I did a quick grep of your code. The following looks like it could be a bug: ---8<--- $ grep MPI_Win_create * ... udp_server.c: MPI_Win_create(image_buff, 2*image_info->image_size*sizeof(uint16), sizeof(uint16), MPI_INFO_NULL, MPI_COMM_WORLD, win); $ grep MPI_Get * ... rms.c: MPI_Get(strip_buff, image_info->buffer_size, MPI_INT, 0, (rank-1)*image_info->buffer_size, image_info->buffer_size, MPI_INT, *win); ---8<--- The window size is "2*image_info->image_size*sizeof(uint16)" and the displacement is "(rank-1)*image_info->buffer_size". The displacements expect a window that is proportional to the number of ranks, but the window has a fixed size. It looks like this would cause your gets to wander outside of the exposed buffer at the target. ~Jim. On Wed, Jul 10, 2013 at 6:11 PM, Jim Dinan <[email protected]> wrote:
From that backtrace, it looks like the displacement/datatype that you gave in the call to MPI_Get() caused the target process to access an invalid location in memory. MPICH does not check whether the window accesses at a process targeted by RMA operations are constrained to the window. I would start by making sure that your gets are contained within the window at the target process.
~Jim.
On Wed, Jul 10, 2013 at 1:33 PM, Sufeng Niu <[email protected]> wrote:
Hi Jeff
Sorry to send so many emails which messed up discuss group email.
I found that the scientific image is too large to upload on github. so I put it on the ftp: ftp://ftp.xray.aps.anl.gov/pub/sector8/ there is 55Fe_run5_dark.tif file.
just put the tif file with the source code. Sorry again on my frequently email broadcast. Thank you so much for your debugging help
Sufeng
On Wed, Jul 10, 2013 at 12:08 PM, <[email protected]> wrote:
Send discuss mailing list submissions to [email protected]
To subscribe or unsubscribe via the World Wide Web, visit https://lists.mpich.org/mailman/listinfo/discuss or, via email, send a message with subject or body 'help' to [email protected]
You can reach the person managing the list at [email protected]
When replying, please edit your Subject line so it is more specific than "Re: Contents of discuss digest..."
Today's Topics:
1. Re: MPI_Win_fence failed (Jeff Hammond) 2. Re: MPI_Win_fence failed (Sufeng Niu)
----------------------------------------------------------------------
Message: 1 Date: Wed, 10 Jul 2013 12:05:09 -0500 From: Jeff Hammond <[email protected]> To: [email protected] Subject: Re: [mpich-discuss] MPI_Win_fence failed Message-ID: <CAGKz= [email protected]> Content-Type: text/plain; charset=ISO-8859-1
use dropbox, pastebin, etc. for attachments. it makes life a lot easier for everyone.
jeff
On Wed, Jul 10, 2013 at 11:57 AM, Sufeng Niu <[email protected]> wrote:
Sorry, I found that this discussion email cannot add figure or attachment.
the backtrace information is below:
processes Location PC Host Rank ID Status 7 _start 0x00402399 `-7 _libc_start_main 0x3685c1ecdd `-7 main 0x00402474 `-7 dkm ... |-6 image_rms 0x004029bb | `-6 rms 0x00402d44 | `-6 PMPI_Win_fence 0x0040c389 | `-6 MPIDI_Win_fence 0x004a45f4 | `-6 MPIDI_CH3I_RMAListComplete 0x004a27d3 | `-6 MPIDI_CH3I_Progress ... `-1 udp 0x004035cf `-1 PMPI_Win_fence 0x0040c389 `-1 MPIDI_Win_fence 0x004a45a0 `-1 MPIDI_CH3I_Progress 0x004292f5 `-1 MPIDI_CH3_PktHandler_Get 0x0049f3f9 `-1 MPIDI_CH3_iSendv 0x004aa67c `- memcpy 0x3685c89329 164.54.54.122 0 20.1-13994 Stopped
On Wed, Jul 10, 2013 at 11:39 AM, <[email protected]> wrote:
Send discuss mailing list submissions to [email protected]
To subscribe or unsubscribe via the World Wide Web, visit https://lists.mpich.org/mailman/listinfo/discuss or, via email, send a message with subject or body 'help' to [email protected]
You can reach the person managing the list at [email protected]
When replying, please edit your Subject line so it is more specific than "Re: Contents of discuss digest..."
