linux-sg2042/arch/sparc/lib/U1memcpy.S

564 lines
14 KiB
ArmAsm

/* U1memcpy.S: UltraSPARC-I/II/IIi/IIe optimized memcpy.
*
* Copyright (C) 1997, 2004 David S. Miller (davem@redhat.com)
* Copyright (C) 1996, 1997, 1998, 1999 Jakub Jelinek (jj@ultra.linux.cz)
*/
#ifdef __KERNEL__
#include <asm/visasm.h>
#include <asm/asi.h>
#define GLOBAL_SPARE g7
#else
#define GLOBAL_SPARE g5
#define ASI_BLK_P 0xf0
#define FPRS_FEF 0x04
#ifdef MEMCPY_DEBUG
#define VISEntry rd %fprs, %o5; wr %g0, FPRS_FEF, %fprs; \
clr %g1; clr %g2; clr %g3; subcc %g0, %g0, %g0;
#define VISExit and %o5, FPRS_FEF, %o5; wr %o5, 0x0, %fprs
#else
#define VISEntry rd %fprs, %o5; wr %g0, FPRS_FEF, %fprs
#define VISExit and %o5, FPRS_FEF, %o5; wr %o5, 0x0, %fprs
#endif
#endif
#ifndef EX_LD
#define EX_LD(x) x
#endif
#ifndef EX_ST
#define EX_ST(x) x
#endif
#ifndef EX_RETVAL
#define EX_RETVAL(x) x
#endif
#ifndef LOAD
#define LOAD(type,addr,dest) type [addr], dest
#endif
#ifndef LOAD_BLK
#define LOAD_BLK(addr,dest) ldda [addr] ASI_BLK_P, dest
#endif
#ifndef STORE
#define STORE(type,src,addr) type src, [addr]
#endif
#ifndef STORE_BLK
#define STORE_BLK(src,addr) stda src, [addr] ASI_BLK_P
#endif
#ifndef FUNC_NAME
#define FUNC_NAME memcpy
#endif
#ifndef PREAMBLE
#define PREAMBLE
#endif
#ifndef XCC
#define XCC xcc
#endif
#define FREG_FROB(f1, f2, f3, f4, f5, f6, f7, f8, f9) \
faligndata %f1, %f2, %f48; \
faligndata %f2, %f3, %f50; \
faligndata %f3, %f4, %f52; \
faligndata %f4, %f5, %f54; \
faligndata %f5, %f6, %f56; \
faligndata %f6, %f7, %f58; \
faligndata %f7, %f8, %f60; \
faligndata %f8, %f9, %f62;
#define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, len, jmptgt) \
EX_LD(LOAD_BLK(%src, %fdest)); \
EX_ST(STORE_BLK(%fsrc, %dest)); \
add %src, 0x40, %src; \
subcc %len, 0x40, %len; \
be,pn %xcc, jmptgt; \
add %dest, 0x40, %dest; \
#define LOOP_CHUNK1(src, dest, len, branch_dest) \
MAIN_LOOP_CHUNK(src, dest, f0, f48, len, branch_dest)
#define LOOP_CHUNK2(src, dest, len, branch_dest) \
MAIN_LOOP_CHUNK(src, dest, f16, f48, len, branch_dest)
#define LOOP_CHUNK3(src, dest, len, branch_dest) \
MAIN_LOOP_CHUNK(src, dest, f32, f48, len, branch_dest)
#define DO_SYNC membar #Sync;
#define STORE_SYNC(dest, fsrc) \
EX_ST(STORE_BLK(%fsrc, %dest)); \
add %dest, 0x40, %dest; \
DO_SYNC
#define STORE_JUMP(dest, fsrc, target) \
EX_ST(STORE_BLK(%fsrc, %dest)); \
add %dest, 0x40, %dest; \
ba,pt %xcc, target; \
nop;
#define FINISH_VISCHUNK(dest, f0, f1, left) \
subcc %left, 8, %left;\
bl,pn %xcc, 95f; \
faligndata %f0, %f1, %f48; \
EX_ST(STORE(std, %f48, %dest)); \
add %dest, 8, %dest;
#define UNEVEN_VISCHUNK_LAST(dest, f0, f1, left) \
subcc %left, 8, %left; \
bl,pn %xcc, 95f; \
fsrc1 %f0, %f1;
#define UNEVEN_VISCHUNK(dest, f0, f1, left) \
UNEVEN_VISCHUNK_LAST(dest, f0, f1, left) \
ba,a,pt %xcc, 93f;
.register %g2,#scratch
.register %g3,#scratch
.text
.align 64
.globl FUNC_NAME
.type FUNC_NAME,#function
FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
srlx %o2, 31, %g2
cmp %g2, 0
tne %xcc, 5
PREAMBLE
mov %o0, %o4
cmp %o2, 0
be,pn %XCC, 85f
or %o0, %o1, %o3
cmp %o2, 16
blu,a,pn %XCC, 80f
or %o3, %o2, %o3
cmp %o2, (5 * 64)
blu,pt %XCC, 70f
andcc %o3, 0x7, %g0
/* Clobbers o5/g1/g2/g3/g7/icc/xcc. */
VISEntry
/* Is 'dst' already aligned on an 64-byte boundary? */
andcc %o0, 0x3f, %g2
be,pt %XCC, 2f
/* Compute abs((dst & 0x3f) - 0x40) into %g2. This is the number
* of bytes to copy to make 'dst' 64-byte aligned. We pre-
* subtract this from 'len'.
