1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346
|
/* This file defines a number of threading schemes.
Copyright (C) 1995, 1996 Free Software Foundation, Inc.
This file is part of Gforth.
Gforth is free software; you can redistribute it and/or
modify it under the terms of the GNU General Public License
as published by the Free Software Foundation; either version 2
of the License, or (at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
This files defines macros for threading. Many sets of macros are
defined. Functionally they have only one difference: Some implement
direct threading, some indirect threading. The other differences are
just variations to help GCC generate faster code for various
machines.
(Well, to tell the truth, there actually is another functional
difference in some pathological cases: e.g., a '!' stores into the
cell where the next executed word comes from; or, the next word
executed comes from the top-of-stack. These differences are one of
the reasons why GCC cannot produce the right variation by itself. We
chose disallowing such practices and using the added implementation
freedom to achieve a significant speedup, because these practices
are not common in Forth (I have never heard of or seen anyone using
them), and it is easy to circumvent problems: A control flow change
will flush any prefetched words; you may want to do a "0
drop" before that to write back the top-of-stack cache.)
These macro sets are used in the following ways: After translation
to C a typical primitive looks like
...
{
DEF_CA
other declarations
NEXT_P0;
main part of the primitive
NEXT_P1;
store results to stack
NEXT_P2;
}
DEF_CA and all the NEXT_P* together must implement NEXT; In the main
part the instruction pointer can be read with IP, changed with
INC_IP(const_inc), and the cell right behind the presently executing
word (i.e. the value of *IP) is accessed with NEXT_INST.
If a primitive does not fall through the main part, it has to do the
rest by itself. If it changes ip, it has to redo NEXT_P0 (perhaps we
should define a macro SET_IP).
Some primitives (execute, dodefer) do not end with NEXT, but with
EXEC(.). If NEXT_P0 has been called earlier, it has to perform
"ip=IP;" to ensure that ip has the right value (NEXT_P0 may change
it).
Finally, there is NEXT1_P1 and NEXT1_P2, which are parts of EXEC
(EXEC(XT) could be defined as "cfa=XT; NEXT1_P1; NEXT1_P2;" (is this
true?)) and are used for making docol faster.
We can define the ways in which these macros are used with a regular
expression:
For a primitive
DEF_CA NEXT_P0 ( IP | INC_IP | NEXT_INST | ip=...; NEXT_P0 ) * ( NEXT_P1 NEXT_P2 | EXEC(...) )
For a run-time routine, e.g., docol:
PFA1(cfa) ( NEXT_P0 NEXT | cfa=...; NEXT1_P1; NEXT1_P2 | EXEC(...) )
This comment does not yet describe all the dependences that the
macros have to satisfy.
To organize the former ifdef chaos, each path is separated
This gives a quite impressive number of paths, but you clearly
find things that go together.
It should be possible to organize the whole thing in a way that
contains less redundancy and allows a simpler description.
*/
#ifndef GETCFA
# define CFA_NEXT
#endif
#ifdef DOUBLY_INDIRECT
# define NEXT_P0 ({cfa=*ip;})
# define IP (ip)
# define NEXT_INST (cfa)
# define INC_IP(const_inc) ({cfa=IP[const_inc]; ip+=(const_inc);})
# define DEF_CA Label ca;
# define NEXT_P1 ({ip++; ca=**cfa;})
# define NEXT_P2 ({goto *ca;})
# define EXEC(XT) ({DEF_CA cfa=(XT); ca=**cfa; goto *ca;})
# define NEXT1_P1 ({ca = **cfa;})
# define NEXT1_P2 ({goto *ca;})
#else /* !defined(DOUBLY_INDIRECT) */
