summaryrefslogtreecommitdiff
path: root/src/arch/micro_asm.py
blob: 14502947750d3628bff32dd38994f0019343b3b3 (plain)
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
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
# Copyright (c) 2003-2005 The Regents of The University of Michigan
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met: redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer;
# redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution;
# neither the name of the copyright holders nor the names of its
# contributors may be used to endorse or promote products derived from
# this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#
# Authors: Gabe Black

import os
import sys
import re
import string
import traceback
# get type names
from types import *

# Prepend the directory where the PLY lex & yacc modules are found
# to the search path.
sys.path[0:0] = [os.environ['M5_PLY']]

from ply import lex
from ply import yacc

##########################################################################
#
# Base classes for use outside of the assembler
#
##########################################################################

class Micro_Container(object):
    def __init__(self, name):
        self.microops = []
        self.name = name
        self.directives = {}
        self.micro_classes = {}
        self.labels = {}

    def add_microop(self, microop):
        self.microops.append(microop)

    def __str__(self):
        string = "%s:\n" % self.name
        for microop in self.microops:
            string += "  %s\n" % microop
        return string

class Combinational_Macroop(Micro_Container):
    pass

class Rom_Macroop(object):
    def __init__(self, name, target):
        self.name = name
        self.target = target

    def __str__(self):
        return "%s: %s\n" % (self.name, self.target)

class Rom(Micro_Container):
    def __init__(self, name):
        super(Rom, self).__init__(name)
        self.externs = {}

##########################################################################
#
# Support classes
#
##########################################################################

class Label(object):
    def __init__(self):
        self.extern = False
        self.name = ""

class Block(object):
    def __init__(self):
        self.statements = []

class Statement(object):
    def __init__(self):
        self.is_microop = False
        self.is_directive = False
        self.params = ""

class Microop(Statement):
    def __init__(self):
        super(Microop, self).__init__()
        self.mnemonic = ""
        self.labels = []
        self.is_microop = True

class Directive(Statement):
    def __init__(self):
        super(Directive, self).__init__()
        self.name = ""
        self.is_directive = True

##########################################################################
#
# Functions that handle common tasks
#
##########################################################################

def print_error(message):
    print
    print "*** %s" % message
    print

def handle_statement(parser, container, statement):
    if statement.is_microop:
        try:
            microop = eval('parser.microops[statement.mnemonic](%s)' %
                    statement.params)
        except:
            print_error("Error creating microop object with mnemonic %s." % \
                    statement.mnemonic)
            raise
        try:
            for label in statement.labels:
                container.labels[label.name] = microop
                if label.extern:
                    container.externs[label.name] = microop
            container.add_microop(microop)
        except:
            print_error("Error adding microop.")
            raise
    elif statement.is_directive:
        try:
            eval('container.directives[statement.name](%s)' % statement.params)
        except:
            print_error("Error executing directive.")
            print container.directives
            raise
    else:
        raise Exception, "Didn't recognize the type of statement", statement

##########################################################################
#
# Lexer specification
#
##########################################################################

# Error handler.  Just call exit.  Output formatted to work under
# Emacs compile-mode.  Optional 'print_traceback' arg, if set to True,
# prints a Python stack backtrace too (can be handy when trying to
# debug the parser itself).
def error(lineno, string, print_traceback = False):
    # Print a Python stack backtrace if requested.
    if (print_traceback):
        traceback.print_exc()
    if lineno != 0:
        line_str = "%d:" % lineno
    else:
        line_str = ""
    sys.exit("%s %s" % (line_str, string))

reserved = ('DEF', 'MACROOP', 'ROM', 'EXTERN')

tokens = reserved + (
        # identifier
        'ID',
        # arguments for microops and directives
        'PARAMS',

        'LPAREN', 'RPAREN',
        'LBRACE', 'RBRACE',
        'COLON', 'SEMI', 'DOT',
        'NEWLINE'
        )

# New lines are ignored at the top level, but they end statements in the
# assembler
states = (
    ('asm', 'exclusive'),
    ('params', 'exclusive'),
)

reserved_map = { }
for r in reserved:
    reserved_map[r.lower()] = r

# Ignore comments
def t_ANY_COMMENT(t):
    r'\#[^\n]*(?=\n)'

def t_ANY_MULTILINECOMMENT(t):
    r'/\*([^/]|((?<!\*)/))*\*/'

# A colon marks the end of a label. It should follow an ID which will
# put the lexer in the "params" state. Seeing the colon will put it back
# in the "asm" state since it knows it saw a label and not a mnemonic.
def t_params_COLON(t):
    r':'
    t.lexer.begin('asm')
    return t

# An "ID" in the micro assembler is either a label, directive, or mnemonic
# If it's either a directive or a mnemonic, it will be optionally followed by
# parameters. If it's a label, the following colon will make the lexer stop
# looking for parameters.
def t_asm_ID(t):
    r'[A-Za-z_]\w*'
    t.type = reserved_map.get(t.value, 'ID')
    t.lexer.begin('params')
    return t

# If there is a label and you're -not- in the assember (which would be caught
# above), don't start looking for parameters.
def t_ANY_ID(t):
    r'[A-Za-z_]\w*'
    t.type = reserved_map.get(t.value, 'ID')
    return t

# Parameters are a string of text which don't contain an unescaped statement
# statement terminator, ie a newline or semi colon.
def t_params_PARAMS(t):
    r'([^\n;\\]|(\\[\n;\\]))+'
    t.lineno += t.value.count('\n')
    unescapeParamsRE = re.compile(r'(\\[\n;\\])')
    def unescapeParams(mo):
        val = mo.group(0)
        print "About to sub %s for %s" % (val[1], val)
        return val[1]
    print "Looking for matches in %s" % t.value
    t.value = unescapeParamsRE.sub(unescapeParams, t.value)
    t.lexer.begin('asm')
    return t

# Braces enter and exit micro assembly
def t_INITIAL_LBRACE(t):
    r'\{'
    t.lexer.begin('asm')
    return t

def t_asm_RBRACE(t):
    r'\}'
    t.lexer.begin('INITIAL')
    return t

# At the top level, keep track of newlines only for line counting.
def t_INITIAL_NEWLINE(t):
    r'\n+'
    t.lineno += t.value.count('\n')

# In the micro assembler, do line counting but also return a token. The
# token is needed by the parser to detect the end of a statement.
def t_asm_NEWLINE(t):
    r'\n+'
    t.lineno += t.value.count('\n')
    return t

# A newline or semi colon when looking for params signals that the statement
# is over and the lexer should go back to looking for regular assembly.
def t_params_NEWLINE(t):
    r'\n+'
    t.lineno += t.value.count('\n')
    t.lexer.begin('asm')
    return t

def t_params_SEMI(t):
    r';'
    t.lexer.begin('asm')
    return t

# Basic regular expressions to pick out simple tokens
t_ANY_LPAREN = r'\('
t_ANY_RPAREN = r'\)'
t_ANY_SEMI   = r';'
t_ANY_DOT    = r'\.'

t_ANY_ignore = ' \t\x0c'

def t_ANY_error(t):
    error(t.lineno, "illegal character '%s'" % t.value[0])
    t.skip(1)

##########################################################################
#
# Parser specification
#
##########################################################################

# Start symbol for a file which may have more than one macroop or rom
# specification.
def p_file(t):
    'file : opt_rom_or_macros'

def p_opt_rom_or_macros_0(t):
    'opt_rom_or_macros : '

def p_opt_rom_or_macros_1(t):
    'opt_rom_or_macros : rom_or_macros'

def p_rom_or_macros_0(t):
    'rom_or_macros : rom_or_macro'

def p_rom_or_macros_1(t):
    'rom_or_macros : rom_or_macros rom_or_macro'

def p_rom_or_macro_0(t):
    '''rom_or_macro : rom_block
                    | macroop_def'''

# Defines a section of microcode that should go in the current ROM
def p_rom_block(t):
    'rom_block : DEF ROM block SEMI'
    if not t.parser.rom:
        print_error("Rom block found, but no Rom object specified.")
        raise TypeError, "Rom block found, but no Rom object was specified."
    for statement in t[3].statements:
        handle_statement(t.parser, t.parser.rom, statement)
    t[0] = t.parser.rom

