sanchayanmaity/gem5
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
gem5/configs/common/Caches.py

92 lines
3.3 KiB
Python
Raw Normal View History

Mem: Use cycles to express cache-related latencies This patch changes the cache-related latencies from an absolute time expressed in Ticks, to a number of cycles that can be scaled with the clock period of the caches. Ultimately this patch serves to enable future work that involves dynamic frequency scaling. As an immediate benefit it also makes it more convenient to specify cache performance without implicitly assuming a specific CPU core operating frequency. The stat blocked_cycles that actually counter in ticks is now updated to count in cycles. As the timing is now rounded to the clock edges of the cache, there are some regressions that change. Plenty of them have very minor changes, whereas some regressions with a short run-time are perturbed quite significantly. A follow-on patch updates all the statistics for the regressions.
2012-10-15 14:10:54 +02:00
# Copyright (c) 2012 ARM Limited
# All rights reserved.
#
# The license below extends only to copyright in the software and shall
# not be construed as granting a license to any other intellectual
# property including but not limited to intellectual property relating
# to a hardware implementation of the functionality of the software
# licensed hereunder. You may use the software subject to the license
# terms below provided that you ensure that this notice is replicated
# unmodified and in its entirety in all distributions of the software,
# modified or unmodified, in source code or in binary form.
#
remove hit_latency and make latency do the right thing set the latency parameter in terms of a latency add caches to tsunami-simple configs configs/common/Caches.py: tests/configs/memtest.py: tests/configs/o3-timing-mp.py: tests/configs/o3-timing.py: tests/configs/simple-atomic-mp.py: tests/configs/simple-timing-mp.py: tests/configs/simple-timing.py: set the latency parameter in terms of a latency configs/common/FSConfig.py: give the bridge a default latency too src/mem/cache/cache_builder.cc: src/python/m5/objects/BaseCache.py: remove hit_latency and make latency do the right thing tests/configs/tsunami-simple-atomic-dual.py: tests/configs/tsunami-simple-atomic.py: tests/configs/tsunami-simple-timing-dual.py: tests/configs/tsunami-simple-timing.py: add caches to tsunami-simple configs --HG-- extra : convert_revision : 37bef7c652e97c8cdb91f471fba62978f89019f1
2007-05-11 00:24:48 +02:00
# Copyright (c) 2006-2007 The Regents of The University of Michigan
factor out common run code from se.py and fs.py. configs/example/fs.py: factor out common code. configs/example/se.py: factor out common code --HG-- extra : convert_revision : 72a1f653c84eae1b7d281e0a5e60ee116ad6b27d
2006-10-27 22:32:26 +02:00
# 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: Lisa Hsu
from m5.objects import *
config: Use shared cache config for regressions This patch uses the common L1, L2 and IOCache configuration for the regressions that all share the same cache parameters. There are a few regressions that use a slightly different configuration (memtest, o3-timing=mp, simple-atomic-mp and simple-timing-mp), and the latter are not changed in this patch. They will be updated in a future patch. The common cache configurations are changed to match the ones used in the regressions, and are slightly changed with respect to what they were. Hopefully this means we can converge on a common base configuration, used both in the normal user configurations and regressions. As only regressions that shared the same cache configuration are updated, no regressions are affected.
2012-10-25 10:32:44 +02:00
# Base implementations of L1, L2, IO and TLB-walker caches. There are
# used in the regressions and also as base components in the
# system-configuration scripts. The values are meant to serve as a
# starting point, and specific parameters can be overridden in the
# specific instantiations.
mem: Add explicit Cache subclass and make BaseCache abstract Open up for other subclasses to BaseCache and transition to using the explicit Cache subclass. --HG-- rename : src/mem/cache/BaseCache.py => src/mem/cache/Cache.py
2015-08-21 13:03:23 +02:00
class L1Cache(Cache):
factor out common run code from se.py and fs.py. configs/example/fs.py: factor out common code. configs/example/se.py: factor out common code --HG-- extra : convert_revision : 72a1f653c84eae1b7d281e0a5e60ee116ad6b27d
2006-10-27 22:32:26 +02:00
assoc = 2
Mem: Use cycles to express cache-related latencies This patch changes the cache-related latencies from an absolute time expressed in Ticks, to a number of cycles that can be scaled with the clock period of the caches. Ultimately this patch serves to enable future work that involves dynamic frequency scaling. As an immediate benefit it also makes it more convenient to specify cache performance without implicitly assuming a specific CPU core operating frequency. The stat blocked_cycles that actually counter in ticks is now updated to count in cycles. As the timing is now rounded to the clock edges of the cache, there are some regressions that change. Plenty of them have very minor changes, whereas some regressions with a short run-time are perturbed quite significantly. A follow-on patch updates all the statistics for the regressions.
