Gitiles
Code Review Sign In
192.168.1.100 / R306 / d2d5ce1c3b5150b4e785d55d94aebeebaf7a90dc / . / ap / build / uClibc / libc / string / sparc / sparc64 / memcpy.S
blob: db63d1da22207e473f82cc445fd57f81027777cb [file] [log] [blame]
yuezonghe824eb0c2024-06-27 02:32:26 -0700[diff] [blame]1/* Copy SIZE bytes from SRC to DEST.
2 For UltraSPARC.
3 Copyright (C) 1996, 97, 98, 99, 2003 Free Software Foundation, Inc.
4 This file is part of the GNU C Library.
5 Contributed by David S. Miller (davem@caip.rutgers.edu) and
6 Jakub Jelinek (jakub@redhat.com).
7
8 The GNU C Library is free software; you can redistribute it and/or
9 modify it under the terms of the GNU Lesser General Public
10 License as published by the Free Software Foundation; either
11 version 2.1 of the License, or (at your option) any later version.
12
13 The GNU C Library is distributed in the hope that it will be useful,
14 but WITHOUT ANY WARRANTY; without even the implied warranty of
15 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
16 Lesser General Public License for more details.
17
18 You should have received a copy of the GNU Lesser General Public
19 License along with the GNU C Library; if not, write to the Free
20 Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
21 02111-1307 USA. */
22
23#include <features.h>
24#include <asm/asi.h>
25#ifndef XCC
26#define USE_BPR
27 .register %g2, #scratch
28 .register %g3, #scratch
29 .register %g6, #scratch
30#define XCC xcc
31#endif
32#define FPRS_FEF 4
33
34#define FREG_FROB(f1, f2, f3, f4, f5, f6, f7, f8, f9) \
35 faligndata %f1, %f2, %f48; \
36 faligndata %f2, %f3, %f50; \
37 faligndata %f3, %f4, %f52; \
38 faligndata %f4, %f5, %f54; \
39 faligndata %f5, %f6, %f56; \
40 faligndata %f6, %f7, %f58; \
41 faligndata %f7, %f8, %f60; \
42 faligndata %f8, %f9, %f62;
43
44#define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, len, jmptgt) \
45 ldda [%src] %asi, %fdest; \
46 add %src, 0x40, %src; \
47 add %dest, 0x40, %dest; \
48 subcc %len, 0x40, %len; \
49 be,pn %xcc, jmptgt; \
50 stda %fsrc, [%dest - 0x40] %asi;
51
52#define LOOP_CHUNK1(src, dest, len, branch_dest) \
53 MAIN_LOOP_CHUNK(src, dest, f0, f48, len, branch_dest)
54#define LOOP_CHUNK2(src, dest, len, branch_dest) \
55 MAIN_LOOP_CHUNK(src, dest, f16, f48, len, branch_dest)
56#define LOOP_CHUNK3(src, dest, len, branch_dest) \
57 MAIN_LOOP_CHUNK(src, dest, f32, f48, len, branch_dest)
58
59#define STORE_SYNC(dest, fsrc) \
60 stda %fsrc, [%dest] %asi; \
61 add %dest, 0x40, %dest;
62
63#define STORE_JUMP(dest, fsrc, target) \
64 stda %fsrc, [%dest] %asi; \
65 add %dest, 0x40, %dest; \
66 ba,pt %xcc, target;
67
68#define VISLOOP_PAD nop; nop; nop; nop; \
69 nop; nop; nop; nop; \
70 nop; nop; nop; nop; \
71 nop; nop; nop;
72
73#define FINISH_VISCHUNK(dest, f0, f1, left) \
74 subcc %left, 8, %left; \
75 bl,pn %xcc, 205f; \
76 faligndata %f0, %f1, %f48; \
77 std %f48, [%dest]; \
78 add %dest, 8, %dest;
79
80#define UNEVEN_VISCHUNK(dest, f0, f1, left) \
81 subcc %left, 8, %left; \
82 bl,pn %xcc, 205f; \
83 fsrc1 %f0, %f1; \
84 ba,a,pt %xcc, 204f;
85
86 /* Macros for non-VIS memcpy code. */
87#define MOVE_BIGCHUNK(src, dst, offset, t0, t1, t2, t3) \
88 ldx [%src + offset + 0x00], %t0; \
89 ldx [%src + offset + 0x08], %t1; \
90 ldx [%src + offset + 0x10], %t2; \
91 ldx [%src + offset + 0x18], %t3; \
92 stw %t0, [%dst + offset + 0x04]; \
93 srlx %t0, 32, %t0; \
94 stw %t0, [%dst + offset + 0x00]; \
95 stw %t1, [%dst + offset + 0x0c]; \
96 srlx %t1, 32, %t1; \
97 stw %t1, [%dst + offset + 0x08]; \
98 stw %t2, [%dst + offset + 0x14]; \
99 srlx %t2, 32, %t2; \
100 stw %t2, [%dst + offset + 0x10]; \
101 stw %t3, [%dst + offset + 0x1c]; \
102 srlx %t3, 32, %t3; \
103 stw %t3, [%dst + offset + 0x18];
104
105#define MOVE_BIGALIGNCHUNK(src, dst, offset, t0, t1, t2, t3) \
106 ldx [%src + offset + 0x00], %t0; \
107 ldx [%src + offset + 0x08], %t1; \
108 ldx [%src + offset + 0x10], %t2; \
109 ldx [%src + offset + 0x18], %t3; \
110 stx %t0, [%dst + offset + 0x00]; \
111 stx %t1, [%dst + offset + 0x08]; \
112 stx %t2, [%dst + offset + 0x10]; \
113 stx %t3, [%dst + offset + 0x18]; \
114 ldx [%src + offset + 0x20], %t0; \
115 ldx [%src + offset + 0x28], %t1; \
116 ldx [%src + offset + 0x30], %t2; \
117 ldx [%src + offset + 0x38], %t3; \
118 stx %t0, [%dst + offset + 0x20]; \
119 stx %t1, [%dst + offset + 0x28]; \
120 stx %t2, [%dst + offset + 0x30]; \
121 stx %t3, [%dst + offset + 0x38];
122
123#define MOVE_LASTCHUNK(src, dst, offset, t0, t1, t2, t3) \
124 ldx [%src - offset - 0x10], %t0; \
