sanchayanmaity/gem5
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
gem5/tests/quick/se/50.memtest/ref/null/none/memtest/config.ini

571 lines
10 KiB
INI
Raw Normal View History

Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[root]
type=Root
children=system
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
full_system=false
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sim_quantum=0
Stats: Re update stats.
2011-02-08 04:23:13 +01:00
time_sync_enable=false
time_sync_period=100000000000
time_sync_spin_threshold=100000000
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system]
type=System
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
children=clk_domain cpu0 cpu1 cpu2 cpu3 cpu4 cpu5 cpu6 cpu7 cpu_clk_domain dvfs_handler l2c membus physmem toL2Bus voltage_domain
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
boot_osflags=a
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
cache_line_size=64
clk_domain=system.clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
init_param=0
kernel=
stats: updates due to recent ruby and x86 changes Also updates many out of date config files.
2014-09-01 23:55:52 +02:00
kernel_addr_check=true
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
load_addr_mask=1099511627775
stats: updates due to recent ruby and x86 changes Also updates many out of date config files.
2014-09-01 23:55:52 +02:00
load_offset=0
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
mem_mode=timing
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
mem_ranges=
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
memories=system.physmem
mmap_using_noreserve=false
stats: Update stats for final tick and memory bandwidth patches
2012-01-25 18:19:50 +01:00
num_work_ids=16
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
readfile=
symbolfile=
Stats: Re update stats.
2011-02-08 04:23:13 +01:00
work_begin_ckpt_count=0
work_begin_cpu_id_exit=-1
work_begin_exit_count=0
work_cpus_ckpt_count=0
work_end_ckpt_count=0
work_end_exit_count=0
work_item_id=-1
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
system_port=system.membus.slave[1]
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
[system.clk_domain]
type=SrcClockDomain
clock=1000
stats: updates due to recent ruby and x86 changes Also updates many out of date config files.
2014-09-01 23:55:52 +02:00
domain_id=-1
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
stats: updates due to recent ruby and x86 changes Also updates many out of date config files.
2014-09-01 23:55:52 +02:00
init_perf_level=0
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
voltage_domain=system.voltage_domain
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.cpu0]
type=MemTest
children=l1c
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.cpu_clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
interval=1
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
max_loads=100000
percent_functional=50
percent_reads=65
percent_uncacheable=10
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
progress_check=5000000
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
progress_interval=10000
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
size=65536
stats: Update stats for final tick and memory bandwidth patches
2012-01-25 18:19:50 +01:00
suppress_func_warnings=false
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
system=system
port=system.cpu0.l1c.cpu_side
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.cpu0.l1c]
type=BaseCache
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
children=tags
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
addr_ranges=0:18446744073709551615
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
assoc=4
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.cpu_clk_domain
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
demand_mshr_reserve=1
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
Update stats for new single bad-address responder. Mostly just config.ini updates, though the different response latency for bad addresses caused very minor timing changes in the O3 Linux boot tests.
2009-04-22 07:55:52 +02:00
forward_snoops=true
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
hit_latency=2
tests: update stats for name changes
2011-04-20 03:45:23 +02:00
is_top_level=true
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
max_miss_count=0
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
mshrs=4
Update stats for new prefetching fixes. Prefetching is not enabled in any of our regressions, so no significant stat values have changed, but zero-valued prefetch stats no longer show up when prefetching is disabled so there are noticable changes in the reference stat files anyway.
2009-02-16 18:09:45 +01:00
prefetch_on_access=false
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
prefetcher=Null
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
response_latency=2
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sequential_access=false
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
size=32768
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
system=system
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
tags=system.cpu0.l1c.tags
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
tgts_per_mshr=20
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
two_queue=false
write_buffers=8
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
cpu_side=system.cpu0.port
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
mem_side=system.toL2Bus.slave[0]
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
[system.cpu0.l1c.tags]
type=LRU
assoc=4
block_size=64
clk_domain=system.cpu_clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
hit_latency=2
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sequential_access=false
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
size=32768
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.cpu1]
type=MemTest
children=l1c
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.cpu_clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
interval=1
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
max_loads=100000
percent_functional=50
percent_reads=65
percent_uncacheable=10
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
progress_check=5000000
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
progress_interval=10000
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
size=65536
stats: Update stats for final tick and memory bandwidth patches
2012-01-25 18:19:50 +01:00
suppress_func_warnings=false
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
system=system
port=system.cpu1.l1c.cpu_side
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.cpu1.l1c]
type=BaseCache
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
children=tags
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
addr_ranges=0:18446744073709551615
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
assoc=4
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.cpu_clk_domain
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
demand_mshr_reserve=1
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
Update stats for new single bad-address responder. Mostly just config.ini updates, though the different response latency for bad addresses caused very minor timing changes in the O3 Linux boot tests.
