Commit graph

468 commits

Author SHA1 Message Date
Brandon Potter 073cb26607 syscall_emul: [patch 14/22] adds identifier system calls
This changeset add fields to the process object and adds the following
three system calls: setpgid, gettid, getpid.
2017-02-27 14:10:02 -05:00
Andreas Hansson f2e2410a50 stats: Get all stats updated to reflect current behaviour
Line everything up again.
2017-02-19 05:30:32 -05:00
Brandon Potter 3886c4a8f2 syscall_emul: [patch 5/22] remove LiveProcess class and use Process instead
The EIOProcess class was removed recently and it was the only other class
which derived from Process. Since every Process invocation is also a
LiveProcess invocation, it makes sense to simplify the organization by
combining the fields from LiveProcess into Process.
2016-11-09 14:27:40 -06:00
Alec Roelke e9311a59ed riscv: Remove ECALL tests from insttest
The system calls tested in rv64i.cpp in RISC-V's insttest suite have
different behavior depending on the operating system and file system they
are run on. This patch ignores the output of those tests and only
ensures that the instructions in RV64I complete successfully.

[Change deletion of ECALL test to block comment.]
[Restore ECALL test but remove test output to test only for completion
without error.]
[Update patch description and again try to push EMPTY files for rv64i
tests.]
2017-02-13 14:26:05 -06:00
Andreas Hansson ebd9018a13 stats: Update stats to reflect cache changes 2016-12-05 16:48:34 -05:00
Jason Lowe-Power 7520331402 tests: Regression stats updated for recent patches 2016-11-30 17:12:59 -05:00
Andreas Hansson b8a162087d stats, alpha: Update ALPHA stats
Reflect the removal of the syscall tracking.
2016-11-17 04:54:18 -05:00
Andreas Hansson 4cf7f6c4ca tests, ruby: Move rubytests from ALPHA (linux) to NULL (none)
This patch avoids compiling ALPHA six times as part of running
'util/regress', and instead relis on NULL with different protocols to
run the rubytest. All we need is the memory system, so there is really
no need to compile the ISA over and over again.

The one downside is the removal of running 'hello' for the variuos
ALPHA and protocol combinations, but if this is a concern we should
rather beef up the synthetic tests for the variuos protocols.

--HG--
rename : build_opts/NULL => build_opts/NULL_MESI_Two_Level
rename : build_opts/NULL => build_opts/NULL_MOESI_CMP_directory
rename : build_opts/NULL => build_opts/NULL_MOESI_CMP_token
rename : build_opts/NULL => build_opts/NULL_MOESI_hammer
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby-MESI_Two_Level/config.ini => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby-MESI_Two_Level/config.ini
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby-MESI_Two_Level/simerr => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby-MESI_Two_Level/simerr
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby-MESI_Two_Level/simout => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby-MESI_Two_Level/simout
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby-MESI_Two_Level/stats.txt => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby-MESI_Two_Level/stats.txt
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby-MOESI_CMP_directory/config.ini => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby-MOESI_CMP_directory/config.ini
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby-MOESI_CMP_directory/simerr => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby-MOESI_CMP_directory/simerr
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby-MOESI_CMP_directory/simout => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby-MOESI_CMP_directory/simout
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby-MOESI_CMP_directory/stats.txt => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby-MOESI_CMP_directory/stats.txt
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby-MOESI_CMP_token/config.ini => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby-MOESI_CMP_token/config.ini
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby-MOESI_CMP_token/simerr => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby-MOESI_CMP_token/simerr
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby-MOESI_CMP_token/simout => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby-MOESI_CMP_token/simout
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby-MOESI_CMP_token/stats.txt => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby-MOESI_CMP_token/stats.txt
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby-MOESI_hammer/config.ini => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby-MOESI_hammer/config.ini
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby-MOESI_hammer/simerr => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby-MOESI_hammer/simerr
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby-MOESI_hammer/simout => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby-MOESI_hammer/simout
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby-MOESI_hammer/stats.txt => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby-MOESI_hammer/stats.txt
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby/config.ini => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby/config.ini
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby/simerr => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby/simerr
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby/simout => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby/simout
rename : tests/quick/se/60.rubytest/ref/alpha/linux/rubytest-ruby/stats.txt => tests/quick/se/60.rubytest/ref/null/none/rubytest-ruby/stats.txt
2016-11-17 04:54:16 -05:00
Andreas Hansson 6ed567d600 alpha: Remove ALPHA tru64 support and associated tests
No one appears to be using it, and it is causing build issues
and increases the development and maintenance effort.
2016-11-17 04:54:14 -05:00
Andreas Hansson 607c277291 stats: Update stats to reflect recent changes to floats
Mostly just splitting out the floats ops and corresponding
reads/writes.
2016-10-19 06:20:04 -04:00
Curtis Dunham c87b717dbd stats: update references 2016-10-13 23:21:40 +01:00
Andreas Sandberg d0ffd2f9b8 test: Make the memtest and memcheck tests functional only
The memtest and memcheck are not designed to test timing. Make them
functional only to make ref diffs less noisy in the future.

Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
2016-09-22 10:49:09 +01:00
Andreas Sandberg ada0e2f02f tests, arm: Make switcheroo and checkpoint tests functional
Switcheroo and checkpoint tests should generally be considered to be
successful if they run to completion.  Remove all reference output
files from the switcheroo and checkopint tests to make them purely
functional.

Change-Id: I70b47853bd662b7a33716d9e0d2154b16077f9dc
Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Curtis Dunham <curtis.dunham@arm.com>
2016-09-16 09:14:31 +01:00
Steve Reinhardt 608a37c844 tests: remove EIO tests
An email sent to gem5-users and gem5-dev asking if anyone was
still using EIO traces got no responses, so it seems like it's
not worth maintaining this any longer.
2016-08-13 23:07:28 -04:00
Andreas Sandberg 55ed9609f1 stats: Update to match classic memory changes 2016-08-12 14:12:59 +01:00
Curtis Dunham ae445c0348 stats: update references 2016-08-02 11:34:32 +01:00
Curtis Dunham 84f138ba96 stats: update references 2016-07-21 17:19:18 +01:00
Abdul Mutaal Ahmad 9c20880fb5 mem: tester for new HMC configuration
This patch provides the example test script to configure different HMC
architecture and run traffic through traffic generator.

Committed by Jason Lowe-Power <jason@lowepower.com>
2016-07-01 09:48:43 -05:00
Andreas Sandberg 9c8710430e stats: Update stats to reflect ARM changes 2016-06-21 16:42:04 +01:00
Andreas Sandberg efb7fb6f85 mem: Resolve TrafficGen trace relative to the config
The traffic generator currently resolves relative trace paths relative
to gem5's current working directory. This can lead to surprising
results for relative paths where the expectation would normally be
that they are resolved relative to the configuration file. This
changeset implements config-relative trace file lookups. The old
behavior is kept as a fallback for configs that expect that behavior.

Change-Id: I1bda4e16725842666ffc37dcb6838c23a6ff138c
Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Curtis Dunham <curtis.dunham@arm.com>
2016-06-20 14:49:37 +01:00
Steve Reinhardt 54aeb1a187 stats: update EIO stats 2016-06-12 20:02:49 -04:00
Andreas Sandberg 85997e66a0 stats: Add power stats to test references
Change-Id: Ic827213134b199446822f128b81d4a480e777fee
2016-06-06 17:16:44 +01:00
Steve Reinhardt 672c06a01d stats: update EIO stats 2016-06-06 00:18:34 -04:00
Andreas Sandberg 1d933447fc stats: Update to match ARM ISA changes 2016-06-02 14:14:36 +01:00
Curtis Dunham dafec4a515 stats: update and fix e273e86a873d 2016-05-31 16:55:47 +01:00
Curtis Dunham 62b6ff22ec stats: update for snoop filter tweak
--HG--
extra : source : 2323557eb4f4866fa1ea1575a9f5969e0022adc1
2016-05-31 11:07:18 +01:00
Steve Reinhardt 2ae8b365c1 tests: update EIO ref stats for removed cache stats
Complaints about changes in EIO tests were due to reference files
that still have removed cache stats from cset 11454:e55afadc4e19.
2016-05-07 14:43:06 -04:00
Andreas Sandberg b80f568bcf tests: Remove stale reference output files
Remove test reference files that are not generated any more:

    * chair.cook.ppm: This file should be generated by eon and not
      mcf, so it shouldn't be included as an output from mcf.

    * system.pc.terminal: The terminal device has been renamed so this
      file is no longer generated.