125 ldx [%src - offset - 0x08], %t1; \
126 stw %t0, [%dst - offset - 0x0c]; \
127 srlx %t0, 32, %t2; \
128 stw %t2, [%dst - offset - 0x10]; \
129 stw %t1, [%dst - offset - 0x04]; \
130 srlx %t1, 32, %t3; \
131 stw %t3, [%dst - offset - 0x08];
132
133#define MOVE_LASTALIGNCHUNK(src, dst, offset, t0, t1) \
134 ldx [%src - offset - 0x10], %t0; \
135 ldx [%src - offset - 0x08], %t1; \
136 stx %t0, [%dst - offset - 0x10]; \
137 stx %t1, [%dst - offset - 0x08];
138
139 /* Macros for non-VIS memmove code. */
140#define RMOVE_BIGCHUNK(src, dst, offset, t0, t1, t2, t3) \
141 ldx [%src - offset - 0x20], %t0; \
142 ldx [%src - offset - 0x18], %t1; \
143 ldx [%src - offset - 0x10], %t2; \
144 ldx [%src - offset - 0x08], %t3; \
145 stw %t0, [%dst - offset - 0x1c]; \
146 srlx %t0, 32, %t0; \
147 stw %t0, [%dst - offset - 0x20]; \
148 stw %t1, [%dst - offset - 0x14]; \
149 srlx %t1, 32, %t1; \
150 stw %t1, [%dst - offset - 0x18]; \
151 stw %t2, [%dst - offset - 0x0c]; \
152 srlx %t2, 32, %t2; \
153 stw %t2, [%dst - offset - 0x10]; \
154 stw %t3, [%dst - offset - 0x04]; \
155 srlx %t3, 32, %t3; \
156 stw %t3, [%dst - offset - 0x08];
157
158#define RMOVE_BIGALIGNCHUNK(src, dst, offset, t0, t1, t2, t3) \
159 ldx [%src - offset - 0x20], %t0; \
160 ldx [%src - offset - 0x18], %t1; \
161 ldx [%src - offset - 0x10], %t2; \
162 ldx [%src - offset - 0x08], %t3; \
163 stx %t0, [%dst - offset - 0x20]; \
164 stx %t1, [%dst - offset - 0x18]; \
165 stx %t2, [%dst - offset - 0x10]; \
166 stx %t3, [%dst - offset - 0x08]; \
167 ldx [%src - offset - 0x40], %t0; \
168 ldx [%src - offset - 0x38], %t1; \
169 ldx [%src - offset - 0x30], %t2; \
170 ldx [%src - offset - 0x28], %t3; \
171 stx %t0, [%dst - offset - 0x40]; \
172 stx %t1, [%dst - offset - 0x38]; \
173 stx %t2, [%dst - offset - 0x30]; \
174 stx %t3, [%dst - offset - 0x28];
175
176#define RMOVE_LASTCHUNK(src, dst, offset, t0, t1, t2, t3) \
177 ldx [%src + offset + 0x00], %t0; \
178 ldx [%src + offset + 0x08], %t1; \
179 stw %t0, [%dst + offset + 0x04]; \
180 srlx %t0, 32, %t2; \
181 stw %t2, [%dst + offset + 0x00]; \
182 stw %t1, [%dst + offset + 0x0c]; \
183 srlx %t1, 32, %t3; \
184 stw %t3, [%dst + offset + 0x08];
185
186#define RMOVE_LASTALIGNCHUNK(src, dst, offset, t0, t1) \
187 ldx [%src + offset + 0x00], %t0; \
188 ldx [%src + offset + 0x08], %t1; \
189 stx %t0, [%dst + offset + 0x00]; \
190 stx %t1, [%dst + offset + 0x08];
191
192 .text
193 .align 32
194
195#ifdef __UCLIBC_SUSV3_LEGACY__
196ENTRY(bcopy)
197 sub %o1, %o0, %o4 /* IEU0 Group */
198 mov %o0, %g3 /* IEU1 */
199 cmp %o4, %o2 /* IEU1 Group */
200 mov %o1, %o0 /* IEU0 */
201 bgeu,pt %XCC, 210f /* CTI */
202 mov %g3, %o1 /* IEU0 Group */
203#ifndef USE_BPR
204 srl %o2, 0, %o2 /* IEU1 */
205#endif
206 brnz,pn %o2, 220f /* CTI Group */
207 add %o0, %o2, %o0 /* IEU0 */
208 retl
209 nop
210END(bcopy)
211#endif
212
213 .align 32
214200: be,pt %xcc, 201f /* CTI */
215 andcc %o0, 0x38, %g5 /* IEU1 Group */
216 mov 8, %g1 /* IEU0 */
217 sub %g1, %g2, %g2 /* IEU0 Group */
218 andcc %o0, 1, %g0 /* IEU1 */
219 be,pt %icc, 2f /* CTI */
220 sub %o2, %g2, %o2 /* IEU0 Group */
2211: ldub [%o1], %o5 /* Load Group */
222 add %o1, 1, %o1 /* IEU0 */
223 add %o0, 1, %o0 /* IEU1 */
224 subcc %g2, 1, %g2 /* IEU1 Group */
225 be,pn %xcc, 3f /* CTI */
226 stb %o5, [%o0 - 1] /* Store */
2272: ldub [%o1], %o5 /* Load Group */
228 add %o0, 2, %o0 /* IEU0 */
229 ldub [%o1 + 1], %g3 /* Load Group */
230 subcc %g2, 2, %g2 /* IEU1 Group */
231 stb %o5, [%o0 - 2] /* Store */
232 add %o1, 2, %o1 /* IEU0 */
233 bne,pt %xcc, 2b /* CTI Group */
234 stb %g3, [%o0 - 1] /* Store */
2353: andcc %o0, 0x38, %g5 /* IEU1 Group */
236201: be,pt %icc, 202f /* CTI */
237 mov 64, %g1 /* IEU0 */
238 fmovd %f0, %f2 /* FPU */
239 sub %g1, %g5, %g5 /* IEU0 Group */
240 alignaddr %o1, %g0, %g1 /* GRU Group */
241 ldd [%g1], %f4 /* Load Group */
242 sub %o2, %g5, %o2 /* IEU0 */
2431: ldd [%g1 + 0x8], %f6 /* Load Group */
244 add %g1, 0x8, %g1 /* IEU0 Group */
245 subcc %g5, 8, %g5 /* IEU1 */
246 faligndata %f4, %f6, %f0 /* GRU Group */
247 std %f0, [%o0] /* Store */
248 add %o1, 8, %o1 /* IEU0 Group */
249 be,pn %xcc, 202f /* CTI */
250 add %o0, 8, %o0 /* IEU1 */
251 ldd [%g1 + 0x8], %f4 /* Load Group */
252 add %g1, 8, %g1 /* IEU0 */
253 subcc %g5, 8, %g5 /* IEU1 */
254 faligndata %f6, %f4, %f0 /* GRU Group */
255 std %f0, [%o0] /* Store */
256 add %o1, 8, %o1 /* IEU0 */
257 bne,pt %xcc, 1b /* CTI Group */
258 add %o0, 8, %o0 /* IEU0 */
259202: membar #LoadStore | #StoreStore | #StoreLoad /* LSU Group */
