Commit graph

115 commits

Author SHA1 Message Date
Brad Beckmann
ac5bb214e3 ruby: Reset ruby stats in RubySystem unserialize
The main purpose for clearing stats in the unserialize process is so
that the profiler can correctly set its start time to the unserialized
value of curTick.
2010-08-20 11:46:13 -07:00
Brad Beckmann
bcdd19df03 ruby: Added SC fail indication to trace profiling 2010-08-20 11:46:13 -07:00
Brad Beckmann
b6d08e0455 ruby: Fixed RubyPort sendTiming callbacks
Fixed RubyPort schedSendTiming calls to match ruby frequency.
2010-08-20 11:46:13 -07:00
Brad Beckmann
8e5c441a54 ruby: fix ruby llsc support to sync sc outcomes
Added support so that ruby can determine the outcome of store conditional
operations and reflect that outcome to M5 physical memory and cpus.
2010-08-20 11:46:12 -07:00
Brad Beckmann
54d76f0ce5 ruby: Fixed L2 cache miss profiling
Fixed L2 cache miss profiling for the MOESI_CMP_token protocol
2010-08-20 11:46:12 -07:00
Brad Beckmann
4b4e725921 ruby: Reincarnated the responding machine profiling
This patch adds back to ruby the capability to understand the response time
for messages that hit in different levels of the cache heirarchy.
Specifically add support for the MI_example, MOESI_hammer, and MOESI_CMP_token
protocols.
2010-08-20 11:46:12 -07:00
Brad Beckmann
808701a10c memtest: Memtester support for DMA
This patch adds DMA testing to the Memtester and is inherits many changes from
Polina's old tester_dma_extension patch.  Since Ruby does not work in atomic
mode, the atomic mode options are removed.
2010-08-20 11:46:12 -07:00
Brad Beckmann
eb1e5636e3 ruby: Fixed printout when Sequencer detects a deadlock 2010-08-20 11:41:35 -07:00
Nathan Binkert
3df84fd8a0 ruby: get rid of the Map class 2010-06-10 23:17:07 -07:00
Nathan Binkert
006818aeea ruby: get rid of Vector and use STL
add a couple of helper functions to base for deleteing all pointers in
a container and outputting containers to a stream
2010-06-10 23:17:07 -07:00
Nathan Binkert
bc87fa30d7 ruby: get rid of RefCnt and Allocator stuff use base/refcnt.hh
This was somewhat tricky because the RefCnt API was somewhat odd.  The
biggest confusion was that the the RefCnt object's constructor that
took a TYPE& cloned the object.  I created an explicit virtual clone()
function for things that took advantage of this version of the
constructor.  I was conservative and used clone() when I was in doubt
of whether or not it was necessary.  I still think that there are
probably too many instances of clone(), but hopefully not too many.

I converted several instances of const MsgPtr & to a simple MsgPtr.
If the function wants to avoid the overhead of creating another
reference, then it should just use a regular pointer instead of a ref
counting ptr.

There were a couple of instances where refcounted objects were created
on the stack.  This seems pretty dangerous since if you ever
accidentally make a reference to that object with a ref counting
pointer, bad things are bound to happen.
2010-06-10 23:17:06 -07:00
Nathan Binkert
141f61d83a ruby: get rid of gems_common/util.hh and .cc and use stuff in src/base 2010-04-02 11:20:32 -07:00
Nathan Binkert
f1c3f3044b ruby: get "using namespace" out of headers
In addition to obvious changes, this required a slight change to the slicc
grammar to allow types with :: in them.  Otherwise slicc barfs on std::string
which we need for the headers that slicc generates.
2010-04-02 11:20:32 -07:00
Nathan Binkert
be10204729 style: another ruby style pass 2010-03-31 16:56:45 -07:00
Nathan Binkert
5ab13e2deb ruby: style pass 2010-03-22 18:43:53 -07:00
Brad Beckmann
66632539b6 ruby: improved isReadWrite fix me comment 2010-03-22 11:19:17 -07:00
Brad Beckmann
f9408f984f ruby: Changed the default set size to 1
Previously, the set size was set to 4.  This was mostly do to the fact that a
crazy graduate student use to create networks with 256 l2 cache banks.  Now it
is far more likely that users will create systems with less than 64 of any
particular controller type.  Therefore Ruby should be optimized for a set size
of 1.
2010-03-21 21:22:21 -07:00
Brad Beckmann
4f044605e8 ruby: Adds configurable bit selection for numa mapping 2010-03-21 21:22:21 -07:00
Brad Beckmann
8b15ed7ebf ruby: Added flag to disable mem_vec allocation
The RubySystem flag no_mem_vec will disable Ruby from allocating it's memory
data array.
2010-03-21 21:22:21 -07:00
Brad Beckmann
92cfd1cac7 ruby: Ruby support for sparse memory
The patch includes direct support for the MI example protocol.
2010-03-21 21:22:21 -07:00
Brad Beckmann
6d22db4eaa ruby: Ruby support for LLSC 2010-03-21 21:22:21 -07:00
Brad Beckmann
d464087101 ruby: Added copyright to many Ruby *.py files 2010-03-21 21:22:20 -07:00
Nathan Binkert
edb59ed263 ruby: Fix copyrights on files
Mostly files missed during import or screwed up during import
2010-03-14 20:58:45 -07:00
Nathan Binkert
fce7c820f4 bugfix: since pow() causes a bug don't use it
It's a power of two anyway, so why use it in the first place.
2010-03-12 15:11:09 -08:00
Nathan Binkert
140785d24c ruby: get rid of std-includes.hh
Do not use "using namespace std;" in headers
Include header files as needed
2010-03-10 18:33:11 -08:00
Brad Beckmann
143d8ea698 ruby: removed last level cache support
Removed the last level cache support and MOESI_hammer's dependency on it.
Replaces the LLC support with the more generic MachineType count.
2010-01-29 20:29:34 -08:00
Brad Beckmann
1feae85017 ruby: Removed static members in RubyPort including hitcallback
Removed static members in RubyPort and removed the ruby request unique id.
2010-01-29 20:29:33 -08:00
Brad Beckmann
a579d3e43c ruby: Removed the old config interface
Removed the old config interface from RubySystem and libruby.
2010-01-29 20:29:33 -08:00
Brad Beckmann
8dd45674ae ruby: Converted Garnet to M5 configuration 2010-01-29 20:29:32 -08:00
Brad Beckmann
134cc3d48d ruby: convert to M5 MemorySize
Converted both ruby caches and directory memory to use the M5 MemorySize python
type.
2010-01-29 20:29:23 -08:00
Brad Beckmann
45230a4f6b ruby: added the GEMS ruby tester 2010-01-29 20:29:23 -08:00
Brad Beckmann
f88faa6c11 ruby: cleaned up ruby profilers
Cleaned up the ruby profilers by moving the memory controller profiling code
out of the main profiler object and into a separate object similar to the
current CacheProfiler.  Both the CacheProfiler and MemCntrlProfiler are
specific to a particular Ruby object, CacheMemory and MemoryControl
respectively.  Therefore, these profilers should not be SimObjects and
created by the python configuration system, but instead private objects.  This
simplifies the creation of these profilers.
2010-01-29 20:29:22 -08:00
Brad Beckmann
cfe41d0a1b ruby: Removed RubySystem::getNumberOfSequencers
removed the static function RubySystem::getNumberOfSequencers and replaced
it with a python config variable
2010-01-29 20:29:21 -08:00
Brad Beckmann
1907e39fd2 ruby: added ruby stats print
Moved the previous rubymem stats print feature to ruby System so that ruby
stats are printed on simulation exit.
2010-01-29 20:29:21 -08:00
Brad Beckmann
ce2d13195b ruby: FS support using the new configuration system 2010-01-29 20:29:21 -08:00
Brad Beckmann
0f6535dba1 ruby: Convered ruby tracing support usage of sequencer
Modified ruby's tracing support to no longer rely on the RubySystem map
to convert a sequencer string name to a sequencer pointer.  As a
temporary solution, the code uses the sim_object find function.
Eventually, we should develop a better fix.
2010-01-29 20:29:20 -08:00
Brad Beckmann
2c9ca672df ruby: Memory Controller Profiler with new config system
This patch includes a rather substantial change to the memory controller
profiler in order to work with the new configuration system.  Most
noteably, the mem_cntrl_profiler no longer uses a string map, but instead
a vector.  Eventually this support should be removed from the main
profiler and go into a separate object.  Each memory controller should have
a pointer to that new mem_cntrl profile object.
2010-01-29 20:29:20 -08:00
Brad Beckmann
2a0555470c ruby: Converted MOESI_hammer dma cntrl to new config system 2010-01-29 20:29:19 -08:00
Brad Beckmann
3b290a35ac ruby: Added the cache profiler to the new config system 2010-01-29 20:29:19 -08:00
Brad Beckmann
4e5f4b5074 ruby: Converted the sequencer deadlock event to m5 eventq 2010-01-29 20:29:19 -08:00
Brad Beckmann
e15abd17f9 ruby: Wrapped ruby events into m5 events
Wrapped ruby events using the m5 event object.  Removed the prio_heap
from ruby's event queue and instead schedule ruby events on the m5 event
queue.
2010-01-29 20:29:19 -08:00
Brad Beckmann
63a60cc81e ruby: Removed the tech_nm variable from RubySystem 2010-01-29 20:29:19 -08:00
Brad Beckmann
12daaed84a ruby: Added clock to ruby system
As a first step to migrate ruby to the M5 eventqueue, added a clock
variable to the ruby system.
2010-01-29 20:29:19 -08:00
Brad Beckmann
ed81489954 ruby: Ruby changes required to use the python config system
This patch includes the necessary changes to connect ruby objects using
the python configuration system.  Mainly it consists of removing
unnecessary ruby object pointers and connecting the necessary object
pointers using the generated param objects.  This patch includes the
slicc changes necessary to connect generated ruby objects together using
the python configuraiton system.
2010-01-29 20:29:19 -08:00
Steve Reinhardt
a8ea70dac6 ruby: Calculate system total memory capacity in Python
rather than in RubySystem object.
2010-01-29 20:29:18 -08:00
Steve Reinhardt
98c94cfe3c ruby: Convert most Ruby objects to M5 SimObjects.
The necessary companion conversion of Ruby objects generated by SLICC
are converted to M5 SimObjects in the following patch, so this patch
alone does not compile.
Conversion of Garnet network models is also handled in a separate
patch; that code is temporarily disabled from compiling to allow
testing of interim code.
2010-01-29 20:29:17 -08:00
Derek Hower
07ea0891f1 ruby: new atomics implementation
This patch changes the way that Ruby handles atomic RMW instructions. This implementation, unlike the prior one, is protocol independent. It works by locking an address from the sequencer immediately after the read portion of an RMW completes. When that address is locked, the coherence controller will only satisfy requests coming from one port (e.g., the mandatory queue) and will ignore all others. After the write portion completed, the line is unlocked. This should also work with multi-line atomics, as long as the blocks are always acquired in the same order.
2010-01-19 17:11:36 -06:00
Derek Hower
279f179bab merge 2010-01-19 15:48:12 -06:00
Derek Hower
5aa104e072 ruby: cleaned up ruby-lang configuration 2009-12-04 13:12:40 -06:00
Brad Beckmann
5d8a669539 Resurrection of the CMP token protocol to GEM5 2009-11-18 16:34:33 -08:00