Today's Topics:
1. Re: MPI_Win_fence failed (Sufeng Niu)
----------------------------------------------------------------------
Message: 1 Date: Wed, 10 Jul 2013 11:39:39 -0500
From: Sufeng Niu <[email protected]> To: [email protected] Subject: Re: [mpich-discuss] MPI_Win_fence failed Message-ID:
<CAFNNHkz8pBfX33icn=+3rdXvqDfWqeu58odpd=mOXLciysHgfg@mail.gmail.com> Content-Type: text/plain; charset="iso-8859-1"
Sorry I forget to add screen shot for backtrace. the screen shot is attached.
Thanks a lot!
Sufeng
On Wed, Jul 10, 2013 at 11:30 AM, <[email protected]> wrote:
Send discuss mailing list submissions to [email protected]
To subscribe or unsubscribe via the World Wide Web, visit https://lists.mpich.org/mailman/listinfo/discuss or, via email, send a message with subject or body 'help' to [email protected]
You can reach the person managing the list at [email protected]
When replying, please edit your Subject line so it is more specific than "Re: Contents of discuss digest..."
Today's Topics:
1. Re: MPI_Win_fence failed (Sufeng Niu)
Message: 1 Date: Wed, 10 Jul 2013 11:30:36 -0500 From: Sufeng Niu <[email protected]> To: [email protected] Subject: Re: [mpich-discuss] MPI_Win_fence failed Message-ID: < CAFNNHkyLj8CbYMmc_w2DA9_+q2Oe3kyus+g6c99ShPk6ZXVkdA@mail.gmail.com> Content-Type: text/plain; charset="iso-8859-1"
Hi Jim,
Thanks a lot for your reply. the basic way for me to debugging is barrier+printf, right now I only have an evaluation version of totalview. the backtrace using totalview shown below. the udp is the udp
collection
and create RMA window, image_rms doing MPI_Get to access the window
There is a segment violation, but I don't know why the program stopped at MPI_Win_fence.
Thanks a lot!
On Wed, Jul 10, 2013 at 10:12 AM, <[email protected]> wrote:
Send discuss mailing list submissions to [email protected]
To subscribe or unsubscribe via the World Wide Web, visit https://lists.mpich.org/mailman/listinfo/discuss or, via email, send a message with subject or body 'help' to [email protected]
You can reach the person managing the list at [email protected]
When replying, please edit your Subject line so it is more specific than "Re: Contents of discuss digest..."
Today's Topics:
1. Re: MPICH3.0.4 make fails with "No rule to make target..." (Wesley Bland) 2. Re: Error in MPI_Finalize on a simple ring test over TCP (Wesley Bland) 3. Restrict number of cores, not threads (Bob Ilgner) 4. Re: Restrict number of cores, not threads (Wesley Bland) 5. Re: Restrict number of cores, not threads (Wesley Bland) 6. Re: Error in MPI_Finalize on a simple ring test over TCP (Thomas Ropars) 7. MPI_Win_fence failed (Sufeng Niu) 8. Re: MPI_Win_fence failed (Jim Dinan)
Message: 1 Date: Wed, 10 Jul 2013 08:29:06 -0500 From: Wesley Bland <[email protected]> To: [email protected] Subject: Re: [mpich-discuss] MPICH3.0.4 make fails with "No rule
to
make target..." Message-ID: <[email protected]> Content-Type: text/plain; charset="iso-8859-1"
Unfortunately, due to the lack of developer resources and
interest,
the last version of MPICH which was supported on Windows was 1.4.1p. You can find that version on the downloads page:
http://www.mpich.org/downloads/
Alternatively, Microsoft maintains a derivative of MPICH which should provide the features you need. You also find a link to that on the downloads page above.
Wesley
On Jul 10, 2013, at 1:16 AM, Don Warren <[email protected]> wrote:
Hello,
As requested in the installation guide, I'm informing this list of a failure to correctly make MPICH3.0.4 on a Win7 system. The specific error encountered is "make[2]: *** No rule to make target `/cygdrive/c/FLASH/mpich-3.0.4/src/mpi/romio/Makefile.am', needed by `/cygdrive/c/FLASH/mpich-3.0.4/src/mpi/romio/Makefile.in'. Stop."
I have confirmed that both Makefile.am and Makefile.in exist in the directory listed. I'm attaching the c.txt and the m.txt files.
Possibly of interest is that the command "make clean" fails at exactly the same folder, with exactly the same error message as shown in m.txt and above.
Any advice you can give would be appreciated. I'm attempting to get FLASH running on my computer, which seems to require MPICH.
Regards, Don Warren
<config-make-outputs.zip>_______________________________________________
discuss mailing list [email protected] To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss