r1, 28]	;Prefetch the next read location
-	ld.ab	r8, [r1,4]
-	prefetchw [r3, 32]	;Prefetch the next write location
-
-	SHIFT_1	(r7, r6, 8)
-	or	r7, r7, r5
-	SHIFT_2	(r5, r6, 24)
-
-	SHIFT_1	(r9, r8, 8)
-	or	r9, r9, r5
-	SHIFT_2	(r5, r8, 24)
-
-	st.ab	r7, [r3, 4]
-	st.ab	r9, [r3, 4]
-.Lcopy8bytes_3:
-
-#ifdef __BIG_ENDIAN__
-	lsr.nz	r5, r5, 24
-#endif
-	stb.ab	r5, [r3, 1]
-
-	and.f	lp_count, r2, 0x07 ;Last 8bytes
-	lpnz	@.Lcopybytewise_3
-	;; LOOP START
-	ldb.ab	r6, [r1,1]
-	stb.ab	r6, [r3,1]
-.Lcopybytewise_3:
-	j	[blink]
-
-END(memcpy)
-libc_hidden_def(memcpy)
diff --git a/libc/string/arc/arcv2/memset.S b/libc/string/arc/arcv2/memset.S
deleted file mode 100644
index 343cfaf81..000000000
--- a/libc/string/arc/arcv2/memset.S
+++ /dev/null
@@ -1,115 +0,0 @@
-
-/*
- * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
- *
- * Licensed under the LGPL v2.1 or later, see the file COPYING.LIB in this tarball.
- */
-
-#include <features.h>
-#include <sysdep.h>
-
-#ifdef DONT_USE_PREALLOC
-#define PREWRITE(A,B)	prefetchw [(A),(B)]
-#else
-#define PREWRITE(A,B)	prealloc [(A),(B)]
-#endif
-
-ENTRY(memset)
-	prefetchw [r0]		; Prefetch the write location
-	mov.f	0, r2
-;;; if size is zero
-	jz.d	[blink]
-	mov	r3, r0		; don't clobber ret val
-
-;;; if length < 8
-	brls.d.nt	r2, 8, .Lsmallchunk
-	mov.f	lp_count,r2
-
-	and.f	r4, r0, 0x03
-	rsub	lp_count, r4, 4
-	lpnz	@.Laligndestination
-	;; LOOP BEGIN
-	stb.ab	r1, [r3,1]
-	sub	r2, r2, 1
-.Laligndestination:
-
-;;; Destination is aligned
-	and	r1, r1, 0xFF
-	asl	r4, r1, 8
-	or	r4, r4, r1
-	asl	r5, r4, 16
-	or	r5, r5, r4
-	mov	r4, r5
-
-	sub3	lp_count, r2, 8
-	cmp     r2, 64
-	bmsk.hi	r2, r2, 5
-	mov.ls	lp_count, 0
-	add3.hi	r2, r2, 8
-
-;;; Convert len to Dwords, unfold x8
-	lsr.f	lp_count, lp_count, 6
-	lpnz	@.Lset64bytes
-	;; LOOP START
-	PREWRITE(r3, 64)	;Prefetch the next write location
-#if defined(__LL64__) || defined(__ARC_LL64__)
-	std.ab	r4, [r3, 8]
-	std.ab	r4, [r3, 8]
-	std.ab	r4, [r3, 8]
-	std.ab	r4, [r3, 8]
-	std.ab	r4, [r3, 8]
-	std.ab	r4, [r3, 8]
-	std.ab	r4, [r3, 8]
-	std.ab	r4, [r3, 8]
-#else
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-#endif
-.Lset64bytes:
-
-	lsr.f	lp_count, r2, 5 ;Last remaining  max 124 bytes
-	lpnz	.Lset32bytes
-	;; LOOP START
-	prefetchw [r3, 32]	;Prefetch the next write location
-#if defined(__LL64__) || defined(__ARC_LL64__)
-	std.ab	r4, [r3, 8]
-	std.ab	r4, [r3, 8]
-	std.ab	r4, [r3, 8]
-	std.ab	r4, [r3, 8]
-#else
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-	st.ab	r4, [r3, 4]
-#endif
-.Lset32bytes:
-
-	and.f	lp_count, r2, 0x1F ;Last remaining 31 bytes
-.Lsmallchunk:
-	lpnz	.Lcopy3bytes
-	;; LOOP START
-	stb.ab	r1, [r3, 1]
-.Lcopy3bytes:
-
-	j	[blink]
-
-END(memset)
-libc_hidden_def(memset)
diff --git a/libc/string/arc/arcv2/strcmp.S b/libc/string/arc/arcv2/strcmp.S
deleted file mode 100644
index 2e0e64a0c..000000000
--- a/libc/string/arc/arcv2/strcmp.S
+++ /dev/null
@@ -1,83 +0,0 @@
-/*
- * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com)
- *
- * Licensed under the LGPL v2.1 or later, see the file COPYING.LIB in this tarball.