2012-10-15 14:10:54 +02:00
hit_latency = 2
response_latency = 2
config: Use shared cache config for regressions This patch uses the common L1, L2 and IOCache configuration for the regressions that all share the same cache parameters. There are a few regressions that use a slightly different configuration (memtest, o3-timing=mp, simple-atomic-mp and simple-timing-mp), and the latter are not changed in this patch. They will be updated in a future patch. The common cache configurations are changed to match the ones used in the regressions, and are slightly changed with respect to what they were. Hopefully this means we can converge on a common base configuration, used both in the normal user configurations and regressions. As only regressions that shared the same cache configuration are updated, no regressions are affected.
2012-10-25 10:32:44 +02:00
mshrs = 4
O3: Remove hardcoded tgts_per_mshr in O3CPU.py. There are two lines in O3CPU.py that set the dcache and icache tgts_per_mshr to 20, ignoring any pre-configured value of tgts_per_mshr. This patch removes these hardcoded lines from O3CPU.py and sets the default L1 cache mshr targets to 20. --HG-- extra : rebase_source : 6f92d950e90496a3102967442814e97dc84db08b
2011-12-01 09:15:22 +01:00
tgts_per_mshr = 20
factor out common run code from se.py and fs.py. configs/example/fs.py: factor out common code. configs/example/se.py: factor out common code --HG-- extra : convert_revision : 72a1f653c84eae1b7d281e0a5e60ee116ad6b27d
2006-10-27 22:32:26 +02:00
mem: Allow read-only caches and check compliance This patch adds a parameter to the BaseCache to enable a read-only cache, for example for the instruction cache, or table-walker cache (not for x86). A number of checks are put in place in the code to ensure a read-only cache does not end up with dirty data. A follow-on patch adds suitable read requests to allow a read-only cache to explicitly ask for clean data.
2015-07-03 16:14:39 +02:00
class L1_ICache(L1Cache):
is_read_only = True
class L1_DCache(L1Cache):
pass
mem: Add explicit Cache subclass and make BaseCache abstract Open up for other subclasses to BaseCache and transition to using the explicit Cache subclass. --HG-- rename : src/mem/cache/BaseCache.py => src/mem/cache/Cache.py
2015-08-21 13:03:23 +02:00
class L2Cache(Cache):
Add L2 cache option to fs.py --l2cache --HG-- extra : convert_revision : 5bdd1129c3b23e91d441e7b83f6a824ef7740fab
2006-11-16 00:22:15 +01:00
assoc = 8
Mem: Use cycles to express cache-related latencies This patch changes the cache-related latencies from an absolute time expressed in Ticks, to a number of cycles that can be scaled with the clock period of the caches. Ultimately this patch serves to enable future work that involves dynamic frequency scaling. As an immediate benefit it also makes it more convenient to specify cache performance without implicitly assuming a specific CPU core operating frequency. The stat blocked_cycles that actually counter in ticks is now updated to count in cycles. As the timing is now rounded to the clock edges of the cache, there are some regressions that change. Plenty of them have very minor changes, whereas some regressions with a short run-time are perturbed quite significantly. A follow-on patch updates all the statistics for the regressions.
2012-10-15 14:10:54 +02:00
hit_latency = 20
response_latency = 20
config: Unify caches used in regressions and adjust L2 MSHRs This patch unified the L1 and L2 caches used throughout the regressions instead of declaring different, but very similar, configurations in the different scripts. The patch also changes the default L2 configuration to match what it used to be for the fs and se scripts (until the last patch that updated the regressions to also make use of the cache config). The MSHRs and targets per MSHR are now set to a more realistic default of 20 and 12, respectively. As a result of both the aforementioned changes, many of the regression stats are changed. A follow-on patch will bump the stats.
2012-10-30 12:44:08 +01:00
mshrs = 20
tgts_per_mshr = 12
config: Use shared cache config for regressions This patch uses the common L1, L2 and IOCache configuration for the regressions that all share the same cache parameters. There are a few regressions that use a slightly different configuration (memtest, o3-timing=mp, simple-atomic-mp and simple-timing-mp), and the latter are not changed in this patch. They will be updated in a future patch. The common cache configurations are changed to match the ones used in the regressions, and are slightly changed with respect to what they were. Hopefully this means we can converge on a common base configuration, used both in the normal user configurations and regressions. As only regressions that shared the same cache configuration are updated, no regressions are affected.
2012-10-25 10:32:44 +02:00
write_buffers = 8
mem: Add explicit Cache subclass and make BaseCache abstract Open up for other subclasses to BaseCache and transition to using the explicit Cache subclass. --HG-- rename : src/mem/cache/BaseCache.py => src/mem/cache/Cache.py
2015-08-21 13:03:23 +02:00
class IOCache(Cache):
config: Use shared cache config for regressions This patch uses the common L1, L2 and IOCache configuration for the regressions that all share the same cache parameters. There are a few regressions that use a slightly different configuration (memtest, o3-timing=mp, simple-atomic-mp and simple-timing-mp), and the latter are not changed in this patch. They will be updated in a future patch. The common cache configurations are changed to match the ones used in the regressions, and are slightly changed with respect to what they were. Hopefully this means we can converge on a common base configuration, used both in the normal user configurations and regressions. As only regressions that shared the same cache configuration are updated, no regressions are affected.
