IRC.git
14 years agoFix the strategy for determination of when the gc mark phase is finished. In phase...
jzhou [Fri, 9 Jul 2010 00:15:16 +0000 (00:15 +0000)]
Fix the strategy for determination of when the gc mark phase is finished.  In phase 2, check if the number of send-out objs and received objs have been changed compared to that in the phase 1.  Also tuned the BAMBOO_SMEM_ZERO_UNIT_SIZE.  Looks like 4KB is OK.

14 years agoChange the local hashtable for recording the pointer mapping info used in the gc...
jzhou [Thu, 8 Jul 2010 21:48:02 +0000 (21:48 +0000)]
Change the local hashtable for recording the pointer mapping info used in the gc flush phase and make it more efficient.  Basically never release allocated memory and use mask instead of modular for hash entry computation.

14 years agoChange the zero out strategy for the shared memory. Do not zero out all the shared...
jzhou [Thu, 8 Jul 2010 01:43:15 +0000 (01:43 +0000)]
Change the zero out strategy for the shared memory.  Do not zero out all the shared memory at a time.  Each core will zero out the share memory chunk allocated to it when it gets the chunk from the master core.  Therefore the zero out process is parallelized.  Also do not zero out the whole chunk, instead, zero out only 4KB at a time when necessary so that there will not be much flush of L2 cache.

14 years agopublic VariableNode getVariableNodeNoMutation( TempDescriptor td ) was added for...
stephey [Wed, 7 Jul 2010 21:56:49 +0000 (21:56 +0000)]
public VariableNode getVariableNodeNoMutation( TempDescriptor td ) was added for client modules to access the Reachgraph after the analysis is done and no modifications are to be made by the client module.

14 years agoAdd a new shared memory allocation strategy: mixed mode. Comparing to the fixed mode...
jzhou [Wed, 7 Jul 2010 00:33:21 +0000 (00:33 +0000)]
Add a new shared memory allocation strategy: mixed mode. Comparing to the fixed mode, there are following differences: 1) the neighbours cores are extended to the cores that a core can reach in no more than 2 flips; 2) introduced a threshold--if the master core can not allocate the neighbour cores' shared memory chunks, it checks current shared memory usage rate, if greater than the threshold it will enable gc, otherwise it tries to allocate the shared memory globally for the request core.

14 years agoAdd a new shared memory allocation strategy: fixed mode. In this mode, the master...
jzhou [Tue, 6 Jul 2010 23:14:19 +0000 (23:14 +0000)]
Add a new shared memory allocation strategy: fixed mode.  In this mode, the master core first allocates the 'local' shared memory chunks to each core.  When there are no more 'local' shared memory chunks for a core, the master core tries to allocate shared memory chunks that are belonging to the core's neighbour cores.  The priority of the neighbour cores are left-right-up-below.  If the master core failed again, it enables GC.

14 years agoset the shared mem as 16MB
jzhou [Fri, 2 Jul 2010 19:50:43 +0000 (19:50 +0000)]
set the shared mem as 16MB

14 years agosome subtle reach state bug fixes uncovered by labyrinth benchmark, the benchmark...
jjenista [Fri, 2 Jul 2010 19:48:14 +0000 (19:48 +0000)]
some subtle reach state bug fixes uncovered by labyrinth benchmark, the benchmark compiles under ooojava and runs to completion now

14 years agonow it is working when only one machine left
jihoonl [Fri, 2 Jul 2010 02:30:30 +0000 (02:30 +0000)]
now it is working when only one machine left

14 years agorecovery done
jihoonl [Fri, 2 Jul 2010 02:19:58 +0000 (02:19 +0000)]
recovery done

14 years agoremove unnecessary files.
yeom [Thu, 1 Jul 2010 17:54:34 +0000 (17:54 +0000)]
remove unnecessary files.

14 years agobring benchmarks to OoOJava: raytracer, kmeans, power, labyrinth.
yeom [Thu, 1 Jul 2010 17:50:46 +0000 (17:50 +0000)]
bring benchmarks to OoOJava: raytracer, kmeans, power, labyrinth.