- */
-
-#include <features.h>
-#include <sysdep.h>
-
-ENTRY(strcmp)
-	or	r2, r0, r1
-	bmsk_s	r2, r2, 1
-	brne	r2, 0, @.Lcharloop
-
-;;; s1 and s2 are word aligned
-	ld.ab	r2, [r0, 4]
-
-	mov_s	r12, 0x01010101
-	ror	r11, r12
-	.align  4
-.LwordLoop:
-	ld.ab	r3, [r1, 4]
-	;; Detect NULL char in str1
-	sub	r4, r2, r12
-	ld.ab	r5, [r0, 4]
-	bic	r4, r4, r2
-	and	r4, r4, r11
-	brne.d.nt	r4, 0, .LfoundNULL
-	;; Check if the read locations are the same
-	cmp	r2, r3
-	beq.d	.LwordLoop
-	mov.eq	r2, r5
-
-	;; A match is found, spot it out
-#ifdef __LITTLE_ENDIAN__
-	swape	r3, r3
-	mov_s	r0, 1
-	swape	r2, r2
-#else
-	mov_s	r0, 1
-#endif
-	cmp_s	r2, r3
-	j_s.d	[blink]
-	bset.lo	r0, r0, 31
-
-	.align 4
-.LfoundNULL:
-#ifdef __BIG_ENDIAN__
-	swape	r4, r4
-	swape	r2, r2
-	swape	r3, r3
-#endif
-	;; Find null byte
-	ffs	r0, r4
-	bmsk	r2, r2, r0
-	bmsk	r3, r3, r0
-	swape	r2, r2
-	swape	r3, r3
-	;; make the return value
-	sub.f	r0, r2, r3
-	mov.hi	r0, 1
-	j_s.d	[blink]
-	bset.lo	r0, r0, 31
-
-	.align 4
-.Lcharloop:
-	ldb.ab	r2, [r0, 1]
-	ldb.ab	r3, [r1, 1]
-	nop
-	breq	r2, 0, .Lcmpend
-	breq	r2, r3, .Lcharloop
-
-	.align 4
-.Lcmpend:
-	j_s.d	[blink]
-	sub	r0, r2, r3
-END(strcmp)
-libc_hidden_def(strcmp)
-
-#ifndef __UCLIBC_HAS_LOCALE__
-strong_alias(strcmp,strcoll)
-libc_hidden_def(strcoll)
-#endif
diff --git a/libc/string/arc/memcpy.S b/libc/string/arc/memcpy.S
index 1c11951e4..69d7220b8 100644
--- a/libc/string/arc/memcpy.S
+++ b/libc/string/arc/memcpy.S
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2013, 2014-2015, 2017 Synopsys, Inc. (www.synopsys.com)
  * Copyright (C) 2007 ARC International (UK) LTD
  *
  * Licensed under the LGPL v2.1 or later, see the file COPYING.LIB in this tarball.
@@ -7,12 +7,18 @@
 
 #include <sysdep.h>
 
+#if !defined(__ARC700__) && !defined(__ARCHS__)
+#error "Neither ARC700 nor ARCHS is defined!"
