charm.git
15 years agoa light weight verrsion that calling _setjmp
Gengbin Zheng [Thu, 9 Mar 2006 06:35:12 +0000 (06:35 +0000)]
a light weight verrsion that calling _setjmp

15 years agochange to ansi c declaration.
Gengbin Zheng [Wed, 8 Mar 2006 16:09:11 +0000 (16:09 +0000)]
change to ansi c declaration.

15 years agominor change status "ok" => "yes"
Gengbin Zheng [Wed, 8 Mar 2006 05:31:16 +0000 (05:31 +0000)]
minor change status "ok" => "yes"

15 years agoadds a few inline to c
Gengbin Zheng [Wed, 8 Mar 2006 05:24:13 +0000 (05:24 +0000)]
adds a few inline to c

15 years agotest if C program accept "inline"
Gengbin Zheng [Wed, 8 Mar 2006 05:21:29 +0000 (05:21 +0000)]
test if C program accept "inline"

15 years agosorted out the mysterous length match error, due to pretty bad typo.
Gengbin Zheng [Wed, 8 Mar 2006 00:58:13 +0000 (00:58 +0000)]
sorted out the mysterous length match error, due to pretty bad typo.

15 years agoWhile looking for the latency problem I'm trying to track down, I noticed
Greg Koenig [Tue, 7 Mar 2006 07:46:02 +0000 (07:46 +0000)]
While looking for the latency problem I'm trying to track down, I noticed
a small bug in memory allocation/deallocation in the path that I intercept
from CmiAlloc() and CmiFree().  Unfortunately this will not fix the latency
problem.  (The princess is in another castle.)

15 years agoisomalloc and isomallocpup global data segment to make it work with any time migration
Gengbin Zheng [Mon, 6 Mar 2006 21:49:58 +0000 (21:49 +0000)]
isomalloc and isomallocpup global data segment to make it work with any time migration

15 years ago*** empty log message ***
Terry L. Wilmarth [Mon, 6 Mar 2006 17:17:08 +0000 (17:17 +0000)]
*** empty log message ***

15 years agouse faster i386 QT instead of "generic"
Gengbin Zheng [Mon, 6 Mar 2006 03:35:34 +0000 (03:35 +0000)]
use faster i386 QT instead of "generic"

15 years agoModify vmi-linux to use Quickthreads on IA-32.
Greg Koenig [Sun, 5 Mar 2006 20:13:24 +0000 (20:13 +0000)]
Modify vmi-linux to use Quickthreads on IA-32.
conv-mach.h must define Context threads for IA-64 (I think).

15 years agoModify vmi-linux to use Quickthreads on IA-32.
Greg Koenig [Sun, 5 Mar 2006 20:11:39 +0000 (20:11 +0000)]
Modify vmi-linux to use Quickthreads on IA-32.

15 years agoThese modifications to GridCommLB allow the balancer to automatically
Greg Koenig [Sun, 5 Mar 2006 20:04:41 +0000 (20:04 +0000)]
These modifications to GridCommLB allow the balancer to automatically
detect cluster topology as well as balance secondarily on measured CPU
load.  The balancer also works with any number of clusters now.

15 years agoRemoved excessive qualifier MsgPacker::
Chao Huang [Fri, 3 Mar 2006 04:39:15 +0000 (04:39 +0000)]
Removed excessive qualifier MsgPacker::

15 years agoporting to ParFUM introduced a bunch of bugs into parallel partitioning
Sayantan Chakravorty [Thu, 2 Mar 2006 23:10:56 +0000 (23:10 +0000)]
porting to ParFUM introduced a bunch of bugs into parallel partitioning
fixed it

15 years agoA token utility to control the number of outstanding [iget] messages.
Yan Shi [Thu, 2 Mar 2006 21:26:55 +0000 (21:26 +0000)]
A token utility to control the number of outstanding [iget] messages.

15 years agoflag: compile flag "-DMEMORYUSAGE_OUTPUT=0" or 1 turns off/on the memory usage printout.
Yan Shi [Thu, 2 Mar 2006 21:24:40 +0000 (21:24 +0000)]
flag: compile flag "-DMEMORYUSAGE_OUTPUT=0" or 1 turns off/on the memory usage printout.

15 years agoChanges to support the k-token iget.
Yan Shi [Thu, 2 Mar 2006 21:22:42 +0000 (21:22 +0000)]
Changes to support the k-token iget.

15 years agoModified the default small message boundary to 2,048 bytes and the
Greg Koenig [Thu, 2 Mar 2006 19:41:56 +0000 (19:41 +0000)]
Modified the default small message boundary to 2,048 bytes and the
default medium message boundary to 32,768 bytes.  These are much more
reasonable numbers for machines with fast memory bandwidth.

15 years agobusy polling network at idle when +idlepoll
Gengbin Zheng [Tue, 28 Feb 2006 20:11:53 +0000 (20:11 +0000)]
busy polling network at idle when +idlepoll

15 years agobuild will pick gmake first
Gengbin Zheng [Sun, 26 Feb 2006 05:45:44 +0000 (05:45 +0000)]
build will pick gmake first

15 years agoFixed a race condition for ++probe-clusters functionality that appears with
Greg Koenig [Sun, 26 Feb 2006 02:44:32 +0000 (02:44 +0000)]
Fixed a race condition for ++probe-clusters functionality that appears with
large numbers of processes (> 64).  In this race, some processes may send
"latency probe" messages to another process that has not yet completed
connection setup, so its latency data is incomplete.  This causes a
segfault.  Solution is to CmiBarrier() before probing latency data and
computing the cluster mapping.  Tested okay on 128 processors now.

15 years agoThis version does a barrier vs. sleep() immediately inside ConverseExit().
Greg Koenig [Sat, 25 Feb 2006 22:06:30 +0000 (22:06 +0000)]
This version does a barrier vs. sleep() immediately inside ConverseExit().
I incorrectly thought this version was wrong due to running on bad nodes
on Tungsten.

Also, *some* of tunc nodes work (high numbers) and some always fail.

15 years agoOkay, this is really strange...
Greg Koenig [Sat, 25 Feb 2006 04:11:52 +0000 (04:11 +0000)]
Okay, this is really strange...

autobuild runs correctly and to completion on nodes from the Tungsten
partition called "tuna" but fails immediately on nodes from "tunc".
I have no idea why.

15 years agoThis version passed the autobuild that I ran on Tungsten.
Greg Koenig [Fri, 24 Feb 2006 19:58:20 +0000 (19:58 +0000)]
This version passed the autobuild that I ran on Tungsten.

15 years agoModified the shutdown process in ConverseExit() so that it hopefully
Greg Koenig [Fri, 24 Feb 2006 06:13:30 +0000 (06:13 +0000)]
Modified the shutdown process in ConverseExit() so that it hopefully
always works with charmrun and with charmgrid.

15 years agoSilly bug. Used ifdef instead of if, so the definition in conv-mach.h does
Chee Wai Lee [Thu, 23 Feb 2006 20:32:02 +0000 (20:32 +0000)]
Silly bug. Used ifdef instead of if, so the definition in conv-mach.h does
nothing!

15 years agohack to try to pass autobuild tonight
Greg Koenig [Thu, 23 Feb 2006 07:50:52 +0000 (07:50 +0000)]
hack to try to pass autobuild tonight

15 years agoModified the way the machine layer shuts down when started from
Greg Koenig [Thu, 23 Feb 2006 07:27:14 +0000 (07:27 +0000)]
Modified the way the machine layer shuts down when started from
charmrun.  This will hopefully help in passing autobuild.

15 years agoaded machine-smp.c
Gengbin Zheng [Wed, 22 Feb 2006 20:32:27 +0000 (20:32 +0000)]
aded machine-smp.c

15 years agoMistake in one of the variable names I had to change due to overloading
Greg Koenig [Wed, 22 Feb 2006 06:46:20 +0000 (06:46 +0000)]
Mistake in one of the variable names I had to change due to overloading
the variable name in the parameter list with a declared variable in a
function.  In one place, I actually needed to use the parameter variable
and didn't.

15 years agoModified ia64 files same way.
Greg Koenig [Wed, 22 Feb 2006 02:51:34 +0000 (02:51 +0000)]
Modified ia64 files same way.

15 years agoChanged these files before to add -DNO_LOCK and shared library path, but
Greg Koenig [Wed, 22 Feb 2006 02:41:42 +0000 (02:41 +0000)]
Changed these files before to add -DNO_LOCK and shared library path, but
for some reason they didn't make it into CVS.

15 years agoThere is a bug in VMI 2.1 where the return code (of type VMI_STATUS) is not
Greg Koenig [Wed, 22 Feb 2006 02:11:21 +0000 (02:11 +0000)]
There is a bug in VMI 2.1 where the return code (of type VMI_STATUS) is not
set for the following three calls:

VMI_RDMA_Set_Publish_Callback()
VMI_RDMA_Set_Put_Notification_Callback()
VMI_RDMA_Set_Get_Notification_Callback()

Modified machine.c to not test the return code for these because it is a
"floating" value.

15 years agoFixed a problem where the declaration of a variable was overloaded as a
Greg Koenig [Tue, 21 Feb 2006 23:22:19 +0000 (23:22 +0000)]
Fixed a problem where the declaration of a variable was overloaded as a
parameter passed into a function.

15 years agoa typo
Gengbin Zheng [Mon, 20 Feb 2006 07:53:15 +0000 (07:53 +0000)]
a typo

15 years agoModified build for Tungsten autobuild.
Greg Koenig [Mon, 20 Feb 2006 07:47:43 +0000 (07:47 +0000)]
Modified build for Tungsten autobuild.

15 years agoMy implementation of eager RDMA message sends has to be able to intercept
Greg Koenig [Mon, 20 Feb 2006 04:41:26 +0000 (04:41 +0000)]
My implementation of eager RDMA message sends has to be able to intercept
calls to free() on the discarded message buffer and instead of freeing the
memory send a "update credit" message to the sender to mark the buffer as
available for more messages.  To do this, I prepend the standard Charm
memory header (size field, ref field) with an additional field which is a
pointer to the eager handle.  For a CmiFree() this field is checked and if
it points to a handle, the handle is updated; otherwise if NULL the memory
is just a regular allocation that can be freed.

The problem with this is when using some of Sameer's comlib routines
like StreamingStrategy and MeshStreamingStrategy (which I originally wrote
but which Sameer modified to include this bug here).  These strategies
pack messages together and send a single stream containing multiple
packed messages.  In order to do this, he uses the ref fields for the
messages in a packed buffer, making them point back to the ref field of
the larger packed buffer.  Since he transfers the entire buffer of packed
memory and does not know about my additional prepended field, he tromples
my marker.

I think the Converse commbench routines also exercise this fault.

To correct this, I modified my code to disable the eager send protocol
by default, so this additional memory field is never used.  If the
environment variable CMI_VMI_EAGER_PROTOCOL=1 is set, eager sends can be
turned on as usual and the additional memory field is added to all memory
allocations.

My machine layer now passes autobuild.

15 years agoModified ConverseExit() so that the VMI termination hack is used by
Greg Koenig [Sat, 18 Feb 2006 02:03:37 +0000 (02:03 +0000)]
Modified ConverseExit() so that the VMI termination hack is used by
default.  AMPI programs that use Isomalloc cause segfault when trying
to cleanly shut down VMI when it unregisters memory.  Easiest thing to do
is to just call exit() and let the OS release memory (which automatically
unpins it).

15 years agoMatching { missing when MEMORYUSAGE_OUTPUT is not set.
Yan Shi [Fri, 17 Feb 2006 16:54:54 +0000 (16:54 +0000)]
Matching { missing when MEMORYUSAGE_OUTPUT is not set.

15 years agoSpelled the variable disable_regcache incorrectly in one place.
Greg Koenig [Fri, 17 Feb 2006 07:13:15 +0000 (07:13 +0000)]
Spelled the variable disable_regcache incorrectly in one place.

15 years agoModified vmi-linux machine layer to understand the concept of distinct
Greg Koenig [Fri, 17 Feb 2006 04:22:58 +0000 (04:22 +0000)]
Modified vmi-linux machine layer to understand the concept of distinct
clusters.  Now it is possible for a PE to determine whether it is in the
same cluster as any other PE.  This will be necessary for the work coming
up in March.

The user may specify which cluster a given sub-job belongs to, or may tell
the machine layer to probe the PE-to-cluster mapping automatically.  In
order to do this, the PEs each measure the point-to-point latency to all
other PEs in the computation and then report this data to PE 0.  PE 0
collects all the latency data and uses it to compute the cluster map.
It then distributes this map to all PEs in the computation.

