sanchayanmaity/gem5
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Config: Add support for restoring using a timing CPU

Browse source 
Currently there is an assumption that restoration from a checkpoint will
happen by first restoring to an atomic CPU and then switching to a timing
CPU. This patch adds support for directly restoring to a timing CPU. It
adds a new option '--restore-with-cpu' which is used to specify the type
of CPU to which the checkpoint should be restored to. It defaults to
'atomic' which was the case before.
This commit is contained in:
Nilay Vaish 2012-01-11 13:50:18 -06:00
parent bf59a9298f
commit 03229f2575
2 changed files with 13 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
configs/common/Options.py
View file

@ -85,6 +85,10 @@ parser.add_option("--work-end-checkpoint-count", action="store", type="int",
help="checkpoint at specified work end count")
parser.add_option("--work-cpus-checkpoint-count", action="store", type="int",
help="checkpoint and exit when active cpu count is reached")
parser.add_option("--restore-with-cpu", action="store", type="choice",
default="atomic", choices = ["atomic", "timing",
"detailed", "inorder"],
help = "cpu type for restoring from a checkpoint")
# CPU Switching - default switch model goes from a checkpoint

10
configs/common/Simulation.py
View file

@ -60,7 +60,15 @@ def setCPUClass(options):
test_mem_mode = 'atomic'
if not atomic:
if options.checkpoint_restore != None or options.fast_forward:
if options.checkpoint_restore != None:
if options.restore_with_cpu != options.cpu_type:
CPUClass = TmpClass
class TmpClass(AtomicSimpleCPU): pass
else:
if options.restore_with_cpu != "atomic":
test_mem_mode = 'timing'
elif options.fast_forward:
CPUClass = TmpClass
class TmpClass(AtomicSimpleCPU): pass
else: