OffTarget

Observed issues › catalog/nvhpc-flang-type-bound-kernel-missing

Appears to behave incorrectlyRun-time error · Fortran · OpenMP · Open

nvc/nvfortran -mp=gpu: compile succeeds but the kernel is missing at run time ("Failed to find device function") for function pointers, static locals, VLAs, long double, type-bound calls

Legality: not independently confirmed. no independent review yet How this is checked

Same issue as catalog/nvhpc-c-function-pointer-kernel-missing; this program is another reproducer of it.

Affected variants

CompilerMI300A gfx942
unified memory (XNACK 1)
MI300A gfx942
copy (XNACK 0)
MI250X gfx90a
copy (XNACK 0)
MI300X gfx942
copy (XNACK 0)
MI350X gfx950
copy (XNACK 0)
A100 sm_80
separate memory
A100 sm_80
managed memory
AFAR 24.3.0correctcorrectunknown
not run
correctcorrectn/an/a
CCE 19.0.0correctcorrectunknown
not run
unknown
not run
unknown
not run
n/an/a
CCE 20.0.2correctcorrectunknown
not run
unknown
not run
unknown
not run
n/an/a
CCE 21.0.3correctcorrectunknown
not run
unknown
not run
unknown
not run
n/an/a
CCE 21.0.4correctcorrectunknown
not run
unknown
not run
unknown
not run
n/an/a
NVHPC 25.11n/an/an/an/an/abehaves incorrectlybehaves incorrectly
NVHPC 26.9n/an/an/an/an/abehaves incorrectlybehaves incorrectly
GCC 16.2.0correctcorrectcorrectcorrectcorrectcorrectn/a

"behaves incorrectly" / "not supported": this issue, confirmed in up to four environments (another build directory, another node, a repeat). "fails another way": a different failure, not counted as this issue. "unknown": not run there, or the runs disagree.

Messages

ResultCompiler and GPUMessage
behaves incorrectlyNVHPC 25.11, A100 separate
NVHPC 25.11, A100 managed
NVHPC 26.9, A100 separate
NVHPC 26.9, A100 managed
show
Accelerator Fatal Error: Failed to find device function 'nvkernel_MAIN__F1L31_2_'! File was compiled with: -gpu=cc80
Rebuild this file with -gpu=cc80 to use NVIDIA Tesla GPU 0
 File: <dir>/nvhpc-flang-type-bound-kernel-missing.f90
 Function: wide_prog:16
 Line: 31

Reproduce

NVHPC 25.11, A100 separate

export LD_LIBRARY_PATH=$NVHPC_25_11/compilers/lib
nvfortran -mp=gpu -gpu=cc80 -gpu=mem:separate -O2 repro.f90 -o repro
OMP_TARGET_OFFLOAD=mandatory ./repro

NVHPC 26.9, A100 separate

export LD_LIBRARY_PATH=$NVHPC_26_9/compilers/lib
nvfortran -mp=gpu -gpu=cc80 -gpu=mem:separate -O2 repro.f90 -o repro
OMP_TARGET_OFFLOAD=mandatory ./repro

AFAR 24.3.0, MI300A unified (runs correctly)

$AFAR/bin/amdflang -fopenmp --offload-arch=gfx942 -O2 repro.f90 -o repro
HSA_XNACK=1 OMP_TARGET_OFFLOAD=mandatory ./repro
Program (78 lines)
! # Draft finding: omp52-w-type-bound-nopass on nvhpc
!
! - compiler: nvhpc
! - toolchain: nvhpc; arch: sm_80; machine: wingtip; memory mode: copy; opt: -O2
! - program: catalog omp52-w-type-bound-nopass (f90, version 52, sha256 b1838fc2dcb2b1e6)
! - expected: check=pass (trusted; elision + model)
! - actual: run_error  (exit_status: 1; without mandatory: exit_status: 1) [the confirmer's class run_error; the matrix's class of
!   the same run is wrong_answer: a run that fails]
! - observed: the run ends with "Accelerator Fatal Error: Failed to find device function 'nvkernel_MAIN__F1L43_2_'! File
!   was compiled with: -gpu=cc80" (NVHPC 25.11 and 26.9, separate and managed memory): the compile succeeds without generating the
!   kernel of the target region that calls a type-bound procedure; the OpenACC form (acc34-w-type-bound-*) runs the parallel loop on
!   the host instead (ran_on_host=1)
! - verdict: compiler_bug by rule R20-runtime-bug: a legal program fails at run time, deterministically, against an expected value
!   from two or more independent sources with an executed witness, and another toolchain, mode, arch or the elision gives the
!   expected value
! - reason: expected trusted check=pass (elision + model): stored main verdict: elision + model agree; witnesses: afar/gfx942/copy,
!   cce19/gfx942/copy, cce20/gfx942/copy, cce21/gfx942/copy, elision
! - citations: RUL-DERIVED-NEEDS-EXECUTION (rulings.md); RUL-WITNESS-PER-MODE (rulings.md);
!   RUL-SAME-COMPILER-RUNS (rulings.md); RUL-PRESENCE-WITNESS (rulings.md); RUL-METAMORPHIC-OTHER-FAMILY
!   (rulings.md)
! - legality: legal: offload.engine.prerun.check accepts it (rerun: offload.engine.rules with the
!   race rule and the restriction checks, and the AFAR flang front end, not under test here); no
!   compiler under test, gfortran or gcc is a legality witness
! - witnesses: afar/gfx942/copy, cce19/gfx942/copy, cce20/gfx942/copy, cce21/gfx942/copy, elision
! - withdrawn: none
!
! Generated by compliance.widen (OpenMP 5.2, free-form Fortran; catalog widening). Do not edit.
! id: omp52-w-type-bound-nopass
! primary atom: base.device.type_bound_nopass
! atoms: base.device.type_bound_nopass
! legal: yes
! observable: yes
! ran_on_host: inside the target region of interest
! evidence: construct
! needs: none
! std: f2008
! feature: a NOPASS type-bound procedure called through a mapped object in device code
! spec: OpenMP 5.2 §1.7, pp.34-35: Fortran 2008 is a normative base language (the Fortran 2018 features whose use is unspecified are
! listed there; this is not one of them)
module wmod
  implicit none
  type op_t
    integer :: k = 0
  contains
    procedure, nopass :: tw => tw_impl
  end type op_t
contains
  integer function tw_impl(x)
    !$omp declare target
    integer, intent(in) :: x
    tw_impl = 2*x + 1
  end function tw_impl
end module wmod

