You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
un hwloc (no description available)
ii hwloc-nox 1.11.5-1 amd64 Hierarchical view of the machine - non-X version of u
un libhwloc-contrib-plugins (no description available)
ii libhwloc-dev:amd64 1.11.5-1 amd64 Hierarchical view of the machine - static libs and he
ii libhwloc-plugins 1.11.5-1 amd64 Hierarchical view of the machine - plugins
un libhwloc0 (no description available)
un libhwloc1 (no description available)
un libhwloc2 (no description available)
un libhwloc3 (no description available)
un libhwloc4 (no description available)
ii libhwloc5:amd64 1.11.5-1 amd64 Hierarchical view of the machine - shared libs
Which operating system and hardware are you running on?
#######******* Chrome OS, Linux penguin 4.14.67-07156-gc116f2c8c400 #1 SMP PREEMPT Sun Sep 9 14:28:13 PDT 2018 x86_64 GNU/Linux
On Unix-like systems, run uname -a so that we know which operating system, distribution, and kernel version you are using.
Post the output of lstopo - if it works
Machine (1413MB) + Package L#0 + L2 L#0 (1024KB)
L1d L#0 (24KB) + L1i L#0 (32KB) + Core L#0 + PU L#0 (P#0)
L1d L#1 (24KB) + L1i L#1 (32KB) + Core L#1 + PU L#1 (P#1)
Describe the machine and the processors it contains, as well as any memory and/or peripherals that matter to your issue
Lenovo Chromebook N22-20, Intel celeron n3050, 2GB ram
Details of the problem
What happened?
I am using mpirun command. The root of the problem seems to be in hwloc. As I see, somebody already had problem like this sebhtml/ray#235 (comment)
How did you start your process?
mpirun -np 1 a.out
mpirun --help
Additional information
sebhtml/ray#235 (comment)
If your issue consists in a wrong topology detection, we also need the following for debugging remotely:
Your link seems to say you're using OpenMPI 1.8.3, which is very old and seems to contain hwloc 1.7.2. We fixed so many bugs since that release in 2013 that I don't know where to start.
You should:
build your own hwloc 1.7.2 and check whether lstopo works there. if it doesn't work, then the bug is already fixed in 1.11.5. if it works, we'd to figure out why it fails in OpenMPI and not in lstopo.
rebuild OpenMPI using your hwloc 1.11.5 instead of its own embedded 1.7.2 (--with-hwloc=/path/to/your/hwloc/1.11.5/install/directory).
bgoglin
changed the title
Problem causing mpirun crash
OpenMPI 1.8.3 crashing in hwloc 1.7.2 on ChromeOS
Dec 8, 2018
lstopo 1.11.5
un hwloc (no description available)
ii hwloc-nox 1.11.5-1 amd64 Hierarchical view of the machine - non-X version of u
un libhwloc-contrib-plugins (no description available)
ii libhwloc-dev:amd64 1.11.5-1 amd64 Hierarchical view of the machine - static libs and he
ii libhwloc-plugins 1.11.5-1 amd64 Hierarchical view of the machine - plugins
un libhwloc0 (no description available)
un libhwloc1 (no description available)
un libhwloc2 (no description available)
un libhwloc3 (no description available)
un libhwloc4 (no description available)
ii libhwloc5:amd64 1.11.5-1 amd64 Hierarchical view of the machine - shared libs
Which operating system and hardware are you running on?
#######******* Chrome OS, Linux penguin 4.14.67-07156-gc116f2c8c400 #1 SMP PREEMPT Sun Sep 9 14:28:13 PDT 2018 x86_64 GNU/Linux
On Unix-like systems, run
uname -a
so that we know which operating system, distribution, and kernel version you are using.Post the output of
lstopo -
if it worksMachine (1413MB) + Package L#0 + L2 L#0 (1024KB)
L1d L#0 (24KB) + L1i L#0 (32KB) + Core L#0 + PU L#0 (P#0)
L1d L#1 (24KB) + L1i L#1 (32KB) + Core L#1 + PU L#1 (P#1)
Describe the machine and the processors it contains, as well as any memory and/or peripherals that matter to your issue
Lenovo Chromebook N22-20, Intel celeron n3050, 2GB ram
Details of the problem
I am using mpirun command. The root of the problem seems to be in hwloc. As I see, somebody already had problem like this sebhtml/ray#235 (comment)
mpirun -np 1 a.out
mpirun --help
Additional information
sebhtml/ray#235 (comment)
If your issue consists in a wrong topology detection, we also need the following for debugging remotely:
Machine (P#0 local=1446596KB total=1446596KB Backend=Linux LinuxCgroup=/ hwlocVersion=1.11.5 ProcessName=lstopo-no-graph$
Package L#0 (P#0 CPUModel=06/4c)
L2Cache L#0 (size=1024KB linesize=64 ways=16)
L1dCache L#0 (size=24KB linesize=64 ways=6)
L1iCache L#0 (size=32KB linesize=64 ways=8)
Core L#0 (P#0)
PU L#0 (P#0)
L1dCache L#1 (size=24KB linesize=64 ways=6)
L1iCache L#1 (size=32KB linesize=64 ways=8)
Core L#1 (P#0)
PU L#1 (P#1)
depth 0: 1 Machine (type #1)
depth 1: 1 Package (type #3)
depth 2: 1 L2Cache (type #4)
depth 3: 2 L1dCache (type #4)
depth 4: 2 L1iCache (type #4)
depth 5: 2 Core (type #5)
depth 6: 2 PU (type #6)
Topology not from this system
The text was updated successfully, but these errors were encountered: