General

Profile

Sam White

Issues

Projects

Activity

06/20/2018

03:14 PM Charm++ Bug #1932 (Merged): Converse pingpong crashes for netlrts-linux-x86_64-smp build during nightly b...

06/19/2018

08:43 PM Charm++ Bug #1937: Threads assigned incorrectly for charm++/openmpi3.1.0/torque
charmrun's +p parameter should be the total number of PEs, while ppn specifies the number of PEs per node. Can you tr...

06/08/2018

06:31 AM Projections Bug #1928: Projections shows idle time for off loaded work from openMP pragmas
src/conv-core/conv-taskQ.{h,C} has tracing code in it, so I'm not sure why that wouldn't show up in Projections. Can ...

06/04/2018

08:18 AM Charm++ Bug #1926 (Merged): mpi-linux-x86_64 failures in autobuild on charm++/megatest
Reverting that commit fixed the issue

05/31/2018

11:41 AM Charm++ Bug #1926: mpi-linux-x86_64 failures in autobuild on charm++/megatest
Can you revert that commit? It has almost no impact on performance from what I can tell

05/30/2018

03:15 PM Charm++ Bug #1926 (Merged): mpi-linux-x86_64 failures in autobuild on charm++/megatest
mpi-linux-x86_64 autobuild hasn't passed since May 2. On May 2nd we merged the C -> C++ machine.c renaming patch...
...
02:44 PM Charm++ Feature #1921: Make Isomalloc/mempool not use the pool for large allocations
K, we should verify that mallocs of size > INT_MAX bytes work correctly, if you haven't already, and then try to figu...
02:25 PM Charm++ Feature #1921: Make Isomalloc/mempool not use the pool for large allocations
Does a malloc of size 1296237920 bytes work on its own with Isomalloc (ignoring other allocations that MiniMD is doing)?
02:14 PM Charm++ Bug #1922: Isomalloc fails with large memory footprints
Related issue to make Isomalloc/mempool not use the pool for large allocations: https://charm.cs.illinois.edu/redmine...
02:13 PM Charm++ Bug #1325: AMPI programs fail to link with Isomalloc heaps
charmc also adds "-Wl,--allow-multiple-definition" to OPTS_LD when using -tlsglobals, I'm not sure why

Also available in: Atom