The latency collection routines are also important for Grid load balancer
work that will be checked in later.

15 years agoAdded in codes for printing out memory usage in timer interrupt. This is
Yan Shi [Thu, 16 Feb 2006 22:55:10 +0000 (22:55 +0000)]
Added in codes for printing out memory usage in timer interrupt. This is
enabled by setting flag MEMORYUSAGE_OUTPUT to 1.

15 years ago*** empty log message ***
Yan Shi [Thu, 16 Feb 2006 20:45:04 +0000 (20:45 +0000)]
*** empty log message ***

15 years agoAdded in keyword [iget] which does nonblocking get, vs [sync] which does
Yan Shi [Thu, 16 Feb 2006 20:44:32 +0000 (20:44 +0000)]
Added in keyword [iget] which does nonblocking get, vs [sync] which does
blocking version.

15 years agoBug fix to coarsening dampening.
Terry L. Wilmarth [Wed, 15 Feb 2006 23:53:43 +0000 (23:53 +0000)]
Bug fix to coarsening dampening.

15 years agomore lam libs
Gengbin Zheng [Wed, 15 Feb 2006 17:07:54 +0000 (17:07 +0000)]
more lam libs

15 years agoa trivial lam option
Gengbin Zheng [Wed, 15 Feb 2006 16:42:51 +0000 (16:42 +0000)]
a trivial lam option

15 years agosequential fix
Eric Bohm [Wed, 15 Feb 2006 15:49:54 +0000 (15:49 +0000)]
sequential fix

15 years agoadded OPTS line suitable for fast sequential building
Eric Bohm [Tue, 14 Feb 2006 21:31:10 +0000 (21:31 +0000)]
added OPTS line suitable for fast sequential building

15 years agoonly relay broadcast via tree after integrated
Gengbin Zheng [Mon, 13 Feb 2006 20:46:05 +0000 (20:46 +0000)]
only relay broadcast via tree after integrated

15 years agoforward declaration of FEM_Interpolate
Gengbin Zheng [Sun, 12 Feb 2006 17:16:42 +0000 (17:16 +0000)]
forward declaration of FEM_Interpolate

15 years agoWill now give correct coordinates when job is run on smaller partitions than the...
Sameer Kumar [Sun, 12 Feb 2006 17:01:39 +0000 (17:01 +0000)]
Will now give correct coordinates when job is run on smaller partitions than the total booted system size.

15 years agoFixed a build error on cu.ncsa.uiuc.edu
Isaac Dooley [Sat, 11 Feb 2006 16:39:29 +0000 (16:39 +0000)]
Fixed a build error on cu.ncsa.uiuc.edu

15 years agoMinor header fixes
Aaron Becker [Fri, 10 Feb 2006 22:17:29 +0000 (22:17 +0000)]
Minor header fixes

15 years agoAdded return values to assignment operators in the old parallel_part.h
Aaron Becker [Fri, 10 Feb 2006 21:59:23 +0000 (21:59 +0000)]
Added return values to assignment operators in the old parallel_part.h
Hopefully this fixes the solaris builds.

15 years agomake phold.seq now works
Terry L. Wilmarth [Fri, 10 Feb 2006 21:58:42 +0000 (21:58 +0000)]
make phold.seq now works

15 years agoSMP configuration for intel-mac
Chao Mei [Fri, 10 Feb 2006 19:58:28 +0000 (19:58 +0000)]
SMP configuration for intel-mac

15 years agoadded a section on fortran compilers in help page.
Gengbin Zheng [Fri, 10 Feb 2006 19:08:28 +0000 (19:08 +0000)]
added a section on fortran compilers in help page.

15 years agoFixing a bug on lemeiux.
Isaac Dooley [Thu, 9 Feb 2006 19:51:23 +0000 (19:51 +0000)]
Fixing a bug on lemeiux.

