charm.git
9 years agoguard ft code by ft macro
Gengbin Zheng [Tue, 1 Nov 2011 14:30:30 +0000 (09:30 -0500)]
guard ft code by ft macro

9 years agoadd a start(callback) function to omit the need for a second QD from user code to...
Gengbin Zheng [Tue, 1 Nov 2011 04:12:51 +0000 (23:12 -0500)]
add a start(callback) function to omit the need for a second QD from user code to flush the buffered message

9 years agosimilar fix for cray-xe mallinfo
Gengbin Zheng [Mon, 31 Oct 2011 17:20:53 +0000 (12:20 -0500)]
similar fix for cray-xe mallinfo

9 years agominor change about a print
Gengbin Zheng [Mon, 31 Oct 2011 17:19:18 +0000 (12:19 -0500)]
minor change about a print

9 years agoSDAG: Move CCounter's pointers stars into its type string, to match changes for templ...
Phil Miller [Mon, 31 Oct 2011 13:49:18 +0000 (08:49 -0500)]
SDAG: Move CCounter's pointers stars into its type string, to match changes for template support

Now tested against the full set of Charm++ examples and tests, rather than the
couple I happened to look at.

9 years agoSDAG: simplify entry method matching logic
Phil Miller [Mon, 31 Oct 2011 07:44:47 +0000 (02:44 -0500)]
SDAG: simplify entry method matching logic

9 years agoSDAG: Consolidate handling of parameter types to improve template support
Phil Miller [Mon, 31 Oct 2011 07:43:56 +0000 (02:43 -0500)]
SDAG: Consolidate handling of parameter types to improve template support

9 years agoxi: rearrange inclusion a bit
Phil Miller [Mon, 31 Oct 2011 07:32:17 +0000 (02:32 -0500)]
xi: rearrange inclusion a bit

9 years agodon't print pid for mpi version. still print for net, which make it easy to pick...
Gengbin Zheng [Mon, 31 Oct 2011 00:50:01 +0000 (19:50 -0500)]
don't print pid for mpi version. still print for net, which make it easy to pick up a process to kill

9 years agoMerge branch 'charm' of charmgit:charm into charm
Gengbin Zheng [Mon, 31 Oct 2011 00:23:31 +0000 (19:23 -0500)]
Merge branch 'charm' of charmgit:charm into charm

9 years agoimplement CkDieNow function for net version too
Gengbin Zheng [Mon, 31 Oct 2011 00:23:07 +0000 (19:23 -0500)]
implement CkDieNow function for net version too

9 years agoclear
Xiang Ni [Mon, 31 Oct 2011 00:22:42 +0000 (19:22 -0500)]
clear

9 years agomissing initialization of total_pes when +wp is not present
Gengbin Zheng [Sun, 30 Oct 2011 22:32:04 +0000 (17:32 -0500)]
missing initialization of total_pes when +wp is not present

9 years agofix a bug in generating bufferMssage call for a when trigger function with no argument.
Gengbin Zheng [Sun, 30 Oct 2011 15:25:15 +0000 (10:25 -0500)]
fix a bug in generating bufferMssage call for a when trigger function with no argument.

9 years agoFT: print out which spare processor is used to replace the failed PE.
Gengbin Zheng [Sun, 30 Oct 2011 02:24:53 +0000 (21:24 -0500)]
FT: print out which spare processor is used to replace the failed PE.

9 years agoavoid TimerInit global synchronization under bgp for FT
Gengbin Zheng [Sun, 30 Oct 2011 01:33:13 +0000 (01:33 +0000)]
avoid TimerInit global synchronization under bgp for FT

9 years agoclean up
Gengbin Zheng [Sun, 30 Oct 2011 01:28:50 +0000 (01:28 +0000)]
clean up

9 years agoupdated
Gengbin Zheng [Sat, 29 Oct 2011 23:50:37 +0000 (18:50 -0500)]
updated

9 years agodon't test -lmpich for bgp builds
Gengbin Zheng [Sat, 29 Oct 2011 23:48:41 +0000 (23:48 +0000)]
don't test -lmpich for bgp builds