+#endif
+
+ENTRY(memcpy)
+
+#ifdef __ARC700__
 /* This memcpy implementation does not support objects of 1GB or larger -
    the check for alignment does not work then.  */
 /* We assume that most sources and destinations are aligned, and
    that also lengths are mostly a multiple of four, although to a lesser
    extent.  */
-ENTRY(memcpy)
 	or	r3,r0,r1
 	asl_s	r3,r3,30
 	mov_s	r5,r0
@@ -67,5 +73,233 @@ ENTRY(memcpy)
 .Lendbloop:
 	j_s.d	[blink]
 	stb	r12,[r5,0]
+#endif /* __ARC700__ */
+
+#ifdef __ARCHS__
+#ifdef __LITTLE_ENDIAN__
+# define SHIFT_1(RX,RY,IMM)	asl	RX, RY, IMM	; <<
+# define SHIFT_2(RX,RY,IMM)	lsr	RX, RY, IMM	; >>
+# define MERGE_1(RX,RY,IMM)	asl	RX, RY, IMM
+# define MERGE_2(RX,RY,IMM)
+# define EXTRACT_1(RX,RY,IMM)	and	RX, RY, 0xFFFF
+# define EXTRACT_2(RX,RY,IMM)	lsr	RX, RY, IMM
+#else
+# define SHIFT_1(RX,RY,IMM)	lsr	RX, RY, IMM	; >>
+# define SHIFT_2(RX,RY,IMM)	asl	RX, RY, IMM	; <<
+# define MERGE_1(RX,RY,IMM)	asl	RX, RY, IMM	; <<
+# define MERGE_2(RX,RY,IMM)	asl	RX, RY, IMM	; <<
+# define EXTRACT_1(RX,RY,IMM)	lsr	RX, RY, IMM
+# define EXTRACT_2(RX,RY,IMM)	lsr	RX, RY, 0x08
+#endif
+
+#if defined(__LL64__) || defined(__ARC_LL64__)
+# define PREFETCH_READ(RX)	prefetch [RX, 56]
+# define PREFETCH_WRITE(RX)	prefetchw [RX, 64]
+# define LOADX(DST,RX)		ldd.ab	DST, [RX, 8]
+# define STOREX(SRC,RX)		std.ab	SRC, [RX, 8]
+# define ZOLSHFT		5
+# define ZOLAND			0x1F
+#else
+# define PREFETCH_READ(RX)	prefetch [RX, 28]
+# define PREFETCH_WRITE(RX)	prefetchw [RX, 32]
+# define LOADX(DST,RX)		ld.ab	DST, [RX, 4]
+# define STOREX(SRC,RX)		st.ab	SRC, [RX, 4]
+# define ZOLSHFT		4
+# define ZOLAND			0xF
+#endif
+
+	prefetch  [r1]		; Prefetch the read location
+	prefetchw [r0]		; Prefetch the write location
+	mov.f	0, r2
+;;; if size is zero
+	jz.d	[blink]
+	mov	r3, r0		; don't clobber ret val
+
+;;; if size <= 8
+	cmp	r2, 8
+	bls.d	@.Lsmallchunk
+	mov.f	lp_count, r2
+
+	and.f	r4, r0, 0x03
+	rsub	lp_count, r4, 4
+	lpnz	@.Laligndestination
+	;; LOOP BEGIN
+	ldb.ab	r5, [r1,1]
+	sub	r2, r2, 1
+	stb.ab	r5, [r3,1]
+.Laligndestination:
+
+;;; Check the alignment of the source
+	and.f	r4, r1, 0x03
+	bnz.d	@.Lsourceunaligned
+
+;;; CASE 0: Both source and destination are 32bit aligned
+;;; Convert len to Dwords, unfold x4
+	lsr.f	lp_count, r2, ZOLSHFT
+	lpnz	@.Lcopy32_64bytes
+	;; LOOP START
+	LOADX (r6, r1)
+	PREFETCH_READ (r1)
+	PREFETCH_WRITE (r3)
+	LOADX (r8, r1)
+	LOADX (r10, r1)
+	LOADX (r4, r1)
+	STOREX (r6, r3)
+	STOREX (r8, r3)
+	STOREX (r10, r3)
+	STOREX (r4, r3)
+.Lcopy32_64bytes:
+
+	and.f	lp_count, r2, ZOLAND ;Last remaining 31 bytes
+.Lsmallchunk:
+	lpnz	@.Lcopyremainingbytes
+	;; LOOP START
+	ldb.ab	r5, [r1,1]
+	stb.ab	r5, [r3,1]
+.Lcopyremainingbytes:
+
+	j	[blink]
+;;; END CASE 0
+
+.Lsourceunaligned:
+	cmp	r4, 2
+	beq.d	@.LunalignedOffby2
+	sub	r2, r2, 1
+
+	bhi.d	@.LunalignedOffby3
+	ldb.ab	r5, [r1, 1]
+