2009-04-22 07:55:52 +02:00
forward_snoops=true
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
hit_latency=2
tests: update stats for name changes
2011-04-20 03:45:23 +02:00
is_top_level=true
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
max_miss_count=0
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
mshrs=4
Update stats for new prefetching fixes. Prefetching is not enabled in any of our regressions, so no significant stat values have changed, but zero-valued prefetch stats no longer show up when prefetching is disabled so there are noticable changes in the reference stat files anyway.
2009-02-16 18:09:45 +01:00
prefetch_on_access=false
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
prefetcher=Null
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
response_latency=2
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sequential_access=false
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
size=32768
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
system=system
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
tags=system.cpu1.l1c.tags
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
tgts_per_mshr=20
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
two_queue=false
write_buffers=8
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
cpu_side=system.cpu1.port
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
mem_side=system.toL2Bus.slave[1]
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
[system.cpu1.l1c.tags]
type=LRU
assoc=4
block_size=64
clk_domain=system.cpu_clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
hit_latency=2
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sequential_access=false
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
size=32768
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.cpu2]
type=MemTest
children=l1c
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.cpu_clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
interval=1
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
max_loads=100000
percent_functional=50
percent_reads=65
percent_uncacheable=10
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
progress_check=5000000
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
progress_interval=10000
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
size=65536
stats: Update stats for final tick and memory bandwidth patches
2012-01-25 18:19:50 +01:00
suppress_func_warnings=false
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
system=system
port=system.cpu2.l1c.cpu_side
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.cpu2.l1c]
type=BaseCache
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
children=tags
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
addr_ranges=0:18446744073709551615
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
assoc=4
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.cpu_clk_domain
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
demand_mshr_reserve=1
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
Update stats for new single bad-address responder. Mostly just config.ini updates, though the different response latency for bad addresses caused very minor timing changes in the O3 Linux boot tests.
2009-04-22 07:55:52 +02:00
forward_snoops=true
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
hit_latency=2
tests: update stats for name changes
2011-04-20 03:45:23 +02:00
is_top_level=true
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
max_miss_count=0
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
mshrs=4
Update stats for new prefetching fixes. Prefetching is not enabled in any of our regressions, so no significant stat values have changed, but zero-valued prefetch stats no longer show up when prefetching is disabled so there are noticable changes in the reference stat files anyway.
2009-02-16 18:09:45 +01:00
prefetch_on_access=false
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
prefetcher=Null
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
response_latency=2
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sequential_access=false
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
size=32768
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
system=system
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
tags=system.cpu2.l1c.tags
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
tgts_per_mshr=20
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
two_queue=false
write_buffers=8
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
cpu_side=system.cpu2.port
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
mem_side=system.toL2Bus.slave[2]
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
[system.cpu2.l1c.tags]
type=LRU
assoc=4
block_size=64
clk_domain=system.cpu_clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
hit_latency=2
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sequential_access=false
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
size=32768
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.cpu3]
type=MemTest
children=l1c
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.cpu_clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
interval=1
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
max_loads=100000
percent_functional=50
percent_reads=65
percent_uncacheable=10
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
progress_check=5000000
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
progress_interval=10000
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
size=65536
stats: Update stats for final tick and memory bandwidth patches
2012-01-25 18:19:50 +01:00
suppress_func_warnings=false
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
system=system
port=system.cpu3.l1c.cpu_side
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.cpu3.l1c]
type=BaseCache
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
children=tags
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
addr_ranges=0:18446744073709551615
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
assoc=4
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.cpu_clk_domain
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
demand_mshr_reserve=1
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
Update stats for new single bad-address responder. Mostly just config.ini updates, though the different response latency for bad addresses caused very minor timing changes in the O3 Linux boot tests.
2009-04-22 07:55:52 +02:00
forward_snoops=true
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
hit_latency=2
tests: update stats for name changes
2011-04-20 03:45:23 +02:00
is_top_level=true
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
max_miss_count=0
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
mshrs=4
Update stats for new prefetching fixes. Prefetching is not enabled in any of our regressions, so no significant stat values have changed, but zero-valued prefetch stats no longer show up when prefetching is disabled so there are noticable changes in the reference stat files anyway.
