September 2015 - petsc-dev - mailman3.cels.anl.gov

use of uninitialized values in PetscSF
by Barry Smith 18 Sep '15

18 Sep '15

Is there any way to fix this use of uninitialized values? 9a10,67 > ==31141== Syscall param writev(vector[...]) points to uninitialised byte(s) > ==31141== at 0xD164CDB: writev (writev.c:51) > ==31141== by 0xCB13596: MPL_large_writev (mplsock.c:32) > ==31141== by 0xCB02DC9: MPIDU_Sock_writev (sock_immed.i:610) > ==31141== by 0xCAC00DD: MPIDI_CH3_iStartMsgv (ch3_istartmsgv.c:110) > ==31141== by 0xCA7DC91: recv_rma_msg (ch3u_rma_sync.c:2198) > ==31141== by 0xCA79CB6: MPIDI_Win_fence (ch3u_rma_sync.c:1295) > ==31141== by 0xC9AD840: PMPI_Win_fence (win_fence.c:111) > ==31141== by 0x51DA7E1: PetscSFRestoreWindow (sfwindow.c:348) > ==31141== by 0x51DD0C9: PetscSFBcastEnd_Window (sfwindow.c:510) > ==31141== by 0x51D0B66: PetscSFBcastEnd (sf.c:1001) > ==31141== by 0x401EB7: main (ex2.c:81) > ==31141== Address 0xe50d12c is 108 bytes inside a block of size 208 alloc'd > ==31141== at 0x4C2B6CD: malloc (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so) > ==31141== by 0xCA7328D: MPIDI_CH3I_RMA_Ops_alloc_tail (mpidrma.h:191) > ==31141== by 0xCA75A49: MPIDI_Get (ch3u_rma_ops.c:290) > ==31141== by 0xC99EC9C: PMPI_Get (get.c:142) > ==31141== by 0x51DCC62: PetscSFBcastBegin_Window (sfwindow.c:495) > ==31141== by 0x51D03C4: PetscSFBcastBegin (sf.c:968) > ==31141== by 0x401DDB: main (ex2.c:79) > ==31141== Uninitialised value was created by a heap allocation > ==31141== at 0x4C2B6CD: malloc (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so) > ==31141== by 0xCA7328D: MPIDI_CH3I_RMA_Ops_alloc_tail (mpidrma.h:191) > ==31141== by 0xCA75A49: MPIDI_Get (ch3u_rma_ops.c:290) > ==31141== by 0xC99EC9C: PMPI_Get (get.c:142) > ==31141== by 0x51DCC62: PetscSFBcastBegin_Window (sfwindow.c:495) > ==31141== by 0x51D03C4: PetscSFBcastBegin (sf.c:968) > ==31141== by 0x401DDB: main (ex2.c:79) > ==31141== > ==31142== Syscall param writev(vector[...]) points to uninitialised byte(s) > ==31142== at 0xD164CDB: writev (writev.c:51) > ==31142== by 0xCB13596: MPL_large_writev (mplsock.c:32) > ==31142== by 0xCB02DC9: MPIDU_Sock_writev (sock_immed.i:610) > ==31142== by 0xCAC00DD: MPIDI_CH3_iStartMsgv (ch3_istartmsgv.c:110) > ==31142== by 0xCA7DC91: recv_rma_msg (ch3u_rma_sync.c:2198) > ==31142== by 0xCA79CB6: MPIDI_Win_fence (ch3u_rma_sync.c:1295) > ==31142== by 0xC9AD840: PMPI_Win_fence (win_fence.c:111) > ==31142== by 0x51DA7E1: PetscSFRestoreWindow (sfwindow.c:348) > ==31142== by 0x51DD0C9: PetscSFBcastEnd_Window (sfwindow.c:510) > ==31142== by 0x51D0B66: PetscSFBcastEnd (sf.c:1001) > ==31142== by 0x401EB7: main (ex2.c:81) > ==31142== Address 0xe49d88c is 108 bytes inside a block of size 208 alloc'd > ==31142== at 0x4C2B6CD: malloc (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so) > ==31142== by 0xCA7328D: MPIDI_CH3I_RMA_Ops_alloc_tail (mpidrma.h:191) > ==31142== by 0xCA75A49: MPIDI_Get (ch3u_rma_ops.c:290) > ==31142== by 0xC99EC9C: PMPI_Get (get.c:142) > ==31142== by 0x51DCC62: PetscSFBcastBegin_Window (sfwindow.c:495) > ==31142== by 0x51D03C4: PetscSFBcastBegin (sf.c:968) > ==31142== by 0x401DDB: main (ex2.c:79) > ==31142== Uninitialised value was created by a heap allocation > ==31142== at 0x4C2B6CD: malloc (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so) > ==31142== by 0xCA7328D: MPIDI_CH3I_RMA_Ops_alloc_tail (mpidrma.h:191) > ==31142== by 0xCA75A49: MPIDI_Get (ch3u_rma_ops.c:290) > ==31142== by 0xC99EC9C: PMPI_Get (get.c:142) > ==31142== by 0x51DCC62: PetscSFBcastBegin_Window (sfwindow.c:495) > ==31142== by 0x51D03C4: PetscSFBcastBegin (sf.c:968) > ==31142== by 0x401DDB: main (ex2.c:79) > ==31142== /sandbox/petsc/petsc.clone/src/vec/is/sf/examples/tutorials Possible problem with ex2_window, diffs above