14 years agochange some bugs are fixed
jihoonl [Thu, 1 Jul 2010 15:45:52 +0000 (15:45 +0000)]
change some bugs are fixed

14 years agobug fixes and extensions
bdemsky [Thu, 1 Jul 2010 08:21:00 +0000 (08:21 +0000)]
bug fixes and extensions

14 years agoplotall2
bdemsky [Thu, 1 Jul 2010 08:03:54 +0000 (08:03 +0000)]
plotall2

14 years agoadd plotting scripts to cvs
bdemsky [Thu, 1 Jul 2010 06:15:31 +0000 (06:15 +0000)]
add plotting scripts to cvs

14 years agobug fix
bdemsky [Thu, 1 Jul 2010 06:14:21 +0000 (06:14 +0000)]
bug fix

14 years agoincorporated OoOJava into build code + fixed a couple of small bugs
yeom [Thu, 1 Jul 2010 04:50:00 +0000 (04:50 +0000)]
incorporated OoOJava into build code + fixed a couple of small bugs

14 years agoStatically ping memory from the nearest memory controller on the cores
jzhou [Thu, 1 Jul 2010 03:10:31 +0000 (03:10 +0000)]
Statically ping memory from the nearest memory controller on the cores

14 years agodebugged the reach graph support for effect conflicts
jjenista [Wed, 30 Jun 2010 18:51:43 +0000 (18:51 +0000)]
debugged the reach graph support for effect conflicts

14 years agoimplemented details to support effect conflict detection
jjenista [Wed, 30 Jun 2010 17:59:24 +0000 (17:59 +0000)]
implemented details to support effect conflict detection

14 years agobug
bdemsky [Wed, 30 Jun 2010 01:30:53 +0000 (01:30 +0000)]
bug

14 years agomore changes according to new effect analysis
yeom [Wed, 30 Jun 2010 01:01:31 +0000 (01:01 +0000)]
more changes according to new effect analysis
and set up debug features of OoOJava analysis

14 years agochanges according to new forms of effect analysis
yeom [Tue, 29 Jun 2010 23:45:49 +0000 (23:45 +0000)]
changes according to new forms of effect analysis

14 years agotweak to interface
jjenista [Tue, 29 Jun 2010 22:50:53 +0000 (22:50 +0000)]
tweak to interface

14 years agoreachability query interface for ooojava heap conflict analysis added
jjenista [Tue, 29 Jun 2010 22:11:27 +0000 (22:11 +0000)]
reachability query interface for ooojava heap conflict analysis added

14 years agogetting close to effects for new disjoint analysis
jjenista [Tue, 29 Jun 2010 19:05:04 +0000 (19:05 +0000)]
getting close to effects for new disjoint analysis

14 years agolittle bug fix
jjenista [Tue, 29 Jun 2010 17:53:08 +0000 (17:53 +0000)]
little bug fix

14 years agochanges.
yeom [Tue, 29 Jun 2010 17:05:53 +0000 (17:05 +0000)]
changes.

14 years agostall site critical regions implemented, including method calls and return values
jjenista [Tue, 29 Jun 2010 00:15:15 +0000 (00:15 +0000)]
stall site critical regions implemented, including method calls and return values

14 years agochanges for debugging
adash [Mon, 28 Jun 2010 23:57:37 +0000 (23:57 +0000)]
changes for debugging

14 years agorestate inaccessible vars for stall site so facts get joined properly
jjenista [Mon, 28 Jun 2010 22:21:43 +0000 (22:21 +0000)]
restate inaccessible vars for stall site so facts get joined properly

14 years agonew test case.
yeom [Mon, 28 Jun 2010 21:38:34 +0000 (21:38 +0000)]
new test case.

14 years agomore effects bug fixes
jjenista [Mon, 28 Jun 2010 21:28:00 +0000 (21:28 +0000)]
more effects bug fixes

14 years agobug fixes for effects analysis
jjenista [Mon, 28 Jun 2010 21:20:05 +0000 (21:20 +0000)]
bug fixes for effects analysis

14 years agomy changes
bdemsky [Mon, 28 Jun 2010 21:19:46 +0000 (21:19 +0000)]
my changes

14 years agostall site taints propagate awesomely, get cleared off also
jjenista [Mon, 28 Jun 2010 19:09:49 +0000 (19:09 +0000)]
stall site taints propagate awesomely, get cleared off also

14 years agoforgot to add moved files back in, injecting stall site taints now also
jjenista [Mon, 28 Jun 2010 18:44:51 +0000 (18:44 +0000)]
forgot to add moved files back in, injecting stall site taints now also

14 years agochanged organization and brought in a few new pieces for new disjoint+ooojava
jjenista [Mon, 28 Jun 2010 18:00:35 +0000 (18:00 +0000)]
changed organization and brought in a few new pieces for new disjoint+ooojava

14 years agochanges.
yeom [Mon, 28 Jun 2010 17:55:41 +0000 (17:55 +0000)]
changes.

