Age | Commit message (Collapse) | Author |
|
SLICC uses pointers for cache and TBE entries but not for directory entries.
This patch changes the protocols, SLICC and Ruby memory system so that even
directory entries are referenced using pointers.
--HG--
extra : rebase_source : abeb4ac78033d003153751f216fd1948251fcfad
|
|
--HG--
extra : rebase_source : ca98021c3f96422374fbd4500da312a5a9dd00df
|
|
panic.
--HG--
extra : rebase_source : 8152d4fa7d7354c9f150a450ae0710e95141ba4b
|
|
--HG--
extra : rebase_source : f9e22de341493a25ac6106c16ac35c61c128a080
|
|
--HG--
extra : rebase_source : c1ab57ea8805703d97cdee4f32410821a2d2a9db
|
|
--HG--
extra : rebase_source : b02ad38b477d87bf28f7677c985ec7fe9a7d4694
|
|
--HG--
extra : rebase_source : df2237b2ce01b1a3e1d6f112a62deadde4d92420
|
|
--HG--
extra : rebase_source : 90f217f28e195a8cee5d64b25c913b452d818676
|
|
--HG--
extra : rebase_source : 16da1c63263f8fd6fef9a842c577343cd6246a35
|
|
When a change in the frame buffer from the VNC server is detected, the new
frame is stored out to the m5out/frames_*/ directory. Specifiy the flag
"--frame-capture" when running configs/example/fs.py to enable this behavior.
--HG--
extra : rebase_source : d4e08e83f4fa6ff79f3dc9c433fc1f0487e057fc
|
|
--HG--
extra : rebase_source : 3301137733cdf5fdb471d56ef7990e7a3a865442
|
|
--HG--
extra : rebase_source : e56d1551d42d46b5f357cd63f9891715b664f6fc
|
|
--HG--
extra : rebase_source : 4697ba9eb1ca8c67fe0915fb8340d7d4ae94caba
|
|
There are two lines in O3CPU.py that set the dcache and icache
tgts_per_mshr to 20, ignoring any pre-configured value of tgts_per_mshr.
This patch removes these hardcoded lines from O3CPU.py and sets the default
L1 cache mshr targets to 20.
--HG--
extra : rebase_source : 6f92d950e90496a3102967442814e97dc84db08b
|
|
Adds the flag 'recvSnoops' which enables pagewalkers using DmaPorts,
to properly configure snoops.
--HG--
extra : rebase_source : 64207bef62c3268ddff2236ee4adae873812325f
|
|
--HG--
extra : rebase_source : 7a5780ab74d7c294682738c7ccb3ce8d56c6fd63
|
|
Squashes the subsequent instructions in O3 pipe after the service call, so that
they see the effect of the system call when re-executed. This isn't really an issue
with FS mode, but can show up in SE mode.
--HG--
extra : rebase_source : 613a69fe1d9834261e25a8cd340aa6b47578e1fe
|
|
--HG--
extra : rebase_source : 043b9307eef3c5b87f8e6370765641e016ed1fa7
|
|
--HG--
extra : rebase_source : 755f4f6eae52f88ed516a1f1ac9e2565725d89c1
|
|
--HG--
extra : rebase_source : 954a009a9f8eef6cae6050ee99f264e0fb456f85
|
|
I forgot to fix this as well per Ali's feedback.
--HG--
extra : rebase_source : e70d031cb5f91e2212a1a73ea1769bf0549b826c
|
|
There was a bug in the mm_disk implementation where a copy paste error
resulted in the d32 variable not being initialised (as it incorrectly
was used instead of d16), and gcc 4.5 complaining.
--HG--
extra : rebase_source : 9515e87b188b9eac189da8034cb13c3bf7d9e20b
|
|
--HG--
extra : rebase_source : 643e3541507576e30d9cd4dec045e5b94532c342
|
|
--HG--
extra : rebase_source : ee79ab89c5a707c1294f38abb84c60f8ef64196c
|
|
--HG--
extra : rebase_source : 1f5e8b7bb6b0a8bb4f951b6d7189964d96ed5df1
|
|
--HG--
extra : rebase_source : c226cd1e5e5ed4d4c64fa9427de4905bd8335e34
|
|
--HG--
extra : rebase_source : 51a2dd4bb643e3dc5b0218a6190cf5c1989f9691
|
|
--HG--
extra : rebase_source : b64c3d2348cb73177024695fb6e205d51bf1cda9
|
|
This patch updates reference statistics for the regression tests. This
update was necessitated by a recent change in behavior of some instructions
in the x86 architecture.
|
|
This patch changes the implementation of Ruby's recvTiming() function so
that it pushes a packet in to the Sequencer instead of a RubyRequest. This
requires changes in the Sequencer's makeRequest() and issueRequest()
functions, as they also need to operate on a Packet instead of RubyRequest.
|
|
|
|
|
|
This patch adds a fault model, which provides the probability of a number of
architectural faults in the interconnection network (e.g., data corruption,
misrouting). These probabilities can be used to realistically inject faults
in GARNET and faithfully evaluate the effectiveness of novel resilient NoC
architectures.
|
|
|
|
This patch adds a new microop for memory barrier. The microop itself does
nothing, but since it is marked as a memory barrier, the O3 CPU should flush
all the pending loads and stores before the fence to the memory system.
|
|
|
|
This patch removes some of the unused typedefs. It also moves
some of the typedefs from Global.hh to TypeDefines.hh. The patch
also eliminates the file NodeID.hh.
|
|
And by "everything" I mean all the quick regressions.
|
|
|
|
|
|
These options were missing from the script ruby_fs.py. This patch adds these
options to the script.
|
|
|
|
In RubySlicc_ComponentMapping.hh, certain '#define's have been used for
mapping MachineType to GenericMachineType. These '#define's are being
eliminated and the code will now be generated by SLICC instead. Also
are being eliminated some of the unused functions from
RubySlicc_ComponentMapping.sm.
|
|
PageTable supported an allocate() call that called back
through the Process to allocate memory, but did not have
a method to map addresses without allocating new pages.
It makes more sense for Process to do the allocation, so
this method was renamed allocateMem() and moved to Process,
and uses a new map() call on PageTable.
The remaining uses of the process pointer in PageTable
were only to get the name and the PID, so by passing these
in directly in the constructor, we can make PageTable
completely independent of Process.
|
|
|
|
Turns out these are due to diff reporting that files
acutally differed via a non-zero exit code.
|
|
Make DmaDevice::getPort() call PioDevice::getPort() instead
of just copying and pasting the code.
Also move definitions from .hh to .cc file.
|
|
Replace the (broken as of previous changeset) swig_objdecl() method
that allowed/forced you to substitute a whole new C++ struct
definition for SWIG to wrap with a set of export_method* hooks
that let you just declare a set of C++ methods (or other declarations)
that get inserted in the auto-generated struct.
Restore the System get/setMemoryMode methods, and use this mechanism
to specialize SimObject as well, eliminating teh need for sim_object.i.
Needed bits of sim_object.i are moved to the new pyobject.i.
Also sucked a little SimObject specialization into cxx_param_decl()
allowing us to get rid of src/sim/sim_object_params.hh. Now the
generation and wrapping of the base SimObject param struct is more
in line with how derived objects are handled.
--HG--
rename : src/python/swig/sim_object.i => src/python/swig/pyobject.i
|
|
- Move the random bits of SWIG code generation out of src/SConscript
file and into methods on the objects being wrapped.
- Cleaned up some variable naming and added some comments to make
the process a little clearer.
- Did a little generated file/module renaming:
- vptype_Foo now Foo_vector
- init_Foo is now Foo_init
This makes it easier to see all the Foo-related files in a
sorted directory listing.
- Made cxx_predecls and swig_predecls normal SimObject classmethods.
- Got rid of swig_objdecls hook, even though this breaks the System
objects get/setMemoryMode method exports. Will be fixing this in
a future changeset.
|
|
|