260 wr %g0, ASI_BLK_P, %asi /* LSU Group */
261 subcc %o2, 0x40, %g6 /* IEU1 Group */
262 mov %o1, %g1 /* IEU0 */
263 andncc %g6, (0x40 - 1), %g6 /* IEU1 Group */
264 srl %g1, 3, %g2 /* IEU0 */
265 sub %o2, %g6, %g3 /* IEU0 Group */
266 andn %o1, (0x40 - 1), %o1 /* IEU1 */
267 and %g2, 7, %g2 /* IEU0 Group */
268 andncc %g3, 0x7, %g3 /* IEU1 */
269 fmovd %f0, %f2 /* FPU */
270 sub %g3, 0x10, %g3 /* IEU0 Group */
271 sub %o2, %g6, %o2 /* IEU1 */
272 alignaddr %g1, %g0, %g0 /* GRU Group */
273 add %g1, %g6, %g1 /* IEU0 Group */
274 subcc %o2, %g3, %o2 /* IEU1 */
275 ldda [%o1 + 0x00] %asi, %f0 /* LSU Group */
276 add %g1, %g3, %g1 /* IEU0 */
277 ldda [%o1 + 0x40] %asi, %f16 /* LSU Group */
278 sub %g6, 0x80, %g6 /* IEU0 */
279 ldda [%o1 + 0x80] %asi, %f32 /* LSU Group */
280 /* Clk1 Group 8-( */
281 /* Clk2 Group 8-( */
282 /* Clk3 Group 8-( */
283 /* Clk4 Group 8-( */
284203: rd %pc, %g5 /* PDU Group 8-( */
285 addcc %g5, %lo(300f - 203b), %g5 /* IEU1 Group */
286 sll %g2, 9, %g2 /* IEU0 */
287 jmpl %g5 + %g2, %g0 /* CTI Group brk forced*/
288 addcc %o1, 0xc0, %o1 /* IEU1 Group */
289
290 .align 512 /* OK, here comes the fun part... */
291300: FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16) LOOP_CHUNK1(o1, o0, g6, 301f)
292 FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32) LOOP_CHUNK2(o1, o0, g6, 302f)
293 FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0) LOOP_CHUNK3(o1, o0, g6, 303f)
294 b,pt %xcc, 300b+4; faligndata %f0, %f2, %f48
295301: FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32) STORE_SYNC(o0, f48) membar #Sync
296 FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0) STORE_JUMP(o0, f48, 400f) membar #Sync
297302: FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0) STORE_SYNC(o0, f48) membar #Sync
298 FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16) STORE_JUMP(o0, f48, 416f) membar #Sync
299303: FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16) STORE_SYNC(o0, f48) membar #Sync
300 FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32) STORE_JUMP(o0, f48, 432f) membar #Sync
301 VISLOOP_PAD
302310: FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18) LOOP_CHUNK1(o1, o0, g6, 311f)
303 FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34) LOOP_CHUNK2(o1, o0, g6, 312f)
304 FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2) LOOP_CHUNK3(o1, o0, g6, 313f)
305 b,pt %xcc, 310b+4; faligndata %f2, %f4, %f48
306311: FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34) STORE_SYNC(o0, f48) membar #Sync
307 FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2) STORE_JUMP(o0, f48, 402f) membar #Sync
308312: FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2) STORE_SYNC(o0, f48) membar #Sync
309 FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18) STORE_JUMP(o0, f48, 418f) membar #Sync
310313: FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18) STORE_SYNC(o0, f48) membar #Sync
311 FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34) STORE_JUMP(o0, f48, 434f) membar #Sync
312 VISLOOP_PAD
313320: FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20) LOOP_CHUNK1(o1, o0, g6, 321f)
314 FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36) LOOP_CHUNK2(o1, o0, g6, 322f)
315 FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4) LOOP_CHUNK3(o1, o0, g6, 323f)
316 b,pt %xcc, 320b+4; faligndata %f4, %f6, %f48
317321: FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36) STORE_SYNC(o0, f48) membar #Sync
318 FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4) STORE_JUMP(o0, f48, 404f) membar #Sync
319322: FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4) STORE_SYNC(o0, f48) membar #Sync
320 FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20) STORE_JUMP(o0, f48, 420f) membar #Sync
321323: FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20) STORE_SYNC(o0, f48) membar #Sync
322 FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36) STORE_JUMP(o0, f48, 436f) membar #Sync
323 VISLOOP_PAD
324330: FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22) LOOP_CHUNK1(o1, o0, g6, 331f)
325 FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38) LOOP_CHUNK2(o1, o0, g6, 332f)
326 FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6) LOOP_CHUNK3(o1, o0, g6, 333f)
327 b,pt %xcc, 330b+4; faligndata %f6, %f8, %f48
328331: FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38) STORE_SYNC(o0, f48) membar #Sync
329 FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6) STORE_JUMP(o0, f48, 406f) membar #Sync