15 years agooops, forgot to check in structure of future message queue
Gengbin Zheng [Thu, 9 Feb 2006 16:49:38 +0000 (16:49 +0000)]
oops, forgot to check in structure of future message queue

15 years agofixed CMK_CF90_FIXED compiler path
Gengbin Zheng [Thu, 9 Feb 2006 08:25:30 +0000 (08:25 +0000)]
fixed CMK_CF90_FIXED compiler path

15 years agoadded notes on using PM pool
Gengbin Zheng [Thu, 9 Feb 2006 04:38:41 +0000 (04:38 +0000)]
added notes on using PM pool

15 years agofixed dependence rule so that it won't recompile every make
Gengbin Zheng [Thu, 9 Feb 2006 04:37:14 +0000 (04:37 +0000)]
fixed dependence rule so that it won't recompile every make

15 years agoimplemented buffering of future messages due to out-of-order delivery.
Gengbin Zheng [Thu, 9 Feb 2006 04:24:41 +0000 (04:24 +0000)]
implemented buffering of future messages due to out-of-order delivery.

15 years agodisable progression thread in mx by setting environment MX_MONOTHREAD=1
Gengbin Zheng [Thu, 9 Feb 2006 01:50:35 +0000 (01:50 +0000)]
disable progression thread in mx by setting environment MX_MONOTHREAD=1

15 years agoOh no! I've changed FEM! THese changes needed for Sandhya's code. I will add them...
Terry L. Wilmarth [Wed, 8 Feb 2006 23:59:42 +0000 (23:59 +0000)]
Oh no!  I've changed FEM!  THese changes needed for Sandhya's code.  I will add them to ParFUM.

15 years agodisable pooling of PM because of multithreading.
Gengbin Zheng [Wed, 8 Feb 2006 23:01:23 +0000 (23:01 +0000)]
disable pooling of PM because of multithreading.

15 years agomoved parmetis.h to parallel_part so external compiles work correctly.
Aaron Becker [Wed, 8 Feb 2006 22:26:45 +0000 (22:26 +0000)]
moved parmetis.h to parallel_part so external compiles work correctly.

15 years ago*** empty log message ***
Nilesh Choudhury [Wed, 8 Feb 2006 21:42:58 +0000 (21:42 +0000)]
*** empty log message ***

15 years ago*** empty log message ***
Nilesh Choudhury [Wed, 8 Feb 2006 21:42:58 +0000 (21:42 +0000)]
*** empty log message ***

15 years ago_registerParFUM
Nilesh Choudhury [Wed, 8 Feb 2006 21:24:05 +0000 (21:24 +0000)]
_registerParFUM

15 years agoAdding the header file.
Isaac Dooley [Wed, 8 Feb 2006 21:11:20 +0000 (21:11 +0000)]
Adding the header file.

15 years agoMerged all orphaned changes from FEM into ParFUM.
Isaac Dooley [Wed, 8 Feb 2006 20:59:49 +0000 (20:59 +0000)]
Merged all orphaned changes from FEM into ParFUM.

15 years agoRemoved cktimer.h
Isaac Dooley [Wed, 8 Feb 2006 20:14:05 +0000 (20:14 +0000)]
Removed cktimer.h

15 years agoMore Header Merging. cktimer is now in ParFUM_internals.h
Isaac Dooley [Wed, 8 Feb 2006 20:10:30 +0000 (20:10 +0000)]
More Header Merging. cktimer is now in ParFUM_internals.h

15 years agoCleaning up and merging header files.
Isaac Dooley [Wed, 8 Feb 2006 20:07:13 +0000 (20:07 +0000)]
Cleaning up and merging header files.

15 years agoSome modifications back-ported from fem. Modified the dependencies so that ParFUM...
Isaac Dooley [Wed, 8 Feb 2006 19:57:37 +0000 (19:57 +0000)]
Some modifications back-ported from fem. Modified the dependencies so that ParFUM is separate from fem.

15 years agoMerged most header files into ParFUM.h and ParFUM_internals.h
Isaac Dooley [Wed, 8 Feb 2006 19:00:36 +0000 (19:00 +0000)]
Merged most header files into ParFUM.h and ParFUM_internals.h

15 years agoFixed a bug in SetMeshSize.
Terry L. Wilmarth [Wed, 8 Feb 2006 17:41:48 +0000 (17:41 +0000)]
Fixed a bug in SetMeshSize.

15 years agoSome setting changes.
Terry L. Wilmarth [Wed, 8 Feb 2006 17:31:26 +0000 (17:31 +0000)]
Some setting changes.