2009-02-16 18:09:45 +01:00
prefetch_on_access=false
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
prefetcher=Null
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
response_latency=2
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sequential_access=false
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
size=32768
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
system=system
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
tags=system.cpu3.l1c.tags
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
tgts_per_mshr=20
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
two_queue=false
write_buffers=8
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
cpu_side=system.cpu3.port
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
mem_side=system.toL2Bus.slave[3]
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
[system.cpu3.l1c.tags]
type=LRU
assoc=4
block_size=64
clk_domain=system.cpu_clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
hit_latency=2
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sequential_access=false
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
size=32768
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.cpu4]
type=MemTest
children=l1c
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.cpu_clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
interval=1
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
max_loads=100000
percent_functional=50
percent_reads=65
percent_uncacheable=10
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
progress_check=5000000
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
progress_interval=10000
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
size=65536
stats: Update stats for final tick and memory bandwidth patches
2012-01-25 18:19:50 +01:00
suppress_func_warnings=false
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
system=system
port=system.cpu4.l1c.cpu_side
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.cpu4.l1c]
type=BaseCache
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
children=tags
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
addr_ranges=0:18446744073709551615
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
assoc=4
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.cpu_clk_domain
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
demand_mshr_reserve=1
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
Update stats for new single bad-address responder. Mostly just config.ini updates, though the different response latency for bad addresses caused very minor timing changes in the O3 Linux boot tests.
2009-04-22 07:55:52 +02:00
forward_snoops=true
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
hit_latency=2
tests: update stats for name changes
2011-04-20 03:45:23 +02:00
is_top_level=true
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
max_miss_count=0
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
mshrs=4
Update stats for new prefetching fixes. Prefetching is not enabled in any of our regressions, so no significant stat values have changed, but zero-valued prefetch stats no longer show up when prefetching is disabled so there are noticable changes in the reference stat files anyway.
2009-02-16 18:09:45 +01:00
prefetch_on_access=false
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
prefetcher=Null
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
response_latency=2
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sequential_access=false
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
size=32768
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
system=system
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
tags=system.cpu4.l1c.tags
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
tgts_per_mshr=20
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
two_queue=false
write_buffers=8
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
cpu_side=system.cpu4.port
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
mem_side=system.toL2Bus.slave[4]
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
[system.cpu4.l1c.tags]
type=LRU
assoc=4
block_size=64
clk_domain=system.cpu_clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
hit_latency=2
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sequential_access=false
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
size=32768
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.cpu5]
type=MemTest
children=l1c
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.cpu_clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
interval=1
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
max_loads=100000
percent_functional=50
percent_reads=65
percent_uncacheable=10
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
progress_check=5000000
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
progress_interval=10000
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
size=65536
stats: Update stats for final tick and memory bandwidth patches
2012-01-25 18:19:50 +01:00
suppress_func_warnings=false
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
system=system
port=system.cpu5.l1c.cpu_side
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.cpu5.l1c]
type=BaseCache
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
children=tags
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
addr_ranges=0:18446744073709551615
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
assoc=4
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.cpu_clk_domain
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
demand_mshr_reserve=1
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
Update stats for new single bad-address responder. Mostly just config.ini updates, though the different response latency for bad addresses caused very minor timing changes in the O3 Linux boot tests.
2009-04-22 07:55:52 +02:00
forward_snoops=true
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
hit_latency=2
tests: update stats for name changes
2011-04-20 03:45:23 +02:00
is_top_level=true
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
max_miss_count=0
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
mshrs=4
Update stats for new prefetching fixes. Prefetching is not enabled in any of our regressions, so no significant stat values have changed, but zero-valued prefetch stats no longer show up when prefetching is disabled so there are noticable changes in the reference stat files anyway.
2009-02-16 18:09:45 +01:00
prefetch_on_access=false
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
prefetcher=Null
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
response_latency=2
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sequential_access=false
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
size=32768
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
system=system
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
tags=system.cpu5.l1c.tags
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
tgts_per_mshr=20
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
two_queue=false
write_buffers=8
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
cpu_side=system.cpu5.port
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
mem_side=system.toL2Bus.slave[5]
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
[system.cpu5.l1c.tags]
type=LRU
assoc=4
block_size=64
clk_domain=system.cpu_clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
hit_latency=2
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sequential_access=false
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
size=32768
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.cpu6]
type=MemTest
children=l1c
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.cpu_clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
interval=1
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
max_loads=100000
percent_functional=50
percent_reads=65
percent_uncacheable=10
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
progress_check=5000000
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
progress_interval=10000
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
size=65536
stats: Update stats for final tick and memory bandwidth patches
2012-01-25 18:19:50 +01:00
suppress_func_warnings=false
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
system=system
port=system.cpu6.l1c.cpu_side
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.cpu6.l1c]
type=BaseCache
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
children=tags
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
addr_ranges=0:18446744073709551615
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
assoc=4
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.cpu_clk_domain
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
demand_mshr_reserve=1
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
Update stats for new single bad-address responder. Mostly just config.ini updates, though the different response latency for bad addresses caused very minor timing changes in the O3 Linux boot tests.