330332: FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6) STORE_SYNC(o0, f48) membar #Sync
331 FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22) STORE_JUMP(o0, f48, 422f) membar #Sync
332333: FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22) STORE_SYNC(o0, f48) membar #Sync
333 FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38) STORE_JUMP(o0, f48, 438f) membar #Sync
334 VISLOOP_PAD
335340: FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24) LOOP_CHUNK1(o1, o0, g6, 341f)
336 FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40) LOOP_CHUNK2(o1, o0, g6, 342f)
337 FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8) LOOP_CHUNK3(o1, o0, g6, 343f)
338 b,pt %xcc, 340b+4; faligndata %f8, %f10, %f48
339341: FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40) STORE_SYNC(o0, f48) membar #Sync
340 FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8) STORE_JUMP(o0, f48, 408f) membar #Sync
341342: FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8) STORE_SYNC(o0, f48) membar #Sync
342 FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24) STORE_JUMP(o0, f48, 424f) membar #Sync
343343: FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24) STORE_SYNC(o0, f48) membar #Sync
344 FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40) STORE_JUMP(o0, f48, 440f) membar #Sync
345 VISLOOP_PAD
346350: FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26) LOOP_CHUNK1(o1, o0, g6, 351f)
347 FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42) LOOP_CHUNK2(o1, o0, g6, 352f)
348 FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10) LOOP_CHUNK3(o1, o0, g6, 353f)
349 b,pt %xcc, 350b+4; faligndata %f10, %f12, %f48
350351: FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42) STORE_SYNC(o0, f48) membar #Sync
351 FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10) STORE_JUMP(o0, f48, 410f) membar #Sync
352352: FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10) STORE_SYNC(o0, f48) membar #Sync
353 FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26) STORE_JUMP(o0, f48, 426f) membar #Sync
354353: FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26) STORE_SYNC(o0, f48) membar #Sync
355 FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42) STORE_JUMP(o0, f48, 442f) membar #Sync
356 VISLOOP_PAD
357360: FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28) LOOP_CHUNK1(o1, o0, g6, 361f)
358 FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44) LOOP_CHUNK2(o1, o0, g6, 362f)
359 FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12) LOOP_CHUNK3(o1, o0, g6, 363f)
360 b,pt %xcc, 360b+4; faligndata %f12, %f14, %f48
361361: FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44) STORE_SYNC(o0, f48) membar #Sync
362 FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12) STORE_JUMP(o0, f48, 412f) membar #Sync
363362: FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12) STORE_SYNC(o0, f48) membar #Sync
364 FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28) STORE_JUMP(o0, f48, 428f) membar #Sync
365363: FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28) STORE_SYNC(o0, f48) membar #Sync
366 FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44) STORE_JUMP(o0, f48, 444f) membar #Sync
367 VISLOOP_PAD
368370: FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30) LOOP_CHUNK1(o1, o0, g6, 371f)
369 FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46) LOOP_CHUNK2(o1, o0, g6, 372f)
370 FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14) LOOP_CHUNK3(o1, o0, g6, 373f)
371 b,pt %xcc, 370b+4; faligndata %f14, %f16, %f48
372371: FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46) STORE_SYNC(o0, f48) membar #Sync
373 FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14) STORE_JUMP(o0, f48, 414f) membar #Sync
374372: FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14) STORE_SYNC(o0, f48) membar #Sync
375 FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30) STORE_JUMP(o0, f48, 430f) membar #Sync
376373: FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30) STORE_SYNC(o0, f48) membar #Sync
377 FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46) STORE_JUMP(o0, f48, 446f) membar #Sync
378 VISLOOP_PAD
379400: FINISH_VISCHUNK(o0, f0, f2, g3)
380402: FINISH_VISCHUNK(o0, f2, f4, g3)
381404: FINISH_VISCHUNK(o0, f4, f6, g3)
382406: FINISH_VISCHUNK(o0, f6, f8, g3)
383408: FINISH_VISCHUNK(o0, f8, f10, g3)
384410: FINISH_VISCHUNK(o0, f10, f12, g3)
385412: FINISH_VISCHUNK(o0, f12, f14, g3)
386414: UNEVEN_VISCHUNK(o0, f14, f0, g3)
387416: FINISH_VISCHUNK(o0, f16, f18, g3)