program wide_prog
  use omp_lib, only: omp_is_initial_device
  use wmod
  implicit none
  integer, parameter :: n = 64
  integer :: a(n), b(n), ref(n)
  type(op_t) :: op
  integer :: i, host_flag
  logical :: ok
  do i = 1, n
    a(i) = i
    b(i) = 0
    ref(i) = 2*i + 1
  end do
  host_flag = 1
  !$omp target teams distribute parallel do map(to: a, op) map(from: b) map(tofrom: host_flag)
  do i = 1, n
    b(i) = op%tw(a(i))
    if (i == 1) host_flag = merge(1, 0, omp_is_initial_device())
  end do
  !$omp end target teams distribute parallel do
  ok = all(b == ref)
  print '(a,i0,a,a)', 'RESULT ran_on_host=', host_flag, ' check=', merge('pass', 'fail', ok)
end program wide_prog

Source in the repository

Something to add? Dispute its legality · Report it fixed in a newer release · Report a mistake on this page

Expected and observed

Expected

check=pass

Observed where it behaves incorrectly

Accelerator Fatal Error: Failed to find device function 'nvkernel_MAIN__F1L31_2_'! File was compiled with: -gpu=cc80
Rebuild this file with -gpu=cc80 to use NVIDIA Tesla GPU 0
 File: <dir>/nvhpc-flang-type-bound-kernel-missing.f90
 Function: wide_prog:16
 Line: 31

What the specification requires

The specification text this program relies on and the compiler is expected to support.

OpenMP 5.2 §1.7 p.34-35

Evidence

Same compiler, one change

  • tw_impl called directly instead of through the type-bound name op%tw: AFAR 24.3.0: correct; CCE 19.0.0: correct; CCE 20.0.2: correct; CCE 21.0.3: correct; CCE 21.0.4: correct; NVHPC 25.11: correct; NVHPC 26.9: correct
    Control program
    module wmod
      implicit none
      type op_t
        integer :: k = 0
      contains
        procedure, nopass :: tw => tw_impl
      end type op_t
    contains
      integer function tw_impl(x)
        !$omp declare target
        integer, intent(in) :: x
        tw_impl = 2*x + 1
      end function tw_impl
    end module wmod
    
    program wide_prog
      use omp_lib, only: omp_is_initial_device
      use wmod
      implicit none
      integer, parameter :: n = 64
      integer :: a(n), b(n), ref(n)
      type(op_t) :: op
      integer :: i, host_flag
      logical :: ok
      do i = 1, n
        a(i) = i
        b(i) = 0
        ref(i) = 2*i + 1
      end do
      host_flag = 1
      !$omp target teams distribute parallel do map(to: a, op) map(from: b) map(tofrom: host_flag)
      do i = 1, n
        b(i) = tw_impl(a(i))
        if (i == 1) host_flag = merge(1, 0, omp_is_initial_device())
      end do
      !$omp end target teams distribute parallel do
      ok = all(b == ref)
      print '(a,i0,a,a)', 'RESULT ran_on_host=', host_flag, ' check=', merge('pass', 'fail', ok)
    end program wide_prog
    

Other compilers run it correctly

AFAR 24.3.0, CCE 19.0.0, CCE 20.0.2, CCE 21.0.3, CCE 21.0.4, GCC 16.2.0