Hi all,

I am trying to run PARSEC in Gem5 under full system mode. The benchmarks
run correctly when I set the simulated physical memory size to <=2GB.
However, I want to simulate a physical memory with 4GB.  When I set "return
'4000MB'" in line 49 of configs/common/Benchmarks.py to set the simulated
physical memory size to 4GB and run PARSEC again (using command
"build/ALPHA/gem5.fast configs/example/fs.py -n 2
--script=../parsecRunscripts/blackscholes_2c_simlarge_ckpts.rcS"), I get
the following error:
**********simout******************
...
panic: M5 panic instruction called at pc = 0xfffffc000031add0.
 @ cycle 470482786500
[execute:build/ALPHA/arch/alpha/generated/atomic_simple_cpu_exec.cc, line
11210]
Memory Usage: 4273680 KBytes
Program aborted at cycle 470482786500
Aborted
**********system.terminal*********
...
setup: forcing memory size to 33554432K (from -98304K).^M
freeing pages 1103:4194304^M
reserving pages 1103:1167^M
SMP: 2 CPUs probed -- cpu_present_map = 3^M
Built 1 zonelists in Zone order, mobility grouping on.  Total pages:
4165632^M
Kernel command line: root=/dev/hda1 console=ttyS0^M
PID hash table entries: 4096 (order: 12, 32768 bytes)^M
Using epoch = 1900^M
Console: colour dummy device 80x25^M
console [ttyS0] enabled^M
Dentry cache hash table entries: 4194304 (order: 12, 33554432 bytes)^M
Inode-cache hash table entries: 2097152 (order: 11, 16777216 bytes)^M
Memory: 33265208k/33554432k available (3757k kernel code, 285456k reserved,
261k data, 208k init)^M
Unable to handle kernel paging request at virtual address 0000000000000000^M
CPU 0 swapper(0): Oops 1^M
pc = [<fffffc00003a12dc>]  ra = [<fffffc00003a11bc>]  ps = 0007    Not
tainted^M
pc is at cache_alloc_refill+0x1ec/0x780^M
ra is at cache_alloc_refill+0xcc/0x780^M
v0 = 0000000000000001  t0 = 0000000000000000  t1 = 0000000000000000^M
t2 = 0000000000000000  t3 = 0000000000000001  t4 = 0000000000000000^M
t5 = 0000000000000000  t6 = fffffc07ff000000  t7 = fffffc0000814000^M
s0 = fffffc000080c2a8  s1 = ffffffffffffffff  s2 = fffffc0000822710^M
s3 = fffffc000080c408  s4 = fffffc07ff000030  s5 = 0000000000000000^M
s6 = fffffc000080c448^M
a0 = fffffc000080c448  a1 = 0000000000000009  a2 = 0000000000000001^M
a3 = 0000000000000002  a4 = 0000000000000000  a5 = 0000000000000044^M
t8 = ffffffffffffffff  t9 = 0000000000200200  t10= 00000000ffffffff^M
t11= fffffc000080c418  pv = fffffc00006bb0f0  at = fffffc000080c428^M
gp = fffffc000085bf40  sp = fffffc0000817d38^M
Trace:^M
[<fffffc00003a10b8>] kmem_cache_alloc+0xb8/0xf0^M
[<fffffc00003a3334>] kmem_cache_create+0x1f4/0x550^M
[<fffffc000031001c>] __start+0x1c/0x20^M
^M
Code: 4821f621  402207a1  e43fffe4  a4470000  a4670008  47f6040a <b4430000>
b4620008 ^M
Kernel panic - not syncing: Attempted to kill the idle task!^M

****************************************

To solve the above issue, I looked up former posts  and got the idea to
recompile system/alpha/console/console.c. I recompiled console.c using the
cross compile tool on the Gem5 website (
http://www.m5sim.org/dist/current/alpha_crosstool.tar.bz2). Then I put the
compiled console binary in the m5_system_2.0b3 folder. However, now I am
getting a different error message:

**********************simout***********
info: Entering event queue @ 0.  Starting simulation...
info: Launching CPU 1 @ 686481000
panic: M5 panic instruction called at pc = 0x8e41.
 @ cycle 697785500
[execute:build/ALPHA/arch/alpha/generated/atomic_simple_cpu_exec.cc, line
11210]
Memory Usage: 4268400 KBytes
Program aborted at cycle 697785500
Aborted

**********************system.terminal*****
^MGot Configuration 623
^Mmemsize FA000000 pages 7D000
^MFirst free page after ROM 0xFFFFFC0000018000
^MHWRPB 0xFFFFFC0000018000 l1pt 0xFFFFFC0000046000 l2pt 0xFFFFFC0000048000
l3pt_rpb 0xFFFFFC000004A000 l3pt_kernel 0xFFFFFC000004E000 l2reserv
0xFFFFFC000004C000
^Mkstart = 0xFFFFFC0000310000, kend = 0xFFFFFC0000899860, kentry =
0xFFFFFC0000310000, numCPUs = 0x2
^MCPU Clock at 2000 MHz IntrClockFrequency=1024
^MBooting with 2 processor(s)
^MKSP: 0x20043FE8 PTBR 0x23
^MKSP: 0x20043FE8 PTBR 0x23
^MConsole Callback at 0x0, fixup at 0x0, crb offset: 0x790
^MMemory cluster 0 [0 - 392]
^MMemory cluster 1 [392 - 511608]
^MInitalizing mdt_bitmap addr 0xFFFFFC0000038000 mem_pages 7D000
^MConsoleDispatch at virt 100008D8 phys 188D8 val FFFFFC00000100A8
^MBootstraping CPU 1 with sp=0xFFFFFC000007C000
^Munix_boot_mem ends at FFFFFC000007E000
^Mk_argc = 0
^Mjumping to kernel at 0xFFFFFC0000310000, (PCBB 0xFFFFFC0000018180 pfn
1101)

************************************************

I then ran GDB on gem5.debug to try to locate the source of the second
error. Here is the gdb output:

**********GDB*************
info: kernel located at:
/home/xunjian1/scratch/m5_system_2.0b3/binaries/vmlinux_2.6.27-gcc_4.3.4
Listening for system connection on port 3456
      0: system.tsunami.io.rtc: Real-time clock set to Thu Jan  1 00:00:00
2009
warn: CoherentBus system.membus has no snooping ports attached!
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
**** REAL SIMULATION ****
9223372036854775807
info: Entering event queue @ 0.  Starting simulation...
info: Launching CPU 1 @ 686481000
panic: M5 panic instruction called at pc = 0x8e41.
 @ cycle 697785500
[execute:build/ALPHA/arch/alpha/generated/atomic_simple_cpu_exec.cc, line
11210]
Memory Usage: 4276644 KBytes

Program received signal SIGABRT, Aborted.
0x00007ffff64f3635 in raise () from /lib64/libc.so.6
Missing separate debuginfos, use: debuginfo-install
glibc-2.12-1.132.el6_5.4.x86_64 keyutils-libs-1.4-4.el6.x86_64
krb5-libs-1.10.3-15.el6_5.1.x86_64 libcom_err-1.41.12-18.el6_5.1.x86_64
libgcc-4.4.7-4.el6.x86_64 libselinux-2.0.94-5.3.el6_4.1.x86_64
libstdc++-4.4.7-4.el6.x86_64 openssl-1.0.1e-16.el6_5.14.x86_64
python-libs-2.6.6-52.el6.x86_64 zlib-1.2.3-29.el6.x86_64
(gdb) bt
#0  0x00007ffff64f3635 in raise () from /lib64/libc.so.6
#1  0x00007ffff64f4e15 in abort () from /lib64/libc.so.6
#2  0x00000000005925cb in __exit_message (prefix=0x11426f7 "panic",
code=-1, func=0x1142d80 "execute",
    file=0x1142780
"build/ALPHA/arch/alpha/generated/atomic_simple_cpu_exec.cc", line=11210,
    fmt=0x11429b0 "M5 panic instruction called at pc = %#x.", a01=...,
a02=..., a03=..., a04=..., a05=..., a06=..., a07=..., a08=..., a09=...,
    a10=..., a11=..., a12=..., a13=..., a14=..., a15=..., a16=...) at
build/ALPHA/base/misc.cc:84
#3  0x00000000004ba2f5 in AlphaISAInst::M5panic::execute (this=0x357e940,
xc=0x7ffef5fe4010, traceData=0x0)
    at build/ALPHA/arch/alpha/generated/atomic_simple_cpu_exec.cc:11210
#4  0x0000000000850820 in AtomicSimpleCPU::tick (this=0x7ffef5fe4010) at
build/ALPHA/cpu/simple/atomic.cc:525
#5  0x000000000084c544 in AtomicSimpleCPU::TickEvent::process
(this=0x7ffef60e4280) at build/ALPHA/cpu/simple/atomic.cc:72
#6  0x0000000000ccd576 in EventQueue::serviceOne (this=0x1992b70) at
build/ALPHA/sim/eventq.cc:204
#7  0x0000000000d186dc in simulate (num_cycles=9223372036854775807) at
build/ALPHA/sim/simulate.cc:73
#8  0x0000000000c7ad88 in _wrap_simulate__SWIG_0 (args=0x28ba7d0) at
build/ALPHA/python/swig/event_wrap.cc:4491

*******************************

I am lost at what I should do next. Please help. Thanks!

Stevo
_______________________________________________
gem5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Reply via email to