mirror of
https://gcc.gnu.org/git/gcc.git
synced 2024-12-15 15:03:40 +08:00
11b8286a83
gcc/ PR middle-end/90115 * flag-types.h (enum openacc_privatization): New. * params.opt (-param=openacc-privatization): New. * doc/invoke.texi (openacc-privatization): Document it. * omp-general.h (get_openacc_privatization_dump_flags): New function. * omp-low.c (oacc_privatization_candidate_p): Add diagnostics. * omp-offload.c (execute_oacc_device_lower) <IFN_UNIQUE_OACC_PRIVATE>: Re-work diagnostics. * target.def (goacc.adjust_private_decl): Add 'location_t' parameter. * doc/tm.texi: Regenerate. * config/gcn/gcn-protos.h (gcn_goacc_adjust_private_decl): Adjust. * config/gcn/gcn-tree.c (gcn_goacc_adjust_private_decl): Likewise. * config/nvptx/nvptx.c (nvptx_goacc_adjust_private_decl): Likewise. Preserve it for... (nvptx_goacc_expand_var_decl): ... use here. gcc/testsuite/ PR middle-end/90115 * c-c++-common/goacc/privatization-1-compute-loop.c: New file. * c-c++-common/goacc/privatization-1-compute.c: Likewise. * c-c++-common/goacc/privatization-1-routine_gang-loop.c: Likewise. * c-c++-common/goacc/privatization-1-routine_gang.c: Likewise. * gfortran.dg/goacc/privatization-1-compute-loop.f90: Likewise. * gfortran.dg/goacc/privatization-1-compute.f90: Likewise. * gfortran.dg/goacc/privatization-1-routine_gang-loop.f90: Likewise. * gfortran.dg/goacc/privatization-1-routine_gang.f90: Likewise. * c-c++-common/goacc-gomp/nesting-1.c: Update. * c-c++-common/goacc/private-reduction-1.c: Likewise. * gfortran.dg/goacc/private-3.f95: Likewise. libgomp/ PR middle-end/90115 * testsuite/libgomp.oacc-fortran/private-atomic-1-vector.f90: New file. * testsuite/libgomp.oacc-c-c++-common/firstprivate-1.c: Update. * testsuite/libgomp.oacc-c-c++-common/host_data-7.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-decompose-1.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-local-worker-1.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-local-worker-2.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-local-worker-3.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-local-worker-4.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-local-worker-5.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-loop-gang-1.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-loop-gang-2.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-loop-gang-3.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-loop-gang-4.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-loop-gang-5.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-loop-gang-6.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-loop-vector-1.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-loop-vector-2.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-loop-worker-1.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-loop-worker-2.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-loop-worker-3.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-loop-worker-4.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-loop-worker-5.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-loop-worker-6.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/kernels-private-vars-loop-worker-7.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/loop-g-1.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/loop-g-2.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/loop-gwv-1.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/loop-gwv-2.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/loop-red-g-1.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/loop-red-gwv-1.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/loop-red-v-1.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/loop-red-v-2.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-red-wv-1.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/loop-v-1.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/loop-w-1.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/loop-wv-1.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/parallel-reduction.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/private-atomic-1-gang.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/private-atomic-1.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/private-variables.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/routine-4.c: Likewise. * testsuite/libgomp.oacc-c-c++-common/static-variable-1.c: Likewise. * testsuite/libgomp.oacc-fortran/acc_on_device-1-1.f90: Likewise. * testsuite/libgomp.oacc-fortran/acc_on_device-1-2.f: Likewise. * testsuite/libgomp.oacc-fortran/acc_on_device-1-3.f: Likewise. * testsuite/libgomp.oacc-fortran/declare-1.f90: Likewise. * testsuite/libgomp.oacc-fortran/host_data-5.F90: Likewise. * testsuite/libgomp.oacc-fortran/if-1.f90: Likewise. * testsuite/libgomp.oacc-fortran/kernels-private-vars-loop-gang-1.f90: Likewise. * testsuite/libgomp.oacc-fortran/kernels-private-vars-loop-gang-2.f90: Likewise. * testsuite/libgomp.oacc-fortran/kernels-private-vars-loop-gang-3.f90: Likewise. * testsuite/libgomp.oacc-fortran/kernels-private-vars-loop-gang-6.f90: Likewise. * testsuite/libgomp.oacc-fortran/kernels-private-vars-loop-vector-1.f90: Likewise. * testsuite/libgomp.oacc-fortran/kernels-private-vars-loop-vector-2.f90: Likewise. * testsuite/libgomp.oacc-fortran/kernels-private-vars-loop-worker-1.f90: Likewise. * testsuite/libgomp.oacc-fortran/kernels-private-vars-loop-worker-2.f90: Likewise. * testsuite/libgomp.oacc-fortran/kernels-private-vars-loop-worker-3.f90: Likewise. * testsuite/libgomp.oacc-fortran/kernels-private-vars-loop-worker-4.f90: Likewise. * testsuite/libgomp.oacc-fortran/kernels-private-vars-loop-worker-5.f90: Likewise. * testsuite/libgomp.oacc-fortran/kernels-private-vars-loop-worker-6.f90: Likewise. * testsuite/libgomp.oacc-fortran/kernels-private-vars-loop-worker-7.f90: Likewise. * testsuite/libgomp.oacc-fortran/optional-private.f90: Likewise. * testsuite/libgomp.oacc-fortran/parallel-dims.f90: Likewise. * testsuite/libgomp.oacc-fortran/private-atomic-1-gang.f90: Likewise. * testsuite/libgomp.oacc-fortran/private-atomic-1-worker.f90: Likewise. * testsuite/libgomp.oacc-fortran/private-variables.f90: Likewise. * testsuite/libgomp.oacc-fortran/privatized-ref-2.f90: Likewise. * testsuite/libgomp.oacc-fortran/routine-7.f90: Likewise.
