| Date: | Sat, 25 Jun 2011 16:03:59 +0800 (CST) |
|---|---|
| From: | wyhsdkd <wyhsdkd@xxxxxxx> |
| Subject: | [Gems-users] Barrier_breaking |
|
Hi, I run the deque microbenchmark on logTM.The configuraion is 4 processors,g_procs_per_chip=4,g_num_L2_banks=4, NoC:HIERACHICAL_SWITCH network, xact_conflict_res:timestamp xact_eager_cd:true. when I run "./deque_TM 3 12 64",it works fine,but when executes "End_workload_transaction } Barrier_breaking(&local_sense,myid,gm.num_threads);"(see in deque.c) I find the output result,only one thread prints " BEGIN BARRIER",another two donnot,after a short while,the serengeti machine shows !
"segmentation fault-core dumped". I use "gdb -c core " and "where" to look for the error,but I get the following information: program terminated with signal 4,illegal instruction. [new process 66811] #0 0x0009eec0 in ??() I donnot know what's the meaning.Could anyone help me ?Thanks in advance! |
| [← Prev in Thread] | Current Thread | [Next in Thread→] |
|---|---|---|
| ||
| Previous by Date: | [Gems-users] Checkpoints creation failure, Andrew Hay |
|---|---|
| Next by Date: | [Gems-users] Question about network topology and Simics core mapping, Hamid Reza Khaleghzadeh |
| Previous by Thread: | Re: [Gems-users] An old question about Ruby Cycles and Simics Cycles, Aoxiang Tang |
| Next by Thread: | [Gems-users] Can gem5 enable ruby in full system mode?, huangyongbing |
| Indexes: | [Date] [Thread] |