#if defined(DIRECT_THREADED) && defined(AUTO_INCREMENT)\
&& defined(LONG_LATENCY) && defined(CFA_NEXT)
#warning scheme 1
# define NEXT_P0 ({cfa=*ip++;})
# define IP (ip-1)
# define NEXT_INST (cfa)
# define INC_IP(const_inc) ({cfa=IP[const_inc]; ip+=(const_inc);})
# define DEF_CA
# define NEXT_P1
# define NEXT_P2 ({goto *cfa;})
# define EXEC(XT) ({cfa=(XT); goto *cfa;})
#endif
#if defined(DIRECT_THREADED) && defined(AUTO_INCREMENT)\
&& defined(LONG_LATENCY) && !defined(CFA_NEXT)
#warning scheme 2
# define NEXT_P0 (ip++)
# define IP (ip-1)
# define NEXT_INST (*(ip-1))
# define INC_IP(const_inc) ({ ip+=(const_inc);})
# define DEF_CA
# define NEXT_P1
# define NEXT_P2 ({goto **(ip-1);})
# define EXEC(XT) ({goto *(XT);})
#endif
#if defined(DIRECT_THREADED) && defined(AUTO_INCREMENT)\
&& !defined(LONG_LATENCY) && defined(CFA_NEXT)
#warning scheme 3
# define NEXT_P0
# define IP (ip)
# define NEXT_INST (*ip)
# define INC_IP(const_inc) ({ip+=(const_inc);})
# define DEF_CA
# define NEXT_P1 ({cfa=*ip++;})
# define NEXT_P2 ({goto *cfa;})
# define EXEC(XT) ({cfa=(XT); goto *cfa;})
#endif
#if defined(DIRECT_THREADED) && defined(AUTO_INCREMENT)\
&& !defined(LONG_LATENCY) && !defined(CFA_NEXT)
#warning scheme 4
# define NEXT_P0
# define IP (ip)
# define NEXT_INST (*ip)
# define INC_IP(const_inc) ({ ip+=(const_inc);})
# define DEF_CA
# define NEXT_P1
# define NEXT_P2 ({goto **(ip++);})
# define EXEC(XT) ({goto *(XT);})
#endif
/* without autoincrement */
#if defined(DIRECT_THREADED) && !defined(AUTO_INCREMENT)\
&& defined(LONG_LATENCY) && defined(CFA_NEXT)
#warning scheme 5
# define NEXT_P0 ({cfa=*ip;})
# define IP (ip)
# define NEXT_INST (cfa)
# define INC_IP(const_inc) ({cfa=IP[const_inc]; ip+=(const_inc);})
# define DEF_CA
# define NEXT_P1 (ip++)
# define NEXT_P2 ({goto *cfa;})
# define EXEC(XT) ({cfa=(XT); goto *cfa;})
#endif
#if defined(DIRECT_THREADED) && !defined(AUTO_INCREMENT)\
&& defined(LONG_LATENCY) && !defined(CFA_NEXT)
#warning scheme 6
# define NEXT_P0
# define IP (ip)
# define NEXT_INST (*ip)
# define INC_IP(const_inc) ({ip+=(const_inc);})
# define DEF_CA
# define NEXT_P1 (ip++)
# define NEXT_P2 ({goto **(ip-1);})
# define EXEC(XT) ({goto *(XT);})
#endif
#if defined(DIRECT_THREADED) && !defined(AUTO_INCREMENT)\
&& !defined(LONG_LATENCY) && defined(CFA_NEXT)
#warning scheme 7
# define NEXT_P0
# define IP (ip)
# define NEXT_INST (*ip)
# define INC_IP(const_inc) ({ip+=(const_inc);})
# define DEF_CA
# define NEXT_P1 ({cfa=*ip++;})
# define NEXT_P2 ({goto *cfa;})
# define EXEC(XT) ({cfa=(XT); goto *cfa;})
#endif
#if defined(DIRECT_THREADED) && !defined(AUTO_INCREMENT)\
&& !defined(LONG_LATENCY) && !defined(CFA_NEXT)
#warning scheme 8
# define NEXT_P0
# define IP (ip)
# define NEXT_INST (*IP)
# define INC_IP(const_inc) ({ ip+=(const_inc);})
# define DEF_CA
# define NEXT_P1 (ip++)
# define NEXT_P2 ({goto **(ip-1);})
# define EXEC(XT) ({goto *(XT);})
#endif
/* common settings for direct THREADED */
/* indirect THREADED */
#if !defined(DIRECT_THREADED) && defined(AUTO_INCREMENT)\
&& defined(LONG_LATENCY) && defined(CISC_NEXT)
# define NEXT_P0 ({cfa=*ip++;})
# define IP (ip-1)
# define NEXT_INST (cfa)
# define INC_IP(const_inc) ({cfa=IP[const_inc]; ip+=(const_inc);})
# define DEF_CA
# define NEXT_P1
# define NEXT_P2 ({goto **cfa;})
# define EXEC(XT) ({cfa=(XT); goto **cfa;})
#endif