2012-10-25 10:32:44 +02:00
assoc = 8
hit_latency = 50
response_latency = 50
Add L2 cache option to fs.py --l2cache --HG-- extra : convert_revision : 5bdd1129c3b23e91d441e7b83f6a824ef7740fab
2006-11-16 00:22:15 +01:00
mshrs = 20
config: Use shared cache config for regressions This patch uses the common L1, L2 and IOCache configuration for the regressions that all share the same cache parameters. There are a few regressions that use a slightly different configuration (memtest, o3-timing=mp, simple-atomic-mp and simple-timing-mp), and the latter are not changed in this patch. They will be updated in a future patch. The common cache configurations are changed to match the ones used in the regressions, and are slightly changed with respect to what they were. Hopefully this means we can converge on a common base configuration, used both in the normal user configurations and regressions. As only regressions that shared the same cache configuration are updated, no regressions are affected.
2012-10-25 10:32:44 +02:00
size = '1kB'
Add L2 cache option to fs.py --l2cache --HG-- extra : convert_revision : 5bdd1129c3b23e91d441e7b83f6a824ef7740fab
2006-11-16 00:22:15 +01:00
tgts_per_mshr = 12
config: Use shared cache config for regressions This patch uses the common L1, L2 and IOCache configuration for the regressions that all share the same cache parameters. There are a few regressions that use a slightly different configuration (memtest, o3-timing=mp, simple-atomic-mp and simple-timing-mp), and the latter are not changed in this patch. They will be updated in a future patch. The common cache configurations are changed to match the ones used in the regressions, and are slightly changed with respect to what they were. Hopefully this means we can converge on a common base configuration, used both in the normal user configurations and regressions. As only regressions that shared the same cache configuration are updated, no regressions are affected.
2012-10-25 10:32:44 +02:00
forward_snoops = False
Add L2 cache option to fs.py --l2cache --HG-- extra : convert_revision : 5bdd1129c3b23e91d441e7b83f6a824ef7740fab
2006-11-16 00:22:15 +01:00
mem: Add explicit Cache subclass and make BaseCache abstract Open up for other subclasses to BaseCache and transition to using the explicit Cache subclass. --HG-- rename : src/mem/cache/BaseCache.py => src/mem/cache/Cache.py
2015-08-21 13:03:23 +02:00
class PageTableWalkerCache(Cache):
X86: Add L1 caches for the TLB walkers. Small L1 caches are connected to the TLB walkers when caches are used. This allows them to participate in the coherence protocol properly.
2011-02-02 03:28:41 +01:00
assoc = 2
Mem: Use cycles to express cache-related latencies This patch changes the cache-related latencies from an absolute time expressed in Ticks, to a number of cycles that can be scaled with the clock period of the caches. Ultimately this patch serves to enable future work that involves dynamic frequency scaling. As an immediate benefit it also makes it more convenient to specify cache performance without implicitly assuming a specific CPU core operating frequency. The stat blocked_cycles that actually counter in ticks is now updated to count in cycles. As the timing is now rounded to the clock edges of the cache, there are some regressions that change. Plenty of them have very minor changes, whereas some regressions with a short run-time are perturbed quite significantly. A follow-on patch updates all the statistics for the regressions.
2012-10-15 14:10:54 +02:00
hit_latency = 2
response_latency = 2
X86: Add L1 caches for the TLB walkers. Small L1 caches are connected to the TLB walkers when caches are used. This allows them to participate in the coherence protocol properly.
2011-02-02 03:28:41 +01:00
mshrs = 10
size = '1kB'
tgts_per_mshr = 12
arch, cpu: Do not forward snoops to table walker This patch simplifies the overall CPU by changing the TLB caches such that they do not forward snoops to the table walker port(s). Note that only ARM and X86 are affected. There is no reason for the ports to snoop as they do not actually take any action, and from a performance point of view we are better of not snooping more than we have to. Should it at a later point be required to snoop for a particular TLB design it is easy enough to add it back.
2015-05-05 09:22:27 +02:00
forward_snoops = False
mem: Allow read-only caches and check compliance This patch adds a parameter to the BaseCache to enable a read-only cache, for example for the instruction cache, or table-walker cache (not for x86). A number of checks are put in place in the code to ensure a read-only cache does not end up with dirty data. A follow-on patch adds suitable read requests to allow a read-only cache to explicitly ask for clean data.
2015-07-03 16:14:39 +02:00
# the x86 table walker actually writes to the table-walker cache
if buildEnv['TARGET_ISA'] == 'x86':
is_read_only = False
else:
is_read_only = True
Reference in a new issue Copy permalink