2009-04-22 07:55:52 +02:00
forward_snoops=true
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
hit_latency=2
tests: update stats for name changes
2011-04-20 03:45:23 +02:00
is_top_level=true
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
max_miss_count=0
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
mshrs=4
Update stats for new prefetching fixes. Prefetching is not enabled in any of our regressions, so no significant stat values have changed, but zero-valued prefetch stats no longer show up when prefetching is disabled so there are noticable changes in the reference stat files anyway.
2009-02-16 18:09:45 +01:00
prefetch_on_access=false
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
prefetcher=Null
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
response_latency=2
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sequential_access=false
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
size=32768
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
system=system
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
tags=system.cpu6.l1c.tags
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
tgts_per_mshr=20
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
two_queue=false
write_buffers=8
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
cpu_side=system.cpu6.port
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
mem_side=system.toL2Bus.slave[6]
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
[system.cpu6.l1c.tags]
type=LRU
assoc=4
block_size=64
clk_domain=system.cpu_clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
hit_latency=2
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sequential_access=false
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
size=32768
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.cpu7]
type=MemTest
children=l1c
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.cpu_clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
interval=1
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
max_loads=100000
percent_functional=50
percent_reads=65
percent_uncacheable=10
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
progress_check=5000000
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
progress_interval=10000
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
size=65536
stats: Update stats for final tick and memory bandwidth patches
2012-01-25 18:19:50 +01:00
suppress_func_warnings=false
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
system=system
port=system.cpu7.l1c.cpu_side
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.cpu7.l1c]
type=BaseCache
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
children=tags
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
addr_ranges=0:18446744073709551615
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
assoc=4
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.cpu_clk_domain
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
demand_mshr_reserve=1
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
Update stats for new single bad-address responder. Mostly just config.ini updates, though the different response latency for bad addresses caused very minor timing changes in the O3 Linux boot tests.
2009-04-22 07:55:52 +02:00
forward_snoops=true
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
hit_latency=2
tests: update stats for name changes
2011-04-20 03:45:23 +02:00
is_top_level=true
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
max_miss_count=0
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
mshrs=4
Update stats for new prefetching fixes. Prefetching is not enabled in any of our regressions, so no significant stat values have changed, but zero-valued prefetch stats no longer show up when prefetching is disabled so there are noticable changes in the reference stat files anyway.
2009-02-16 18:09:45 +01:00
prefetch_on_access=false
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
prefetcher=Null
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
response_latency=2
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sequential_access=false
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
size=32768
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
system=system
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
tags=system.cpu7.l1c.tags
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
tgts_per_mshr=20
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
two_queue=false
write_buffers=8
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
cpu_side=system.cpu7.port
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
mem_side=system.toL2Bus.slave[7]
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
[system.cpu7.l1c.tags]
type=LRU
assoc=4
block_size=64
clk_domain=system.cpu_clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
hit_latency=2
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sequential_access=false
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
size=32768
[system.cpu_clk_domain]
type=SrcClockDomain
clock=500
stats: updates due to recent ruby and x86 changes Also updates many out of date config files.
2014-09-01 23:55:52 +02:00
domain_id=-1
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
stats: updates due to recent ruby and x86 changes Also updates many out of date config files.
2014-09-01 23:55:52 +02:00
init_perf_level=0
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
voltage_domain=system.voltage_domain
stats: updates due to recent ruby and x86 changes Also updates many out of date config files.
2014-09-01 23:55:52 +02:00
[system.dvfs_handler]
type=DVFSHandler
domains=
enable=false
eventq_index=0
sys_clk_domain=system.clk_domain
transition_latency=100000000
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.l2c]
type=BaseCache
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
children=tags
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
addr_ranges=0:18446744073709551615
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
assoc=8
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.cpu_clk_domain
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
demand_mshr_reserve=1
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
Update stats for new single bad-address responder. Mostly just config.ini updates, though the different response latency for bad addresses caused very minor timing changes in the O3 Linux boot tests.
2009-04-22 07:55:52 +02:00
forward_snoops=true
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
hit_latency=20
tests: update stats for name changes
2011-04-20 03:45:23 +02:00
is_top_level=false
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
max_miss_count=0
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
mshrs=20
Update stats for new prefetching fixes. Prefetching is not enabled in any of our regressions, so no significant stat values have changed, but zero-valued prefetch stats no longer show up when prefetching is disabled so there are noticable changes in the reference stat files anyway.