9 years agominor cleanup
Gengbin Zheng [Sat, 29 Oct 2011 22:23:01 +0000 (17:23 -0500)]
minor cleanup

9 years agoa minor optimization to find reverse buddy
Gengbin Zheng [Sat, 29 Oct 2011 22:16:00 +0000 (17:16 -0500)]
a minor optimization to find reverse buddy

9 years agoguard new function with mem checkpoint macro
Gengbin Zheng [Sat, 29 Oct 2011 22:11:05 +0000 (17:11 -0500)]
guard new function with mem checkpoint macro

9 years agoFurther reducing the size for memoryAccess to make sure that it runs on every machine
Nikhil Jain [Sat, 29 Oct 2011 16:41:17 +0000 (11:41 -0500)]
Further reducing the size for memoryAccess to make sure that it runs on every machine

9 years agoMerge branch 'charm' of charmgit:charm into charm
Harshitha Menon [Sat, 29 Oct 2011 07:05:03 +0000 (02:05 -0500)]
Merge branch 'charm' of charmgit:charm into charm

9 years agocksequence implementation with memory compaction
Harshitha Menon [Sat, 29 Oct 2011 06:52:19 +0000 (01:52 -0500)]
cksequence implementation with memory compaction

9 years agofix a bug when multiple crashes. The spare processors need to be updated with the...
Gengbin Zheng [Sat, 29 Oct 2011 06:27:11 +0000 (01:27 -0500)]
fix a bug when multiple crashes. The spare processors need to be updated with the petorank array.
added a function CkHasCheckpoints(0 which returns true when there is already checkpoints.

9 years agofix issue at end of program, where MPI_Barrier needs to be called on all processors...
Gengbin Zheng [Sat, 29 Oct 2011 03:04:20 +0000 (22:04 -0500)]
fix issue at end of program, where MPI_Barrier needs to be called on all processors including spare and crashed processors and MPI_Finalize is called to properly exit the MPI program.

9 years agoMeshStreamer: Tried to add const wherever possible and inserted some
Lukasz Wesolowski [Fri, 28 Oct 2011 22:33:20 +0000 (17:33 -0500)]
MeshStreamer: Tried to add const wherever possible and inserted some
missing parameter names in function prototypes.

9 years agoMerge branch 'charm' of charmgit:charm into charm
Gengbin Zheng [Fri, 28 Oct 2011 22:05:28 +0000 (17:05 -0500)]
Merge branch 'charm' of charmgit:charm into charm

9 years agodemonstrate inmem checkpoint restart on MPI layer:
Gengbin Zheng [Fri, 28 Oct 2011 22:04:08 +0000 (17:04 -0500)]
demonstrate inmem checkpoint restart on MPI layer:
1. CkDieNow()  to fake die a processor
2. +wp <numpe> to specify the number of charm processors,  +p fires with spared processors
3. a spared processor will be activated to replace the crashed one.

9 years agoMeshStreamer: Removed capacity from MeshStreamerMessage to decrease
Lukasz Wesolowski [Fri, 28 Oct 2011 21:56:48 +0000 (16:56 -0500)]
MeshStreamer: Removed capacity from MeshStreamerMessage to decrease
message size. Capacity can be obtained directly from the library.
Moved assert which checks that no messages remain after flush.
The check now occurs after all three flush phases are finished.

9 years agofix a bug in ckmulticast pipelining
Akhil Langer [Fri, 28 Oct 2011 19:09:50 +0000 (14:09 -0500)]
fix a bug in ckmulticast pipelining

9 years agoMerge branch 'charm' of charmgit:charm into charm
Akhil Langer [Fri, 28 Oct 2011 18:17:04 +0000 (13:17 -0500)]
Merge branch 'charm' of charmgit:charm into charm