14 years agoadd more steps to OoO analysis
yeom [Mon, 28 Jun 2010 17:52:17 +0000 (17:52 +0000)]
add more steps to OoO analysis

14 years agoworking on the remaining procedures of OoOJava analysis.
yeom [Sat, 26 Jun 2010 23:27:12 +0000 (23:27 +0000)]
working on the remaining procedures of OoOJava analysis.

14 years agoDo effects as a global space, don't even need to consider call site transform, taints...
jjenista [Sat, 26 Jun 2010 21:36:37 +0000 (21:36 +0000)]
Do effects as a global space, don't even need to consider call site transform, taints propagate interprocedurally and pick everything up, whoo hoo

14 years agoboth reach states and taints were not propagating to caller contexts with the correct...
jjenista [Sat, 26 Jun 2010 19:18:50 +0000 (19:18 +0000)]
both reach states and taints were not propagating to caller contexts with the correct caller-context predicates.  They should get the caller context predicates from the pre-call-site state or taint that indicated they should be brought from the callee.

14 years agomore changes
bdemsky [Fri, 25 Jun 2010 23:51:08 +0000 (23:51 +0000)]
more changes

14 years agochanges
bdemsky [Fri, 25 Jun 2010 23:16:32 +0000 (23:16 +0000)]
changes

14 years agogetting effects analysis going, need a few more pieces before call site analysis...
jjenista [Fri, 25 Jun 2010 22:41:14 +0000 (22:41 +0000)]
getting effects analysis going, need a few more pieces before call site analysis will work

14 years agoprint more data
bdemsky [Fri, 25 Jun 2010 21:28:25 +0000 (21:28 +0000)]
print more data

14 years agoupdates to transsim for journal submission
bdemsky [Fri, 25 Jun 2010 20:05:43 +0000 (20:05 +0000)]
updates to transsim for journal submission

14 years agorblock effects dont collect over method call, but its close
jjenista [Fri, 25 Jun 2010 18:59:20 +0000 (18:59 +0000)]
rblock effects dont collect over method call, but its close

14 years agoanalysis collects effects per method and interprocedurally
jjenista [Fri, 25 Jun 2010 18:18:50 +0000 (18:18 +0000)]
analysis collects effects per method and interprocedurally

14 years agoCapture the version with shared hash table for pointer mapping info required in the...
jzhou [Thu, 24 Jun 2010 23:50:43 +0000 (23:50 +0000)]
Capture the version with shared hash table for pointer mapping info required in the flush phase

14 years agobug fix, now interprocedural seems cool, unitl the next bug HA
jjenista [Thu, 24 Jun 2010 21:19:46 +0000 (21:19 +0000)]
bug fix, now interprocedural seems cool, unitl the next bug HA

14 years agotaints tested, propagate interprocedurally
jjenista [Thu, 24 Jun 2010 20:51:44 +0000 (20:51 +0000)]
taints tested, propagate interprocedurally

14 years agorblock in set vars get tainted on rblock enter and wiped at rblock exit, works nicely
jjenista [Thu, 24 Jun 2010 18:15:37 +0000 (18:15 +0000)]
rblock in set vars get tainted on rblock enter and wiped at rblock exit, works nicely

14 years agojust an interesting test case I never got around to checking in or exploring too...
jjenista [Thu, 24 Jun 2010 16:57:05 +0000 (16:57 +0000)]
just an interesting test case I never got around to checking in or exploring too much

14 years agochanges.
yeom [Thu, 24 Jun 2010 16:52:25 +0000 (16:52 +0000)]
changes.

