July 2013 - discuss - mailman3.cels.anl.gov

Errors occurred when compiling fpi.f with g95
by Wen-Chung Liu 16 Jul '13

16 Jul '13

Dear all： I've simply try to compile the example file fpi.f with g95 compiler. My OS is Windows 7 64 bits. Therefore, I use 1.4.1p1 x86_64 version of MPICH2. And I got errors listed below: C:\Program Files\MPICH2\examples>g95 -I"C:/Program Files/MPICH2/include" -L"C:/Program Files/MPICH2/lib" fpi.f -lfmpich2g C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.text+0x1e): undefined reference to `mpi_init__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.text+0x42): undefined reference to `mpi_comm_rank__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.text+0x66): undefined reference to `mpi_comm_size__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.text+0x248): undefined reference to `mpi_bcast__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.text+0x3a9): undefined reference to `mpi_reduce__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.text+0x465): undefined reference to `mpi_finalize__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.data+0x0): undefined reference to `mpi_comm_dup_fn__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.data+0x4): undefined reference to `mpi_comm_null_delete_fn__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.data+0x8): undefined reference to `mpi_conversion_fn_null__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.data+0xc): undefined reference to `mpi_dup_fn__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.data+0x10): undefined reference to `mpi_comm_null_copy_fn__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.data+0x14): undefined reference to `mpi_null_copy_fn__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.data+0x18): undefined reference to `mpi_null_delete_fn__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.data+0x1c): undefined reference to `mpi_type_dup_fn__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.data+0x20): undefined reference to `mpi_type_null_delete_fn__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.data+0x24): undefined reference to `mpi_win_dup_fn__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.data+0x28): undefined reference to `mpi_win_null_copy_fn__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.data+0x2c): undefined reference to `mpi_win_null_delete_fn__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.data+0x30): undefined reference to `mpi_wtime__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.data+0x34): undefined reference to `mpi_wtick__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.data+0x38): undefined reference to `pmpi_wtime__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.data+0x3c): undefined reference to `pmpi_wtick__' C:\Users\Troy\AppData\Local\Temp/ccUROg3z.o:fpi.f:(.data+0x40): undefined reference to `mpi_type_null_copy_fn__' I've try to run mpi.exe with mpiexec. It works well. I've also reinstall MPICH2, but get same errors. What steps did I lost? Could anyone give me some advises? best regards, Troy

1 0

Re: [mpich-discuss] custom defined mpi data type
by Rajeev Thakur 16 Jul '13

16 Jul '13

disp[0] should correspond to width, disp[1] to length, …, disp[6] to image_size. The code below has disp[1] for width, disp[6] for buffer_size, and the disp for image_size is missing altogether. On Jul 15, 2013, at 4:32 PM, Sufeng Niu wrote: > Hi, > > I try to broadcast a self-defined data type struct, but I found that every time the last value I cannot send it out. ex: > my data struct is: > typedef struct image_info_type{ > int width; > int length; > int page_num; > int buffer_width; > int buffer_length; > long int buffer_size; > long int image_size; > } image_info_type; > > in my MPI program: > ............... > int count = 7; > MPI_Datatype MPI_Imageinfo; > MPI_Datatype types[7] = {MPI_INT, MPI_INT, MPI_INT, MPI_INT, MPI_INT, MPI_LONG, MPI_LONG}; > int len[7] = {1, 1, 1, 1, 1, 1, 1}; > MPI_Aint disp[7]; > long int base; > MPI_Address(image_info, disp); > MPI_Address(&(image_info->width), disp+1); > MPI_Address(&(image_info->length), disp+2); > MPI_Address(&(image_info->page_num), disp+3); > MPI_Address(&(image_info->buffer_width), disp+4); > MPI_Address(&(image_info->buffer_length), disp+5); > MPI_Address(&(image_info->buffer_size), disp+6); > base = disp[0]; > for(i=0; i<7; i++) > disp[i] -= base; > > MPI_Type_struct(count, len, disp, types, &MPI_Imageinfo); > MPI_Type_commit(&MPI_Imageinfo); > ................... > > However, when I print out every information on each rank. the image_size is always 0. I cannot figure out anything wrong with my program. I would appreicate that if any one can give any suggestions. Thank you! > > > -- > Best Regards, > Sufeng Niu > ECASP lab, ECE department, Illinois Institute of Technology > Tel: 312-731-7219 > _______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss

1 0

custom defined mpi data type
by Sufeng Niu 15 Jul '13

15 Jul '13

Hi, I try to broadcast a self-defined data type struct, but I found that every time the last value I cannot send it out. ex: my data struct is: typedef struct image_info_type{ int width; int length; int page_num; int buffer_width; int buffer_length; long int buffer_size; long int image_size; } image_info_type; in my MPI program: ............... int count = 7; MPI_Datatype MPI_Imageinfo; MPI_Datatype types[7] = {MPI_INT, MPI_INT, MPI_INT, MPI_INT, MPI_INT, MPI_LONG, MPI_LONG}; int len[7] = {1, 1, 1, 1, 1, 1, 1}; MPI_Aint disp[7]; long int base; MPI_Address(image_info, disp); MPI_Address(&(image_info->width), disp+1); MPI_Address(&(image_info->length), disp+2); MPI_Address(&(image_info->page_num), disp+3); MPI_Address(&(image_info->buffer_width), disp+4); MPI_Address(&(image_info->buffer_length), disp+5); MPI_Address(&(image_info->buffer_size), disp+6); base = disp[0]; for(i=0; i<7; i++) disp[i] -= base; MPI_Type_struct(count, len, disp, types, &MPI_Imageinfo); MPI_Type_commit(&MPI_Imageinfo); ................... However, when I print out every information on each rank. the image_size is always 0. I cannot figure out anything wrong with my program. I would appreicate that if any one can give any suggestions. Thank you! -- Best Regards, Sufeng Niu ECASP lab, ECE department, Illinois Institute of Technology Tel: 312-731-7219

1 0

Re: [mpich-discuss] Fwd: MPICH2 installation and running problem
by Pavan Balaji 14 Jul '13

14 Jul '13

Once again: http://wiki.mpich.org/mpich/index.php/Frequently_Asked_Questions#Q:_Why_can… On 07/13/2013 10:52 PM, Sarath Samarasekara wrote: > Hi Antonio, > Thanks. I think now I have down loaded and installed the relevant MPICH2 > version. I can see SMPD running now and I am able to run CPI.exe using > the code "mpiexec -n 2 -localonly cpi.exe". However when I try to run > fds files I get the following error. (My intention is to rum fds files) > > C:\Users\Sarath\Desktop\working>mpiexec -n 2 -localonly simple_64_test2.fds > CreateProcess('simple_64_test2.fds') failed, error 193 > launch_process failed. > launch failed: CreateProcess(simple_64_test2.fds) on 'PC' failed, error > 193 - (n > ull) > CreateProcess('simple_64_test2.fds') failed, error 193 > launch_process failed. > launch failed: CreateProcess(simple_64_test2.fds) on 'PC' failed, error > 193 - (n > ull) > > C:\Users\Sarath\Desktop\working> > Is there a solution to this? > > > On Thu, Jul 11, 2013 at 6:22 AM, Antonio J. Peï¿½a <apenya(a)mcs.anl.gov > <mailto:[email protected]>> wrote: > > __ > > Hi Sam, > > Please refer to this FAQ: > > http://wiki.mpich.org/mpich/index.php/Frequently_Asked_Questions#Q:_Why_can… > > -Antonio > > On Wednesday, July 10, 2013 02:26:49 PM Sarath Samarasekara wrote: > > > Hi, > I am trying to install MPICH2 in my PC (running widows 7, 64 bit). > I have tried with the following versions, but I couldn't do a > successful installation. > MPICH2-1.0.6p1-win32-ia32 > MPICH2-1.4.1p1-win-ia32 > MPICH2-1.4.1p1-win-x86-64 > MPICH2-1.0-1-win32-ia32 > Administrator command prompt used. > I have added C:\Program Files\MPICH2\bin" to system Path > Control panel- Administrative tools-Services shows MPICH2 but it > doesn't show SMPD. > SMPD -status just hangs at the command prompt. > > Following is an output of SMPD -status -d for you information. > What am I missing?. How do I get this going? Thank you for your > advice in advance. > > Regards, > Sam > > C:\>smpd -status -d > [-1:3564]..\smpd_get_opt_int > [-1:3564]../smpd_get_opt_int > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt_int > [-1:3564]../smpd_get_opt_int > [-1:3564]..\smpd_get_opt_int > [-1:3564]../smpd_get_opt_int > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt_string > [-1:3564]../smpd_get_opt_string > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_hostname > [-1:3564]../smpd_get_hostname > [-1:3564]..\smpd_get_opt_string > [-1:3564]../smpd_get_opt_string > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt_string > [-1:3564]../smpd_get_opt_string > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt_string > [-1:3564]../smpd_get_opt_string > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt_string > [-1:3564]../smpd_get_opt_string > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt_string > [-1:3564]../smpd_get_opt_string > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt_string > [-1:3564]../smpd_get_opt_string > [-1:3564]..\smpd_get_opt_string > [-1:3564]../smpd_get_opt_string > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_do_console > [-1:3564]...\smpd_get_smpd_data > [-1:3564]....\smpd_get_smpd_data_from_environment > [-1:3564]..../smpd_get_smpd_data_from_environment > [-1:3564].../smpd_get_smpd_data > [-1:3564]...\SMPDU_Sock_create_set > no smpd running on PC > [00:3564].../smpd_do_console > [00:3564]...\smpd_exit > [00:3564]....\smpd_kill_all_processes > [00:3564]..../smpd_kill_all_processes > [00:3564]....\smpd_finalize_drive_maps > [00:3564]..../smpd_finalize_drive_maps > > C:\> > > > _______________________________________________ > discuss mailing list discuss(a)mpich.org <mailto:[email protected]> > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss > > > > > _______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss > -- Pavan Balaji http://www.mcs.anl.gov/~balaji