# Defines a macroop that jumps to an external label in the ROM
def p_macroop_def_0(t):
    'macroop_def : DEF MACROOP ID LPAREN ID RPAREN SEMI'
    if not t.parser.rom_macroop_type:
        print_error("ROM based macroop found, but no ROM macroop class was specified.")
        raise TypeError, "ROM based macroop found, but no ROM macroop class was specified."
    macroop = t.parser.rom_macroop_type(t[3], t[5])
    t.parser.macroops[t[3]] = macroop


# Defines a macroop that is combinationally generated
def p_macroop_def_1(t):
    'macroop_def : DEF MACROOP ID block SEMI'
    try:
        curop = t.parser.macro_type(t[3])
    except TypeError:
        print_error("Error creating macroop object.")
        raise
    for statement in t[4].statements:
        handle_statement(t.parser, curop, statement)
    t.parser.macroops[t[3]] = curop

# A block of statements
def p_block(t):
    'block : LBRACE statements RBRACE'
    block = Block()
    block.statements = t[2]
    t[0] = block

def p_statements_0(t):
    'statements : statement'
    if t[1]:
        t[0] = [t[1]]
    else:
        t[0] = []

def p_statements_1(t):
    'statements : statements statement'
    if t[2]:
        t[1].append(t[2])
    t[0] = t[1]

def p_statement(t):
    'statement : content_of_statement end_of_statement'
    t[0] = t[1]

# A statement can be a microop or an assembler directive
def p_content_of_statement_0(t):
    '''content_of_statement : microop
                            | directive'''
    t[0] = t[1]

# Ignore empty statements
def p_content_of_statement_1(t):
    'content_of_statement : '
    pass

# Statements are ended by newlines or a semi colon
def p_end_of_statement(t):
    '''end_of_statement : NEWLINE
                        | SEMI'''
    pass

# Different flavors of microop to avoid shift/reduce errors
def p_microop_0(t):
    'microop : labels ID'
    microop = Microop()
    microop.labels = t[1]
    microop.mnemonic = t[2]
    t[0] = microop

def p_microop_1(t):
    'microop : ID'
    microop = Microop()
    microop.mnemonic = t[1]
    t[0] = microop

def p_microop_2(t):
    'microop : labels ID PARAMS'
    microop = Microop()
    microop.labels = t[1]
    microop.mnemonic = t[2]
    microop.params = t[3]
    t[0] = microop

def p_microop_3(t):
    'microop : ID PARAMS'
    microop = Microop()
    microop.mnemonic = t[1]
    microop.params = t[2]
    t[0] = microop

# Labels in the microcode
def p_labels_0(t):
    'labels : label'
    t[0] = [t[1]]

def p_labels_1(t):
    'labels : labels label'
    t[1].append(t[2])
    t[0] = t[1]

def p_label_0(t):
    'label : ID COLON'
    label = Label()
    label.is_extern = False
    label.text = t[1]
    t[0] = label

def p_label_1(t):
    'label : EXTERN ID COLON'
    label = Label()
    label.is_extern = True
    label.text = t[2]
    t[0] = label

# Directives for the macroop
def p_directive_0(t):
    'directive : DOT ID'
    directive = Directive()
    directive.name = t[2]
    t[0] = directive

def p_directive_1(t):
    'directive : DOT ID PARAMS'
    directive = Directive()
    directive.name = t[2]
    directive.params = t[3]
    t[0] = directive

# Parse error handler.  Note that the argument here is the offending
# *token*, not a grammar symbol (hence the need to use t.value)
def p_error(t):
    if t:
        error(t.lineno, "syntax error at '%s'" % t.value)
    else:
        error(0, "unknown syntax error", True)

class MicroAssembler(object):

    def __init__(self, macro_type, microops,
            rom = None, rom_macroop_type = None):
        self.lexer = lex.lex()
        self.parser = yacc.yacc()
        self.parser.macro_type = macro_type
        self.parser.macroops = {}
        self.parser.microops = microops
        self.parser.rom = rom
        self.parser.rom_macroop_type = rom_macroop_type

    def assemble(self, asm):
        self.parser.parse(asm, lexer=self.lexer)
        # Begin debug printing
        for macroop in self.parser.macroops.values():
            print macroop
        print self.parser.rom
        # End debug printing
        macroops = self.parser.macroops
        self.parser.macroops = {}
        return macroops