Project

General

Profile

Activity

From 09/09/2018 to 10/08/2018

10/08/2018

03:49 PM Bug #1985 (Merged): charmxi fails silently on SDAG constructors
Evan Ramos
01:33 PM Bug #1985 (Implemented): charmxi fails silently on SDAG constructors
https://charm.cs.illinois.edu/gerrit/#/c/charm/+/4663 Evan Ramos
12:52 PM Bug #1960 (In Progress): tests/charm++/megatest hangs on netlrts-win-x86_64-smp build
Juan found what looks to be the culprit, a buggy implementation of @CmiNodeBarrierCount@ on Windows. Evan Ramos
07:51 PM Feature #1987: Take advantage of streamable reductions inside CkMulticast
Related: https://charm.cs.illinois.edu/redmine/issues/1987 Sam White
07:51 PM Feature #1987 (In Progress): Take advantage of streamable reductions inside CkMulticast
ckreduction optimizes for streamable reductions (those that can be combined on the fly as they are processed). The or... Sam White
07:49 PM Feature #1986 (New): Avoid msg creation when contributing a pointer to a streamable reduction
ckreduction currently optimizes for streamable reductions by combining messages as they arrive, but this doesn't avoi... Sam White

10/06/2018

07:54 PM Bug #1985: charmxi fails silently on SDAG constructors
The documentation should also be updated to mention this restriction Sam White
07:49 PM Bug #1985 (Merged): charmxi fails silently on SDAG constructors
charmxi should give a clear error that putting SDAG code in a chare constructor is not supported. Sam White

10/05/2018

04:22 PM Bug #1984 (Implemented): Support for [immediate] callbacks in the zero copy API
Fix: https://charm.cs.illinois.edu/gerrit/#/c/charm/+/4655/
Add an [immediate] callback zero copy API example: htt...
Sam White

10/04/2018

11:07 AM Bug #1984 (Merged): Support for [immediate] callbacks in the zero copy API
Currently, in SMP mode, the zero copy API forwards all callbacks to their 'srcPe' via ckcallbackgroup, but this assum... Sam White
09:33 PM Feature #693 (Merged): add CcdCallBacksReset() to header file (or improve callback frequency)
Sam White

10/02/2018

04:50 PM Feature #934 (Merged): Isomalloc: refactor to associate migratable allocations with entities othe...
We don't have any any examples/tests of using Isomalloc without an associated CthThread, but the interface to do that... Sam White
04:48 PM Bug #1981 (Merged): pami{lrts} builds fail because of a crash in cthtest
Sam White
01:15 PM Cleanup #1907: Reimplement CmiNumNodes et al using hwloc
The basic functionality of the current API needs to be maintained. Being able to get basic topology information with... Eric Bohm
12:26 PM Cleanup #1907: Reimplement CmiNumNodes et al using hwloc
The current API also doesn't expose information about sockets or anything much beyond NumCores, NumPhysicalNodes, and... Sam White

10/01/2018

02:53 PM Feature #1742 (In Progress): Send large readonly variables using the Nocopy API to reduce memory ...
Nitin Bhat
02:42 PM Feature #1983 (Merged): C++11 std::chrono timer implementation of CmiWallTimer and friends
C++11 added support for standard high resolution timers. Evaluate which of those is most appropriate for our implemen... Sam White

09/28/2018

12:29 PM Cleanup #1982 (In Progress): Rewrite conv-conds.c in C++
Once we switch Converse over to C++, we can rewrite the data structures in conv-conds.c with STL containers rather th... Sam White

09/27/2018

05:44 PM Bug #1981 (Implemented): pami{lrts} builds fail because of a crash in cthtest
https://charm.cs.illinois.edu/gerrit/c/charm/+/4626 Evan Ramos
04:00 PM Bug #1981: pami{lrts} builds fail because of a crash in cthtest
The commit causing the issue seems to be https://charm.cs.illinois.edu/gerrit/#/c/charm/+/4472/.
Nitin Bhat
02:19 PM Bug #1981: pami{lrts} builds fail because of a crash in cthtest
Output:... Nitin Bhat
02:18 PM Bug #1981 (Merged): pami{lrts} builds fail because of a crash in cthtest

Stack trace:...
Nitin Bhat
03:00 PM Cleanup #338: Remove "custom packed messages" in favor of PUP framework
There should be a fair amount of synergy between the underlying intent of this and the work being done for DDT in AMPI. Eric Bohm
02:56 PM Feature #634: Mechanism (fence/barrier) to delay execution of long methods until latency-sensitiv...
The basic issue here ties into critical path management, as seen in Isaac's work. http://charm.cs.illinois.edu/newPa... Eric Bohm
02:01 PM Feature #1918: Enable immediate method tracing when CMK_SMP_TRACE_COMMTHREAD is enabled
I disagree that CMK_SMP_TRACE_COMMTHREAD should automatically imply tracing immediate messages. Immediate messages a... Eric Bohm
12:22 PM Feature #873 (Resolved): send messages from non-PE threads
#1393 Merged Michael Robson

09/25/2018

03:14 PM Support #1732: Add CUDA as an option in the build script
The build option probably shouldn't be named @cuda@ because CUDA can be used regardless of the option.
A better name...
Jaemin Choi
03:12 PM Cleanup #1489 (Merged): Delete GPU dummy mempool
Jaemin Choi
03:12 PM Documentation #1491 (Merged): Update GPUManager documentation
Jaemin Choi
03:12 PM Feature #1456 (Merged): Add more stream callbacks for use after HToD transfer and kernel execution
Jaemin Choi
03:11 PM Cleanup #1454 (Merged): GPUManager API change
Jaemin Choi
03:11 PM Feature #1451 (Merged): NVTX integration for profiling
Jaemin Choi
03:11 PM Feature #1450 (Merged): Clean up and add CUDA example programs
Jaemin Choi
03:10 PM Feature #1393 (Merged): Redesign of Hybrid API (GPU Manager) to support concurrent kernel execution
Jaemin Choi

09/21/2018

03:22 PM Cleanup #1980 (Merged): Remove the old RDMA API (CkDirect/CmiDirect) from source code and libraries
Fix:
https://charm.cs.illinois.edu/gerrit/#/c/charm/+/4599/
https://charm.cs.illinois.edu/gerrit/#/c/charm/+/4600/
...
Nitin Bhat
03:12 PM Feature #195 (Implemented): Modify old charm++/converse onesided/direct API and examples to new r...
Gerrit:
https://charm.cs.illinois.edu/gerrit/#/c/charm/+/4594/
https://charm.cs.illinois.edu/gerrit/#/c/charm/+/459...
Nitin Bhat

09/20/2018

02:33 PM Feature #195 (In Progress): Modify old charm++/converse onesided/direct API and examples to new r...
Examples to be removed/modified:
1. charm/examples/charm++/onesided
2. charm/tests/charm++/pingpong
3. charm/exa...
Nitin Bhat
01:33 PM Feature #1667: Direct API for nocopy operations on sender-side and receiver-side
We could potentially use sendmsg and WSASend on netlrts-tcp as Juan did here, though I don't think it should be a pri... Sam White
01:28 PM Feature #1667 (Merged): Direct API for nocopy operations on sender-side and receiver-side
Netlrts will not have a true "zero copy" implementation, it'll use the generic copy based implementation. Nitin Bhat
01:30 PM Feature #1919 (Merged): Zerocopy Direct API: Allow user to pass an arbitrary reference pointer in...
Was merged on 07/03/2018, but the redmine issue was not updated. Nitin Bhat
01:29 PM Feature #1459 (New): Zero-copy send support for the netlrts machine layer
Nitin Bhat
01:20 PM Bug #1960: tests/charm++/megatest hangs on netlrts-win-x86_64-smp build
Last night it got through megatest but not simplearrayhello. So there is something peculiar going on in our windows ... Eric Bohm
01:12 PM Feature #1834: Functionality to Broadcast large buffers using the nocopy API
Since the broadcast API was initially implemented in the entry method style, the design scheme discussed before was n... Nitin Bhat
01:07 PM Feature #1657 (Implemented): CMA support for nocopy sends using the Entry Method API across proce...
By implementing the Entry Method API internally using the Direct API, the Entry Method API internally gets CMA suppor... Nitin Bhat
01:04 PM Feature #1468 (Implemented): Enable pre-pinning memory for the zero-copy message sends through th...
By implementing the Entry Method API internally using the Direct API, the Entry Method API can be used for passing pr... Nitin Bhat

09/17/2018

11:05 AM Bug #1978 (Merged): Segmentation fault in examples/charm++/arraysection and cleanup
Sam White

09/13/2018

08:36 PM Feature #1971 (Closed): Explore use of non-temporal stores in the RTS
Sam White
07:51 PM Bug #1978 (Implemented): Segmentation fault in examples/charm++/arraysection and cleanup
2D section example: https://charm.cs.illinois.edu/gerrit/#/c/charm/+/4568/ Sam White

09/12/2018

05:59 PM Feature #13: CkCallback to section breaks
There is a test case for which it seems to break.
A section proxy for a 2D array consisting of 1D elements [0, *]:...
Raghavendra Kanakagiri
12:29 PM Feature #13: CkCallback to section breaks
CkCallback's to sections are still non-migratable, but at least work on the same PE they are created on now: https://... Sam White
10:25 AM Bug #1978: Segmentation fault in examples/charm++/arraysection and cleanup
Yes, it works for me. Will add a 2D array example.
Raghavendra Kanakagiri
08:26 AM Bug #1978: Segmentation fault in examples/charm++/arraysection and cleanup
The example builds and runs correctly now for me. Can you try it, and then add a 2D example? Sam White
08:20 AM Bug #1978 (In Progress): Segmentation fault in examples/charm++/arraysection and cleanup
Cleanup here: https://charm.cs.illinois.edu/gerrit/#/c/charm/+/4566/
Still need a 2D example...
Sam White
09:25 PM Bug #1978: Segmentation fault in examples/charm++/arraysection and cleanup
Some things to clean up:
1. It doesn't compile on my Mac using GCC:...
Sam White
09:18 PM Bug #1978 (Merged): Segmentation fault in examples/charm++/arraysection and cleanup
Segmentation fault when the example in
charm++/arraysection is run.
On a different system setup it runs into an er...
Raghavendra Kanakagiri
10:21 AM Bug #1977 (Closed): Broadcast on a 2D array section segfaults
CkMulticast library needs to be used for a section broadcast.
A message inherited from CkMcastBaseMsg needs to be i...
Raghavendra Kanakagiri
09:15 PM Bug #1977 (Closed): Broadcast on a 2D array section segfaults
Segmentation fault when a section created using 2D array elements is either used in creating a callback or used for b... Raghavendra Kanakagiri

09/11/2018

10:30 AM Bug #1976 (New): ci files with extensive code blocks result in incorrect line numbering in synta...
unclear exactly what trips up the translator, but I've found the charmxi emitted line numbers for errors to be garbag... Eric Bohm
12:14 AM Support #1761: Update GPU Manager Tracing API
New patch using CUPTI Activity API: https://charm.cs.illinois.edu/gerrit/#/c/charm/+/4560/ Jaemin Choi
 

Also available in: Atom