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
|
#!/usr/bin/env python
# Tool for canonical RISC-V architecture string.
# Copyright (C) 2011-2022 Free Software Foundation, Inc.
# Contributed by Andrew Waterman (andrew@sifive.com).
#
# This file is part of GCC.
#
# GCC 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 3, or (at your option)
# any later version.
#
# GCC 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 GCC; see the file COPYING3. If not see
# <http://www.gnu.org/licenses/>.
# TODO: Extract riscv_subset_t from riscv-common.cc and make it can be compiled
# standalone to replace this script, that also prevents us implementing
# that twice and keep sync again and again.
from __future__ import print_function
import sys
import argparse
import collections
import itertools
from functools import reduce
SUPPORTED_ISA_SPEC = ["2.2", "20190608", "20191213"]
CANONICAL_ORDER = "imafdgqlcbjktpvn"
LONG_EXT_PREFIXES = ['z', 's', 'h', 'x']
#
# IMPLIED_EXT(ext) -> implied extension list.
#
IMPLIED_EXT = {
"d" : ["f", "zicsr"],
"f" : ["zicsr"],
"zk" : ["zkn", "zkr", "zkt"],
"zkn" : ["zbkb", "zbkc", "zbkx", "zkne", "zknd", "zknh"],
"zks" : ["zbkb", "zbkc", "zbkx", "zksed", "zksh"],
"v" : ["zvl128b", "zve64d"],
"zve32x" : ["zvl32b"],
"zve64x" : ["zve32x", "zvl64b"],
"zve32f" : ["f", "zve32x"],
"zve64f" : ["f", "zve32f", "zve64x"],
"zve64d" : ["d", "zve64f"],
"zvl64b" : ["zvl32b"],
"zvl128b" : ["zvl64b"],
"zvl256b" : ["zvl128b"],
"zvl512b" : ["zvl256b"],
"zvl1024b" : ["zvl512b"],
"zvl2048b" : ["zvl1024b"],
"zvl4096b" : ["zvl2048b"],
"zvl8192b" : ["zvl4096b"],
"zvl16384b" : ["zvl8192b"],
"zvl32768b" : ["zvl16384b"],
"zvl65536b" : ["zvl32768b"],
}
def arch_canonicalize(arch, isa_spec):
# TODO: Support extension version.
is_isa_spec_2p2 = isa_spec == '2.2'
new_arch = ""
extra_long_ext = []
if arch[:5] in ['rv32e', 'rv32i', 'rv32g', 'rv64i', 'rv64g']:
new_arch = arch[:5].replace("g", "imafd")
if arch[:5] in ['rv32g', 'rv64g']:
if not is_isa_spec_2p2:
extra_long_ext = ['zicsr', 'zifencei']
else:
raise Exception("Unexpected arch: `%s`" % arch[:5])
# Find any Z, S, H or X
long_ext_prefixes_idx = map(lambda x: arch.find(x), LONG_EXT_PREFIXES)
# Filter out any non-existent index.
long_ext_prefixes_idx = list(filter(lambda x: x != -1, long_ext_prefixes_idx))
if long_ext_prefixes_idx:
first_long_ext_idx = min(long_ext_prefixes_idx)
long_exts = arch[first_long_ext_idx:].split("_")
std_exts = list(arch[5:first_long_ext_idx])
else:
long_exts = []
std_exts = list(arch[5:])
long_exts += extra_long_ext
#
# Handle implied extensions.
#
any_change = True
while any_change:
any_change = False
for ext in std_exts + long_exts:
if ext in IMPLIED_EXT:
implied_exts = IMPLIED_EXT[ext]
for implied_ext in implied_exts:
if implied_ext == 'zicsr' and is_isa_spec_2p2:
continue
if implied_ext not in std_exts + long_exts:
long_exts.append(implied_ext)
any_change = True
# Single letter extension might appear in the long_exts list,
# becasue we just append extensions list to the arch string.
std_exts += list(filter(lambda x:len(x) == 1, long_exts))
def longext_sort (exts):
if not exts.startswith("zxm") and exts.startswith("z"):
# If "Z" extensions are named, they should be ordered first by CANONICAL.
if exts[1] not in CANONICAL_ORDER:
raise Exception("Unsupported extension `%s`" % exts)
canonical_sort = CANONICAL_ORDER.index(exts[1])
else:
canonical_sort = -1
return (exts.startswith("x"), exts.startswith("zxm"),
LONG_EXT_PREFIXES.index(exts[0]), canonical_sort, exts[1:])
# Removing duplicates.
long_exts = list(set(long_exts))
# Multi-letter extension must be in lexicographic order.
long_exts = list(sorted(filter(lambda x:len(x) != 1, long_exts),
key=longext_sort))
# Put extensions in canonical order.
for ext in CANONICAL_ORDER:
if ext in std_exts:
new_arch += ext
# Check every extension is processed.
for ext in std_exts:
if ext == '_':
continue
if ext not in CANONICAL_ORDER:
raise Exception("Unsupported extension `%s`" % ext)
# Concat rest of the multi-char extensions.
if long_exts:
new_arch += "_" + "_".join(long_exts)
return new_arch
if len(sys.argv) < 2:
print ("Usage: %s <arch_str> [<arch_str>*]" % sys.argv)
sys.exit(1)
parser = argparse.ArgumentParser()
parser.add_argument('-misa-spec', type=str,
default='20191213',
choices=SUPPORTED_ISA_SPEC)
parser.add_argument('arch_strs', nargs=argparse.REMAINDER)
args = parser.parse_args()
for arch in args.arch_strs:
print (arch_canonicalize(arch, args.misa_spec))
|