*/
sub %o0, %o1, %GLOBAL_SPARE
sub %g2, 0x40, %g2
sub %g0, %g2, %g2
sub %o2, %g2, %o2
andcc %g2, 0x7, %g1
be,pt %icc, 2f
and %g2, 0x38, %g2
1: subcc %g1, 0x1, %g1
EX_LD(LOAD(ldub, %o1 + 0x00, %o3))
EX_ST(STORE(stb, %o3, %o1 + %GLOBAL_SPARE))
bgu,pt %XCC, 1b
add %o1, 0x1, %o1
add %o1, %GLOBAL_SPARE, %o0
2: cmp %g2, 0x0
and %o1, 0x7, %g1
be,pt %icc, 3f
alignaddr %o1, %g0, %o1
EX_LD(LOAD(ldd, %o1, %f4))
1: EX_LD(LOAD(ldd, %o1 + 0x8, %f6))
add %o1, 0x8, %o1
subcc %g2, 0x8, %g2
faligndata %f4, %f6, %f0
EX_ST(STORE(std, %f0, %o0))
be,pn %icc, 3f
add %o0, 0x8, %o0
EX_LD(LOAD(ldd, %o1 + 0x8, %f4))
add %o1, 0x8, %o1
subcc %g2, 0x8, %g2
faligndata %f6, %f4, %f0
EX_ST(STORE(std, %f0, %o0))
bne,pt %icc, 1b
add %o0, 0x8, %o0
/* Destination is 64-byte aligned. */
3:
membar #LoadStore | #StoreStore | #StoreLoad
subcc %o2, 0x40, %GLOBAL_SPARE
add %o1, %g1, %g1
andncc %GLOBAL_SPARE, (0x40 - 1), %GLOBAL_SPARE
srl %g1, 3, %g2
sub %o2, %GLOBAL_SPARE, %g3
andn %o1, (0x40 - 1), %o1
and %g2, 7, %g2
andncc %g3, 0x7, %g3
fmovd %f0, %f2
sub %g3, 0x8, %g3
sub %o2, %GLOBAL_SPARE, %o2
add %g1, %GLOBAL_SPARE, %g1
subcc %o2, %g3, %o2
EX_LD(LOAD_BLK(%o1, %f0))
add %o1, 0x40, %o1
add %g1, %g3, %g1
EX_LD(LOAD_BLK(%o1, %f16))
add %o1, 0x40, %o1
sub %GLOBAL_SPARE, 0x80, %GLOBAL_SPARE
EX_LD(LOAD_BLK(%o1, %f32))
add %o1, 0x40, %o1
/* There are 8 instances of the unrolled loop,
* one for each possible alignment of the
* source buffer. Each loop instance is 452
* bytes.