14 years agoadd rblock relation analysis and makefile aware of new analysis files
jjenista [Thu, 24 Jun 2010 00:21:36 +0000 (00:21 +0000)]
add rblock relation analysis and makefile aware of new analysis files

14 years agoMore pieces for new version of analysis
jjenista [Wed, 23 Jun 2010 23:57:55 +0000 (23:57 +0000)]
More pieces for new version of analysis

14 years agodebugging..
jihoonl [Wed, 23 Jun 2010 23:48:17 +0000 (23:48 +0000)]
debugging..

14 years agochang
jihoonl [Wed, 23 Jun 2010 07:07:54 +0000 (07:07 +0000)]
chang

14 years agochange
jihoonl [Wed, 23 Jun 2010 06:47:09 +0000 (06:47 +0000)]
change

14 years agoget set up part of the stall site analysis
yeom [Wed, 23 Jun 2010 02:58:27 +0000 (02:58 +0000)]
get set up part of the stall site analysis

14 years agoUpdated taint class to allow call site plus var taints as well
jjenista [Wed, 23 Jun 2010 00:58:32 +0000 (00:58 +0000)]
Updated taint class to allow call site plus var taints as well

14 years agotaints at reach graph level implemented
jjenista [Tue, 22 Jun 2010 23:21:03 +0000 (23:21 +0000)]
taints at reach graph level implemented

14 years agogot the hooks in place to get taints for rblocks
jjenista [Tue, 22 Jun 2010 21:40:01 +0000 (21:40 +0000)]
got the hooks in place to get taints for rblocks

14 years agoset up OoOJava analysis.
yeom [Tue, 22 Jun 2010 20:46:56 +0000 (20:46 +0000)]
set up OoOJava analysis.

14 years agoGetting taints to propagate in new analysis, no parameter taints, RBLOCK taints only
jjenista [Tue, 22 Jun 2010 18:37:39 +0000 (18:37 +0000)]
Getting taints to propagate in new analysis, no parameter taints, RBLOCK taints only

14 years agochange
jihoonl [Tue, 22 Jun 2010 05:33:31 +0000 (05:33 +0000)]
change

14 years agorecovery..
jihoonl [Tue, 22 Jun 2010 04:09:44 +0000 (04:09 +0000)]
recovery..
still needs to fix

14 years agoCapture the version with mapinfo phase
jzhou [Mon, 21 Jun 2010 21:37:28 +0000 (21:37 +0000)]
Capture the version with mapinfo phase

14 years agocapturing partially implemented taints before altering implementation
jjenista [Mon, 21 Jun 2010 21:32:26 +0000 (21:32 +0000)]
capturing partially implemented taints before altering implementation

14 years agoForgot to include the makefile from the previous update.
stephey [Sat, 19 Jun 2010 00:17:29 +0000 (00:17 +0000)]
Forgot to include the makefile from the previous update.

14 years agoAdding Labyrinth3D files
stephey [Sat, 19 Jun 2010 00:15:30 +0000 (00:15 +0000)]
Adding Labyrinth3D files

in mlp, Normal_Java is a form of Labyrinth3D that can compile under normal Java.
in mlp, rBlocked is the rBlocked version that will compile with our compiler
NOTE: there seems to be a bug with make java in that the program skips right over rBlocks to print out statistics on the last part of the program EVEN THOUGH there are data dependencies. Yonghun suspects it's a bug in the compiler and will investigate over the weekend

in Original, Normal_Java is the original Labyrinth3D code with TM code removed and slightly modded to work with Normal Java.

14 years agotaints working intraprocedurally, a bug in inter I'm working out now
jjenista [Thu, 17 Jun 2010 23:21:15 +0000 (23:21 +0000)]
taints working intraprocedurally, a bug in inter I'm working out now

14 years agogetting parameter taints in new analysis
jjenista [Thu, 17 Jun 2010 22:20:37 +0000 (22:20 +0000)]
getting parameter taints in new analysis

14 years agoget partially set up new version of disjoint analysis with OoOJava analysis checked...
jjenista [Thu, 17 Jun 2010 21:15:23 +0000 (21:15 +0000)]
get partially set up new version of disjoint analysis with OoOJava analysis checked in to properly fix compiler and get yong hun in on the workspace

14 years agoJim, could you check in the rest of disjointness so that this compiles?
bdemsky [Wed, 16 Jun 2010 19:17:14 +0000 (19:17 +0000)]
Jim, could you check in the rest of disjointness so that this compiles?

This is a temporary fix to make the compiler work.

