https://gcc.gnu.org/bugzilla/show_bug.cgi?id=95150
Chinoune <mehdi.chinoune at hotmail dot com> changed:
What |Removed |Added
----------------------------------------------------------------------------
Status|UNCONFIRMED |RESOLVED
Resolution|--- |WONTFIX
--- Comment #8 from Chinoune <mehdi.chinoune at hotmail dot com> ---
Adding "parallel do" to openmp directive solves the problem.
The crash reappears with "collapse(2)" with both OpenMP and OpenACC.
program main
implicit none
integer, parameter :: sp = selected_real_kind(6,37)
real(sp), allocatable :: a(:,:), b(:,:), c(:,:)
character( len=5 ) :: val
integer :: n, l, m
integer :: i, j, k
integer :: t1, t2
real(sp) :: tic
!
call get_command_argument( 1, val )
read( val, *) n
l = n
m = n
!
call system_clock( t1, tic)
!
allocate( a(l,m), b(m,n), c(l,n) )
!
call random_number(a)
call random_number(b)
c = 0._sp
!
!$acc data copyin(a,b) copy(c)
!$acc parallel loop collapse(3)
!$omp target teams distribute parallel do collapse(3) map( to:a,b ) map(
tofrom:c )
do j = 1, n
do k = 1, m
do i = 1, l
c(i,j) = a(i,k)*b(k,j) + c(i,j)
end do
end do
end do
!$acc end data
!
call system_clock(t2)
print*, n, (t2-t1)/tic, sum(c)
!
end program main
$ gfortran -O3 -fopenmp -foffload=nvptx-none matmul.f90 -o test.x
$ for i in {1..5}; do ./test.x $((512*2**$i)); done
1024 0.287999988 268377424.
2048 7.40000010E-02 0.00000000
4096 0.170000002 0.00000000
8192 0.574000001 0.00000000
16384 2.10400009 0.00000000