140 lines
5.8 KiB
Fortran
140 lines
5.8 KiB
Fortran
! OpenACC parallelism dimensions clauses: num_gangs, num_workers,
|
|
! vector_length.
|
|
|
|
! { dg-additional-sources parallel-dims-aux.c }
|
|
! { dg-do run }
|
|
! { dg-prune-output "command-line option '-fintrinsic-modules-path=.*' is valid for Fortran but not for C" }
|
|
|
|
! { dg-additional-options "-fopt-info-note-omp" }
|
|
! { dg-additional-options "--param=openacc-privatization=noisy" }
|
|
! { dg-additional-options "-foffload=-fopt-info-note-omp" }
|
|
! { dg-additional-options "-foffload=--param=openacc-privatization=noisy" }
|
|
! for testing/documenting aspects of that functionality.
|
|
|
|
! { dg-additional-options "-Wopenacc-parallelism" } for testing/documenting
|
|
! aspects of that functionality.
|
|
|
|
! See also '../libgomp.oacc-c-c++-common/parallel-dims.c'.
|
|
|
|
module acc_routines
|
|
implicit none (type, external)
|
|
|
|
interface
|
|
integer function acc_gang() bind(C)
|
|
!$acc routine seq
|
|
end function acc_gang
|
|
|
|
integer function acc_worker() bind(C)
|
|
!$acc routine seq
|
|
end function acc_worker
|
|
|
|
integer function acc_vector() bind(C)
|
|
!$acc routine seq
|
|
end function acc_vector
|
|
end interface
|
|
end module acc_routines
|
|
|
|
program main
|
|
use iso_c_binding
|
|
use openacc
|
|
use acc_routines
|
|
implicit none (type, external)
|
|
|
|
integer :: gangs_min, gangs_max, workers_min, workers_max, vectors_min, vectors_max
|
|
integer :: vectors_actual
|
|
integer :: i, j, k
|
|
|
|
call acc_init (acc_device_default)
|
|
|
|
! OpenACC parallel construct.
|
|
|
|
!TODO
|
|
|
|
|
|
! OpenACC kernels construct.
|
|
|
|
!TODO
|
|
|
|
|
|
! OpenACC serial construct.
|
|
|
|
! GR, WS, VS.
|
|
|
|
gangs_min = huge(gangs_min) ! INT_MAX
|
|
workers_min = huge(workers_min) ! INT_MAX
|
|
vectors_min = huge(vectors_min) ! INT_MAX
|
|
gangs_max = -huge(gangs_max) - 1 ! INT_MIN
|
|
workers_max = -huge(gangs_max) - 1 ! INT_MIN
|
|
vectors_max = -huge(gangs_max) - 1 ! INT_MIN
|
|
!$acc serial &
|
|
!$acc reduction (min: gangs_min, workers_min, vectors_min) reduction (max: gangs_max, workers_max, vectors_max) ! { dg-warning "using vector_length \\(32\\), ignoring 1" "" { target openacc_nvidia_accel_selected } }
|
|
! { dg-note {variable 'D\.[0-9]+' declared in block isn't candidate for adjusting OpenACC privatization level: not addressable} "" { target *-*-* } .-1 }
|
|
do i = 100, -99, -1
|
|
gangs_min = acc_gang ();
|
|
gangs_max = acc_gang ();
|
|
workers_min = acc_worker ();
|
|
workers_max = acc_worker ();
|
|
vectors_min = acc_vector ();
|
|
vectors_max = acc_vector ();
|
|
end do
|
|
!$acc end serial
|
|
if (gangs_min /= 0 .or. gangs_max /= 1 - 1 &
|
|
.or. workers_min /= 0 .or. workers_max /= 1 - 1 &
|
|
.or. vectors_min /= 0 .or. vectors_max /= 1 - 1) &
|
|
stop 1
|
|
|
|
! Composition of GP, WP, VP.