388418: FINISH_VISCHUNK(o0, f18, f20, g3)
389420: FINISH_VISCHUNK(o0, f20, f22, g3)
390422: FINISH_VISCHUNK(o0, f22, f24, g3)
391424: FINISH_VISCHUNK(o0, f24, f26, g3)
392426: FINISH_VISCHUNK(o0, f26, f28, g3)
393428: FINISH_VISCHUNK(o0, f28, f30, g3)
394430: UNEVEN_VISCHUNK(o0, f30, f0, g3)
395432: FINISH_VISCHUNK(o0, f32, f34, g3)
396434: FINISH_VISCHUNK(o0, f34, f36, g3)
397436: FINISH_VISCHUNK(o0, f36, f38, g3)
398438: FINISH_VISCHUNK(o0, f38, f40, g3)
399440: FINISH_VISCHUNK(o0, f40, f42, g3)
400442: FINISH_VISCHUNK(o0, f42, f44, g3)
401444: FINISH_VISCHUNK(o0, f44, f46, g3)
402446: UNEVEN_VISCHUNK(o0, f46, f0, g3)
403204: ldd [%o1], %f2 /* Load Group */
404 add %o1, 8, %o1 /* IEU0 */
405 subcc %g3, 8, %g3 /* IEU1 */
406 faligndata %f0, %f2, %f8 /* GRU Group */
407 std %f8, [%o0] /* Store */
408 bl,pn %xcc, 205f /* CTI */
409 add %o0, 8, %o0 /* IEU0 Group */
410 ldd [%o1], %f0 /* Load Group */
411 add %o1, 8, %o1 /* IEU0 */
412 subcc %g3, 8, %g3 /* IEU1 */
413 faligndata %f2, %f0, %f8 /* GRU Group */
414 std %f8, [%o0] /* Store */
415 bge,pt %xcc, 204b /* CTI */
416 add %o0, 8, %o0 /* IEU0 Group */
417205: brz,pt %o2, 207f /* CTI Group */
418 mov %g1, %o1 /* IEU0 */
419206: ldub [%o1], %g5 /* LOAD */
420 add %o1, 1, %o1 /* IEU0 */
421 add %o0, 1, %o0 /* IEU1 */
422 subcc %o2, 1, %o2 /* IEU1 */
423 bne,pt %xcc, 206b /* CTI */
424 stb %g5, [%o0 - 1] /* Store Group */
425207: membar #StoreLoad | #StoreStore /* LSU Group */
426 wr %g0, FPRS_FEF, %fprs
427 retl
428 mov %g4, %o0
429
430208: andcc %o2, 1, %g0 /* IEU1 Group */
431 be,pt %icc, 2f+4 /* CTI */
4321: ldub [%o1], %g5 /* LOAD Group */
433 add %o1, 1, %o1 /* IEU0 */
434 add %o0, 1, %o0 /* IEU1 */
435 subcc %o2, 1, %o2 /* IEU1 Group */
436 be,pn %xcc, 209f /* CTI */
437 stb %g5, [%o0 - 1] /* Store */
4382: ldub [%o1], %g5 /* LOAD Group */
439 add %o0, 2, %o0 /* IEU0 */
440 ldub [%o1 + 1], %o5 /* LOAD Group */
441 add %o1, 2, %o1 /* IEU0 */
442 subcc %o2, 2, %o2 /* IEU1 Group */
443 stb %g5, [%o0 - 2] /* Store */
444 bne,pt %xcc, 2b /* CTI */
445 stb %o5, [%o0 - 1] /* Store */
446209: retl
447 mov %g4, %o0
448
449#ifdef USE_BPR
450
451 /* void *__align_cpy_4(void *dest, void *src, size_t n)
452 * SPARC v9 SYSV ABI
453 * Like memcpy, but results are undefined if (!n || ((dest | src | n) & 3))
454 */
455
456 .align 32
457ENTRY(__align_cpy_4)
458 mov %o0, %g4 /* IEU0 Group */
459 cmp %o2, 15 /* IEU1 */
460 bleu,pn %xcc, 208b /* CTI */
461 cmp %o2, (64 * 6) /* IEU1 Group */
462 bgeu,pn %xcc, 200b /* CTI */
463 andcc %o0, 7, %g2 /* IEU1 Group */
464 ba,pt %xcc, 216f /* CTI */
465 andcc %o1, 4, %g0 /* IEU1 Group */
466END(__align_cpy_4)
467
468 /* void *__align_cpy_8(void *dest, void *src, size_t n)
469 * SPARC v9 SYSV ABI
470 * Like memcpy, but results are undefined if (!n || ((dest | src | n) & 7))
471 */
472
473 .align 32
474ENTRY(__align_cpy_8)
475 mov %o0, %g4 /* IEU0 Group */
476 cmp %o2, 15 /* IEU1 */
477 bleu,pn %xcc, 208b /* CTI */
478 cmp %o2, (64 * 6) /* IEU1 Group */
479 bgeu,pn %xcc, 201b /* CTI */
480 andcc %o0, 0x38, %g5 /* IEU1 Group */
481 andcc %o2, -128, %g6 /* IEU1 Group */
482 bne,a,pt %xcc, 82f + 4 /* CTI */
483 ldx [%o1], %g1 /* Load */
484 ba,pt %xcc, 41f /* CTI Group */
485 andcc %o2, 0x70, %g6 /* IEU1 */
486END(__align_cpy_8)
487
488 /* void *__align_cpy_16(void *dest, void *src, size_t n)
489 * SPARC v9 SYSV ABI
490 * Like memcpy, but results are undefined if (!n || ((dest | src | n) & 15))
491 */
492
493 .align 32
494ENTRY(__align_cpy_16)
495 mov %o0, %g4 /* IEU0 Group */
496 cmp %o2, (64 * 6) /* IEU1 */
497 bgeu,pn %xcc, 201b /* CTI */
498 andcc %o0, 0x38, %g5 /* IEU1 Group */
499 andcc %o2, -128, %g6 /* IEU1 Group */
500 bne,a,pt %xcc, 82f + 4 /* CTI */
501 ldx [%o1], %g1 /* Load */
502 ba,pt %xcc, 41f /* CTI Group */
503 andcc %o2, 0x70, %g6 /* IEU1 */
504END(__align_cpy_16)
505
506#endif
507
508 .align 32
509ENTRY(memcpy)
510210:
511#ifndef USE_BPR
512 srl %o2, 0, %o2 /* IEU1 Group */
513#endif
514 brz,pn %o2, 209b /* CTI Group */
515 mov %o0, %g4 /* IEU0 */
516218: cmp %o2, 15 /* IEU1 Group */
517 bleu,pn %xcc, 208b /* CTI */
518 cmp %o2, (64 * 6) /* IEU1 Group */
519 bgeu,pn %xcc, 200b /* CTI */
520 andcc %o0, 7, %g2 /* IEU1 Group */
521 sub %o0, %o1, %g5 /* IEU0 */
522 andcc %g5, 3, %o5 /* IEU1 Group */
523 bne,pn %xcc, 212f /* CTI */
524 andcc %o1, 3, %g0 /* IEU1 Group */
525 be,a,pt %xcc, 216f /* CTI */
526 andcc %o1, 4, %g0 /* IEU1 Group */
527 andcc %o1, 1, %g0 /* IEU1 Group */
528 be,pn %xcc, 4f /* CTI */
529 andcc %o1, 2, %g0 /* IEU1 Group */