9 years agockmulticast.C - SPLIT_NUM is redundant, set the FRAGMENT_SIZE for pipelining to be...
Akhil Langer [Fri, 28 Oct 2011 18:16:50 +0000 (13:16 -0500)]
ckmulticast.C - SPLIT_NUM is redundant, set the FRAGMENT_SIZE for pipelining to be 32k and increase the MAX_FRAGS to be 100 to allow large messages

9 years agoMerge branch 'charm' of charmgit:charm into charm
Gengbin Zheng [Fri, 28 Oct 2011 03:54:43 +0000 (20:54 -0700)]
Merge branch 'charm' of charmgit:charm into charm

9 years agotweak pxshm to work for SMP build
Gengbin Zheng [Fri, 28 Oct 2011 03:54:18 +0000 (20:54 -0700)]
tweak pxshm to work for SMP build

9 years agoMempool: Declare variables before other statements, to appease MSVC
Phil Miller [Fri, 28 Oct 2011 01:55:36 +0000 (20:55 -0500)]
Mempool: Declare variables before other statements, to appease MSVC

9 years agoreducing the test count
Nikhil Jain [Thu, 27 Oct 2011 17:15:29 +0000 (12:15 -0500)]
reducing the test count

9 years agoMerge branch 'charm' of charmgit:charm into charm
Yanhua Sun [Thu, 27 Oct 2011 06:23:47 +0000 (23:23 -0700)]
Merge branch 'charm' of charmgit:charm into charm

9 years agomake mempool thread-safe in smp; fix smp performance problem in gemini
Yanhua Sun [Thu, 27 Oct 2011 06:23:27 +0000 (23:23 -0700)]
make mempool thread-safe in smp; fix smp performance problem in gemini

9 years agoMerge branch 'charm' of charmgit:charm into charm
Gengbin Zheng [Thu, 27 Oct 2011 05:03:00 +0000 (00:03 -0500)]
Merge branch 'charm' of charmgit:charm into charm

9 years agofix CmiGetRestartPhase definition
Gengbin Zheng [Thu, 27 Oct 2011 05:02:44 +0000 (00:02 -0500)]
fix CmiGetRestartPhase definition

9 years agocorrection the previous error of misplacing memoryAccess file
Nikhil Jain [Wed, 26 Oct 2011 23:35:14 +0000 (18:35 -0500)]
correction the previous error of misplacing memoryAccess file

9 years agoMerge branch 'charm' of charmgit:charm into charm
Gengbin Zheng [Wed, 26 Oct 2011 21:20:23 +0000 (16:20 -0500)]
Merge branch 'charm' of charmgit:charm into charm

9 years agoin FT when using GROUP_LEVEL_REDUCTION, don't flush nodeproxy since it does not exist
Gengbin Zheng [Wed, 26 Oct 2011 21:19:56 +0000 (16:19 -0500)]
in FT when using GROUP_LEVEL_REDUCTION, don't flush nodeproxy since it does not exist

9 years agoadding a new test to commbench
Nikhil Jain [Wed, 26 Oct 2011 21:10:42 +0000 (16:10 -0500)]
adding a new test to commbench

9 years agoRemove redundant check for NULL in MeshStreamer
Lukasz Wesolowski [Wed, 26 Oct 2011 20:41:38 +0000 (15:41 -0500)]
Remove redundant check for NULL in MeshStreamer

9 years agofix a compile problem when not using mempool
Yanhua Sun [Wed, 26 Oct 2011 18:13:11 +0000 (11:13 -0700)]
fix a compile problem when not using mempool

9 years agowhen flush message buffer which are below the full capacity, set message size to... hpcc-2011 hpcc-2011
Gengbin Zheng [Tue, 25 Oct 2011 07:10:50 +0000 (02:10 -0500)]
when flush message buffer which are below the full capacity, set message size to the actual data size.

9 years agomake MeshStreamer a ck-lib library
Gengbin Zheng [Tue, 25 Oct 2011 04:13:01 +0000 (23:13 -0500)]
make MeshStreamer a ck-lib library

9 years agoFixing bug in compilation flag for fault tolerance.
Xiang Ni [Mon, 24 Oct 2011 21:52:54 +0000 (16:52 -0500)]
Fixing bug in compilation flag for fault tolerance.