Change-Id: I3962efe1ff25479ca276115f7564eccb5fac8cf9
Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
2016-04-28 15:16:52 +01:00
Andreas Hansson 8845aae4da tests: Add a basic memcheck regression
This patch adds a simple regression that calls the existing
memcheck.py script.

--HG--
rename : tests/configs/learning-gem5-p1-simple.py => tests/configs/memcheck.py
rename : tests/quick/se/70.tgen/test.py => tests/quick/se/51.memcheck/test.py
2016-04-25 03:46:12 -04:00
Andreas Hansson b006ad26d4 stats: Update stats to reflect cache changes
Removed unused stats, now counting WriteLineReq, and changed how
uncacheable writes are handled while responses are outstanding.
2016-04-21 04:48:24 -04:00
Andreas Hansson d9193d1b20 stats: Match current behaviour
Small changes to the branch predictor and BTB caused stats changes
throughout.
2016-04-09 12:13:40 -04:00
Curtis Dunham 1d61224a8b stats: update stats for thermals, indirect BP 2016-04-08 11:01:45 -05:00
Steve Reinhardt d7c083864c stats: update stats for ld.so support
Additional auxv entries leads to more instructions in start-up
while walking the list, along with different cache conflicts
wrt stack entries.
2016-03-17 10:32:53 -07:00
Steve Reinhardt 4fc69db8f8 stats: update stats for mmap changes 2016-03-17 10:30:58 -07:00
Steve Reinhardt 9d8fec0d90 stats: update stats for mmap() change.
SE O3 runs see an additional reg read per mmap() call.
2016-03-17 10:25:11 -07:00
Steve Reinhardt 807e2705b4 stats: update gpu-ruby-GPU_RfO stats
Output changed way back in this cset:

changeset:   11345:b6a66a90e0a1
user:        John Kalamatianos <john.kalamatianos@amd.com>
summary:     gpu: fix bugs with MemFence, Flat Instrs and Resource utilization
2016-02-18 10:42:03 -05:00
Krishnendra Nathella cabd4768c7 cpu: Fix LLSC atomic CPU wakeup
Writes to locked memory addresses (LLSC) did not wake up the locking
CPU. This can lead to deadlocks on multi-core runs. In AtomicSimpleCPU,
recvAtomicSnoop was checking if the incoming packet was an invalidation
(isInvalidate) and only then handled a locked snoop. But, writes are
seen instead of invalidates when running without caches (fast-forward
configurations). As as simple fix, now handleLockedSnoop is also called
even if the incoming snoop packet are from writes.
2015-07-19 15:03:30 -05:00
Matteo Andreozzi 496a8c6c92 cpu: TraceGen fix for tick frequency check
Bug fix for check on protobuf file frequency being different than
global frequency.

The ASCII encoder script is also fixed, and the example trace used in
the regressions is updated.
2016-02-24 04:16:55 -05:00
Andreas Hansson c6cede244b stats: Update stats to reflect changes to cache and crossbar 2016-02-10 04:08:27 -05:00
Steve Reinhardt ce35c06c6e stats: update EIO stats for recent changes 2016-02-06 01:35:03 -05:00
Tony Gutierrez 1285d639eb stats: update stats to after GPU checkin 2016-01-22 10:42:13 -05:00
Tony Gutierrez 1a7d3f9fcb gpu-compute: AMD's baseline GPU model 2016-01-19 14:28:22 -05:00
Steve Reinhardt 2b49d3b6ca tests: update EIO reference outputs 2015-12-28 15:43:06 -05:00
Anthony Gutierrez 4935f0d5ff stats: bump stats to reflect ruby tester changes 2015-12-12 17:27:38 -05:00
Andreas Sandberg bbcbe028fe stats: Update to reflect changes to PCI handling 2015-12-05 00:11:25 +00:00
Andreas Sandberg 5a249e03a4 stats: Update to reflect changes to RealView platform code 2015-12-04 00:19:05 +00:00
Nilay Vaish de489e1997 stats: updates due to recent chagnesets 2015-11-16 05:08:57 -06:00
Nilay Vaish e1385784f2 stats: remove wb_penalized and wb_penalized_rate 2015-11-16 04:58:29 -06:00
Andreas Hansson 324bc9771d stats: Update stats to match cache changes 2015-11-06 03:26:50 -05:00
Joel Hestness 735c4a8766 stats: Update for UDelayEvent quiesce change 2015-10-10 16:45:41 -05:00