14 years agoUnder Original/Normal_Java/ one would find the original Labyrinth project ported...
stephey [Wed, 16 Jun 2010 00:32:28 +0000 (00:32 +0000)]
Under Original/Normal_Java/ one would find the original Labyrinth project ported to Transactional Memory by Jihoon and reported to normal Java by Stephen Yang

Under mlp is the Labyrinth project modified with rblocks. Under mlp/Normal_Java is a version that can be compiled and run on the normal Java platform. Under rBlocked is the rBlocked version that SHOULD run under OoOJava compiler. Both of which are ported by Stephen Yang (from Jihoon's original port)

NOTE that at this point in time, the rBlocked version causes a NullPointerException in the OoOJava compiler but will compile and produce correct results under normal Java.

14 years agogenerate emails
adash [Tue, 1 Jun 2010 17:42:05 +0000 (17:42 +0000)]
generate emails

14 years agoporting effects analysis
jjenista [Thu, 27 May 2010 19:11:38 +0000 (19:11 +0000)]
porting effects analysis

14 years agoporting effects analysis to new disjoint analysis
jjenista [Wed, 26 May 2010 22:21:57 +0000 (22:21 +0000)]
porting effects analysis to new disjoint analysis

14 years agoCan now use the rblock keyword instead of sese keyword to write OoOJava programs...
jjenista [Wed, 26 May 2010 17:33:04 +0000 (17:33 +0000)]
Can now use the rblock keyword instead of sese keyword to write OoOJava programs, but both work interchangeably so old programs are still fine

14 years agoA nice example of using OoOJava to parallelize an algorithm that is much clearer...
jjenista [Tue, 25 May 2010 23:18:54 +0000 (23:18 +0000)]
A nice example of using OoOJava to parallelize an algorithm that is much clearer than existing parallel implementations

14 years agochanges
bdemsky [Tue, 25 May 2010 22:15:53 +0000 (22:15 +0000)]
changes

14 years agoreal fix for the bug...not just the symptom
bdemsky [Tue, 25 May 2010 22:11:03 +0000 (22:11 +0000)]
real fix for the bug...not just the symptom

14 years agobug fix
bdemsky [Tue, 25 May 2010 21:53:53 +0000 (21:53 +0000)]
bug fix

14 years agobyte info
jihoonl [Tue, 25 May 2010 16:10:09 +0000 (16:10 +0000)]
byte info

14 years agosimultaneous failure
jihoonl [Sat, 22 May 2010 00:46:51 +0000 (00:46 +0000)]
simultaneous failure

14 years agosingle failure
jihoonl [Fri, 21 May 2010 21:48:38 +0000 (21:48 +0000)]
single failure

14 years agofix: make OID only available for MLP.
yeom [Fri, 21 May 2010 21:37:49 +0000 (21:37 +0000)]
fix: make OID only available for MLP.

14 years agochanges
adash [Wed, 19 May 2010 20:22:15 +0000 (20:22 +0000)]
changes

14 years agomore changes to compile recovery benchmarks
adash [Wed, 19 May 2010 20:20:05 +0000 (20:20 +0000)]
more changes to compile recovery benchmarks

14 years agoadd missing files
adash [Wed, 19 May 2010 17:21:30 +0000 (17:21 +0000)]
add missing files

14 years agocommiting all latest changes to recovery folder
adash [Tue, 18 May 2010 22:47:04 +0000 (22:47 +0000)]
commiting all latest changes to recovery folder

14 years agooptimized picking of read-set during pile creation
adash [Tue, 18 May 2010 22:38:40 +0000 (22:38 +0000)]
optimized picking of read-set during pile creation

14 years agochanges to Spider benchmark
adash [Tue, 18 May 2010 22:29:16 +0000 (22:29 +0000)]
changes to Spider benchmark

14 years agochanges
adash [Mon, 17 May 2010 21:04:17 +0000 (21:04 +0000)]
changes

14 years agothrow error instead of exit so caller code can report location of array initializers
jjenista [Tue, 11 May 2010 17:39:10 +0000 (17:39 +0000)]
throw error instead of exit so caller code can report location of array initializers

14 years agochnges to Game benchmark
adash [Tue, 11 May 2010 00:37:25 +0000 (00:37 +0000)]
chnges to Game benchmark