Re: [Gems-users] why the ruby cannot run multi-processors

[Greg Byrd <gbyrd@xxxxxxxx>]

The Simics system you are simulating must also have the same number of processors.  It appears that you have one processor in your Simics image, and you are telling GEMS that there are 4.

...Greg

On Wed, Apr 6, 2011 at 1:45 PM, <wangshuz@xxxxxxxxxxxxxxxxx> wrote:

Hello All,

I use Simics4.2 and GEMS 2.1.1

I can load ruby successfully. However I just can set "g_NUM_PROCESSORS 1". when I want  to set the processor number to 2 or more. It always have some problems.

This is my report of my error:

simics> instruction-fetch-mode instruction-fetch-trace

[board_cmp0.cpu[0] info] Instruction fetch trace is implemented using instruction cache access trace with a suitable cache line size.

simics> istc-disable

Turning I-STC off and flushing old data

simics> dstc-disable

Turning D-STC off and flushing old data

simics> cpu-switch-time 1

simics> load-module ruby

successful installation of the ruby timing model.

Registering a user decoder for the 'ultrasparc-ii' class.

simics> ruby0.init

Ruby Timing Mode

Creating event queue...

Creating event queue done

Creating system...

  Processors: 4

Segmentation fault (SIGSEGV) in main thread

#0  0x002ae010 (/home/shu/gems/simics-4.2.72/x86-linux/bin/libsimics-common.so + 0xb9010)

#1  0x002ae0c6 in SIM_step_count + 0x36 (/home/shu/gems/simics-4.2.72/x86-linux/bin/libsimics-common.so + 0xb90c6)

#2  0x02564ad2 in _ZN15SimicsProcessorC1EP6Systemi + 0x122 (/home/shu/gems/simics_42_workspace/x86-linux/lib/ruby.so + 0x23aad2)

#3  0x02559f71 in _ZN12SimicsDriverC1EP6System + 0x221 (/home/shu/gems/simics_42_workspace/x86-linux/lib/ruby.so + 0x22ff71)

#4  0x0257b2dc in _ZN6SystemC1Ev + 0x41c (/home/shu/gems/simics_42_workspace/x86-linux/lib/ruby.so + 0x2512dc)

#5  0x02497b0a in init_simulator + 0x28a (/home/shu/gems/simics_42_workspace/x86-linux/lib/ruby.so + 0x16db0a)

#6  0x02497f95 in _ZN9initvar_t8allocateEv + 0x15 (/home/shu/gems/simics_42_workspace/x86-linux/lib/ruby.so + 0x16df95)

#7  0x024aa997 in _ZN9initvar_t12dispatch_setEPvP11conf_objectP10attr_valueS4_ + 0xe7 (/home/shu/gems/simics_42_workspace/x86-linux/lib/ruby.so + 0x180997)

#8  0x024aac3f in initvar_dispatch_set + 0x2f (/home/shu/gems/simics_42_workspace/x86-linux/lib/ruby.so + 0x180c3f)

#9  0x00281123 (/home/shu/gems/simics-4.2.72/x86-linux/bin/libsimics-common.so + 0x8c123)

#10  0x00281acd in SIM_set_attribute + 0x5d (/home/shu/gems/simics-4.2.72/x86-linux/bin/libsimics-common.so + 0x8cacd)

#11  0x0032a6e3 (/home/shu/gems/simics-4.2.72/x86-linux/bin/libsimics-common.so + 0x1356e3)

#12  0x0063cf4d in PyCFunction_Call + 0x15d (/home/shu/gems/simics-4.2.72/x86-linux/sys/lib/libpython2.5.so.1.0 + 0x58f4d)

#13  0x0068a48c in PyEval_EvalFrameEx + 0x5d6c (/home/shu/gems/simics-4.2.72/x86-linux/sys/lib/libpython2.5.so.1.0 + 0xa648c)

#14  0x0068b893 in PyEval_EvalCodeEx + 0x793 (/home/shu/gems/simics-4.2.72/x86-linux/sys/lib/libpython2.5.so.1.0 + 0xa7893)

#15  0x00628fd0 (/home/shu/gems/simics-4.2.72/x86-linux/sys/lib/libpython2.5.so.1.0 + 0x44fd0)

The simulation state has been corrupted. Simulation cannot continue.

Please restart Simics.

Traceback (most recent call last):

  File "/mp/simics-4.2/src/core/common/terminal_frontend.py", line 509, in <lambda>

  File "/mp/simics-4.2/src/core/common/terminal_frontend.py", line 383, in write

  File "/mp/simics-4.2/src/core/common/terminal_frontend.py", line 363, in write_line

  File "/mp/simics-4.2/src/core/common/terminal_frontend.py", line 354, in output_text

  File "/mp/simics-4.2/src/core/common/terminal_frontend.py", line 342, in raw_write

SimExc_Index: Non-existent processor id

Exception in Python call

I don't know why I have these problems .

Regards,

Shu Wang

_______________________________________________
Gems-users mailing list
Gems-users@xxxxxxxxxxx
https://lists.cs.wisc.edu/mailman/listinfo/gems-users
Use Google to search the GEMS Users mailing list by adding "site:https://lists.cs.wisc.edu/archive/gems-users/" to your search.