1 0

Re: [mpich-discuss] Fwd: MPICH2 installation and running problem
by Sarath Samarasekara 13 Jul '13

13 Jul '13

Hi Antonio, Thanks. I think now I have down loaded and installed the relevant MPICH2 version. I can see SMPD running now and I am able to run CPI.exe using the code "mpiexec -n 2 -localonly cpi.exe". However when I try to run fds files I get the following error. (My intention is to rum fds files) C:\Users\Sarath\Desktop\working>mpiexec -n 2 -localonly simple_64_test2.fds CreateProcess('simple_64_test2.fds') failed, error 193 launch_process failed. launch failed: CreateProcess(simple_64_test2.fds) on 'PC' failed, error 193 - (n ull) CreateProcess('simple_64_test2.fds') failed, error 193 launch_process failed. launch failed: CreateProcess(simple_64_test2.fds) on 'PC' failed, error 193 - (n ull) C:\Users\Sarath\Desktop\working> Is there a solution to this? On Thu, Jul 11, 2013 at 6:22 AM, Antonio J. Peña <apenya(a)mcs.anl.gov> wrote: > ** > > > > Hi Sam, > > > > Please refer to this FAQ: > > > > > http://wiki.mpich.org/mpich/index.php/Frequently_Asked_Questions#Q:_Why_can… > > > > -Antonio > > > > > > On Wednesday, July 10, 2013 02:26:49 PM Sarath Samarasekara wrote: > > > Hi, > I am trying to install MPICH2 in my PC (running widows 7, 64 bit). > I have tried with the following versions, but I couldn't do a successful > installation. > MPICH2-1.0.6p1-win32-ia32 > MPICH2-1.4.1p1-win-ia32 > MPICH2-1.4.1p1-win-x86-64 > MPICH2-1.0-1-win32-ia32 > Administrator command prompt used. > I have added C:\Program Files\MPICH2\bin" to system Path > Control panel- Administrative tools-Services shows MPICH2 but it doesn't > show SMPD. > SMPD -status just hangs at the command prompt. > > Following is an output of SMPD -status -d for you information. > What am I missing?. How do I get this going? Thank you for your advice in > advance. > > Regards, > Sam > > C:\>smpd -status -d > [-1:3564]..\smpd_get_opt_int > [-1:3564]../smpd_get_opt_int > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt_int > [-1:3564]../smpd_get_opt_int > [-1:3564]..\smpd_get_opt_int > [-1:3564]../smpd_get_opt_int > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt_string > [-1:3564]../smpd_get_opt_string > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_hostname > [-1:3564]../smpd_get_hostname > [-1:3564]..\smpd_get_opt_string > [-1:3564]../smpd_get_opt_string > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt_string > [-1:3564]../smpd_get_opt_string > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt_string > [-1:3564]../smpd_get_opt_string > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt_string > [-1:3564]../smpd_get_opt_string > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt_string > [-1:3564]../smpd_get_opt_string > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_get_opt_string > [-1:3564]../smpd_get_opt_string > [-1:3564]..\smpd_get_opt_string > [-1:3564]../smpd_get_opt_string > [-1:3564]..\smpd_get_opt > [-1:3564]../smpd_get_opt > [-1:3564]..\smpd_do_console > [-1:3564]...\smpd_get_smpd_data > [-1:3564]....\smpd_get_smpd_data_from_environment > [-1:3564]..../smpd_get_smpd_data_from_environment > [-1:3564].../smpd_get_smpd_data > [-1:3564]...\SMPDU_Sock_create_set > no smpd running on PC > [00:3564].../smpd_do_console > [00:3564]...\smpd_exit > [00:3564]....\smpd_kill_all_processes > [00:3564]..../smpd_kill_all_processes > [00:3564]....\smpd_finalize_drive_maps > [00:3564]..../smpd_finalize_drive_maps > > C:\> > > _______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss >

1 0

Re: [mpich-discuss] Can I choose between MPI_WIN_UNIFIED and MPI_WIN_SEPARATE ?
by Pavan Balaji 13 Jul '13

13 Jul '13

FYI, we are discussing allowing the user to ask for a "required" value for the memory model, in MPI-3.1. The idea is that if you are only going to do PUT/GET/ACC accesses and not direct load/store, there's no semantic difference between UNIFIED and SEPARATE. In that case, if the user specifies that "required" is only SEPARATE, the implementation can have a bit more flexibility in choosing UNIFIED vs. SEPARATE. For MPI-3, ch3 will return UNIFIED. As Jeff mentioned, there was a bug in mpich-3.0 to mpich-3.0.4, so we were returning SEPARATE. That's fixed in the git master. In the next release, we'll correctly return UNIFIED. -- Pavan On 07/13/2013 11:05 AM, Jeff Hammond wrote: > UNIFIED means that the public and private window are the same. > SEPARATE, which is equivalent to MPI-2 RMA behavior, requires explicit > synchronization of the public and private windows, e.g. with > MPI_WIN_SYNC. If you are in the unified model, SYNC is a no-op. > > You cannot choose this because UNIFIED requires the hardware to > provide something that is not always present. There is little to no > value in asking for SEPARATE if UNIFIED is available. I can imagine > scenarios where it might be useful but they are mostly contrived. > > MPICH's ch3 device is going to provide UNIFIED, btw, at least in the > trunk. Pavan committed that fix a few days ago. > > Jeff > > On Sat, Jul 13, 2013 at 10:57 AM, Ronny Brendel <ronnybrendel(a)gmail.com> wrote: >> Hey, >> >> Can I choose between the two memory models, or is this provided by the >> mpi implementation or underlying hardware? >> >> If I can choose: How can I? >> If I cannot choose: Why is that? >> >> >> I tried using MPI_Win_set_attr to set it, but Mpich throws an error >> that the key is invalid. >> >> (I am using mpich 3.0.4) >> >> Reading the standard I couldn't find out wether this is supposed to be >> choosable by the user. I just assumed it is. Because, if I don't query >> MPI_WIN_MODEL, there is a chance my program works on one but not on >> the other. >> So I have a correct program depending on which model there is and the >> code looks exactly the same. Which is behavior I would not expect. >> >> I hope you can help, >> cheers, >> Ronny >> _______________________________________________ >> discuss mailing list discuss(a)mpich.org >> To manage subscription options or unsubscribe: >> https://lists.mpich.org/mailman/listinfo/discuss > > > -- Pavan Balaji http://www.mcs.anl.gov/~balaji

1 0

Re: [mpich-discuss] Can I choose between MPI_WIN_UNIFIED and MPI_WIN_SEPARATE ?
by Jeff Hammond 13 Jul '13

13 Jul '13

UNIFIED means that the public and private window are the same. SEPARATE, which is equivalent to MPI-2 RMA behavior, requires explicit synchronization of the public and private windows, e.g. with MPI_WIN_SYNC. If you are in the unified model, SYNC is a no-op. You cannot choose this because UNIFIED requires the hardware to provide something that is not always present. There is little to no value in asking for SEPARATE if UNIFIED is available. I can imagine scenarios where it might be useful but they are mostly contrived. MPICH's ch3 device is going to provide UNIFIED, btw, at least in the trunk. Pavan committed that fix a few days ago. Jeff On Sat, Jul 13, 2013 at 10:57 AM, Ronny Brendel <ronnybrendel(a)gmail.com> wrote: > Hey, > > Can I choose between the two memory models, or is this provided by the > mpi implementation or underlying hardware? > > If I can choose: How can I? > If I cannot choose: Why is that? > > > I tried using MPI_Win_set_attr to set it, but Mpich throws an error > that the key is invalid. > > (I am using mpich 3.0.4) > > Reading the standard I couldn't find out wether this is supposed to be > choosable by the user. I just assumed it is. Because, if I don't query > MPI_WIN_MODEL, there is a chance my program works on one but not on > the other. > So I have a correct program depending on which model there is and the > code looks exactly the same. Which is behavior I would not expect. > > I hope you can help, > cheers, > Ronny > _______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss -- Jeff Hammond jeff.science(a)gmail.com