+;;; CASE 1: The source is unaligned, off by 1
+	;; Hence I need to read 1 byte for a 16bit alignment
+	;; and 2bytes to reach 32bit alignment
+	ldh.ab	r6, [r1, 2]
+	sub	r2, r2, 2
+	;; Convert to words, unfold x2
+	lsr.f	lp_count, r2, 3
+	MERGE_1 (r6, r6, 8)
+	MERGE_2 (r5, r5, 24)
+	or	r5, r5, r6
+
+	;; Both src and dst are aligned
+	lpnz	@.Lcopy8bytes_1
+	;; LOOP START
+	ld.ab	r6, [r1, 4]
+	prefetch [r1, 28]	;Prefetch the next read location
+	ld.ab	r8, [r1,4]
+	prefetchw [r3, 32]	;Prefetch the next write location
+
+	SHIFT_1	(r7, r6, 24)
+	or	r7, r7, r5
+	SHIFT_2	(r5, r6, 8)
+
+	SHIFT_1	(r9, r8, 24)
+	or	r9, r9, r5
+	SHIFT_2	(r5, r8, 8)
+
+	st.ab	r7, [r3, 4]
+	st.ab	r9, [r3, 4]
+.Lcopy8bytes_1:
+
+	;; Write back the remaining 16bits
+	EXTRACT_1 (r6, r5, 16)
+	sth.ab	r6, [r3, 2]
+	;; Write back the remaining 8bits
+	EXTRACT_2 (r5, r5, 16)
+	stb.ab	r5, [r3, 1]
+
+	and.f	lp_count, r2, 0x07 ;Last 8bytes
+	lpnz	@.Lcopybytewise_1
+	;; LOOP START
+	ldb.ab	r6, [r1,1]
+	stb.ab	r6, [r3,1]
+.Lcopybytewise_1:
+	j	[blink]
+
+.LunalignedOffby2:
+;;; CASE 2: The source is unaligned, off by 2
+	ldh.ab	r5, [r1, 2]
+	sub	r2, r2, 1
+
+	;; Both src and dst are aligned
+	;; Convert to words, unfold x2
+	lsr.f	lp_count, r2, 3
+#ifdef __BIG_ENDIAN__
+	asl.nz	r5, r5, 16
+#endif
+	lpnz	@.Lcopy8bytes_2
+	;; LOOP START
+	ld.ab	r6, [r1, 4]
+	prefetch [r1, 28]	;Prefetch the next read location
+	ld.ab	r8, [r1,4]
+	prefetchw [r3, 32]	;Prefetch the next write location
+
+	SHIFT_1	(r7, r6, 16)
+	or	r7, r7, r5
+	SHIFT_2	(r5, r6, 16)
+
+	SHIFT_1	(r9, r8, 16)
+	or	r9, r9, r5
+	SHIFT_2	(r5, r8, 16)
+
+	st.ab	r7, [r3, 4]
+	st.ab	r9, [r3, 4]
+.Lcopy8bytes_2:
+
+#ifdef __BIG_ENDIAN__
+	lsr.nz	r5, r5, 16
+#endif
+	sth.ab	r5, [r3, 2]
+
+	and.f	lp_count, r2, 0x07 ;Last 8bytes
+	lpnz	@.Lcopybytewise_2
+	;; LOOP START
+	ldb.ab	r6, [r1,1]
+	stb.ab	r6, [r3,1]
+.Lcopybytewise_2:
+	j	[blink]
+
+.LunalignedOffby3:
+;;; CASE 3: The source is unaligned, off by 3
+;;; Hence, I need to read 1byte for achieve the 32bit alignment
+
+	;; Both src and dst are aligned
+	;; Convert to words, unfold x2
+	lsr.f	lp_count, r2, 3
+#ifdef __BIG_ENDIAN__
+	asl.ne	r5, r5, 24
+#endif
+	lpnz	@.Lcopy8bytes_3
+	;; LOOP START
+	ld.ab	r6, [r1, 4]
+	prefetch [r1, 28]	;Prefetch the next read location
+	ld.ab	r8, [r1,4]
+	prefetchw [r3, 32]	;Prefetch the next write location
+
+	SHIFT_1	(r7, r6, 8)
+	or	r7, r7, r5
+	SHIFT_2	(r5, r6, 24)
+
+	SHIFT_1	(r9, r8, 8)
+	or	r9, r9, r5
+	SHIFT_2	(r5, r8, 24)
+
+	st.ab	r7, [r3, 4]
+	st.ab	r9, [r3, 4]
+.Lcopy8bytes_3:
+
+#ifdef __BIG_ENDIAN__
+	lsr.nz	r5, r5, 24
+#endif
+	stb.ab	r5, [r3, 1]
+
+	and.f	lp_count, r2, 0x07 ;Last 8bytes
+	lpnz	@.Lcopybytewise_3
+	;; LOOP START
+	ldb.ab	r6, [r1,1]
+	stb.ab	r6, [r3,1]
+.Lcopybytewise_3:
+	j	[blink]
+#endif /* __ARCHS__ */
+
 END(memcpy)
 libc_hidden_def(memcpy)
diff --git a/libc/string/arc/memset.S b/libc/string/arc/memset.S
index f4048455a..0b74ddc7f 100644