9 years agoMerge branch 'charm' of charmgit:charm into charm
Gengbin Zheng [Mon, 24 Oct 2011 21:02:26 +0000 (16:02 -0500)]
Merge branch 'charm' of charmgit:charm into charm

9 years agofix the HACK when dealing with WhenTrigger data structure.
Gengbin Zheng [Mon, 24 Oct 2011 21:01:09 +0000 (16:01 -0500)]
fix the HACK when dealing with WhenTrigger data structure.
It is only work when "when" function is "void" type.

9 years agoTyped Reductions example: Don't leak command line argument message
Phil Miller [Sun, 23 Oct 2011 23:43:09 +0000 (18:43 -0500)]
Typed Reductions example: Don't leak command line argument message

9 years agoTyped Reductions example: accept standard Charm++ make arguments
Phil Miller [Sun, 23 Oct 2011 23:42:45 +0000 (18:42 -0500)]
Typed Reductions example: accept standard Charm++ make arguments

9 years agoTyped Reductions: Don't double-free message delivered from null-reduction
Phil Miller [Sun, 23 Oct 2011 23:42:09 +0000 (18:42 -0500)]
Typed Reductions: Don't double-free message delivered from null-reduction

9 years ago32K stack seems to be small for MPI version of charm. Where program can trap in charm...
Gengbin Zheng [Sun, 23 Oct 2011 05:06:04 +0000 (00:06 -0500)]
32K stack seems to be small for MPI version of charm. Where program can trap in charm send, and calling progress engine for flow control./

9 years agoScotch based LBs including ScotchRefine and ScotchTopo to work with the latest versio...
Harshitha Menon [Sat, 22 Oct 2011 19:43:51 +0000 (14:43 -0500)]
Scotch based LBs including ScotchRefine and ScotchTopo to work with the latest version of Scotch

9 years agoMerge branch 'charm' of charmgit:charm into charm
Gengbin Zheng [Sat, 22 Oct 2011 03:01:08 +0000 (22:01 -0500)]
Merge branch 'charm' of charmgit:charm into charm

9 years agoautoconfig test offsetof
Gengbin Zheng [Sat, 22 Oct 2011 02:57:17 +0000 (21:57 -0500)]
autoconfig test offsetof

9 years agotyped redn: Update example program to also reduce an array of doubles
Ramprasad Venkataraman [Fri, 21 Oct 2011 18:08:59 +0000 (13:08 -0500)]
typed redn: Update example program to also reduce an array of doubles

Intended as a sanity check to ensure recent bug fixes don't get unfixed

9 years agoxlat: Generate redn_wrapper fn definitions for mainchare redn targets too
Ramprasad Venkataraman [Fri, 21 Oct 2011 17:39:01 +0000 (12:39 -0500)]
xlat: Generate redn_wrapper fn definitions for mainchare redn targets too

Mystifyingly, the typed reductions example code would not build because the
generated code contained declarations, but no definitions, of the redn_wrapper
functions. It turns out this behavior could be toggled by changing the
reduction root from a mainchare to a regular chare. Some investigation with
Phil's help seemed to indicate that the genCall to generate the redn_wrapper
definition could not be reached for mainchares because of an incomplete if
condition. Fix.

9 years agoxlat: Delete msgs destined for reductiontarget entry methods after use
Ramprasad Venkataraman [Thu, 20 Oct 2011 01:07:44 +0000 (20:07 -0500)]
xlat: Delete msgs destined for reductiontarget entry methods after use

9 years agoxlat: For reductiontargets, compute numElements based on sizeof target type
Ramprasad Venkataraman [Thu, 20 Oct 2011 00:44:24 +0000 (19:44 -0500)]
xlat: For reductiontargets, compute numElements based on sizeof target type

The generated code for reductiontarget entry methods was wrongly calculating
the number of elements in the reduction message by dividing the msg data size
by the sizeof the other variable in the function call (which usually is int
numElements)!

