summaryrefslogtreecommitdiff
path: root/configs/splash2/cluster.py
blob: f819bd19e45de682a576e4047a45f867226c89cc (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
# Copyright (c) 2006-2007 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: Ron Dreslinski

# Simple test script
#
# "m5 test.py"

from __future__ import print_function

import os
import optparse
import sys

import m5
from m5.objects import *

# --------------------
# Define Command Line Options
# ====================

parser = optparse.OptionParser()

parser.add_option("-d", "--detailed", action="store_true")
parser.add_option("-t", "--timing", action="store_true")
parser.add_option("-m", "--maxtick", type="int")
parser.add_option("-c", "--numclusters",
                  help="Number of clusters", type="int")
parser.add_option("-n", "--numcpus",
                  help="Number of cpus in total", type="int")
parser.add_option("-f", "--frequency",
                  default = "1GHz",
                  help="Frequency of each CPU")
parser.add_option("--l1size",
                  default = "32kB")
parser.add_option("--l1latency",
                  default = 1)
parser.add_option("--l2size",
                  default = "256kB")
parser.add_option("--l2latency",
                  default = 10)
parser.add_option("--rootdir",
                  help="ROot directory of Splash2",
                  default="/dist/splash2/codes/")
parser.add_option("-b", "--benchmark",
                  help="Splash 2 benchmark to run")

(options, args) = parser.parse_args()

if args:
    print("Error: script doesn't take any positional arguments")
    sys.exit(1)

# --------------------
# Define Splash2 Benchmarks
# ====================
class Cholesky(Process):
        executable = options.rootdir + '/kernels/cholesky/CHOLESKY'
        cmd = 'CHOLESKY -p' + str(options.numcpus) + ' '\
             + options.rootdir + '/kernels/cholesky/inputs/tk23.O'

class FFT(Process):
        executable = options.rootdir + 'kernels/fft/FFT'
        cmd = 'FFT -p' + str(options.numcpus) + ' -m18'

class LU_contig(Process):
        executable = options.rootdir + 'kernels/lu/contiguous_blocks/LU'
        cmd = 'LU -p' + str(options.numcpus)

class LU_noncontig(Process):
        executable = options.rootdir + 'kernels/lu/non_contiguous_blocks/LU'
        cmd = 'LU -p' + str(options.numcpus)

class Radix(Process):
        executable = options.rootdir + 'kernels/radix/RADIX'
        cmd = 'RADIX -n524288 -p' + str(options.numcpus)

class Barnes(Process):
        executable = options.rootdir + 'apps/barnes/BARNES'
        cmd = 'BARNES'
        input = options.rootdir + 'apps/barnes/input.p' + str(options.numcpus)

class FMM(Process):
        executable = options.rootdir + 'apps/fmm/FMM'
        cmd = 'FMM'
        input = options.rootdir + 'apps/fmm/inputs/input.2048.p' + str(options.numcpus)

class Ocean_contig(Process):
        executable = options.rootdir + 'apps/ocean/contiguous_partitions/OCEAN'
        cmd = 'OCEAN -p' + str(options.numcpus)

class Ocean_noncontig(Process):
        executable = options.rootdir + 'apps/ocean/non_contiguous_partitions/OCEAN'
        cmd = 'OCEAN -p' + str(options.numcpus)

class Raytrace(Process):
        executable = options.rootdir + 'apps/raytrace/RAYTRACE'
        cmd = 'RAYTRACE -p' + str(options.numcpus) + ' ' \
             + options.rootdir + 'apps/raytrace/inputs/teapot.env'

class Water_nsquared(Process):
        executable = options.rootdir + 'apps/water-nsquared/WATER-NSQUARED'
        cmd = 'WATER-NSQUARED'
        input = options.rootdir + 'apps/water-nsquared/input.p' + str(options.numcpus)

class Water_spatial(Process):
        executable = options.rootdir + 'apps/water-spatial/WATER-SPATIAL'
        cmd = 'WATER-SPATIAL'
        input = options.rootdir + 'apps/water-spatial/input.p' + str(options.numcpus)


# --------------------
# Base L1 Cache Definition
# ====================

class L1(Cache):
    latency = options.l1latency
    mshrs = 12
    tgts_per_mshr = 8

# ----------------------
# Base L2 Cache Definition
# ----------------------

class L2(Cache):
    latency = options.l2latency
    mshrs = 92
    tgts_per_mshr = 16
    write_buffers = 8

