Observed issues › catalog/cce-acc-allocate-in-compute-crash

Appears to behave incorrectlyCrashes or aborts at run time · Fortran · OpenACC · Open

ftn: ALLOCATE/DEALLOCATE of a local allocatable in device code aborts (SIGABRT), OpenMP and OpenACC

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

Same issue as catalog/cce-flang-allocate-in-target-crash; this program is another reproducer of it.

Affected variants

Compiler	MI300A 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 24.3.0	n/a	n/a	n/a	n/a	n/a	n/a	n/a
CCE 19.0.0	behaves incorrectly	behaves incorrectly	behaves incorrectly	unknown not run	unknown not run	n/a	n/a
CCE 20.0.2	behaves incorrectly	behaves incorrectly	behaves incorrectly	unknown not run	unknown not run	n/a	n/a
CCE 21.0.3	behaves incorrectly	behaves incorrectly	behaves incorrectly	unknown not run	unknown not run	n/a	n/a
CCE 21.0.4	behaves incorrectly	behaves incorrectly	behaves incorrectly	unknown not run	unknown not run	n/a	n/a
NVHPC 25.11	n/a	n/a	n/a	n/a	n/a	fails another way	fails another way
NVHPC 26.9	n/a	n/a	n/a	n/a	n/a	fails another way	fails another way
GCC 16.2.0	correct	correct	correct	correct	correct	correct	n/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

Result	Compiler and GPU	Message
behaves incorrectly	CCE 19.0.0, MI300A unified	show :0:rocdevice.cpp :2994: 1714753759840 us: Callback: Queue 0x155545600000 aborting with error : HSA_STATUS_ERROR_EXCEPTION: An HSAIL operation resulted in a hardware exception. code: 0x1016
behaves incorrectly	CCE 19.0.0, MI300A copy	show :0:rocdevice.cpp :2994: 1714760781508 us: Callback: Queue 0x155545600000 aborting with error : HSA_STATUS_ERROR_EXCEPTION: An HSAIL operation resulted in a hardware exception. code: 0x1016
behaves incorrectly	CCE 19.0.0, MI250X	show :0:rocdevice.cpp :2994: 1570956944340 us: Callback: Queue 0x155545600000 aborting with error : HSA_STATUS_ERROR_EXCEPTION: An HSAIL operation resulted in a hardware exception. code: 0x1016
behaves incorrectly	CCE 20.0.2, MI300A unified	show :0:rocdevice.cpp :2994: 1715110980932 us: Callback: Queue 0x155545600000 aborting with error : HSA_STATUS_ERROR_EXCEPTION: An HSAIL operation resulted in a hardware exception. code: 0x1016
behaves incorrectly	CCE 20.0.2, MI300A copy	show :0:rocdevice.cpp :2994: 1715127167799 us: Callback: Queue 0x155545600000 aborting with error : HSA_STATUS_ERROR_EXCEPTION: An HSAIL operation resulted in a hardware exception. code: 0x1016
behaves incorrectly	CCE 20.0.2, MI250X	show ACC: ERROR: invalid dope vector (dv_versn=0) 'w(:)' from cce-acc-allocate-in-compute-crash.f90:14 ACC: libcrayacc/acc_dopevector.c:34 CRAY_ACC_ERROR - Invalid dope vector
behaves incorrectly	CCE 21.0.3, MI300A unified CCE 21.0.3, MI300A copy CCE 21.0.4, MI300A unified CCE 21.0.4, MI300A copy	show ACC: ERROR: invalid dope vector (dv_versn=47) 'w(:)' from cce-acc-allocate-in-compute-crash.f90:14 ACC: libcrayacc/acc_dopevector.c:34 CRAY_ACC_ERROR - Invalid dope vector
behaves incorrectly	CCE 21.0.3, MI250X	show :0:rocdevice.cpp :3586: 1570926103836 us: Callback: Queue 0x155545200000 aborting with error : HSA_STATUS_ERROR_EXCEPTION: An HSAIL operation resulted in a hardware exception. code: 0x1016 ACC: libcrayacc/acc_hw_amd.c:1496 CRAY_ACC_ERROR - hipStreamSynchronize returned hipErrorLaunchFailure: 'unspecified launch failure' from cce-acc-allocate-in-compute-crash.f90:23 ACC: libcrayacc/acc_hw_amd.c:1476 CRAY_ACC_ERROR - hipDeviceSynchronize returned hipErrorLaunchFailure: 'unspecified launch failure' Thread execution stopped at FILE cce-acc-allocate-in-compute-crash.f90 LINE 18 due to a Fortran allocate/deallocate statement. Kernel Name: wide_prog_$ck_L14_1 VGPU=0x8ef9b0 SWq=0x15555537e000, HWq=0x155545200000, id=1 Dispatch Header =0xb02 (type=2, barrier=1, acquire=1, release=1), setup=0 grid=[1, 1, 1], workgroup=[1, 1, 1]
behaves incorrectly	CCE 21.0.4, MI250X	show :0:rocdevice.cpp :3586: 1570854166473 us: Callback: Queue 0x155545200000 aborting with error : HSA_STATUS_ERROR_EXCEPTION: An HSAIL operation resulted in a hardware exception. code: 0x1016 ACC: libcrayacc/acc_hw_amd.c:1496 CRAY_ACC_ERROR - hipStreamSynchronize returned hipErrorLaunchFailure: 'unspecified launch failure' from cce-acc-allocate-in-compute-crash.f90:23 ACC: libcrayacc/acc_hw_amd.c:1476 CRAY_ACC_ERROR - hipDeviceSynchronize returned hipErrorLaunchFailure: 'unspecified launch failure' Thread execution stopped at FILE cce-acc-allocate-in-compute-crash.f90 LINE 18 due to a Fortran allocate/deallocate statement. Kernel Name: wide_prog_$ck_L14_1 VGPU=0x8ef9b0 SWq=0x15555537e000, HWq=0x155545200000, id=1 Dispatch Header =0xb02 (type=2, barrier=1, acquire=1, release=1), setup=0 grid=[1, 1, 1], workgroup=[1, 1, 1]
fails another way	NVHPC 25.11, A100 separate NVHPC 25.11, A100 managed NVHPC 26.9, A100 separate NVHPC 26.9, A100 managed	show NVFORTRAN-S-1219-Unimplemented feature: BLOCK construct in the scope of a parallel directive. (cce-acc-allocate-in-compute-crash.f90: 16) 0 inform, 0 warnings, 1 severes, 0 fatal for wide_prog

Reproduce

CCE 19.0.0, MI300A unified

module load cce/19.0.0 craype-accel-amd-gfx942 rocm/6.4.3
module unload cray-mpich
ftn -h acc -O2 repro.f90 -o repro
HSA_XNACK=1 ./repro

CCE 20.0.2, MI300A unified

module load cce/20.0.2 craype-accel-amd-gfx942 rocm/6.4.3
module unload cray-mpich
ftn -h acc -O2 repro.f90 -o repro
HSA_XNACK=1 ./repro

CCE 21.0.3, MI300A unified

module load cce/21.0.3 craype-accel-amd-gfx942 rocm/7.2.0
module unload cray-mpich
ftn -h acc -O2 repro.f90 -o repro
HSA_XNACK=1 ./repro

CCE 21.0.4, MI300A unified

module load cce/21.0.4 craype-accel-amd-gfx942 rocm/7.2.0
module unload cray-mpich
ftn -h acc -O2 repro.f90 -o repro
HSA_XNACK=1 ./repro

GCC 16.2.0, MI300A unified (runs correctly)

export LD_LIBRARY_PATH=$GCC_16_2/lib64:/opt/rocm-7.2.1/lib
$GCC_16_2/bin/gfortran -fopenacc -foffload=amdgcn-amdhsa -foffload-options=amdgcn-amdhsa=-march=gfx942 -O2 repro.f90 -o repro
HSA_XNACK=1 ./repro

Program (59 lines)

! # Draft finding: acc34-w-allocate-in-device on cce19
!
! - compiler: cce19
! - toolchain: cce19; arch: gfx942; machine: tuolumne; memory mode: unified; opt: -O2
! - program: catalog acc34-w-allocate-in-device (f90, version 34, sha256 bc9f4dc73a5f7637)
! - expected: check=pass (trusted; elision + model)
! - actual: crash  (crash: SIGABRT)
! - 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: 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: elision
! - withdrawn: none
!
! Generated by compliance.widen (OpenACC 3.4, free-form Fortran; catalog widening). Do not edit.
! id: acc34-w-allocate-in-device
! primary atom: base.device.allocate
! atoms: base.device.allocate
! legal: yes
! observable: yes
! ran_on_host: inside the compute region of interest (acc_on_device)
! evidence: construct
! needs: none
! std: f2008
! feature: ALLOCATE and DEALLOCATE of a local allocatable array in a target region
! spec: OpenACC 3.4 §1.8, p.16: Fortran 2008 is a normative base language (the features whose use is unspecified are listed there;
! this is not one of them)
program wide_prog
  use openacc, only: acc_device_host, acc_on_device
  implicit none
  integer, parameter :: n = 64
  integer :: a(n), b(n), ref(n)
  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
  !$acc serial copyin(a) copyout(b) copy(host_flag)
    host_flag = merge(1, 0, acc_on_device(acc_device_host))
    block
      integer, allocatable :: w(:)
      allocate(w(n))
      w = 2*a + 1
      b = w
      deallocate(w)
    end block
  !$acc end serial
  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

:0:rocdevice.cpp            :2994: 1714753759840 us:  Callback: Queue 0x155545600000 aborting with error : HSA_STATUS_ERROR_EXCEPTION: An HSAIL operation resulted in a hardware exception. code: 0x1016

What the specification requires

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

OpenACC 3.4 §1.8 p.16

Evidence

Same compiler, one change

w a fixed-size local array (no ALLOCATE/DEALLOCATE): CCE 19.0.0: correct; CCE 20.0.2: correct; CCE 21.0.3: correct; CCE 21.0.4: correct

Control program

program wide_prog
  use openacc, only: acc_device_host, acc_on_device
  implicit none
  integer, parameter :: n = 64
  integer :: a(n), b(n), ref(n)
  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
  !$acc serial copyin(a) copyout(b) copy(host_flag)
    host_flag = merge(1, 0, acc_on_device(acc_device_host))
    block
      integer :: w(n)
      w = 2*a + 1
      b = w
    end block
  !$acc end serial
  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

GCC 16.2.0