1 0

Re: [petsc-dev] Nested event logging and human friendly output
by Barry Smith 18 Sep '15

18 Sep '15

Thank you for contributing the nested logging. I have incorporated into the PETSc branch barry/xml-nested-logging if you look at https://bitbucket.org/petsc/petsc/commits/bb1d7374b64f295b2ed5ff23b89435d65… you can see exactly what I have incorporated into PETSc. I will merge it into next for portability testing in the next couple of days. I expect over time as I understand it better I will be able to improve its integration with PETSc. Currently to generate the nested logging it is as simple to use as -log_view :filename.xml:ascii_xml Thanks again, Barry > On Sep 14, 2015, at 7:45 AM, Koos Huijssen <koos.huijssen(a)vortech.nl> wrote: > > Dear PETSc development team, > > We have developed an extension of the PETSc event logging facilities that has the following advanced features: > > - It allows logging of events in the form of a nested tree. So if some function is called from multiple locations in the code, these instances are distinguished. This in contrast with the standard event logger, which only logs the amount of total call time. > - It allows the output report to be formatted in XML format. This output can then be viewed in a human-friendly form in a web browser > with the use of the XSL Transformation script performance_xml2html.xsl. The html features an nested timings tree that can be expanded and collapsed as desired. > > This tool has been very useful for us to analyze the code and pinpoint performance bottle necks. We think that it can be useful for others as well, and therefore we are providing the code here for integration in the open source distribution of PETSc. > > For more information I refer to the included manual. We have also provided a test program and a makefile for convenience. The test program can be run using MPI with for instance 3-6 processes. > > I apologize for not using the git repo to submit the developed code. I also apologize for not adhering to the PETSc coding standards (or at least not as far as I know), but I hope that it is not too far off.. Apart from the whole capital/underscore standardization stuff one issue may require special attention, namely the (ab)use of the format PETSc_VIEWER_ASCII_IMPL for signaling the XML format in XMLViewer.c. I couldn't find an already existing and better fitting format, but it could be necessary to add a new format here for this purpose. > > Can you take it up from here and realize the integration of the code in the PETSc distribution? > > With kind regards, > > Koos Huijssen > > -- > ____________________________________________________________________ > > VORtech BV - Scientific software engineers > ____________________________________________________________________ > > Dr.ir. Koos Huijssen > > P.O. Box 260 > 2600 AG Delft > The Netherlands > > phone +31(0)15-285 0125 > mobile +31(0)6-3333 0803 > email koos.huijssen(a)vortech.nl > web www.vortech.nl > ____________________________________________________________________ > > <timers.tar.gz>

1 0

Re: [petsc-dev] broken options handling with intel 16.0 compilers on mac OS
by Jeff Hammond 17 Sep '15

17 Sep '15

Please report this via premier.intel.com. Jeff On Wed, Sep 16, 2015 at 11:13 AM, Blaise A Bourdin <bourdin(a)lsu.edu> wrote: > Hi, > > I am testing intel 16 compilers under mac OS, and notice that options > handling for all past and current versions of petsc is broken in fortran > (options are not parsed). > I narrowed it down to *argc at start.c:168 always being 0 when intel 16 is > used (but taking the right value using intel 15 or gcc 5), but I can’t find > my way through the multiple macros to figure out what is really the matter… > The problem does not seem to arise under linux with the same compilers. > > Any idea of what is going on? Any test I can run to help (I assume that > you don’t have a test box with the latest intel compilers)? Is it a petsc > bug or an intel bug? > > I use an up to date pets-dev master, and the configure.log file is > available at > https://filestogeaux.lsu.edu/public/download.php?FILE=bourdin/89329uFByT9 > > Thanks, > > Blaise > > -- > Department of Mathematics and Center for Computation & Technology > Louisiana State University, Baton Rouge, LA 70803, USA > Tel. +1 (225) 578 1612, Fax +1 (225) 578 4276 > http://www.math.lsu.edu/~bourdin > > > > > > > > -- Jeff Hammond jeff.science(a)gmail.com http://jeffhammond.github.io/