Fix this by using sizeof target data type

9 years agoMerge branch 'charm' of charmgit:charm into charm
Yanhua Sun [Thu, 20 Oct 2011 02:35:03 +0000 (19:35 -0700)]
Merge branch 'charm' of charmgit:charm into charm

9 years agofixed smp bug in sharing smsg_list
Yanhua Sun [Thu, 20 Oct 2011 02:34:52 +0000 (19:34 -0700)]
fixed smp bug in sharing smsg_list

9 years agoAdding type MPI_LONG_LONG as a synonym of MPI_LONG_LONG_INT
Esteban Meneses [Wed, 19 Oct 2011 19:57:36 +0000 (14:57 -0500)]
Adding type MPI_LONG_LONG as a synonym of MPI_LONG_LONG_INT

9 years agoupdated
Gengbin Zheng [Wed, 19 Oct 2011 02:41:00 +0000 (21:41 -0500)]
updated

9 years agoclean up conv-mach-opt.sh when re-configure after switching compilers (e.g. on Cray)
Gengbin Zheng [Wed, 19 Oct 2011 02:39:14 +0000 (21:39 -0500)]
clean up conv-mach-opt.sh when re-configure after switching compilers (e.g. on Cray)

9 years agoPGI Compiler: Set workaround macro definitions properly on shared compiler config
Phil Miller [Tue, 18 Oct 2011 16:02:10 +0000 (11:02 -0500)]
PGI Compiler: Set workaround macro definitions properly on shared compiler config

9 years agoappease my whitespace ocd
Ramprasad Venkataraman [Tue, 18 Oct 2011 15:31:13 +0000 (10:31 -0500)]
appease my whitespace ocd

9 years agocomlib: Use CmiMsgHeaderExt instead of CmiMsgHeaderBasic to get the strategy ID
Ramprasad Venkataraman [Mon, 17 Oct 2011 16:41:59 +0000 (11:41 -0500)]
comlib: Use CmiMsgHeaderExt instead of CmiMsgHeaderBasic to get the strategy ID

9 years agoPGI/Fujitsu compilers: split macros for different workarounds
Phil Miller [Mon, 17 Oct 2011 19:32:30 +0000 (14:32 -0500)]
PGI/Fujitsu compilers: split macros for different workarounds

9 years agoa fix for VC++ compiler error
Gengbin Zheng [Mon, 17 Oct 2011 00:03:31 +0000 (19:03 -0500)]
a fix for VC++ compiler error

9 years agoMerge branch 'charm' of charmgit:charm into charm
Gengbin Zheng [Fri, 14 Oct 2011 22:34:43 +0000 (17:34 -0500)]
Merge branch 'charm' of charmgit:charm into charm

9 years agofixed 1Mb bug
Yanhua Sun [Sat, 15 Oct 2011 05:14:04 +0000 (22:14 -0700)]
fixed 1Mb bug

9 years agofor non pgCC compilers add -lrt for shm functions
Gengbin Zheng [Sat, 15 Oct 2011 05:01:23 +0000 (22:01 -0700)]
for non pgCC compilers add -lrt for shm functions

9 years agoiin replay mode, prevent CmiSwitchToPEFn switching to a non-existent thread
Gengbin Zheng [Fri, 14 Oct 2011 22:33:15 +0000 (17:33 -0500)]
iin replay mode, prevent CmiSwitchToPEFn switching to a non-existent thread

9 years agoa sanity check for reduction table and enumerate type.
Gengbin Zheng [Fri, 14 Oct 2011 10:52:59 +0000 (05:52 -0500)]
a sanity check for reduction table and enumerate type.
also add comments in the header file as reminder

9 years agofix a compilation error for non-smp
Gengbin Zheng [Fri, 14 Oct 2011 16:50:23 +0000 (09:50 -0700)]
fix a compilation error for non-smp

9 years agodo not catch signal if not built for charmdebug
Gengbin Zheng [Fri, 14 Oct 2011 06:35:30 +0000 (23:35 -0700)]
do not catch signal if not built for charmdebug

9 years agoa bug in setcpuaffinity for cray, only rank 0 set the affinity
Gengbin Zheng [Fri, 14 Oct 2011 05:05:56 +0000 (22:05 -0700)]
a bug in setcpuaffinity for cray, only rank 0 set the affinity

9 years agofix a bug that machine.c uses wrong thread_level variable.
Gengbin Zheng [Fri, 14 Oct 2011 01:50:06 +0000 (18:50 -0700)]
fix a bug that machine.c uses wrong thread_level variable.

