-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
http://reviews.gem5.org/r/2228/
-----------------------------------------------------------

Review request for Default.


Repository: gem5


Description
-------

Changeset 10169:059294941a1b
---------------------------
fix draining bug where multiple cores hit max_insts_any_thread simultaneously

This can occur when using fast-forwarding for two cores.  Both cores hit 
max_insts_any_thread simultaneously, the first causes an event that drops back 
to python, but then second event stays in the queue.  If this occurs while 
trying to switch cores, drain's simulate() returns with the second max_insts 
event, rather than the Drain Finished event.  This just adds a loop to wait 
until the Drain Finished event occurs.


=======================
Unmodified test case
=======================

./build/ARM/gem5.debug configs/example/se.py -n2 --cpu-type=detailed --caches 
-F 100 --maxinsts=10000 --cmd="sjeng;sjeng"
gem5 Simulator System.  http://gem5.org
gem5 is copyrighted software; use the --copyright option for details.

gem5 compiled Apr 16 2014 09:34:34
gem5 started Apr 22 2014 09:16:09
gem5 executing on morgoth
command line: ./build/ARM/gem5.debug configs/example/se.py -n2 
--cpu-type=detailed --caches -F 100 --maxinsts=10000 --cmd=sjeng;sjeng
Global frequency set at 1000000000000 ticks per second
      0: system.switch_cpus0.isa: ISA system set to: 0 0x5707680
      0: system.switch_cpus1.isa: ISA system set to: 0 0x5707680
      0: system.cpu0.isa: ISA system set to: 0 0x5707680
      0: system.cpu1.isa: ISA system set to: 0 0x5707680
0: system.remote_gdb.listener: listening for remote gdb #0 on port 7000
0: system.remote_gdb.listener: listening for remote gdb #1 on port 7001
Switch at instruction count:100
info: Entering event queue @ 0.  Starting simulation...
Switched CPUS @ tick 61500
switching cpus
info: Entering event queue @ 61500.  Starting simulation...
gem5.debug: build/ARM/python/swig/drain_wrap.cc:3233: void 
cleanupDrainManager(DrainManager*): Assertion `drain_manager->getCount() == 0' 
failed.
Program aborted at cycle 61500
Aborted (core dumped)


=======================
Modified test case
=======================

./build/ARM/gem5.debug configs/example/se.py -n2 --cpu-type=detailed --caches 
-F 100 --maxinsts=10000 --cmd="sjeng;sjeng"
gem5 Simulator System.  http://gem5.org
gem5 is copyrighted software; use the --copyright option for details.

gem5 compiled Apr 22 2014 09:48:20
gem5 started Apr 22 2014 09:54:03
gem5 executing on morgoth
command line: ./build/ARM/gem5.debug configs/example/se.py -n2 
--cpu-type=detailed --caches -F 100 --maxinsts=10000 --cmd=sjeng;sjeng
Global frequency set at 1000000000000 ticks per second
      0: system.switch_cpus0.isa: ISA system set to: 0 0x51f4680
      0: system.switch_cpus1.isa: ISA system set to: 0 0x51f4680
      0: system.cpu0.isa: ISA system set to: 0 0x51f4680
      0: system.cpu1.isa: ISA system set to: 0 0x51f4680
0: system.remote_gdb.listener: listening for remote gdb #0 on port 7000
0: system.remote_gdb.listener: listening for remote gdb #1 on port 7001
Switch at instruction count:100
info: Entering event queue @ 0.  Starting simulation...
Switched CPUS @ tick 61500
switching cpus
info: Entering event queue @ 61500.  Starting simulation...
info: Entering event queue @ 61500.  Starting simulation...
warn: User mode does not have SPSR
warn: User mode does not have SPSR
warn: User mode does not have SPSR
warn: User mode does not have SPSR
warn: User mode does not have SPSR
warn: User mode does not have SPSR
warn: User mode does not have SPSR
warn: User mode does not have SPSR
**** REAL SIMULATION ****
info: Entering event queue @ 62000.  Starting simulation...
warn: CP14 unimplemented crn[14], opc1[7], crm[15], opc2[7]
info: Increasing stack size by one page.
info: Increasing stack size by one page.
info: Increasing stack size by one page.
info: Increasing stack size by one page.
info: Increasing stack size by one page.
info: Increasing stack size by one page.
info: Increasing stack size by one page.
info: Increasing stack size by one page.
info: Increasing stack size by one page.
info: Increasing stack size by one page.
info: Increasing stack size by one page.
info: Increasing stack size by one page.
Exiting @ tick 16120500 because a thread reached the max instruction count


Diffs
-----

  src/python/m5/simulate.py 7d7f635e7447 

Diff: http://reviews.gem5.org/r/2228/diff/


Testing
-------

passes build/ARM/tests/debug/quick/se


Thanks,

Andrew Lukefahr

_______________________________________________
gem5-dev mailing list
[email protected]
http://m5sim.org/mailman/listinfo/gem5-dev

Reply via email to