--- a/libc/string/arc/memset.S
+++ b/libc/string/arc/memset.S
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2013, 2014-2015, 2017 Synopsys, Inc. (www.synopsys.com)
  * Copyright (C) 2007 ARC International (UK) LTD
  *
  * Licensed under the LGPL v2.1 or later, see the file COPYING.LIB in this tarball.
@@ -7,10 +7,15 @@
 
 #include <sysdep.h>
 
-#define SMALL	7 /* Must be at least 6 to deal with alignment/loop issues.  */
+#if !defined(__ARC700__) && !defined(__ARCHS__)
+#error "Neither ARC700 nor ARCHS is defined!"
+#endif
 
 ENTRY(memset)
 
+#ifdef __ARC700__
+#define SMALL	7 /* Must be at least 6 to deal with alignment/loop issues.  */
+
 	mov_s	r4,r0
 	or	r12,r0,r2
 	bmsk.f	r12,r12,1
@@ -47,5 +52,111 @@ ENTRY(memset)
 	stb.ab	r1,[r4,1]
 .Ltiny_end:
 	j_s	[blink]
+#endif /* __ARC700__ */
+
+#ifdef __ARCHS__
+#ifdef DONT_USE_PREALLOC
+#define PREWRITE(A,B)	prefetchw [(A),(B)]
+#else
+#define PREWRITE(A,B)	prealloc [(A),(B)]
+#endif
+
+	prefetchw [r0]		; Prefetch the write location
+	mov.f	0, r2
+;;; if size is zero
+	jz.d	[blink]
+	mov	r3, r0		; don't clobber ret val
+
+;;; if length < 8
+	brls.d.nt	r2, 8, .Lsmallchunk
+	mov.f	lp_count,r2
+
+	and.f	r4, r0, 0x03
+	rsub	lp_count, r4, 4
+	lpnz	@.Laligndestination
+	;; LOOP BEGIN
+	stb.ab	r1, [r3,1]
+	sub	r2, r2, 1
+.Laligndestination:
+
+;;; Destination is aligned
+	and	r1, r1, 0xFF
+	asl	r4, r1, 8
+	or	r4, r4, r1
+	asl	r5, r4, 16
+	or	r5, r5, r4
+	mov	r4, r5
+
+	sub3	lp_count, r2, 8
+	cmp     r2, 64
+	bmsk.hi	r2, r2, 5
+	mov.ls	lp_count, 0
+	add3.hi	r2, r2, 8
+
+;;; Convert len to Dwords, unfold x8
+	lsr.f	lp_count, lp_count, 6
+	lpnz	@.Lset64bytes
+	;; LOOP START
+	PREWRITE(r3, 64)	;Prefetch the next write location
+#if defined(__LL64__) || defined(__ARC_LL64__)
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+#else
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+#endif
+.Lset64bytes:
+
+	lsr.f	lp_count, r2, 5 ;Last remaining  max 124 bytes
+	lpnz	.Lset32bytes
+	;; LOOP START
+	prefetchw [r3, 32]	;Prefetch the next write location
+#if defined(__LL64__) || defined(__ARC_LL64__)
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+	std.ab	r4, [r3, 8]
+#else
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+#endif
+.Lset32bytes:
+
+	and.f	lp_count, r2, 0x1F ;Last remaining 31 bytes
+.Lsmallchunk:
+	lpnz	.Lcopy3bytes
+	;; LOOP START
+	stb.ab	r1, [r3, 1]
+.Lcopy3bytes:
+
+	j	[blink]
+#endif /* __ARCHS__ */
+
 END(memset)
 libc_hidden_def(memset)
diff --git a/libc/string/arc/strcmp.S b/libc/string/arc/strcmp.S
index 5a0e56045..ad38d9e00 100644
--- a/libc/string/arc/strcmp.S
+++ b/libc/string/arc/strcmp.S
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
+ * Copyright (C) 2013, 2014-2015, 2017 Synopsys, Inc. (www.synopsys.com)
  * Copyright (C) 2007 ARC International (UK) LTD
  *
  * Licensed under the LGPL v2.1 or later, see the file COPYING.LIB in this tarball.
