Hi,

I’m trying to figure out how to modify cache size of gem5 with ruby memory 
subsystem, but seems if the l1d cache size is lower than 64kB, there will be a 
kernel panic under SE model.

The command I’m using is:

./build/X86/gem5.opt configs/example/se.py --ruby --caches —l1d_size=64kB -c 
./tests/test-progs/hello/bin/x86/linux/hello

And that works fine, but if I change l1d_size to 32kB, an panic occurred.

./build/X86/gem5.opt configs/example/se.py --ruby --caches —l1d_size=32kB -c 
./tests/test-progs/hello/bin/x86/linux/hello

gem5 Simulator System.  http://gem5.org
gem5 is copyrighted software; use the --copyright option for details.

gem5 compiled Apr  4 2014 02:53:40
gem5 started Apr  4 2014 16:53:15
gem5 executing on gem5
command line: ./build/X86/gem5.opt configs/example/se.py --ruby --caches 
--l1d_size=32kB -c ./tests/test-progs/hello/bin/x86/linux/hello
Global frequency set at 1000000000000 ticks per second
0: system.remote_gdb.listener: listening for remote gdb #0 on port 7000
**** REAL SIMULATION ****
info: Entering event queue @ 0.  Starting simulation...
panic: Tried to read unmapped address 0x9f2ec0.
 @ tick 116208
[invoke:build/X86/arch/x86/faults.cc, line 160]
Memory Usage: 116208 KBytes
Program aborted at cycle 28320000
fish: Job 1, “./build/X86/gem5.opt configs/example/se.py --ruby --caches 
--l1d_size=32kB -c ./tests/test-progs/hello/bin/x86/linux/hello” terminated by 
signal SIGABRT (Abort)

But in ./configs/example/ruby_mem_test.py, they actually change l1d_size to 
some much smaller size. Is there any documents on that?

Best,

Baoxu Shi(Dash)
Computer Science and Engineering Department
University of Notre Dame
[email protected]



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

Reply via email to