1 0

Can I choose between MPI_WIN_UNIFIED and MPI_WIN_SEPARATE ?
by Ronny Brendel 13 Jul '13

13 Jul '13

Hey, Can I choose between the two memory models, or is this provided by the mpi implementation or underlying hardware? If I can choose: How can I? If I cannot choose: Why is that? I tried using MPI_Win_set_attr to set it, but Mpich throws an error that the key is invalid. (I am using mpich 3.0.4) Reading the standard I couldn't find out wether this is supposed to be choosable by the user. I just assumed it is. Because, if I don't query MPI_WIN_MODEL, there is a chance my program works on one but not on the other. So I have a correct program depending on which model there is and the code looks exactly the same. Which is behavior I would not expect. I hope you can help, cheers, Ronny

1 0

Error in building making Mpich
by Wei-Hao Huang 11 Jul '13

11 Jul '13

Hi, I've tried to make mpich-3.0.4 after compiling it on our cluster and I'm running into these errors: make[3]: Leaving directory `/export/software/mpich-3.0.4/build/src/mpl' Making all in tools/topo/hwloc/hwloc make[3]: Entering directory `/export/software/mpich-3.0.4/build/src/pm/hydra/tools/topo/hwloc/hwloc' Making all in src make[4]: Entering directory `/export/software/mpich-3.0.4/build/src/pm/hydra/tools/topo/hwloc/hwloc/src' make[5]: Entering directory `/export/software/mpich-3.0.4/build/src/pm/hydra/tools/topo/hwloc/hwloc/src' CC topology.lo CC traversal.lo In file included from ../../../../../../../../../source/mpich-3.0.4/src/pm/hydra/tools/topo/hwloc/hwloc/src/traversal.c:12: /export/software/mpich-3.0.4/source/mpich-3.0.4/src/pm/hydra/tools/topo/hwloc/hwloc/include/private/misc.h:41:2: error: #error "unknown size for unsigned int." make[5]: *** [traversal.lo] Error 1 make[5]: Leaving directory `/export/software/mpich-3.0.4/build/src/pm/hydra/tools/topo/hwloc/hwloc/src' make[4]: *** [all-recursive] Error 1 make[4]: Leaving directory `/export/software/mpich-3.0.4/build/src/pm/hydra/tools/topo/hwloc/hwloc/src' make[3]: *** [all-recursive] Error 1 make[3]: Leaving directory `/export/software/mpich-3.0.4/build/src/pm/hydra/tools/topo/hwloc/hwloc' make[2]: *** [all-recursive] Error 1 make[2]: Leaving directory `/export/software/mpich-3.0.4/build/src/pm/hydra' make[1]: *** [all-recursive] Error 1 make[1]: Leaving directory ` *my configuration line is:* ../source/mpich-3.0.4/configure --prefix=/export/software/mpich-3.0.4/output/ --enable-fast=O2 --enable-mpe --enable-threads=runtime --enable-checkpointing --with-mpe --with-hydra-ckpointlib=blcr --with-blcr=/export/software/blcr-0.8.3/output/ LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/export/software/blcr-0.8.3/output/lib/ --enable-shared --enable-sharedlibs=gcc This is strange to be as I've run the same thing on our test server and it works. I can configure, make and make install successfully. The only difference in the configuration is the path of blcr, which is in /export/software/blcr/output/ I have the same error when I tried to install hydra on its own. It seems like the configure script defines the unsigned int as 0 by itself. I've attached the config log file on this email. If anyone has an idea, that would be great! Sincerely, -- *Wei-Hao (Andrei) Huang* *BlueShark Systems Administrator* *Enterprise Systems, Information Technology* *B.S. Aerospace Engineering (May 2014)* *Florida Institute of Technology* *whuang2010(a)my.fit.edu* <whuang2010(a)my.fit.edu> *ΛΧΑ BN746* *ΦΗΣ, ΤΒΠ, ΣΓΤ*

1 0

Re: [mpich-discuss] MPI_Win_fence failed
by Sufeng Niu 10 Jul '13

10 Jul '13

Thank you so much! I figure it out the problem. it is really amazing by this debugging method with my limited knowledge. I was shocked. just like a magic. Thank you so much for your help! Sufeng On Wed, Jul 10, 2013 at 5:18 PM, <discuss-request(a)mpich.org> wrote: > Send discuss mailing list submissions to > discuss(a)mpich.org > > 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 > discuss-request(a)mpich.org > > You can reach the person managing the list at > discuss-owner(a)mpich.org > > 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 (Jim Dinan) > > > ---------------------------------------------------------------------- > > Message: 1 > Date: Wed, 10 Jul 2013 18:18:32 -0400 > From: Jim Dinan <james.dinan(a)gmail.com> > To: discuss(a)mpich.org > Subject: Re: [mpich-discuss] MPI_Win_fence failed > Message-ID: > < > CAOoEU4GHbqbzmB7eZmfG1Zp23QCjAT5-YjnvEqjxhdgOomXNKA(a)mail.gmail.com> > Content-Type: text/plain; charset="iso-8859-1" > > 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 <james.dinan(a)gmail.com> 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 <sniu(a)hawk.iit.edu> 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, <discuss-request(a)mpich.org> wrote: > >> > >>> Send discuss mailing list submissions to > >>> discuss(a)mpich.org > >>> > >>> 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 > >>> discuss-request(a)mpich.org > >>> > >>> You can reach the person managing the list at > >>> discuss-owner(a)mpich.org > >>> > >>> 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 <jeff.science(a)gmail.com> > >>> To: discuss(a)mpich.org > >>> Subject: Re: [mpich-discuss] MPI_Win_fence failed > >>> Message-ID: > >>> <CAGKz= > >>> uJ-aoHqK5A_tS6YfWaaxjw5AjhHM7xL1A0XaUSUjKvDcQ(a)mail.gmail.com> > >>> 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 <sniu(a)hawk.iit.edu> > 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, <discuss-request(a)mpich.org> wrote: > >>> >> > >>> >> Send discuss mailing list submissions to > >>> >> discuss(a)mpich.org > >>> >> > >>> >> 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 > >>> >> discuss-request(a)mpich.org > >>> >> > >>> >> You can reach the person managing the list at > >>> >> discuss-owner(a)mpich.org > >>> >> > >>> >> 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 <sniu(a)hawk.iit.edu> > >>> >> To: discuss(a)mpich.org > >>> >> Subject: Re: [mpich-discuss] MPI_Win_fence failed > >>> >> Message-ID: > >>> >> > >>> >> <CAFNNHkz8pBfX33icn=+3rdXvqDfWqeu58odpd=mOXLciysHgfg(a)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, <discuss-request(a)mpich.org> > wrote: > >>> >> > >>> >> > Send discuss mailing list submissions to > >>> >> > discuss(a)mpich.org > >>> >> > > >>> >> > 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 > >>> >> > discuss-request(a)mpich.org > >>> >> > > >>> >> > You can reach the person managing the list at > >>> >> > discuss-owner(a)mpich.org > >>> >> > > >>> >> > 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 <sniu(a)hawk.iit.edu> > >>> >> > To: discuss(a)mpich.org > >>> >> > Subject: Re: [mpich-discuss] MPI_Win_fence failed > >>> >> > Message-ID: > >>> >> > < > >>> >> > > CAFNNHkyLj8CbYMmc_w2DA9_+q2Oe3kyus+g6c99ShPk6ZXVkdA(a)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, <discuss-request(a)mpich.org> > >>> wrote: > >>> >> > > >>> >> > > Send discuss mailing list submissions to > >>> >> > > discuss(a)mpich.org > >>> >> > > > >>> >> > > 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 > >>> >> > > discuss-request(a)mpich.org > >>> >> > > > >>> >> > > You can reach the person managing the list at > >>> >> > > discuss-owner(a)mpich.org > >>> >> > > > >>> >> > > 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 <wbland(a)mcs.anl.gov> > >>> >> > > To: discuss(a)mpich.org > >>> >> > > Subject: Re: [mpich-discuss] MPICH3.0.4 make fails with "No rule > >>> to > >>> >> > > make target..." > >>> >> > > Message-ID: <F48FC916-31F7-4F82-95F8-2D6A6C45264F(a)mcs.anl.gov> > >>> >> > > 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 <don.warren(a)gmail.com> > >>> 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 discuss(a)mpich.org > >>> >> > > > To manage subscription options or unsubscribe: > >>> >> > > > https://lists.mpich.org/mailman/listinfo/discuss > >>> >> > > > >>> >> > >

1 0