Commit graph

237 commits

Author SHA1 Message Date
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
Brad Beckmann
8011e80725 ruby: The persistent table files from GEMS
These files are need by the MOESI_CMP_token protocol.
2009-11-18 16:34:32 -08:00
Brad Beckmann
2783a7b9ad ruby: returns the number of LLC needed for broadcast
Added feature to CacheMemory to return the number of last level caches.
This count is need for broadcast protocols such as MOESI_hammer.
2009-11-18 16:34:31 -08:00
Brad Beckmann
7b8fcecf11 ruby: cache configuration fix to use bytes
Changed cache size to be in bytes instead of kb so that testers can use very
small caches and increase the chance of writeback races.
2009-11-18 16:34:31 -08:00
Brad Beckmann
99338a7460 ruby: fix CacheMemory destructor 2009-11-18 16:33:35 -08:00
Brad Beckmann
7ab484624f ruby: split CacheMemory.hh into a .hh and a .cc 2009-11-18 16:33:35 -08:00
Brad Beckmann
204d1776ca ruby: Fixed Directory memory destructor 2009-11-18 13:55:58 -08:00
Brad Beckmann
3cf24f9716 ruby: Support for merging ALPHA_FS and ruby
Connects M5 cpu and dma ports directly to ruby sequencers and dma
sequencers.  Rubymem also includes a pio port so that pio requests
and be forwarded to a special pio bus connecting to device pio
ports.
2009-11-18 13:55:58 -08:00
Brad Beckmann
17e14efa7e ruby: Ruby 64-bit address output fixes. 2009-11-18 13:55:57 -08:00
Derek Hower
9ef5e72917 ruby: added sequencer stats to track what requests are waiting on 2009-11-18 11:55:30 -06:00
Derek Hower
f7f475a6f4 ruby: gave ALIASED_REQUEST priority over BUFFER_FULL in sequencer 2009-11-13 09:44:51 -06:00
Derek Hower
2ee04d6587 ruby: reduce the memory usage of ruby by making memory vector page based 2009-11-13 09:43:39 -06:00
Derek Hower
ceb8fde914 ruby: cache memory bugfix 2009-11-13 09:42:47 -06:00
Polina Dudnik
4f463b3a26 Atomics bug fix 2009-09-21 13:04:52 -05:00
Polina Dudnik
114d8724dd Functionality migrated to sequencer. 2009-09-17 17:39:52 -05:00
Derek Hower
31a3ef03cb ruby: improve libruby_issue_request feedback 2009-09-15 21:37:40 -05:00
Derek Hower
144459032a removed isReady from the library interface 2009-09-15 20:49:54 -05:00
Derek Hower
11f3f83068 ruby:removed unused code from CacheMemory 2009-09-14 17:52:46 -05:00
Derek Hower
0637fe0bfd ruby: removed SMT-related Sequencer assert 2009-09-10 21:19:54 -05:00
Derek Hower
3bb2fcfc84 ruby: made Locked read/write atomic requests within ruby 2009-09-09 12:39:10 -05:00
Derek Hower
15aa180570 merge 2009-08-25 10:37:21 -05:00
Derek Hower
6cd552483b Automated merge with ssh://hg@m5sim.org/m5 2009-08-25 10:10:23 -05:00
Derek Hower
03bf748ac7 ruby: CacheMemory tag lookup uses a hash instead of a loop 2009-08-25 10:09:47 -05:00
Polina Dudnik
a4fc1bad94 [mq]: first_patch 2009-08-21 15:52:46 -05:00
Polina Dudnik
6654fe02da Made servicing_atomic a counter and added started writes:
a function for setting the flag to indicate that
the rmw_writes started issuing
2009-08-15 12:45:11 -05:00
Polina Dudnik
de25decf37 Multi-line RMW handling 2009-08-14 14:24:15 -05:00
Polina Dudnik
4b924fd16c SMT atomics modifications:
don't allow enquing from other threads if servicing and atomic for a thread
2009-08-14 14:06:14 -05:00
Derek Hower
33b28fde7a slicc: added MOESI_CMP_directory, DMA SequencerMsg, parameterized controllers
This changeset contains a lot of different changes that are too
mingled to separate.  They are:

1.  Added MOESI_CMP_directory

I made the changes necessary to bring back MOESI_CMP_directory,
including adding a DMA controller.  I got rid of MOESI_CMP_directory_m
and made MOESI_CMP_directory use a memory controller. Added a new
configuration for two level protocols in general, and
MOESI_CMP_directory in particular.

2.  DMA Sequencer uses a generic SequencerMsg

I will eventually make the cache Sequencer use this type as well.  It
doesn't contain an offset field, just a physical address and a length.
MI_example has been updated to deal with this.

3. Parameterized Controllers

SLICC controllers can now take custom parameters to use for mapping,
latencies, etc.  Currently, only int parameters are supported.
2009-08-04 12:52:52 -05:00
Derek Hower
d9ff3021ba ruby: fixed clearStats 2009-07-29 13:46:58 -05:00
Derek Hower
469256d823 ruby: removed unused/incorrect profiler state 2009-07-27 21:43:43 -05:00
Derek Hower
7f34ee36ec ruby: fixed sequencer RMW data bug 2009-07-21 19:42:09 -05:00
Derek Hower
e59d0e3e89 ruby: moved cache stats from Profiler to CacheMemory
Caches are now responsible for their own statistic gathering.  This
requires a direct callback from the protocol on misses, and so all
future protocols need to take this into account.
2009-07-20 09:40:43 -05:00
Derek Hower
7cd2d8f687 ruby: removed all refs to old RubyConfig 2009-07-18 18:20:03 -05:00
Derek Hower
f3d8d29342 ruby: removed dead files 2009-07-18 18:17:48 -05:00
Derek Hower
926ab6e6db merge 2009-07-18 17:40:20 -05:00
Derek Hower
4b7ea4cb51 ruby: fixed dma sequencer bug
The DMASequencer was still using a parameter from the old RubyConfig,
causing an offset error when the requested data wasn't block aligned.
This changeset also includes a fix to MI_example for a similar bug.
2009-07-18 17:03:51 -05:00
Polina Dudnik
5f551d9ca2 1. Got rid of unused functions in DirectoryMemory
2. Reintroduced RMW_Read and RMW_Write
3. Defined -2 in the Sequencer as well as made a note about mandatory queue

Did not address the issues in the slicc because remaking the atomics altogether to allow
multiple processors to issue atomic requests at once
2009-07-13 17:22:29 -05:00
Polina Dudnik
9a675a0391 Changes to add tracing and replaying command-line options
Trace is automatically ended upon a manual checkpoint
2009-07-13 12:50:10 -05:00
Polina Dudnik
b28058917c Locked requests should actually be converted to ST rather than ATOMIC, because ATOMIC is for RMW. 2009-07-13 12:11:17 -05:00
Polina Dudnik
c66af9f474 Minor fixes for compiling 2009-07-13 11:59:13 -05:00
Polina Dudnik
7606c71ea5 Replaced RMW with Locked. RMW will be used for the coherence-aided atomics other than LLSC 2009-07-13 11:37:56 -05:00
Polina Dudnik
faf823f947 Moved the lock check and clearing the lock into makeRequest 2009-07-13 11:34:38 -05:00
Polina Dudnik
86ce60e5cd Forgot to replace one of the RubyRequest_RMW 2009-07-13 11:25:23 -05:00
Polina Dudnik
226981b2a6 Reintegrated Derek's functional implementation of atomics with a minor change: don't clear lock on failure 2009-07-13 11:13:29 -05:00
Nathan Binkert
a7904e2cf3 ruby: apply some fixes that were overwritten by the recent ruby import. 2009-07-06 15:49:47 -07:00
Nathan Binkert
1f6933503d scons: update SCons files for changes in ruby. 2009-07-06 15:49:47 -07:00
Nathan Binkert
92de70b69a ruby: Import the latest ruby changes from gems.
This was done with an automated process, so there could be things that were
done in this tree in the past that didn't make it.  One known regression
is that atomic memory operations do not seem to work properly anymore.
2009-07-06 15:49:47 -07:00
Nathan Binkert
05f6a4a6b9 ruby: replace strings that were missed in original ruby import. 2009-07-06 15:49:47 -07:00
Nathan Binkert
d3d8a5a83b copyright: I missed some copyrights during ruby integration 2009-06-10 00:41:56 -07:00
Nathan Binkert
47877cf2db types: add a type for thread IDs and try to use it everywhere 2009-05-26 09:23:13 -07:00
Nathan Binkert
5207586b26 ruby: deal with printf warnings and convert some to cprintf 2009-05-12 22:33:05 -07:00
Nathan Binkert
cf6b4ef734 ruby: add RUBY sticky option that must be set to add ruby to the build
Default is false
2009-05-11 10:38:46 -07:00
Daniel Sanchez
93f2f69657 ruby: Working M5 interface and updated Ruby interface.
This changeset also includes a lot of work from Derek Hower <drh5@cs.wisc.edu>

RubyMemory is now both a driver for Ruby and a port for M5.  Changed
makeRequest/hitCallback interface. Brought packets (superficially)
into the sequencer. Modified tester infrastructure to be packet based.
and Ruby can be used together through the example ruby_se.py
script. SPARC parallel applications work, and the timing *seems* right
from combined M5/Ruby debug traces. To run,
% build/ALPHA_SE/m5.debug configs/example/ruby_se.py -c
  tests/test-progs/hello/bin/alpha/linux/hello -n 4 -t
2009-05-11 10:38:46 -07:00
Polina Dudnik
7769cc9092 ruby: decommission code
1. Set.* and BigSet.* are replaced with OptBigSet.* which was renamed Set.*
2. Decomissioned all bloom filters
3. Decomissioned ruby/simics directory
2009-05-11 10:38:46 -07:00
Derek Hower
0ccf8f35a5 ruby: removed dead functions from the sequencer 2009-05-11 10:38:46 -07:00
Polina Dudnik
29f82f265a ruby: Removed g_SIMULATING flag
1. removed checks from tester files
2. removed else clause in Sequencer and DirectoryMemory else clause is
needed by the tester, it is up to Derek to revive it elsewhere when he
gets to it

Also:
1. Changed m_entries in DirectoryMemory to a map
2. And replaced SIMICS_read_physical_memory with a call to now-dummy
Derek's-to-be readPhysMem function
2009-05-11 10:38:46 -07:00
Nathan Binkert
7311fd7182 ruby: Migrate all of ruby and slicc to SCons.
Add the PROTOCOL sticky option sets the coherence protocol that slicc
will parse and therefore ruby will use.  This whole process was made
difficult by the fact that the set of files that are output by slicc
are not easily known ahead of time.  The easiest thing wound up being
to write a parser for slicc that would tell me.  Incidentally this
means we now have a slicc grammar written in python.
2009-05-11 10:38:46 -07:00
Nathan Binkert
e40b8e34c8 ruby: clean up a few warnings 2009-05-11 10:38:45 -07:00
Dan Gibson
8b9f70b9e4 ruby: Fixed some unresolved references. 2009-05-11 10:38:45 -07:00
Nathan Binkert
24da30e317 ruby: Make ruby #includes use full paths to the files they're including.
This basically means changing all #include statements and changing
autogenerated code so that it generates the correct paths.  Because
slicc generates #includes, I had to hard code the include paths to
mem/protocol.
2009-05-11 10:38:45 -07:00
Dan Gibson
d8c592a05d ruby: remove unnecessary code.
1) Removing files from the ruby build left some unresovled
symbols. Those have been fixed.

2) Most of the dependencies on Simics data types and the simics
interface files have been removed.

3) Almost all mention of opal is gone.

4) Huge chunks of LogTM are now gone.

5) Handling 1-4 left ~hundreds of unresolved references, which were
fixed, yielding a snowball effect (and the massive size of this
delta).
2009-05-11 10:38:45 -07:00
Derek Hower
6ceaffd724 ruby: Cleaned up sequencer. Removed LogTM specific code. 2009-05-11 10:38:45 -07:00
Derek Hower
3d2acc547c ruby: added Packet interface to makeRequest and isReady.
Also pushed Packet usage into the Sequencer
2009-05-11 10:38:45 -07:00
Derek Hower
6e8373fad6 ruby: Renamed Ruby's EventQueue to RubyEventQueue
--HG--
rename : src/mem/ruby/eventqueue/EventQueue.cc => src/mem/ruby/eventqueue/RubyEventQueue.cc
rename : src/mem/ruby/eventqueue/EventQueue.hh => src/mem/ruby/eventqueue/RubyEventQueue.hh
rename : src/mem/ruby/eventqueue/EventQueueNode.cc => src/mem/ruby/eventqueue/RubyEventQueueNode.cc
rename : src/mem/ruby/eventqueue/EventQueueNode.hh => src/mem/ruby/eventqueue/RubyEventQueueNode.hh
2009-05-11 10:38:45 -07:00
Daniel Sanchez
ab5e4a22b3 ruby: Removed System name clash by renaming ruby's System to RubySystem 2009-05-11 10:38:44 -07:00
Nathan Binkert
2f30950143 ruby: Import ruby and slicc from GEMS
We eventually plan to replace the m5 cache hierarchy with the GEMS
hierarchy, but for now we will make both live alongside eachother.
2009-05-11 10:38:43 -07:00