PGI User Forum
 SearchSearch   MemberlistMemberlist     RegisterRegister   ProfileProfile    Log inLog in 

CUDA-x86.

pgprof Internal Error with acc data local & update host

 
Post new topic   Reply to topic    PGI User Forum Forum Index -> Debugging and Profiling
View previous topic :: View next topic  
Author Message
escj



Joined: 30 Sep 2009
Posts: 37
Location: Laboratoire d'Aérologie, Toulouse, FRANCE
PostPosted: Fri Aug 31, 2012 8:20 am    Post subject: pgprof Internal Error with acc data local & update host Reply with quote
Hello .

I'am using the last pgi/12.8 version ( but all are inpacted I think )

I have a strange "Internal Error" with "pgprof" with I think the "update" clause .
( If I change a little the code to remove this update all is OK )

Perhaps I'm doing something wrong with this update clause ?

Compile & run under "pgcollect" of this simple example is OK ...
but the "pgprof" give then this error in a pop-up window
when trying to browse the profile of the main program :

Quote:

pgprof: Internal Error. Couldn't find line information for query
pgprof.out@simple_local_update_host.f90@simple_local_update_host@9



Here is the source "simple_local_update_host.f90"
( ;-) extracted from the big real code )

Code:

PROGRAM simple_local_update_host

  IMPLICIT NONE

  INTEGER , PARAMETER :: n=10 , MAXIT = 3
  INTEGER  :: j,it
  REAL     :: a(n)

  !$acc data region local (a)

  !$acc region
  DO  j = 1,n
     a(j) = j*1.0
  END DO
  !$acc end region

  do it=1,MAXIT

     !$acc region
     DO  j = 1,n
        a(j) = a(j) * 2.0
     END DO
     !$acc end region

     !$acc update host (a(1:1),a(n:n))
     print*,"a=",a(1),a(n)

  end do

  !$acc end data region

END PROGRAM simple_local_update_host


the compilation
Code:

pgf90 -g -O0 -ta=nvidia,cc20  -Minfo=acc,ccff simple_local_update_host.f90 -o simple_local_update_host
+ pgf90 -g -O0 -ta=nvidia,cc20 -Minfo=acc,ccff simple_local_update_host.f90 -o simple_local_update_host
simple_local_update_host:
      9, Generating local(a(:))
     11, Generating local(a(:))
         Generating compute capability 2.0 binary
     12, Loop is parallelizable
         Accelerator kernel generated
         12, !$acc loop gang, vector(32) ! blockidx%x threadidx%x
             CC 2.0 : 8 registers; 0 shared, 40 constant, 0 local memory bytes
     19, Generating local(a(:))
         Generating compute capability 2.0 binary
     20, Loop is parallelizable
         Accelerator kernel generated
         20, !$acc loop gang, vector(32) ! blockidx%x threadidx%x
             CC 2.0 : 8 registers; 0 shared, 40 constant, 0 local memory bytes
     25, Generating update host(a(10))
         Generating update host(a(:1))


the run under "pgcollect"
Code:

pgcollect simple_local_update_host
 a=    2.000000        20.00000   
 a=    4.000000        40.00000   
 a=    8.000000        80.00000   
target process has terminated, writing profile data



A+

Juan
Back to top
View user's profile
mkcolg



Joined: 30 Jun 2004
Posts: 4996
Location: The Portland Group Inc.
PostPosted: Fri Aug 31, 2012 9:45 am    Post subject: Reply with quote
Hi Juan,

Thanks for the report. I was able to reproduce this issue and have sent a report (TPR#18908) to our Tools engineers. Your use of the update directive is correct and this looks like a problem with either pgcollect or pgprof. I'm not sure which.

In the meantime, you can view basic profiling information by setting the environment variable "PGI_ACC_TIME=1" instead of using pgcollect.

Thanks again,
Mat
Back to top
View user's profile
escj



Joined: 30 Sep 2009
Posts: 37
Location: Laboratoire d'Aérologie, Toulouse, FRANCE
PostPosted: Thu Sep 06, 2012 2:44 pm    Post subject: Reply with quote
Tank you Mat

A+

Juan
Back to top
View user's profile
escj



Joined: 30 Sep 2009
Posts: 37
Location: Laboratoire d'Aérologie, Toulouse, FRANCE
PostPosted: Tue Sep 11, 2012 5:46 am    Post subject: Reply with quote
Hello Mat .

I could test the simple example with an old pgi/10.9 compiler ...
... and the problem disappear .

With the example compiled with pgi/11.10 it come back again ...

So the problem was probably introduced in the pgi/11.X release .

Also, it must be a compiler bug ...

The profile generated with a compiler pgi/10.9
could be read with pgprof of superior version, 11.10 or 12.8
... without problem

A+

Juan
Back to top
View user's profile
mkcolg



Joined: 30 Jun 2004
Posts: 4996
Location: The Portland Group Inc.
PostPosted: Tue Sep 11, 2012 3:11 pm    Post subject: Reply with quote
Thank Juan. I added this information to TPR#18908.

- Mat
Back to top
View user's profile
Display posts from previous:   
Post new topic   Reply to topic    PGI User Forum Forum Index -> Debugging and Profiling All times are GMT - 7 Hours
Page 1 of 1

 
Jump to:  
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum


Powered by phpBB © 2001, 2002 phpBB Group