Hi,
I am trying to use pyfr2.0.3 with rocm6.0.3 to run the test case but with error:
Traceback (most recent call last):
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/lib/python3.11/site-packages/pyfr/backends/hip/rocblas.py", line 121, in mul
algo, dt = self._mul_cache[ckey]
~~~~~~~~~~~~~~~^^^^^^
KeyError: (<class 'numpy.float64'>, 1.0, 0.0, 768, 16, 16, 768, 64, 768)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/bin/pyfr", line 8, in <module>
sys.exit(main())
^^^^^^
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/lib/python3.11/site-packages/pyfr/__main__.py", line 124, in main
args.process(args)
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/lib/python3.11/site-packages/pyfr/__main__.py", line 258, in process_run
_process_common(
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/lib/python3.11/site-packages/pyfr/__main__.py", line 243, in _process_common
solver = get_solver(backend, rallocs, mesh, soln, cfg)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/lib/python3.11/site-packages/pyfr/solvers/__init__.py", line 14, in get_solver
return get_integrator(backend, systemcls, rallocs, mesh, initsoln, cfg)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/lib/python3.11/site-packages/pyfr/integrators/__init__.py", line 34, in get_integrator
return integrator(backend, systemcls, rallocs, mesh, initsoln, cfg)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/lib/python3.11/site-packages/pyfr/integrators/dual/phys/controllers.py", line 6, in __init__
super().__init__(*args, **kwargs)
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/lib/python3.11/site-packages/pyfr/integrators/dual/phys/steppers.py", line 14, in __init__
super().__init__(*args, **kwargs)
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/lib/python3.11/site-packages/pyfr/integrators/dual/phys/base.py", line 23, in __init__
self.pseudointegrator.commit()
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/lib/python3.11/site-packages/pyfr/integrators/dual/pseudo/multip.py", line 127, in commit
s.system.commit()
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/lib/python3.11/site-packages/pyfr/solvers/base/system.py", line 67, in commit
self._gen_kernels(self.nregs, self.ele_map.values(), self._int_inters,
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/lib/python3.11/site-packages/pyfr/solvers/base/system.py", line 202, in _gen_kernels
kern = kgetter(i)
^^^^^^^^^^
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/lib/python3.11/site-packages/pyfr/solvers/baseadvec/elements.py", line 74, in <lambda>
kernels['disu'] = lambda uin: self._be.kernel(
^^^^^^^^^^^^^^^^
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/lib/python3.11/site-packages/pyfr/backends/base/backend.py", line 196, in kernel
kern = kern_meth(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/lib/python3.11/site-packages/pyfr/backends/hip/rocblas.py", line 143, in mul
dt = self._benchmark(gemm)
^^^^^^^^^^^^^^^^^^^^^
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/lib/python3.11/site-packages/pyfr/backends/hip/provider.py", line 47, in _benchmark
kfunc(stream)
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/lib/python3.11/site-packages/pyfr/backends/hip/rocblas.py", line 114, in gemm
w.rocblas_gemm_ex(
File "/pfs/lustrep2/projappl/project_465000921/zhenyang/ENV_rocm6/pyfr203_rocm6_lintrip/lib/python3.11/site-packages/pyfr/ctypesutil.py", line 37, in _errcheck
raise self._statuses[status]
pyfr.backends.hip.rocblas.RocBLASInvalidValue
srun: error: nid007964: task 0: Exited with exit code 1
srun: Terminating StepId=8009219.0
The computer system is just updated. I wonder if it is the problem with the cluster.
Regards,
Zhenyang