1 0

Re: [petsc-dev] Nested event logging and human friendly output
by Barry Smith 17 Sep '15

17 Sep '15

I'm sorry but I cannot determine how to display the output in a browser. From the manual it says: If the xsl file is located in the same folder as the XML file, and if the files are located there as well, then the automatic conversion by the web browser results in a display such as Figure 1. but I have no idea what files the "_the_files_ are located there as well" means? I now have two files joe.xml that was generated by your code and begins with  <petscroot> <runspecification desc="Run Specification"> <executable desc="Executable">./ex1</executable> <architecture desc="Architecture">arch-debug</architecture> <hostname desc="Host">visitor097-045.wl.anl-external.org</hostname> <nprocesses desc="Number of processes">1</nprocesses> and performance_xml2html.xsl How, exactly, do I use these two files, opening either one in Chrome or Firefox produces nothing useful. Barry > On Sep 14, 2015, at 7:45 AM, Koos Huijssen <koos.huijssen(a)vortech.nl> wrote: > > Dear PETSc development team, > > We have developed an extension of the PETSc event logging facilities that has the following advanced features: > > - It allows logging of events in the form of a nested tree. So if some function is called from multiple locations in the code, these instances are distinguished. This in contrast with the standard event logger, which only logs the amount of total call time. > - It allows the output report to be formatted in XML format. This output can then be viewed in a human-friendly form in a web browser > with the use of the XSL Transformation script performance_xml2html.xsl. The html features an nested timings tree that can be expanded and collapsed as desired. > > This tool has been very useful for us to analyze the code and pinpoint performance bottle necks. We think that it can be useful for others as well, and therefore we are providing the code here for integration in the open source distribution of PETSc. > > For more information I refer to the included manual. We have also provided a test program and a makefile for convenience. The test program can be run using MPI with for instance 3-6 processes. > > I apologize for not using the git repo to submit the developed code. I also apologize for not adhering to the PETSc coding standards (or at least not as far as I know), but I hope that it is not too far off.. Apart from the whole capital/underscore standardization stuff one issue may require special attention, namely the (ab)use of the format PETSc_VIEWER_ASCII_IMPL for signaling the XML format in XMLViewer.c. I couldn't find an already existing and better fitting format, but it could be necessary to add a new format here for this purpose. > > Can you take it up from here and realize the integration of the code in the PETSc distribution? > > With kind regards, > > Koos Huijssen > > -- > ____________________________________________________________________ > > VORtech BV - Scientific software engineers > ____________________________________________________________________ > > Dr.ir. Koos Huijssen > > P.O. Box 260 > 2600 AG Delft > The Netherlands > > phone +31(0)15-285 0125 > mobile +31(0)6-3333 0803 > email koos.huijssen(a)vortech.nl > web www.vortech.nl > ____________________________________________________________________ > > <timers.tar.gz>

1 0

Re: [petsc-dev] error codes/strings
by Marco Zocca 17 Sep '15

17 Sep '15

Oops, yes :) that one and ~/petsc-3.5.3/src/sys/error/err.c Thank you, Marco On 17 September 2015 at 17:50, Nathan Collier <nathaniel.collier(a)gmail.com> wrote: > Perhaps you want this file? > > $PETSC_DIR/include/petscerror.h > > Nate > > On Thu, Sep 17, 2015 at 11:04 AM Marco Zocca <zocca.marco(a)gmail.com> wrote: >> >> Dear PETSc-dev, >> >> which files in the library hold the error codes and associated error >> strings? I would also much appreciate if you could point me to the >> same information within Tao. >> >> Thank you in advance and kind regards, >> >> Marco Zocca

1 0

Re: [petsc-dev] error codes/strings
by Nathan Collier 17 Sep '15

17 Sep '15

Perhaps you want this file? $PETSC_DIR/include/petscerror.h Nate On Thu, Sep 17, 2015 at 11:04 AM Marco Zocca <zocca.marco(a)gmail.com> wrote: > Dear PETSc-dev, > > which files in the library hold the error codes and associated error > strings? I would also much appreciate if you could point me to the > same information within Tao. > > Thank you in advance and kind regards, > > Marco Zocca >

1 0

error codes/strings
by Marco Zocca 17 Sep '15

17 Sep '15

Dear PETSc-dev, which files in the library hold the error codes and associated error strings? I would also much appreciate if you could point me to the same information within Tao. Thank you in advance and kind regards, Marco Zocca

1 0

Re: [petsc-dev] broken options handling with intel 16.0 compilers on mac OS
by Satish Balay 16 Sep '15

16 Sep '15

Well - the petscconf.h is identicall for both builds. So the change in behavior must be due to some internal changes in ifort on Mac [as you say - it works fine on linux] Can you try using the branch 'balay/ftn-command_argument' - and see if that works for you? Satish On Wed, 16 Sep 2015, Blaise A Bourdin wrote: > Hi Satish, > > It is at https://filestogeaux.lsu.edu/public/download.php?FILE=bourdin/38806CDddLJ > > > On Sep 16, 2015, at 10:34 AM, Satish Balay <balay(a)mcs.anl.gov> wrote: > > > > Do you have configure.log fr intel-15 compiler - on the same machine? > > > > It would be good to compare petscconf.h between intel-15 and intel-16. > > bourdin@galerkin:petsc-dev (master)$ diff Darwin-intel15.0-g//include/petscconf.h Darwin-intel16.0-g//include/petscconf.h > 85c85 > < #define PETSC_LIB_DIR "/opt/HPC/petsc-dev/Darwin-intel15.0-g/lib" > --- > > #define PETSC_LIB_DIR "/opt/HPC/petsc-dev/Darwin-intel16.0-g/lib" > 489c489 > < #define PETSC_ARCH "Darwin-intel15.0-g" > --- > > #define PETSC_ARCH "Darwin-intel16.0-g” > Not very exciting! > > I am attaching the one for intel16 > >

1 0

Re: [petsc-dev] broken options handling with intel 16.0 compilers on mac OS
by Blaise A Bourdin 16 Sep '15

16 Sep '15

Hi Satish, It is at https://filestogeaux.lsu.edu/public/download.php?FILE=bourdin/38806CDddLJ > On Sep 16, 2015, at 10:34 AM, Satish Balay <balay(a)mcs.anl.gov> wrote: > > Do you have configure.log fr intel-15 compiler - on the same machine? > > It would be good to compare petscconf.h between intel-15 and intel-16. bourdin@galerkin:petsc-dev (master)$ diff Darwin-intel15.0-g//include/petscconf.h Darwin-intel16.0-g//include/petscconf.h 85c85 < #define PETSC_LIB_DIR "/opt/HPC/petsc-dev/Darwin-intel15.0-g/lib" --- > #define PETSC_LIB_DIR "/opt/HPC/petsc-dev/Darwin-intel16.0-g/lib" 489c489 < #define PETSC_ARCH "Darwin-intel15.0-g" --- > #define PETSC_ARCH "Darwin-intel16.0-g” Not very exciting! I am attaching the one for intel16

1 0

Re: [petsc-dev] broken options handling with intel 16.0 compilers on mac OS
by Satish Balay 16 Sep '15

16 Sep '15

Do you have configure.log fr intel-15 compiler - on the same machine? It would be good to compare petscconf.h between intel-15 and intel-16. Satish On Wed, 16 Sep 2015, Blaise A Bourdin wrote: > Hi, > > I am testing intel 16 compilers under mac OS, and notice that options handling for all past and current versions of petsc is broken in fortran (options are not parsed). > I narrowed it down to *argc at start.c:168 always being 0 when intel 16 is used (but taking the right value using intel 15 or gcc 5), but I can’t find my way through the multiple macros to figure out what is really the matter… > The problem does not seem to arise under linux with the same compilers. > > Any idea of what is going on? Any test I can run to help (I assume that you don’t have a test box with the latest intel compilers)? Is it a petsc bug or an intel bug? > > I use an up to date pets-dev master, and the configure.log file is available at https://filestogeaux.lsu.edu/public/download.php?FILE=bourdin/89329uFByT9 > > Thanks, > > Blaise > >

1 0