15 years agofixed boundary nodes not getting coarsened
Nilesh Choudhury [Wed, 8 Feb 2006 16:58:17 +0000 (16:58 +0000)]
fixed boundary nodes not getting coarsened

15 years agoadded double complex
Gengbin Zheng [Wed, 8 Feb 2006 04:14:58 +0000 (04:14 +0000)]
added double complex

15 years agoSome modifications to coarsening algorithm, default adaptivity settings, added mesh_s...
Terry L. Wilmarth [Tue, 7 Feb 2006 23:37:30 +0000 (23:37 +0000)]
Some modifications to coarsening algorithm, default adaptivity settings, added mesh_sizing to interpolate element copy, and commented out mesh sizing in the adaptivity code.

15 years agoAdded fpup_complex and fpup_complexes for Fortran
Chao Huang [Tue, 7 Feb 2006 22:35:15 +0000 (22:35 +0000)]
Added fpup_complex and fpup_complexes for Fortran

15 years agochange mx_wait to mx_test after ipeek. This does not show any difference to performan...
Gengbin Zheng [Tue, 7 Feb 2006 19:48:41 +0000 (19:48 +0000)]
change mx_wait to mx_test after ipeek. This does not show any difference to performance though

15 years agochanged mask to CmiUint8
Gengbin Zheng [Tue, 7 Feb 2006 19:41:47 +0000 (19:41 +0000)]
changed mask to CmiUint8

15 years agoimplemented active message mode, which is now the default.
Gengbin Zheng [Tue, 7 Feb 2006 09:03:43 +0000 (09:03 +0000)]
implemented active message mode, which is now the default.

15 years agoMX version does not need to create data socket.
Gengbin Zheng [Tue, 7 Feb 2006 08:56:23 +0000 (08:56 +0000)]
MX version does not need to create data socket.

15 years agoupdated path to mx lib
Gengbin Zheng [Tue, 7 Feb 2006 08:54:45 +0000 (08:54 +0000)]
updated path to mx lib

15 years agoAdded generic AdaptMesh function to perform both refinement and coarsening on a mesh.
Terry L. Wilmarth [Mon, 6 Feb 2006 21:19:40 +0000 (21:19 +0000)]
Added generic AdaptMesh function to perform both refinement and coarsening on a mesh.

15 years agoadded MACHSTAT5
Gengbin Zheng [Mon, 6 Feb 2006 08:17:58 +0000 (08:17 +0000)]
added MACHSTAT5

15 years agoadded dependence to immediate.c
Gengbin Zheng [Mon, 6 Feb 2006 08:17:30 +0000 (08:17 +0000)]
added dependence to immediate.c

15 years agoprint header size
Gengbin Zheng [Sun, 5 Feb 2006 17:54:22 +0000 (17:54 +0000)]
print header size

15 years agofixed conversion of header so that it works for 64 bit machine.
Gengbin Zheng [Sun, 5 Feb 2006 04:35:54 +0000 (04:35 +0000)]
fixed conversion of header so that it works for 64 bit machine.

15 years agoConfiguration files for building charm on the Intel-iMac machine
Chao Mei [Sat, 4 Feb 2006 22:47:50 +0000 (22:47 +0000)]
Configuration files for building charm on the Intel-iMac machine

15 years agoCmiMemoryIs() can now tell whether it is gnu or gnuold malloc.
Gengbin Zheng [Sat, 4 Feb 2006 22:00:50 +0000 (22:00 +0000)]
CmiMemoryIs() can now tell whether it is gnu or gnuold malloc.
Tuned down DEFAULT_TRIM_THRESHOLD, DEFAULT_MMAP_MAX a little bit in memory-gnu.c in favor of preventing memory fragmentation.

15 years agoadvanced sub version number to 12
Gengbin Zheng [Sat, 4 Feb 2006 21:57:57 +0000 (21:57 +0000)]
advanced sub version number to 12

15 years agoinclude Makefile.machine which is machine dependent and include better dependence...
Gengbin Zheng [Sat, 4 Feb 2006 17:11:35 +0000 (17:11 +0000)]
include Makefile.machine which is machine dependent and include better dependence rule.

15 years agocreate dummy Makefile.machine
Gengbin Zheng [Sat, 4 Feb 2006 17:05:47 +0000 (17:05 +0000)]
create dummy Makefile.machine