9 years agoforgot to update reduceTable for long-based reduce functions
Gengbin Zheng [Fri, 14 Oct 2011 00:59:54 +0000 (19:59 -0500)]
forgot to update reduceTable for long-based reduce functions

9 years ago++debug does not work with ++local, message to user
Ehsan [Thu, 13 Oct 2011 22:05:07 +0000 (17:05 -0500)]
++debug does not work with ++local, message to user

9 years agoa mpi-smp that every worker threads send messages instead of going through comm thread.
Gengbin Zheng [Thu, 13 Oct 2011 19:37:49 +0000 (12:37 -0700)]
a mpi-smp that every worker threads send messages instead of going through comm thread.

9 years agouse gemini specific macro instead of CMK_CRAYXE
Gengbin Zheng [Thu, 13 Oct 2011 18:40:39 +0000 (11:40 -0700)]
use gemini specific macro instead of CMK_CRAYXE

9 years agocomplete the previous checkin about reduction.
Gengbin Zheng [Thu, 13 Oct 2011 15:24:05 +0000 (10:24 -0500)]
complete the previous checkin about reduction.

9 years agoadd reduction function for long int, like sum_long
Gengbin Zheng [Thu, 13 Oct 2011 15:12:44 +0000 (10:12 -0500)]
add reduction function for long int, like sum_long

9 years agofix compilation errors for GNU compiler
Gengbin Zheng [Wed, 12 Oct 2011 21:54:23 +0000 (14:54 -0700)]
fix compilation errors for GNU compiler

9 years agofixed myrank problem
Yanhua Sun [Wed, 12 Oct 2011 19:20:23 +0000 (12:20 -0700)]
fixed myrank problem

9 years agominor change to machine common
Yanhua Sun [Wed, 12 Oct 2011 16:47:05 +0000 (09:47 -0700)]
minor change to machine common

9 years agofix a bug in CRAY SMP that comm thread not synchronous with work threads
Gengbin Zheng [Wed, 12 Oct 2011 16:41:37 +0000 (09:41 -0700)]
fix a bug in CRAY SMP that comm thread not synchronous with work threads

9 years agoupdated
Gengbin Zheng [Wed, 12 Oct 2011 16:16:34 +0000 (11:16 -0500)]
updated

9 years agoMerge branch 'charm' of charmgit:charm into charm
Gengbin Zheng [Wed, 12 Oct 2011 16:11:39 +0000 (09:11 -0700)]
Merge branch 'charm' of charmgit:charm into charm

9 years agoonly test cray specific test in autoconfig when CMK_BUILD_CRAY is set
Gengbin Zheng [Wed, 12 Oct 2011 16:11:11 +0000 (09:11 -0700)]
only test cray specific test in autoconfig when CMK_BUILD_CRAY is set

9 years agoMerge branch 'charm' of charmgit:charm into charm
Yanhua Sun [Wed, 12 Oct 2011 16:10:03 +0000 (09:10 -0700)]
Merge branch 'charm' of charmgit:charm into charm

9 years agocommunication thread responsible for all communication
Yanhua Sun [Wed, 12 Oct 2011 16:09:52 +0000 (09:09 -0700)]
communication thread responsible for all communication

9 years agosetup cray xe specific conv-mach files.
Gengbin Zheng [Wed, 12 Oct 2011 16:01:26 +0000 (09:01 -0700)]
setup cray xe specific conv-mach files.

9 years agofix compilation error
Gengbin Zheng [Wed, 12 Oct 2011 06:04:45 +0000 (23:04 -0700)]
fix compilation error