|
|
|
|
vectors_actual = 1 ! Implicit 'vector_length (1)' clause.
|
|
gangs_min = huge(gangs_min) ! INT_MAX
|
|
workers_min = huge(workers_min) ! INT_MAX
|
|
vectors_min = huge(vectors_min) ! INT_MAX
|
|
gangs_max = -huge(gangs_max) - 1 ! INT_MIN
|
|
workers_max = -huge(gangs_max) - 1 ! INT_MIN
|
|
vectors_max = -huge(gangs_max) - 1 ! INT_MIN
|
|
!$acc serial copy (vectors_actual) &
|
|
!$acc copy (gangs_min, gangs_max, workers_min, workers_max, vectors_min, vectors_max) ! { dg-warning "using vector_length \\(32\\), ignoring 1" "" { target openacc_nvidia_accel_selected } }
|
|
! { dg-bogus "\[Ww\]arning: region contains gang partitioned code but is not gang partitioned" "TODO 'serial'" { xfail *-*-* } .-1 }
|
|
! { dg-bogus "\[Ww\]arning: region contains worker partitioned code but is not worker partitioned" "TODO 'serial'" { xfail *-*-* } .-2 }
|
|
! { dg-bogus "\[Ww\]arning: region contains vector partitioned code but is not vector partitioned" "TODO 'serial'" { xfail *-*-* } .-3 }
|
|
! { dg-note {variable 'C.[0-9]+' declared in block potentially has improper OpenACC privatization level: 'const_decl'} "TODO" { target *-*-* } .-4 }
|
|
!TODO Unhandled 'CONST_DECL' instance for constant argument in 'acc_on_device' call.
|
|
if (acc_on_device (acc_device_nvidia)) then
|
|
! The GCC nvptx back end enforces vector_length (32).
|
|
! It's unclear if that's actually permissible here;
|
|
! <https://github.com/OpenACC/openacc-spec/issues/238> "OpenACC 'serial'
|
|
! construct might not actually be serial".
|
|
vectors_actual = 32
|
|
end if
|
|
!$acc loop gang reduction (min: gangs_min, workers_min, vectors_min) reduction (max: gangs_max, workers_max, vectors_max)
|
|
! { dg-note {variable 'i' in 'private' clause isn't candidate for adjusting OpenACC privatization level: not addressable} "" { target *-*-* } .-1 }
|
|
do i = 100, -99, -1
|
|
!$acc loop worker reduction (min: gangs_min, workers_min, vectors_min) reduction (max: gangs_max, workers_max, vectors_max)
|
|
! { dg-note {variable 'j' in 'private' clause isn't candidate for adjusting OpenACC privatization level: not addressable} "" { target *-*-* } .-1 }
|
|
! { dg-note {variable 'D\.[0-9]+' declared in block isn't candidate for adjusting OpenACC privatization level: not addressable} "" { target *-*-* } .-2 }
|
|
do j = 100, -99, -1
|
|
!$acc loop vector reduction (min: gangs_min, workers_min, vectors_min) reduction (max: gangs_max, workers_max, vectors_max)
|
|
! { dg-note {variable 'k' in 'private' clause isn't candidate for adjusting OpenACC privatization level: not addressable} "" { target *-*-* } .-1 }
|
|
do k = 100 * vectors_actual, -99 * vectors_actual, -1
|
|
gangs_min = acc_gang ();
|
|
gangs_max = acc_gang ();
|
|
workers_min = acc_worker ();
|
|
workers_max = acc_worker ();
|
|
vectors_min = acc_vector ();
|
|
vectors_max = acc_vector ();
|
|
end do
|
|
end do
|
|
end do
|
|
!$acc end serial
|
|
if (acc_get_device_type () .eq. acc_device_nvidia) then
|
|
if (vectors_actual /= 32) stop 2
|
|
else
|
|
if (vectors_actual /= 1) stop 3
|
|
end if
|
|
if (gangs_min /= 0 .or. gangs_max /= 1 - 1 &
|
|
.or. workers_min /= 0 .or. workers_max /= 1 - 1 &
|
|
.or. vectors_min /= 0 .or. vectors_max /= vectors_actual - 1) &
|
|
stop 4
|
|
|
|
end program main
|