# ----------------------
# Define the clusters with their cpus
# ----------------------
class Cluster:
    pass

cpusPerCluster = options.numcpus/options.numclusters

busFrequency = Frequency(options.frequency)
busFrequency *= cpusPerCluster

all_cpus = []
all_l1s = []
all_l1buses = []
if options.timing:
    clusters = [ Cluster() for i in xrange(options.numclusters)]
    for j in xrange(options.numclusters):
        clusters[j].id = j
    for cluster in clusters:
        cluster.clusterbus = L2XBar(clock=busFrequency)
        all_l1buses += [cluster.clusterbus]
        cluster.cpus = [TimingSimpleCPU(cpu_id = i + cluster.id,
                                        clock=options.frequency)
                        for i in xrange(cpusPerCluster)]
        all_cpus += cluster.cpus
        cluster.l1 = L1(size=options.l1size, assoc = 4)
        all_l1s += [cluster.l1]
elif options.detailed:
    clusters = [ Cluster() for i in xrange(options.numclusters)]
    for j in xrange(options.numclusters):
        clusters[j].id = j
    for cluster in clusters:
        cluster.clusterbus = L2XBar(clock=busFrequency)
        all_l1buses += [cluster.clusterbus]
        cluster.cpus = [DerivO3CPU(cpu_id = i + cluster.id,
                                   clock=options.frequency)
                        for i in xrange(cpusPerCluster)]
        all_cpus += cluster.cpus
        cluster.l1 = L1(size=options.l1size, assoc = 4)
        all_l1s += [cluster.l1]
else:
    clusters = [ Cluster() for i in xrange(options.numclusters)]
    for j in xrange(options.numclusters):
        clusters[j].id = j
    for cluster in clusters:
        cluster.clusterbus = L2XBar(clock=busFrequency)
        all_l1buses += [cluster.clusterbus]
        cluster.cpus = [AtomicSimpleCPU(cpu_id = i + cluster.id,
                                        clock=options.frequency)
                        for i in xrange(cpusPerCluster)]
        all_cpus += cluster.cpus
        cluster.l1 = L1(size=options.l1size, assoc = 4)
        all_l1s += [cluster.l1]

# ----------------------
# Create a system, and add system wide objects
# ----------------------
system = System(cpu = all_cpus, l1_ = all_l1s, l1bus_ = all_l1buses,
                physmem = SimpleMemory(),
                membus = SystemXBar(clock = busFrequency))
system.clock = '1GHz'

system.toL2bus = L2XBar(clock = busFrequency)
system.l2 = L2(size = options.l2size, assoc = 8)

# ----------------------
# Connect the L2 cache and memory together
# ----------------------

system.physmem.port = system.membus.master
system.l2.cpu_side = system.toL2bus.slave
system.l2.mem_side = system.membus.master

# ----------------------
# Connect the L2 cache and clusters together
# ----------------------
for cluster in clusters:
    cluster.l1.cpu_side = cluster.clusterbus.master
    cluster.l1.mem_side = system.toL2bus.slave
    for cpu in cluster.cpus:
        cpu.icache_port = cluster.clusterbus.slave
        cpu.dcache_port = cluster.clusterbus.slave

# ----------------------
# Define the root
# ----------------------

root = Root(full_system = False, system = system)

# --------------------
# Pick the correct Splash2 Benchmarks
# ====================
if options.benchmark == 'Cholesky':
    root.workload = Cholesky()
elif options.benchmark == 'FFT':
    root.workload = FFT()
elif options.benchmark == 'LUContig':
    root.workload = LU_contig()
elif options.benchmark == 'LUNoncontig':
    root.workload = LU_noncontig()
elif options.benchmark == 'Radix':
    root.workload = Radix()
elif options.benchmark == 'Barnes':
    root.workload = Barnes()
elif options.benchmark == 'FMM':
    root.workload = FMM()
elif options.benchmark == 'OceanContig':
    root.workload = Ocean_contig()
elif options.benchmark == 'OceanNoncontig':
    root.workload = Ocean_noncontig()
elif options.benchmark == 'Raytrace':
    root.workload = Raytrace()
elif options.benchmark == 'WaterNSquared':
    root.workload = Water_nsquared()
elif options.benchmark == 'WaterSpatial':
    root.workload = Water_spatial()
else:
    m5.util.panic("""
The --benchmark environment variable was set to something improper.
Use Cholesky, FFT, LUContig, LUNoncontig, Radix, Barnes, FMM, OceanContig,
OceanNoncontig, Raytrace, WaterNSquared, or WaterSpatial
""")

# --------------------
# Assign the workload to the cpus
# ====================

for cluster in clusters:
    for cpu in cluster.cpus:
        cpu.workload = root.workload

# ----------------------
# Run the simulation
# ----------------------

if options.timing or options.detailed:
    root.system.mem_mode = 'timing'

# instantiate configuration
m5.instantiate()

# simulate until program terminates
if options.maxtick:
    exit_event = m5.simulate(options.maxtick)
else:
    exit_event = m5.simulate(m5.MaxTick)

print('Exiting @ tick', m5.curTick(), 'because', exit_event.getCause())