530 ldub [%o1], %g2 /* Load Group */
531 add %o1, 1, %o1 /* IEU0 */
532 add %o0, 1, %o0 /* IEU1 */
533 sub %o2, 1, %o2 /* IEU0 Group */
534 bne,pn %xcc, 5f /* CTI Group */
535 stb %g2, [%o0 - 1] /* Store */
5364: lduh [%o1], %g2 /* Load Group */
537 add %o1, 2, %o1 /* IEU0 */
538 add %o0, 2, %o0 /* IEU1 */
539 sub %o2, 2, %o2 /* IEU0 */
540 sth %g2, [%o0 - 2] /* Store Group + bubble */
5415: andcc %o1, 4, %g0 /* IEU1 */
542216: be,a,pn %xcc, 2f /* CTI */
543 andcc %o2, -128, %g6 /* IEU1 Group */
544 lduw [%o1], %g5 /* Load Group */
545 add %o1, 4, %o1 /* IEU0 */
546 add %o0, 4, %o0 /* IEU1 */
547 sub %o2, 4, %o2 /* IEU0 Group */
548 stw %g5, [%o0 - 4] /* Store */
549 andcc %o2, -128, %g6 /* IEU1 Group */
5502: be,pn %xcc, 215f /* CTI */
551 andcc %o0, 4, %g0 /* IEU1 Group */
552 be,pn %xcc, 82f + 4 /* CTI Group */
5535: MOVE_BIGCHUNK(o1, o0, 0x00, g1, g3, g5, o5)
554 MOVE_BIGCHUNK(o1, o0, 0x20, g1, g3, g5, o5)
555 MOVE_BIGCHUNK(o1, o0, 0x40, g1, g3, g5, o5)
556 MOVE_BIGCHUNK(o1, o0, 0x60, g1, g3, g5, o5)
55735: subcc %g6, 128, %g6 /* IEU1 Group */
558 add %o1, 128, %o1 /* IEU0 */
559 bne,pt %xcc, 5b /* CTI */
560 add %o0, 128, %o0 /* IEU0 Group */
561215: andcc %o2, 0x70, %g6 /* IEU1 Group */
56241: be,pn %xcc, 80f /* CTI */
563 andcc %o2, 8, %g0 /* IEU1 Group */
564 /* Clk1 8-( */
565 /* Clk2 8-( */
566 /* Clk3 8-( */
567 /* Clk4 8-( */
56879: rd %pc, %o5 /* PDU Group */
569 sll %g6, 1, %g5 /* IEU0 Group */
570 add %o1, %g6, %o1 /* IEU1 */
571 sub %o5, %g5, %o5 /* IEU0 Group */
572 jmpl %o5 + %lo(80f - 79b), %g0 /* CTI Group brk forced*/
573 add %o0, %g6, %o0 /* IEU0 Group */
57436: MOVE_LASTCHUNK(o1, o0, 0x60, g2, g3, g5, o5)
575 MOVE_LASTCHUNK(o1, o0, 0x50, g2, g3, g5, o5)
576 MOVE_LASTCHUNK(o1, o0, 0x40, g2, g3, g5, o5)
577 MOVE_LASTCHUNK(o1, o0, 0x30, g2, g3, g5, o5)
578 MOVE_LASTCHUNK(o1, o0, 0x20, g2, g3, g5, o5)
579 MOVE_LASTCHUNK(o1, o0, 0x10, g2, g3, g5, o5)
580 MOVE_LASTCHUNK(o1, o0, 0x00, g2, g3, g5, o5)
58180: be,pt %xcc, 81f /* CTI */
582 andcc %o2, 4, %g0 /* IEU1 */
583 ldx [%o1], %g2 /* Load Group */
584 add %o0, 8, %o0 /* IEU0 */
585 stw %g2, [%o0 - 0x4] /* Store Group */
586 add %o1, 8, %o1 /* IEU1 */
587 srlx %g2, 32, %g2 /* IEU0 Group */
588 stw %g2, [%o0 - 0x8] /* Store */
58981: be,pt %xcc, 1f /* CTI */
590 andcc %o2, 2, %g0 /* IEU1 Group */
591 lduw [%o1], %g2 /* Load Group */
592 add %o1, 4, %o1 /* IEU0 */
593 stw %g2, [%o0] /* Store Group */
594 add %o0, 4, %o0 /* IEU0 */
5951: be,pt %xcc, 1f /* CTI */
596 andcc %o2, 1, %g0 /* IEU1 Group */
597 lduh [%o1], %g2 /* Load Group */
598 add %o1, 2, %o1 /* IEU0 */
599 sth %g2, [%o0] /* Store Group */
600 add %o0, 2, %o0 /* IEU0 */
6011: be,pt %xcc, 211f /* CTI */
602 nop /* IEU1 */
603 ldub [%o1], %g2 /* Load Group */
604 stb %g2, [%o0] /* Store Group + bubble */
605211: retl
606 mov %g4, %o0
607
60882: MOVE_BIGALIGNCHUNK(o1, o0, 0x00, g1, g3, g5, o5)
609 MOVE_BIGALIGNCHUNK(o1, o0, 0x40, g1, g3, g5, o5)
61037: subcc %g6, 128, %g6 /* IEU1 Group */
611 add %o1, 128, %o1 /* IEU0 */
612 bne,pt %xcc, 82b /* CTI */
613 add %o0, 128, %o0 /* IEU0 Group */
614 andcc %o2, 0x70, %g6 /* IEU1 */
615 be,pn %xcc, 84f /* CTI */
616 andcc %o2, 8, %g0 /* IEU1 Group */
617 /* Clk1 8-( */
618 /* Clk2 8-( */
619 /* Clk3 8-( */
620 /* Clk4 8-( */
62183: rd %pc, %o5 /* PDU Group */
622 add %o1, %g6, %o1 /* IEU0 Group */
623 sub %o5, %g6, %o5 /* IEU1 */
624 jmpl %o5 + %lo(84f - 83b), %g0 /* CTI Group brk forced*/
625 add %o0, %g6, %o0 /* IEU0 Group */
62638: MOVE_LASTALIGNCHUNK(o1, o0, 0x60, g2, g3)
627 MOVE_LASTALIGNCHUNK(o1, o0, 0x50, g2, g3)
628 MOVE_LASTALIGNCHUNK(o1, o0, 0x40, g2, g3)
629 MOVE_LASTALIGNCHUNK(o1, o0, 0x30, g2, g3)
630 MOVE_LASTALIGNCHUNK(o1, o0, 0x20, g2, g3)
631 MOVE_LASTALIGNCHUNK(o1, o0, 0x10, g2, g3)
632 MOVE_LASTALIGNCHUNK(o1, o0, 0x00, g2, g3)
63384: be,pt %xcc, 85f /* CTI Group */
634 andcc %o2, 4, %g0 /* IEU1 */
635 ldx [%o1], %g2 /* Load Group */
636 add %o0, 8, %o0 /* IEU0 */
637 add %o1, 8, %o1 /* IEU0 Group */
638 stx %g2, [%o0 - 0x8] /* Store */
63985: be,pt %xcc, 1f /* CTI */
640 andcc %o2, 2, %g0 /* IEU1 Group */
641 lduw [%o1], %g2 /* Load Group */
642 add %o0, 4, %o0 /* IEU0 */
643 add %o1, 4, %o1 /* IEU0 Group */
644 stw %g2, [%o0 - 0x4] /* Store */
6451: be,pt %xcc, 1f /* CTI */
646 andcc %o2, 1, %g0 /* IEU1 Group */
647 lduh [%o1], %g2 /* Load Group */
648 add %o0, 2, %o0 /* IEU0 */
649 add %o1, 2, %o1 /* IEU0 Group */
650 sth %g2, [%o0 - 0x2] /* Store */
6511: be,pt %xcc, 1f /* CTI */
652 nop /* IEU0 Group */
653 ldub [%o1], %g2 /* Load Group */
