PGI User Forum
 SearchSearch   MemberlistMemberlist     RegisterRegister   ProfileProfile    Log inLog in 

Free OpenACC Webinar

[OpenACC Fortran] Linear algebra in kernel loop
Goto page Previous  1, 2
 
Post new topic   Reply to topic    PGI User Forum Forum Index -> Accelerator Programming
View previous topic :: View next topic  
Author Message
mkcolg



Joined: 30 Jun 2004
Posts: 6215
Location: The Portland Group Inc.

PostPosted: Wed Jul 24, 2013 11:12 am    Post subject: Reply with quote

Hi e3lb89cz,

I'm still not convienced that it's just a memory limit issue but I don't see the exact cause myself so will pass this on to engineering (logged as TPR#19484).

As a work around, you can limit the privatization to each gang by putting the private clause on the parallel construct. Though, you'll be limiting the amount of parallelziation.

Code:
% cat test2.f90
program inversematrix

  implicit   real*8 (a-h,o-z)

  real*8  a(6,6,10000)
  real*8 ::  c(6,6), L(6,6), U(6,6), b(6), d(6), x(6)

  niter = 10000
  n = 6

  a = 0.0d0
  do ie = 1, niter
  do i = 1, n
  a(i,i,ie) = 1.0d0
  enddo
  enddo

!$acc parallel private(c,L,U,b,d,x)
!$acc loop
  do ie = 1, niter

  c(:,:)=a(:,:,ie)
  L=c
  U=L
  b(:) = U(:,1)
  d=b
  x=d
  a(:,:,ie)=L(:,:)

  enddo
!$acc end parallel

  print *, a(1,1,1)
end program inversematrix
% pgf90 -acc -Minfo test2.f90 -ta=nvidia ; a.out
inversematrix:
     11, Memory zero idiom, array assignment replaced by call to pgf90_mzero8
     18, Accelerator kernel generated
         20, !$acc loop gang ! blockidx%x
         22, !$acc loop vector(256) ! threadidx%x
         25, !$acc loop vector(256) ! threadidx%x
         28, !$acc loop vector(256) ! threadidx%x
     18, Generating present_or_copy(a(:,:,:))
         Generating NVIDIA code
         Generating compute capability 1.3 binary
         Generating compute capability 2.0 binary
         Generating compute capability 3.0 binary
     22, Loop is parallelizable
     25, Loop is parallelizable
     28, Loop is parallelizable
    1.000000000000000     


- Mat
Back to top
View user's profile
jtull



Joined: 30 Jun 2004
Posts: 445

PostPosted: Fri Nov 01, 2013 3:35 pm    Post subject: 19484 - OpenACC: Launch error when using larger private data Reply with quote

The current 13.10 release corrects this reported problem.

thanks,
dave
Back to top
View user's profile
Display posts from previous:   
Post new topic   Reply to topic    PGI User Forum Forum Index -> Accelerator Programming All times are GMT - 7 Hours
Goto page Previous  1, 2
Page 2 of 2

 
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 © phpBB Group