Date: | Thu, 13 Mar 2008 16:50:50 -0700 |
---|---|
From: | "Jim Leek" <jrleek@xxxxxxxxx> |
Subject: | [Gems-users] Another el timestamp issue? |
I just got the following assertion running logTM with EL_Timestamp. I was doing the SPLASH-2 raytrace benchmark on teapot. end_transaction_magic_call: transaction started: 3317, transaction completed: 3285, transaction_limit: 10000, mem_res: 846.074219 mem_total: 876.199219 mem_ratio: 0.965619 commitTransaction ERROR NOT IN XACT proc =0 logical_proc = 0 xid = 16 isOpen = 0 tid = 31 pc = [0x1f8c0, line 0x1f8c0] level = 0 time = 11297793 simics-common: log_tm/TransactionInterfaceManager.C:243: void TransactionInterfaceManager::commitTransaction(int, int, bool): Assertion `m_transactionLevel[thread] >= 1' failed. *** Simics getting shaky, switching to 'safe' mode. *** Simics (main thread) received an abort signal, probably an assertion. Starting command line. (May have skipped commands in script files.) Has anyone seen this before? This is actually the second time I've gotten it with this configuration. So far, EL_Timestamp is the only style to exhibit this behavior. Jim |
[← Prev in Thread] | Current Thread | [Next in Thread→] |
---|---|---|
|
Previous by Date: | Re: [Gems-users] Opal wont catch magic breakpoint, Luke Yen |
---|---|
Next by Date: | [Gems-users] GEMS Compilation Error, Berkin Ozisikyilmaz |
Previous by Thread: | Re: [Gems-users] about Garnet, Greg Byrd |
Next by Thread: | [Gems-users] big CPI?, pathscale |
Indexes: | [Date] [Thread] |