654 stb %g2, [%o0] /* Store Group + bubble */
6551: retl
656 mov %g4, %o0
657
658212: brz,pt %g2, 2f /* CTI Group */
659 mov 8, %g1 /* IEU0 */
660 sub %g1, %g2, %g2 /* IEU0 Group */
661 sub %o2, %g2, %o2 /* IEU0 Group */
6621: ldub [%o1], %g5 /* Load Group */
663 add %o1, 1, %o1 /* IEU0 */
664 add %o0, 1, %o0 /* IEU1 */
665 subcc %g2, 1, %g2 /* IEU1 Group */
666 bne,pt %xcc, 1b /* CTI */
667 stb %g5, [%o0 - 1] /* Store */
6682: andn %o2, 7, %g5 /* IEU0 Group */
669 and %o2, 7, %o2 /* IEU1 */
670 fmovd %f0, %f2 /* FPU */
671 alignaddr %o1, %g0, %g1 /* GRU Group */
672 ldd [%g1], %f4 /* Load Group */
6731: ldd [%g1 + 0x8], %f6 /* Load Group */
674 add %g1, 0x8, %g1 /* IEU0 Group */
675 subcc %g5, 8, %g5 /* IEU1 */
676 faligndata %f4, %f6, %f0 /* GRU Group */
677 std %f0, [%o0] /* Store */
678 add %o1, 8, %o1 /* IEU0 Group */
679 be,pn %xcc, 213f /* CTI */
680 add %o0, 8, %o0 /* IEU1 */
681 ldd [%g1 + 0x8], %f4 /* Load Group */
682 add %g1, 8, %g1 /* IEU0 */
683 subcc %g5, 8, %g5 /* IEU1 */
684 faligndata %f6, %f4, %f0 /* GRU Group */
685 std %f0, [%o0] /* Store */
686 add %o1, 8, %o1 /* IEU0 */
687 bne,pn %xcc, 1b /* CTI Group */
688 add %o0, 8, %o0 /* IEU0 */
689213: brz,pn %o2, 214f /* CTI Group */
690 nop /* IEU0 */
691 ldub [%o1], %g5 /* LOAD */
692 add %o1, 1, %o1 /* IEU0 */
693 add %o0, 1, %o0 /* IEU1 */
694 subcc %o2, 1, %o2 /* IEU1 */
695 bne,pt %xcc, 206b /* CTI */
696 stb %g5, [%o0 - 1] /* Store Group */
697214: wr %g0, FPRS_FEF, %fprs
698 retl
699 mov %g4, %o0
700END(memcpy)
701libc_hidden_def(memcpy)
702
703 .align 32
704228: andcc %o2, 1, %g0 /* IEU1 Group */
705 be,pt %icc, 2f+4 /* CTI */
7061: ldub [%o1 - 1], %o5 /* LOAD Group */
707 sub %o1, 1, %o1 /* IEU0 */
708 sub %o0, 1, %o0 /* IEU1 */
709 subcc %o2, 1, %o2 /* IEU1 Group */
710 be,pn %xcc, 229f /* CTI */
711 stb %o5, [%o0] /* Store */
7122: ldub [%o1 - 1], %o5 /* LOAD Group */
713 sub %o0, 2, %o0 /* IEU0 */
714 ldub [%o1 - 2], %g5 /* LOAD Group */
715 sub %o1, 2, %o1 /* IEU0 */
716 subcc %o2, 2, %o2 /* IEU1 Group */
717 stb %o5, [%o0 + 1] /* Store */
718 bne,pt %xcc, 2b /* CTI */
719 stb %g5, [%o0] /* Store */
720229: retl
721 mov %g4, %o0
722219: retl
723 nop
724
725 .align 32
726ENTRY(memmove)
727#ifndef USE_BPR
728 srl %o2, 0, %o2 /* IEU1 Group */
729#endif
730 brz,pn %o2, 219b /* CTI Group */
731 sub %o0, %o1, %o4 /* IEU0 */
732 cmp %o4, %o2 /* IEU1 Group */
733 bgeu,pt %XCC, 218b /* CTI */
734 mov %o0, %g4 /* IEU0 */
735 add %o0, %o2, %o0 /* IEU0 Group */
736220: add %o1, %o2, %o1 /* IEU1 */
737 cmp %o2, 15 /* IEU1 Group */
738 bleu,pn %xcc, 228b /* CTI */
739 andcc %o0, 7, %g2 /* IEU1 Group */
740 sub %o0, %o1, %g5 /* IEU0 */
741 andcc %g5, 3, %o5 /* IEU1 Group */
742 bne,pn %xcc, 232f /* CTI */
743 andcc %o1, 3, %g0 /* IEU1 Group */
744 be,a,pt %xcc, 236f /* CTI */
745 andcc %o1, 4, %g0 /* IEU1 Group */
746 andcc %o1, 1, %g0 /* IEU1 Group */
747 be,pn %xcc, 4f /* CTI */
748 andcc %o1, 2, %g0 /* IEU1 Group */
749 ldub [%o1 - 1], %g2 /* Load Group */
750 sub %o1, 1, %o1 /* IEU0 */
751 sub %o0, 1, %o0 /* IEU1 */
752 sub %o2, 1, %o2 /* IEU0 Group */
753 be,pn %xcc, 5f /* CTI Group */
754 stb %g2, [%o0] /* Store */
7554: lduh [%o1 - 2], %g2 /* Load Group */
756 sub %o1, 2, %o1 /* IEU0 */
757 sub %o0, 2, %o0 /* IEU1 */
758 sub %o2, 2, %o2 /* IEU0 */
759 sth %g2, [%o0] /* Store Group + bubble */
7605: andcc %o1, 4, %g0 /* IEU1 */
761236: be,a,pn %xcc, 2f /* CTI */
762 andcc %o2, -128, %g6 /* IEU1 Group */
763 lduw [%o1 - 4], %g5 /* Load Group */
764 sub %o1, 4, %o1 /* IEU0 */
765 sub %o0, 4, %o0 /* IEU1 */
766 sub %o2, 4, %o2 /* IEU0 Group */
767 stw %g5, [%o0] /* Store */
768 andcc %o2, -128, %g6 /* IEU1 Group */
7692: be,pn %xcc, 235f /* CTI */
770 andcc %o0, 4, %g0 /* IEU1 Group */
771 be,pn %xcc, 282f + 4 /* CTI Group */
7725: RMOVE_BIGCHUNK(o1, o0, 0x00, g1, g3, g5, o5)
773 RMOVE_BIGCHUNK(o1, o0, 0x20, g1, g3, g5, o5)
774 RMOVE_BIGCHUNK(o1, o0, 0x40, g1, g3, g5, o5)
775 RMOVE_BIGCHUNK(o1, o0, 0x60, g1, g3, g5, o5)
776 subcc %g6, 128, %g6 /* IEU1 Group */
777 sub %o1, 128, %o1 /* IEU0 */
778 bne,pt %xcc, 5b /* CTI */
779 sub %o0, 128, %o0 /* IEU0 Group */
780235: andcc %o2, 0x70, %g6 /* IEU1 Group */
78141: be,pn %xcc, 280f /* CTI */
782 andcc %o2, 8, %g0 /* IEU1 Group */
783 /* Clk1 8-( */
784 /* Clk2 8-( */
785 /* Clk3 8-( */
786 /* Clk4 8-( */
787279: rd %pc, %o5 /* PDU Group */
788 sll %g6, 1, %g5 /* IEU0 Group */
789 sub %o1, %g6, %o1 /* IEU1 */
790 sub %o5, %g5, %o5 /* IEU0 Group */
791 jmpl %o5 + %lo(280f - 279b), %g0 /* CTI Group brk forced*/
792 sub %o0, %g6, %o0 /* IEU0 Group */
