Hello everyone,
I have a larger program that I am trying to convert so that the
computationally intensive part will run on an NVidia GPU using OpenMP.
However, I am running into trouble when compiling the program. The part
of the program to run on the GPU contains calls to subroutines, where
variables declared in a separate module are used. This seems to be
creating issues. I have reduced the problem to the attached files.
I compile as follows:
gfortran test_link.f90 common_vars.f90 parameters.f90 -O0 -fopenmp -Wall
-Wextra -o test_link
With the file test_link.f90 as attached, the program compiles and runs
without a problem.
If I remove the comments for the subroutine TEST() and comment out line
31 in test_link.f90 (the line "I = NR") the compilation gives the
following error:
ptxas /tmp/ccw3FqJD.o, line 52; error : Illegal operand type to
instruction 'ld'
ptxas /tmp/ccw3FqJD.o, line 52; error : Unknown symbol
'__common_vars_MOD_nr$linkptr'
ptxas fatal : Ptx assembly aborted due to errors
nvptx-as: ptxas returned 255 exit status
mkoffload: fatal error:
/home/myself/apps/gcc-10.2.0/bin/x86_64-pc-linux-gnu-accel-nvptx-none-gcc
returned 1 exit status
compilation terminated.
lto-wrapper: fatal error:
/home/myself/apps/gcc-10.2.0/libexec/gcc/x86_64-pc-linux-gnu/10.2.0//accel/nvptx-none/mkoffload
returned 1 exit status
compilation terminated.
/usr/bin/ld: error: lto-wrapper failed
collect2: error: ld returned 1 exit status
Is this a bug in gfortran or have I misunderstood how DECLARE TARGET
LINK works in combination with using subroutines?
And a last point: If I use -O3 during compilation the program compiles
and runs fine in both cases. I assume that TEST() is inlined in this
case and the error disappears?
Any help to overcome this issue is more than welcome.
Best regards,
Ioannis E. Venetis
PS1: The problem happens with gcc 10.2 that I compiled myself:
$ ~/apps/gcc-10.2.0/bin/gfortran -v
Using built-in specs.
COLLECT_GCC=/home/myself/apps/gcc-10.2.0/bin/gfortran
COLLECT_LTO_WRAPPER=/home/myself/apps/gcc-10.2.0/libexec/gcc/x86_64-pc-linux-gnu/10.2.0/lto-wrapper
OFFLOAD_TARGET_NAMES=nvptx-none
Target: x86_64-pc-linux-gnu
Configured with: ../gcc-10.2.0/configure
--enable-offload-targets=nvptx-none
--with-cuda-driver-include=/usr/local/cuda/include
--with-cuda-driver-lib=/usr/local/cuda/lib64 --disable-bootstrap
--disable-multilib --enable-languages=c,c++,fortran,lto
--prefix=/home/myself/apps/gcc-10.2.0
Thread model: posix
Supported LTO compression algorithms: zlib
gcc version 10.2.0 (GCC)
PS2: Same problem also happens with gcc 9.3 as installed on Ubuntu 16.04
from apt:
$ gfortran -v
Using built-in specs.
COLLECT_GCC=gfortran
COLLECT_LTO_WRAPPER=/usr/lib/gcc/x86_64-linux-gnu/9/lto-wrapper
OFFLOAD_TARGET_NAMES=nvptx-none:hsa
OFFLOAD_TARGET_DEFAULT=1
Target: x86_64-linux-gnu
Configured with: ../src/configure -v --with-pkgversion='Ubuntu
9.3.0-10ubuntu2~16.04'
--with-bugurl=file:///usr/share/doc/gcc-9/README.Bugs
--enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2
--prefix=/usr --with-gcc-major-version-only --program-suffix=-9
--program-prefix=x86_64-linux-gnu- --enable-shared
--enable-linker-build-id --libexecdir=/usr/lib
--without-included-gettext --enable-threads=posix --libdir=/usr/lib
--enable-nls --enable-clocale=gnu --enable-libstdcxx-debug
--enable-libstdcxx-time=yes --with-default-libstdcxx-abi=new
--enable-gnu-unique-object --disable-vtable-verify --enable-plugin
--with-system-zlib --with-target-system-zlib=auto --enable-objc-gc=auto
--enable-multiarch --disable-werror --with-arch-32=i686 --with-abi=m64
--with-multilib-list=m32,m64,mx32 --enable-multilib --with-tune=generic
--enable-offload-targets=nvptx-none,hsa --without-cuda-driver
--enable-checking=release --build=x86_64-linux-gnu
--host=x86_64-linux-gnu --target=x86_64-linux-gnu
Thread model: posix
gcc version 9.3.0 (Ubuntu 9.3.0-10ubuntu2~16.04)
MODULE COMMON_VARS
USE PARAMETERS
IMPLICIT NONE
!$OMP DECLARE TARGET LINK(NR)
INTEGER :: NR
END MODULE COMMON_VARS
MODULE PARAMETERS
IMPLICIT NONE
INTEGER, PARAMETER :: MAX_SOURCE_POSITIONS = 100
END MODULE PARAMETERS
PROGRAM TEST_LINK
USE COMMON_VARS
USE PARAMETERS
IMPLICIT NONE
REAL :: XMO(MAX_SOURCE_POSITIONS), DCP(MAX_SOURCE_POSITIONS)
INTEGER :: IS1(MAX_SOURCE_POSITIONS), IS2(MAX_SOURCE_POSITIONS)
INTEGER :: X, Y, Z, MAX_X, MAX_Y, MAX_Z, ISOUR, I
MAX_X = 3
MAX_Y = 4
MAX_Z = 5
NR = 6
!$OMP TARGET MAP(TOFROM:IS1,IS2,DCP,XMO) MAP(TO:NR)
!$OMP TEAMS DISTRIBUTE PARALLEL DO COLLAPSE(3)
DO X = 1, MAX_X
DO Y = 1, MAX_Y
DO Z = 1, MAX_Z
ISOUR = (X - 1)*MAX_Y*MAX_Z + (Y - 1)*MAX_Z + Z
XMO(ISOUR) = 1.0 * NR
DCP(ISOUR) = 2.0 * NR
IS1(ISOUR) = 3 * NR
IS2(ISOUR) = 4 * NR
I = NR
! CALL TEST()
ENDDO ! End of z loop
ENDDO ! End of y loop
ENDDO ! End of x loop
!$OMP END TEAMS DISTRIBUTE PARALLEL DO
!$OMP END TARGET
DO X = 1, MAX_X
DO Y = 1, MAX_Y
DO Z = 1, MAX_Z
ISOUR = (X - 1)*MAX_Y*MAX_Z + (Y - 1)*MAX_Z + Z
WRITE(*, *) 'ISOUR = ', ISOUR, 'XMO = ', XMO(ISOUR), 'DCP = ', DCP(ISOUR), 'IS1 = ', IS1(ISOUR), 'IS2 = ', IS2(ISOUR)
ENDDO ! End of z loop
ENDDO ! End of y loop
ENDDO ! End of x loop
END PROGRAM TEST_LINK
! SUBROUTINE TEST()
! !$OMP DECLARE TARGET
! USE COMMON_VARS
! IMPLICIT NONE
! INTEGER I
! I = NR
! END SUBROUTINE TEST