*/
sll %g2, 3, %o3
sub %o3, %g2, %o3
sllx %o3, 4, %o3
add %o3, %g2, %o3
sllx %o3, 2, %g2
1: rd %pc, %o3
add %o3, %lo(1f - 1b), %o3
jmpl %o3 + %g2, %g0
nop
.align 64
1: FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16)
LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)
LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0)
LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
ba,pt %xcc, 1b+4
faligndata %f0, %f2, %f48
1: FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)
STORE_SYNC(o0, f48)
FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0)
STORE_JUMP(o0, f48, 40f)
2: FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0)
STORE_SYNC(o0, f48)
FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16)
STORE_JUMP(o0, f48, 48f)
3: FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16)
STORE_SYNC(o0, f48)
FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)
STORE_JUMP(o0, f48, 56f)
1: FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18)
LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)
LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2)
LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
ba,pt %xcc, 1b+4
faligndata %f2, %f4, %f48
1: FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)
STORE_SYNC(o0, f48)
FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2)
STORE_JUMP(o0, f48, 41f)
2: FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2)
STORE_SYNC(o0, f48)
FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18)
STORE_JUMP(o0, f48, 49f)
3: FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18)
STORE_SYNC(o0, f48)
FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)
STORE_JUMP(o0, f48, 57f)
1: FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)
LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)
LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4)
LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
ba,pt %xcc, 1b+4
faligndata %f4, %f6, %f48
1: FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)
STORE_SYNC(o0, f48)
FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4)
STORE_JUMP(o0, f48, 42f)
2: FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4)
STORE_SYNC(o0, f48)
FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)
STORE_JUMP(o0, f48, 50f)
3: FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)
STORE_SYNC(o0, f48)
FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)
STORE_JUMP(o0, f48, 58f)
1: FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)
LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)
LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6)
LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
ba,pt %xcc, 1b+4
faligndata %f6, %f8, %f48
1: FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)
STORE_SYNC(o0, f48)
FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6)
STORE_JUMP(o0, f48, 43f)
2: FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6)
STORE_SYNC(o0, f48)
FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)
STORE_JUMP(o0, f48, 51f)
3: FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)
STORE_SYNC(o0, f48)
FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)
STORE_JUMP(o0, f48, 59f)
1: FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)
LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)
LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8)
LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
ba,pt %xcc, 1b+4
faligndata %f8, %f10, %f48
1: FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)
STORE_SYNC(o0, f48)
FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8)
STORE_JUMP(o0, f48, 44f)
2: FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8)
STORE_SYNC(o0, f48)
FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)
STORE_JUMP(o0, f48, 52f)
3: FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)
STORE_SYNC(o0, f48)
FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)
STORE_JUMP(o0, f48, 60f)
1: FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)
LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)
LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10)
LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
ba,pt %xcc, 1b+4
faligndata %f10, %f12, %f48
1: FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)
STORE_SYNC(o0, f48)
FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10)
STORE_JUMP(o0, f48, 45f)
2: FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10)
STORE_SYNC(o0, f48)
FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)
STORE_JUMP(o0, f48, 53f)
3: FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)
STORE_SYNC(o0, f48)
FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)
STORE_JUMP(o0, f48, 61f)
1: FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)
LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)
LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12)
LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
ba,pt %xcc, 1b+4
faligndata %f12, %f14, %f48
1: FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)
STORE_SYNC(o0, f48)
FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12)
STORE_JUMP(o0, f48, 46f)
2: FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12)
STORE_SYNC(o0, f48)
FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)
STORE_JUMP(o0, f48, 54f)
3: FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)
STORE_SYNC(o0, f48)
FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)
STORE_JUMP(o0, f48, 62f)
1: FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)
LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14)
LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
ba,pt %xcc, 1b+4
faligndata %f14, %f16, %f48
1: FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
STORE_SYNC(o0, f48)
FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14)
STORE_JUMP(o0, f48, 47f)
2: FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14)
STORE_SYNC(o0, f48)
FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)
STORE_JUMP(o0, f48, 55f)
3: FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)
STORE_SYNC(o0, f48)
FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
STORE_JUMP(o0, f48, 63f)
40: FINISH_VISCHUNK(o0, f0, f2, g3)
41: FINISH_VISCHUNK(o0, f2, f4, g3)
42: FINISH_VISCHUNK(o0, f4, f6, g3)
43: FINISH_VISCHUNK(o0, f6, f8, g3)
44: FINISH_VISCHUNK(o0, f8, f10, g3)
45: FINISH_VISCHUNK(o0, f10, f12, g3)
46: FINISH_VISCHUNK(o0, f12, f14, g3)
47: UNEVEN_VISCHUNK(o0, f14, f0, g3)
48: FINISH_VISCHUNK(o0, f16, f18, g3)
49: FINISH_VISCHUNK(o0, f18, f20, g3)
50: FINISH_VISCHUNK(o0, f20, f22, g3)
51: FINISH_VISCHUNK(o0, f22, f24, g3)
52: FINISH_VISCHUNK(o0, f24, f26, g3)
53: FINISH_VISCHUNK(o0, f26, f28, g3)
54: FINISH_VISCHUNK(o0, f28, f30, g3)
55: UNEVEN_VISCHUNK(o0, f30, f0, g3)
56: FINISH_VISCHUNK(o0, f32, f34, g3)
57: FINISH_VISCHUNK(o0, f34, f36, g3)
58: FINISH_VISCHUNK(o0, f36, f38, g3)
59: FINISH_VISCHUNK(o0, f38, f40, g3)
60: FINISH_VISCHUNK(o0, f40, f42, g3)
61: FINISH_VISCHUNK(o0, f42, f44, g3)
62: FINISH_VISCHUNK(o0, f44, f46, g3)
63: UNEVEN_VISCHUNK_LAST(o0, f46, f0, g3)
93: EX_LD(LOAD(ldd, %o1, %f2))
add %o1, 8, %o1
subcc %g3, 8, %g3
faligndata %f0, %f2, %f8
EX_ST(STORE(std, %f8, %o0))
bl,pn %xcc, 95f
add %o0, 8, %o0
EX_LD(LOAD(ldd, %o1, %f0))
add %o1, 8, %o1
subcc %g3, 8, %g3
faligndata %f2, %f0, %f8
EX_ST(STORE(std, %f8, %o0))
bge,pt %xcc, 93b
add %o0, 8, %o0
95: brz,pt %o2, 2f
mov %g1, %o1
1: EX_LD(LOAD(ldub, %o1, %o3))
add %o1, 1, %o1
subcc %o2, 1, %o2
EX_ST(STORE(stb, %o3, %o0))
bne,pt %xcc, 1b
add %o0, 1, %o0
2: membar #StoreLoad | #StoreStore
VISExit
retl
mov EX_RETVAL(%o4), %o0
.align 64
70: /* 16 < len <= (5 * 64) */
bne,pn %XCC, 75f
sub %o0, %o1, %o3
72: andn %o2, 0xf, %GLOBAL_SPARE
and %o2, 0xf, %o2
1: EX_LD(LOAD(ldx, %o1 + 0x00, %o5))
EX_LD(LOAD(ldx, %o1 + 0x08, %g1))
subcc %GLOBAL_SPARE, 0x10, %GLOBAL_SPARE
EX_ST(STORE(stx, %o5, %o1 + %o3))
add %o1, 0x8, %o1
EX_ST(STORE(stx, %g1, %o1 + %o3))
bgu,pt %XCC, 1b
add %o1, 0x8, %o1
73: andcc %o2, 0x8, %g0
be,pt %XCC, 1f
nop
EX_LD(LOAD(ldx, %o1, %o5))
sub %o2, 0x8, %o2
EX_ST(STORE(stx, %o5, %o1 + %o3))
add %o1, 0x8, %o1
1: andcc %o2, 0x4, %g0
be,pt %XCC, 1f
nop
EX_LD(LOAD(lduw, %o1, %o5))
sub %o2, 0x4, %o2
EX_ST(STORE(stw, %o5, %o1 + %o3))
add %o1, 0x4, %o1
1: cmp %o2, 0
be,pt %XCC, 85f
nop
ba,pt %xcc, 90f
nop
75: andcc %o0, 0x7, %g1
sub %g1, 0x8, %g1
be,pn %icc, 2f
sub %g0, %g1, %g1
sub %o2, %g1, %o2
1: EX_LD(LOAD(ldub, %o1, %o5))
subcc %g1, 1, %g1
EX_ST(STORE(stb, %o5, %o1 + %o3))
bgu,pt %icc, 1b
add %o1, 1, %o1
2: add %o1, %o3, %o0
andcc %o1, 0x7, %g1
bne,pt %icc, 8f
sll %g1, 3, %g1
cmp %o2, 16
bgeu,pt %icc, 72b
nop
ba,a,pt %xcc, 73b
8: mov 64, %o3
andn %o1, 0x7, %o1
EX_LD(LOAD(ldx, %o1, %g2))
sub %o3, %g1, %o3
andn %o2, 0x7, %GLOBAL_SPARE
sllx %g2, %g1, %g2
1: EX_LD(LOAD(ldx, %o1 + 0x8, %g3))
subcc %GLOBAL_SPARE, 0x8, %GLOBAL_SPARE
add %o1, 0x8, %o1
srlx %g3, %o3, %o5
or %o5, %g2, %o5
EX_ST(STORE(stx, %o5, %o0))
add %o0, 0x8, %o0
bgu,pt %icc, 1b
sllx %g3, %g1, %g2
srl %g1, 3, %g1
andcc %o2, 0x7, %o2
be,pn %icc, 85f
add %o1, %g1, %o1
ba,pt %xcc, 90f
sub %o0, %o1, %o3
.align 64
80: /* 0 < len <= 16 */
andcc %o3, 0x3, %g0
bne,pn %XCC, 90f
sub %o0, %o1, %o3
1: EX_LD(LOAD(lduw, %o1, %g1))
subcc %o2, 4, %o2
EX_ST(STORE(stw, %g1, %o1 + %o3))
bgu,pt %XCC, 1b
add %o1, 4, %o1
85: retl
mov EX_RETVAL(%o4), %o0
.align 32
90: EX_LD(LOAD(ldub, %o1, %g1))
subcc %o2, 1, %o2
EX_ST(STORE(stb, %g1, %o1 + %o3))
bgu,pt %XCC, 90b
add %o1, 1, %o1
retl
mov EX_RETVAL(%o4), %o0
.size FUNC_NAME, .-FUNC_NAME