2009-02-16 18:09:45 +01:00
prefetch_on_access=false
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
prefetcher=Null
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
response_latency=20
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sequential_access=false
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
size=65536
stats: update stats for insts/ops and master id changes
2012-02-12 23:07:43 +01:00
system=system
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
tags=system.l2c.tags
regressions: update stats due to branch predictor changes The actual statistical values are being updated for only two tests belonging to sparc architecture and inorder cpu: 00.hello and 02.insttest. For others the patch updates config.ini and name changes to statistical variables.
2013-01-24 19:29:00 +01:00
tgts_per_mshr=12
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
two_queue=false
write_buffers=8
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
cpu_side=system.toL2Bus.master[0]
mem_side=system.membus.slave[0]
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
[system.l2c.tags]
type=LRU
assoc=8
block_size=64
clk_domain=system.cpu_clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
hit_latency=20
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
sequential_access=false
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
size=65536
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.membus]
stats: updates due to changes to x86, stale configs.
2014-10-11 23:18:51 +02:00
type=CoherentXBar
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
forward_latency=4
frontend_latency=3
response_latency=2
stats: updates due to changes to x86, stale configs.
2014-10-11 23:18:51 +02:00
snoop_filter=Null
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
snoop_response_latency=4
regressions: update due to cache latency fix
2013-03-28 00:36:21 +01:00
system=system
tests: update reference config.ini files for previous cset Rename 'responder_set' to 'use_default_range'.
2010-08-17 14:06:22 +02:00
use_default_range=false
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
width=16
Regression Tests: Update statistics
2012-10-02 21:35:46 +02:00
master=system.physmem.port
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
slave=system.l2c.mem_side system.system_port
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.physmem]
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
type=SimpleMemory
Regression Tests: Update statistics
2012-10-02 21:35:46 +02:00
bandwidth=73.000000
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.clk_domain
conf_table_reported=true
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
in_addr_map=true
Make default PhysicalMemory latency slightly more realistic. Also update stats to reflect change.
2008-08-04 00:13:29 +02:00
latency=30000
tests: update config.ini and stdout for the various tests. These files were a bit too out of date and resulted in a bit of confusion.
2008-07-22 23:00:18 +02:00
latency_var=0
null=false
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
range=0:134217727
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
port=system.membus.master[0]
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
[system.toL2Bus]
stats: updates due to changes to x86, stale configs.
2014-10-11 23:18:51 +02:00
type=CoherentXBar
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
clk_domain=system.cpu_clk_domain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
forward_latency=0
frontend_latency=1
response_latency=1
stats: updates due to changes to x86, stale configs.
2014-10-11 23:18:51 +02:00
snoop_filter=Null
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
snoop_response_latency=1
regressions: update due to cache latency fix
2013-03-28 00:36:21 +01:00
system=system
tests: update reference config.ini files for previous cset Rename 'responder_set' to 'use_default_range'.
2010-08-17 14:06:22 +02:00
use_default_range=false
stats: changes to due to recent set of patches
2015-03-09 15:39:09 +01:00
width=32
stats: update stats for no_value -> nan Lots of accumulated older changes too.
2012-05-09 20:52:14 +02:00
master=system.l2c.cpu_side
slave=system.cpu0.l1c.mem_side system.cpu1.l1c.mem_side system.cpu2.l1c.mem_side system.cpu3.l1c.mem_side system.cpu4.l1c.mem_side system.cpu5.l1c.mem_side system.cpu6.l1c.mem_side system.cpu7.l1c.mem_side
Add short memtest run to quick regressions. Caveats: - Even though memtest is ISA-independent, it will only run for the Alpha builds, since there's no way to specify ISA-independent reference files and I didn't want to commit 3 copies since I'm not sure we want to run it for all the different ISAs anyway. - Reference outputs were generated on my laptop, so performance numbers will be low compared to zizzer. --HG-- extra : convert_revision : 210fe4abecc19fbab0b15402c6cb4863650bab66
2007-02-07 06:16:33 +01:00
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
[system.voltage_domain]
type=VoltageDomain
stats: update stats for cache occupancy and clock domain changes
2014-01-24 22:29:33 +01:00
eventq_index=0
tests: update reference outputs Apparently only stats.txt was updated the last time, so this changeset updates other reference output files (config.ini, simout, simerr, ruby.stats) so that test output diffs should not be cluttered with irrelevant changes. There are a few stats.txt updates too, but they are in the minority.
2013-09-28 21:25:17 +02:00
voltage=1.000000
Reference in a new issue Copy permalink