#if !defined(DIRECT_THREADED) && defined(AUTO_INCREMENT)\
&& defined(LONG_LATENCY) && !defined(CISC_NEXT)
# define NEXT_P0 ({cfa=*ip++;})
# define IP (ip-1)
# define NEXT_INST (cfa)
# define INC_IP(const_inc) ({cfa=IP[const_inc]; ip+=(const_inc);})
# define DEF_CA Label ca;
# define NEXT_P1 ({ca=*cfa;})
# define NEXT_P2 ({goto *ca;})
# define EXEC(XT) ({DEF_CA cfa=(XT); ca=*cfa; goto *ca;})
#endif
#if !defined(DIRECT_THREADED) && defined(AUTO_INCREMENT)\
&& !defined(LONG_LATENCY) && defined(CISC_NEXT)
# define NEXT_P0
# define IP (ip)
# define NEXT_INST (*ip)
# define INC_IP(const_inc) ({ip+=(const_inc);})
# define DEF_CA
# define NEXT_P1
# define NEXT_P2 ({cfa=*ip++; goto **cfa;})
# define EXEC(XT) ({cfa=(XT); goto **cfa;})
#endif
#if !defined(DIRECT_THREADED) && defined(AUTO_INCREMENT)\
&& !defined(LONG_LATENCY) && !defined(CISC_NEXT)
# define NEXT_P0 ({cfa=*ip++;})
# define IP (ip-1)
# define NEXT_INST (cfa)
# define INC_IP(const_inc) ({cfa=IP[const_inc]; ip+=(const_inc);})
# define DEF_CA Label ca;
# define NEXT_P1 ({ca=*cfa;})
# define NEXT_P2 ({goto *ca;})
# define EXEC(XT) ({DEF_CA cfa=(XT); ca=*cfa; goto *ca;})
#endif
/* without autoincrement */
#if !defined(DIRECT_THREADED) && !defined(AUTO_INCREMENT)\
&& defined(LONG_LATENCY) && defined(CISC_NEXT)
# define NEXT_P0 ({cfa=*ip;})
# define IP (ip)
# define NEXT_INST (cfa)
# define INC_IP(const_inc) ({cfa=IP[const_inc]; ip+=(const_inc);})
# define DEF_CA
# define NEXT_P1 (ip++)
# define NEXT_P2 ({goto **cfa;})
# define EXEC(XT) ({cfa=(XT); goto **cfa;})
#endif
#if !defined(DIRECT_THREADED) && !defined(AUTO_INCREMENT)\
&& defined(LONG_LATENCY) && !defined(CISC_NEXT)
# define NEXT_P0 ({cfa=*ip;})
# define IP (ip)
# define NEXT_INST (cfa)
# define INC_IP(const_inc) ({cfa=IP[const_inc]; ip+=(const_inc);})
# define DEF_CA Label ca;
# define NEXT_P1 ({ip++; ca=*cfa;})
# define NEXT_P2 ({goto *ca;})
# define EXEC(XT) ({DEF_CA cfa=(XT); ca=*cfa; goto *ca;})
#endif
#if !defined(DIRECT_THREADED) && !defined(AUTO_INCREMENT)\
&& !defined(LONG_LATENCY) && defined(CISC_NEXT)
# define NEXT_P0
# define IP (ip)
# define NEXT_INST (*ip)
# define INC_IP(const_inc) ({ip+=(const_inc);})
# define DEF_CA
# define NEXT_P1
# define NEXT_P2 ({cfa=*ip++; goto **cfa;})
# define EXEC(XT) ({cfa=(XT); goto **cfa;})
#endif
#if !defined(DIRECT_THREADED) && !defined(AUTO_INCREMENT)\
&& !defined(LONG_LATENCY) && !defined(CISC_NEXT)
# define NEXT_P0 ({cfa=*ip;})
# define IP (ip)
# define NEXT_INST (cfa)
# define INC_IP(const_inc) ({cfa=IP[const_inc]; ip+=(const_inc);})
# define DEF_CA Label ca;
# define NEXT_P1 ({ip++; ca=*cfa;})
# define NEXT_P2 ({goto *ca;})
# define EXEC(XT) ({DEF_CA cfa=(XT); ca=*cfa; goto *ca;})
#endif
#if defined(CISC_NEXT) && !defined(LONG_LATENCY)
# define NEXT1_P1
# ifdef DIRECT_THREADED
# define NEXT1_P2 ({goto *cfa;})
# else
# define NEXT1_P2 ({goto **cfa;})
# endif /* DIRECT_THREADED */
#else /* !defined(CISC_NEXT) || defined(LONG_LATENCY) */
# ifdef DIRECT_THREADED
# define NEXT1_P1
# define NEXT1_P2 ({goto *cfa;})
# else /* !DIRECT_THREADED */
# define NEXT1_P1 ({ca = *cfa;})
# define NEXT1_P2 ({goto *ca;})
# endif /* !DIRECT_THREADED */
#endif /* !defined(CISC_NEXT) || defined(LONG_LATENCY) */
#endif /* !defined(DOUBLY_INDIRECT) */
#define NEXT ({DEF_CA NEXT_P1; NEXT_P2;})
|