Date: | Sun, 28 Feb 2010 18:18:56 +0330 |
---|---|
From: | mohammad maghsoudloo <mohammad.maghsoudloo@xxxxxxxxx> |
Subject: | [Gems-users] Questions about Creating Warm Checkpoint |
I am trying to run a benchmark (BARNES in Splash-2) using SIMICS+RUBY & I made a cold checkpoint of benchmark as described in isca tutorial,I followed it & I also checked the earlier posts.
Here is what I am doing: simics> read-configuration ../checkpoints/cold.check
simics> @sys.path.append("../gen-scripts")
simics> @import mfacet
simics> istc-disable
simics> dstc-disable
simics> instruction-fetch-mode instruction-fetch-trace
simics> cpu-switch-time 1
simics> magic-break-enable
simics> load-module ruby
simics> ruby0.setparam g_NUM_PROCESSORS 1
simics> ruby0.setparam g_MEMORY_SIZE_BYTES 4294967296
simics> ruby0.setparam g_NUM_L2_BANKS 8
simics> ruby0.setparam L2_CACHE_ASSOC 4
simics> ruby0.setparam L2_CACHE_NUM_SETS_BITS 16
simics> ruby0.setparam NETWORK_LINK_LATENCY 50
simics> ruby0.init
simics> c
After this i am typing this command in solaris console to run benchmark & create warm checkpoint "./BARNES < input" but i am getting following error :
Segmentation fault (SIGSEGV) in main thread The simulation state has been corrupted. Simulation cannot continue. Please restart Simics. [cpu0] v:0x0000000000012078 p:0x00007012078 magic (sethi 0x400, %g0) What i am doing wrong? "Please help me"
|
[← Prev in Thread] | Current Thread | [Next in Thread→] |
---|---|---|
|
Previous by Date: | [Gems-users] MEMBAR implementation in opal+ruby, Byn Choi |
---|---|
Next by Date: | , (nil) |
Previous by Thread: | [Gems-users] Question about multiprogrammed workload simulation methodology, 안정섭 |
Next by Thread: | [Gems-users] Reference count and number of misses per set, Liz Joy |
Indexes: | [Date] [Thread] |