793 RMOVE_LASTCHUNK(o1, o0, 0x60, g2, g3, g5, o5)
794 RMOVE_LASTCHUNK(o1, o0, 0x50, g2, g3, g5, o5)
795 RMOVE_LASTCHUNK(o1, o0, 0x40, g2, g3, g5, o5)
796 RMOVE_LASTCHUNK(o1, o0, 0x30, g2, g3, g5, o5)
797 RMOVE_LASTCHUNK(o1, o0, 0x20, g2, g3, g5, o5)
798 RMOVE_LASTCHUNK(o1, o0, 0x10, g2, g3, g5, o5)
799 RMOVE_LASTCHUNK(o1, o0, 0x00, g2, g3, g5, o5)
800280: be,pt %xcc, 281f /* CTI */
801 andcc %o2, 4, %g0 /* IEU1 */
802 ldx [%o1 - 8], %g2 /* Load Group */
803 sub %o0, 8, %o0 /* IEU0 */
804 stw %g2, [%o0 + 4] /* Store Group */
805 sub %o1, 8, %o1 /* IEU1 */
806 srlx %g2, 32, %g2 /* IEU0 Group */
807 stw %g2, [%o0] /* Store */
808281: be,pt %xcc, 1f /* CTI */
809 andcc %o2, 2, %g0 /* IEU1 Group */
810 lduw [%o1 - 4], %g2 /* Load Group */
811 sub %o1, 4, %o1 /* IEU0 */
812 stw %g2, [%o0 - 4] /* Store Group */
813 sub %o0, 4, %o0 /* IEU0 */
8141: be,pt %xcc, 1f /* CTI */
815 andcc %o2, 1, %g0 /* IEU1 Group */
816 lduh [%o1 - 2], %g2 /* Load Group */
817 sub %o1, 2, %o1 /* IEU0 */
818 sth %g2, [%o0 - 2] /* Store Group */
819 sub %o0, 2, %o0 /* IEU0 */
8201: be,pt %xcc, 211f /* CTI */
821 nop /* IEU1 */
822 ldub [%o1 - 1], %g2 /* Load Group */
823 stb %g2, [%o0 - 1] /* Store Group + bubble */
824211: retl
825 mov %g4, %o0
826
827282: RMOVE_BIGALIGNCHUNK(o1, o0, 0x00, g1, g3, g5, o5)
828 RMOVE_BIGALIGNCHUNK(o1, o0, 0x40, g1, g3, g5, o5)
829 subcc %g6, 128, %g6 /* IEU1 Group */
830 sub %o1, 128, %o1 /* IEU0 */
831 bne,pt %xcc, 282b /* CTI */
832 sub %o0, 128, %o0 /* IEU0 Group */
833 andcc %o2, 0x70, %g6 /* IEU1 */
834 be,pn %xcc, 284f /* CTI */
835 andcc %o2, 8, %g0 /* IEU1 Group */
836 /* Clk1 8-( */
837 /* Clk2 8-( */
838 /* Clk3 8-( */
839 /* Clk4 8-( */
840283: rd %pc, %o5 /* PDU Group */
841 sub %o1, %g6, %o1 /* IEU0 Group */
842 sub %o5, %g6, %o5 /* IEU1 */
843 jmpl %o5 + %lo(284f - 283b), %g0 /* CTI Group brk forced*/
844 sub %o0, %g6, %o0 /* IEU0 Group */
845 RMOVE_LASTALIGNCHUNK(o1, o0, 0x60, g2, g3)
846 RMOVE_LASTALIGNCHUNK(o1, o0, 0x50, g2, g3)
847 RMOVE_LASTALIGNCHUNK(o1, o0, 0x40, g2, g3)
848 RMOVE_LASTALIGNCHUNK(o1, o0, 0x30, g2, g3)
849 RMOVE_LASTALIGNCHUNK(o1, o0, 0x20, g2, g3)
850 RMOVE_LASTALIGNCHUNK(o1, o0, 0x10, g2, g3)
851 RMOVE_LASTALIGNCHUNK(o1, o0, 0x00, g2, g3)
852284: be,pt %xcc, 285f /* CTI Group */
853 andcc %o2, 4, %g0 /* IEU1 */
854 ldx [%o1 - 8], %g2 /* Load Group */
855 sub %o0, 8, %o0 /* IEU0 */
856 sub %o1, 8, %o1 /* IEU0 Group */
857 stx %g2, [%o0] /* Store */
858285: be,pt %xcc, 1f /* CTI */
859 andcc %o2, 2, %g0 /* IEU1 Group */
860 lduw [%o1 - 4], %g2 /* Load Group */
861 sub %o0, 4, %o0 /* IEU0 */
862 sub %o1, 4, %o1 /* IEU0 Group */
863 stw %g2, [%o0] /* Store */
8641: be,pt %xcc, 1f /* CTI */
865 andcc %o2, 1, %g0 /* IEU1 Group */
866 lduh [%o1 - 2], %g2 /* Load Group */
867 sub %o0, 2, %o0 /* IEU0 */
868 sub %o1, 2, %o1 /* IEU0 Group */
869 sth %g2, [%o0] /* Store */
8701: be,pt %xcc, 1f /* CTI */
871 nop /* IEU0 Group */
872 ldub [%o1 - 1], %g2 /* Load Group */
873 stb %g2, [%o0 - 1] /* Store Group + bubble */
8741: retl
875 mov %g4, %o0
876
877232: brz,pt %g2, 2f /* CTI Group */
878 sub %o2, %g2, %o2 /* IEU0 Group */
8791: ldub [%o1 - 1], %g5 /* Load Group */
880 sub %o1, 1, %o1 /* IEU0 */
881 sub %o0, 1, %o0 /* IEU1 */
882 subcc %g2, 1, %g2 /* IEU1 Group */
883 bne,pt %xcc, 1b /* CTI */
884 stb %g5, [%o0] /* Store */
8852: andn %o2, 7, %g5 /* IEU0 Group */
886 and %o2, 7, %o2 /* IEU1 */
887 fmovd %f0, %f2 /* FPU */
888 alignaddr %o1, %g0, %g1 /* GRU Group */
889 ldd [%g1], %f4 /* Load Group */
8901: ldd [%g1 - 8], %f6 /* Load Group */
891 sub %g1, 8, %g1 /* IEU0 Group */
892 subcc %g5, 8, %g5 /* IEU1 */
893 faligndata %f6, %f4, %f0 /* GRU Group */
894 std %f0, [%o0 - 8] /* Store */
895 sub %o1, 8, %o1 /* IEU0 Group */
896 be,pn %xcc, 233f /* CTI */
897 sub %o0, 8, %o0 /* IEU1 */
898 ldd [%g1 - 8], %f4 /* Load Group */
899 sub %g1, 8, %g1 /* IEU0 */
900 subcc %g5, 8, %g5 /* IEU1 */
901 faligndata %f4, %f6, %f0 /* GRU Group */
902 std %f0, [%o0 - 8] /* Store */
903 sub %o1, 8, %o1 /* IEU0 */
904 bne,pn %xcc, 1b /* CTI Group */
905 sub %o0, 8, %o0 /* IEU0 */
906233: brz,pn %o2, 234f /* CTI Group */
907 nop /* IEU0 */
908237: ldub [%o1 - 1], %g5 /* LOAD */
909 sub %o1, 1, %o1 /* IEU0 */
910 sub %o0, 1, %o0 /* IEU1 */
911 subcc %o2, 1, %o2 /* IEU1 */
912 bne,pt %xcc, 237b /* CTI */
913 stb %g5, [%o0] /* Store Group */
914234: wr %g0, FPRS_FEF, %fprs
915 retl
916 mov %g4, %o0
917END(memmove)
918libc_hidden_def(memmove)
919
920#ifdef USE_BPR
921weak_alias(memcpy,__align_cpy_1)
922weak_alias(memcpy,__align_cpy_2)
923#endif