22cff118f7
... to diagnose potentially suboptimal choices regarding OpenACC parallelism.
Not enabled by default: too noisy ("*potentially* suboptimal choices"); see
XFAILed 'dg-bogus'es.
gcc/c-family/
* c.opt (Wopenacc-parallelism): New.
gcc/fortran/
* lang.opt (Wopenacc-parallelism): New.
gcc/
* omp-offload.c (oacc_validate_dims): Implement
'-Wopenacc-parallelism'.
* doc/invoke.texi (-Wopenacc-parallelism): Document.
gcc/testsuite/
* c-c++-common/goacc/diag-parallelism-1.c: New.
* c-c++-common/goacc/acc-icf.c: Specify '-Wopenacc-parallelism',
and match diagnostics, as appropriate.
* c-c++-common/goacc/classify-kernels-unparallelized.c: Likewise.
* c-c++-common/goacc/classify-kernels.c: Likewise.
* c-c++-common/goacc/classify-parallel.c: Likewise.
* c-c++-common/goacc/classify-routine.c: Likewise.
* c-c++-common/goacc/classify-serial.c: Likewise.
* c-c++-common/goacc/kernels-decompose-1.c: Likewise.
* c-c++-common/goacc/kernels-decompose-2.c: Likewise.
* c-c++-common/goacc/parallel-dims-1.c: Likewise.
* c-c++-common/goacc/parallel-reduction.c: Likewise.
* c-c++-common/goacc/pr70688.c: Likewise.
* c-c++-common/goacc/routine-1.c: Likewise.
* c-c++-common/goacc/routine-level-of-parallelism-2.c: Likewise.
* c-c++-common/goacc/uninit-dim-clause.c: Likewise.
* gfortran.dg/goacc/classify-kernels-unparallelized.f95: Likewise.
* gfortran.dg/goacc/classify-kernels.f95: Likewise.
* gfortran.dg/goacc/classify-parallel.f95: Likewise.
* gfortran.dg/goacc/classify-routine.f95: Likewise.
* gfortran.dg/goacc/classify-serial.f95: Likewise.
* gfortran.dg/goacc/kernels-decompose-1.f95: Likewise.
* gfortran.dg/goacc/kernels-decompose-2.f95: Likewise.
* gfortran.dg/goacc/parallel-tree.f95: Likewise.
* gfortran.dg/goacc/routine-4.f90: Likewise.
* gfortran.dg/goacc/routine-level-of-parallelism-1.f90: Likewise.
* gfortran.dg/goacc/routine-module-mod-1.f90: Likewise.
* gfortran.dg/goacc/routine-multiple-directives-1.f90: Likewise.
* gfortran.dg/goacc/uninit-dim-clause.f95: Likewise.
libgomp/
* testsuite/libgomp.oacc-c-c++-common/firstprivate-1.c: Specify
'-Wopenacc-parallelism', and match diagnostics, as appropriate.
* testsuite/libgomp.oacc-c-c++-common/loop-auto-1.c: Likewise.
* testsuite/libgomp.oacc-c-c++-common/loop-red-w-1.c: Likewise.
* testsuite/libgomp.oacc-c-c++-common/loop-red-w-2.c: Likewise.
* testsuite/libgomp.oacc-c-c++-common/loop-w-1.c: Likewise.
* testsuite/libgomp.oacc-c-c++-common/mode-transitions.c:
Likewise.
* testsuite/libgomp.oacc-c-c++-common/par-reduction-1.c: Likewise.
* testsuite/libgomp.oacc-c-c++-common/par-reduction-2.c: Likewise.
* testsuite/libgomp.oacc-c-c++-common/parallel-dims.c: Likewise.
* testsuite/libgomp.oacc-c-c++-common/parallel-reduction.c:
Likewise.
* testsuite/libgomp.oacc-c-c++-common/pr85381-3.c: Likewise.
* testsuite/libgomp.oacc-c-c++-common/private-variables.c:
Likewise.
* testsuite/libgomp.oacc-c-c++-common/reduction-5.c: Likewise.
* testsuite/libgomp.oacc-c-c++-common/reduction-7.c: Likewise.
* testsuite/libgomp.oacc-c-c++-common/routine-g-1.c: Likewise.
* testsuite/libgomp.oacc-c-c++-common/routine-w-1.c: Likewise.
* testsuite/libgomp.oacc-c-c++-common/routine-wv-2.c: Likewise.
* testsuite/libgomp.oacc-c-c++-common/static-variable-1.c:
Likewise.
* testsuite/libgomp.oacc-fortran/optional-private.f90: Likewise.
* testsuite/libgomp.oacc-fortran/par-reduction-2-1.f: Likewise.
* testsuite/libgomp.oacc-fortran/par-reduction-2-2.f: Likewise.