@@ -8,6 +8,13 @@
 #include <features.h>
 #include <sysdep.h>
 
+#if !defined(__ARC700__) && !defined(__ARCHS__)
+#error "Neither ARC700 nor ARCHS is defined!"
+#endif
+
+ENTRY(strcmp)
+
+#ifdef __ARC700__
 /* 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
@@ -15,7 +22,6 @@
    source 1; however, that would increase the overhead for loop setup / finish,
    and strcmp might often terminate early.  */
 
-ENTRY(strcmp)
 	or	r2,r0,r1
 	bmsk_s	r2,r2,1
 	brne	r2,0,.Lcharloop
@@ -93,6 +99,77 @@ ENTRY(strcmp)
 .Lcmpend:
 	j_s.d	[blink]
 	sub	r0,r2,r3
+#endif /* __ARC700__ */
+
+#ifdef __ARCHS__
+	or	r2, r0, r1
+	bmsk_s	r2, r2, 1
+	brne	r2, 0, @.Lcharloop
+
+;;; s1 and s2 are word aligned
+	ld.ab	r2, [r0, 4]
+
+	mov_s	r12, 0x01010101
+	ror	r11, r12
+	.align  4
+.LwordLoop:
+	ld.ab	r3, [r1, 4]
+	;; Detect NULL char in str1
+	sub	r4, r2, r12
+	ld.ab	r5, [r0, 4]
+	bic	r4, r4, r2
+	and	r4, r4, r11
+	brne.d.nt	r4, 0, .LfoundNULL
+	;; Check if the read locations are the same
+	cmp	r2, r3
+	beq.d	.LwordLoop
+	mov.eq	r2, r5
+
+	;; A match is found, spot it out
+#ifdef __LITTLE_ENDIAN__
+	swape	r3, r3
+	mov_s	r0, 1
+	swape	r2, r2
+#else
+	mov_s	r0, 1
+#endif
+	cmp_s	r2, r3
+	j_s.d	[blink]
+	bset.lo	r0, r0, 31
+
+	.align 4
+.LfoundNULL:
+#ifdef __BIG_ENDIAN__
+	swape	r4, r4
+	swape	r2, r2
+	swape	r3, r3
+#endif
+	;; Find null byte
+	ffs	r0, r4
+	bmsk	r2, r2, r0
+	bmsk	r3, r3, r0
+	swape	r2, r2
+	swape	r3, r3
+	;; make the return value
+	sub.f	r0, r2, r3
+	mov.hi	r0, 1
+	j_s.d	[blink]
+	bset.lo	r0, r0, 31
+
+	.align 4
+.Lcharloop:
+	ldb.ab	r2, [r0, 1]
+	ldb.ab	r3, [r1, 1]
+	nop
+	breq	r2, 0, .Lcmpend
+	breq	r2, r3, .Lcharloop
+
+	.align 4
+.Lcmpend:
+	j_s.d	[blink]
+	sub	r0, r2, r3
+#endif /* __ARCHS__ */
+
 END(strcmp)
 libc_hidden_def(strcmp)