* testsuite/libgomp.oacc-fortran/parallel-dims.f90: Likewise.
* testsuite/libgomp.oacc-fortran/parallel-reduction.f90: Likewise.
* testsuite/libgomp.oacc-fortran/pr84028.f90: Likewise.
* testsuite/libgomp.oacc-fortran/private-variables.f90: Likewise.
* testsuite/libgomp.oacc-fortran/reduction-1.f90: Likewise.
* testsuite/libgomp.oacc-fortran/reduction-5.f90: Likewise.
* testsuite/libgomp.oacc-fortran/reduction-6.f90: Likewise.
* testsuite/libgomp.oacc-fortran/routine-7.f90: Likewise.
Co-Authored-By: Nathan Sidwell <nathan@codesourcery.com>
Co-Authored-By: Tom de Vries <vries@codesourcery.com>
Co-Authored-By: Julian Brown <julian@codesourcery.com>
Co-Authored-By: Kwok Cheung Yeung <kcy@codesourcery.com>
98 lines
2 KiB
Fortran
98 lines
2 KiB
Fortran
! { dg-do run }
|
|
! { dg-additional-options "-cpp" }
|
|
|
|
! { dg-additional-options "-Wopenacc-parallelism" } for testing/documenting
|
|
! aspects of that functionality.
|
|
|
|
program reduction
|
|
implicit none
|
|
|
|
integer, parameter :: n = 100, n2 = 1000, chunksize = 10
|
|
integer :: i, gs1, gs2, ws1, ws2, vs1, vs2, cs1, cs2, hs1, hs2
|
|
integer :: j, red, vred
|
|
|
|
gs1 = 0
|
|
gs2 = 0
|
|
ws1 = 0
|
|
ws2 = 0
|
|
vs1 = 0
|
|
vs2 = 0
|
|
cs1 = 0
|
|
cs2 = 0
|
|
hs1 = 0
|
|
hs2 = 0
|
|
|
|
!$acc parallel num_gangs (1000)
|
|
!$acc loop reduction(+:gs1, gs2) gang
|
|
do i = 1, n
|
|
gs1 = gs1 + 1
|
|
gs2 = gs2 + 2
|
|
end do
|
|
!$acc end parallel
|
|
|
|
!$acc parallel num_workers (4) vector_length (32)
|
|
! { dg-warning "region is vector partitioned but does not contain vector partitioned code" "" { target *-*-* } .-1 }
|
|
!$acc loop reduction(+:ws1, ws2) worker
|
|
do i = 1, n
|
|
ws1 = ws1 + 1
|
|
ws2 = ws2 + 2
|
|
end do
|
|
!$acc end parallel
|
|
|
|
!$acc parallel vector_length (32)
|
|
!$acc loop reduction(+:vs1, vs2) vector
|
|
do i = 1, n
|
|
vs1 = vs1 + 1
|
|
vs2 = vs2 + 2
|
|
end do
|
|
!$acc end parallel
|
|
|
|
!$acc parallel num_gangs(8) num_workers(4) vector_length(32)
|
|
!$acc loop reduction(+:cs1, cs2) gang worker vector
|
|
do i = 1, n
|
|
cs1 = cs1 + 1
|
|
cs2 = cs2 + 2
|
|
end do
|
|
!$acc end parallel
|
|
|
|
! Verify the results on the host
|
|
do i = 1, n
|
|
hs1 = hs1 + 1
|
|
hs2 = hs2 + 2
|
|
end do
|
|
|
|
if (gs1 .ne. hs1) STOP 1
|
|
if (gs2 .ne. hs2) STOP 2
|
|
|
|
if (ws1 .ne. hs1) STOP 3
|
|
if (ws2 .ne. hs2) STOP 4
|
|
|
|
if (vs1 .ne. hs1) STOP 5
|
|
if (vs2 .ne. hs2) STOP 6
|
|
|
|
if (cs1 .ne. hs1) STOP 7
|
|
if (cs2 .ne. hs2) STOP 8
|
|
|
|
! Nested reductions.
|
|
|
|
red = 0
|
|
vred = 0
|
|
|
|
!$acc parallel num_gangs(10) vector_length(32)
|
|
!$acc loop reduction(+:red) gang
|
|
do i = 1, n/chunksize
|
|
!$acc loop reduction(+:red) vector
|
|
do j = 1, chunksize
|
|
red = red + chunksize
|
|
end do
|
|
end do
|
|
!$acc end parallel
|
|
|
|
do i = 1, n/chunksize
|
|
do j = 1, chunksize
|
|
vred = vred + chunksize
|
|
end do
|
|
end do
|
|
|
|
if (red .ne. vred) STOP 9
|
|
end program reduction
|