-
Notifications
You must be signed in to change notification settings - Fork 7
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
#487 working deePDM-py + horovod-hack
- Loading branch information
1 parent
342e902
commit 86c81ba
Showing
6 changed files
with
9,107 additions
and
11 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,85 @@ | ||
| easyblock = 'PythonBundle' | ||
|
|
||
| name = 'DeePDM-kit' | ||
| version = '3.0.1' | ||
| # versionsuffix = '-CUDA-%(cudaver)s' | ||
|
|
||
| homepage = 'https://github.com/deepmodeling/deepmd-kit/' | ||
| description = "A deep learning package for many-body potential energy representation and molecular dynamics." | ||
|
|
||
| toolchain = {'name': 'foss', 'version': '2023a'} | ||
|
|
||
| # DEPS: | ||
| # OK scikit-build-core>=0.5,<0.11,!=0.6.0 | ||
| # OK 'numpy>=1.21', | ||
| # OK 'scipy', | ||
| # OK 'pyyaml', | ||
| # ok 'dargs >= 0.4.7', | ||
| # OK "h5py>=3.6.0,!=3.11.0; platform_system=='Linux' and platform_machine=='aarch64'", | ||
| # ok 'wcmatch', | ||
| # OK 'ml_dtypes', | ||
| # ok 'mendeleev', | ||
| # ok 'array-api-compat', | ||
| # ok dpdata | ||
| # parallel training deps: | ||
| # NO horovod - | ||
| # OK mpi4py | ||
|
|
||
| builddependencies = [ | ||
| ('scikit-build-core', '0.9.3'), | ||
| ('hatchling', '1.18.0'), | ||
| ('poetry', '1.5.1'), | ||
| ('git', '2.41.0', '-nodocs'), | ||
| ] | ||
| dependencies = [ | ||
| # ('CUDA', '12.6.0', '', SYSTEM), | ||
| ('Python', '3.11.3'), | ||
| ('SciPy-bundle', '2023.07'), | ||
| ('ml_dtypes', '0.3.2'), | ||
| ('PyYAML', '6.0'), | ||
| ('h5py', '3.9.0'), | ||
| ('PyTorch', '2.1.2'), | ||
| # ('TensorFlow', '2.15.1'), | ||
| # ('jax', '0.4.25'), | ||
| ('mpi4py', '3.1.4'), | ||
| # ('protobuf', '24.0'), | ||
| # horovod | ||
| ] | ||
|
|
||
| use_pip = True | ||
| sanity_pip_check = True | ||
|
|
||
| # preinstallopts = 'module swap protobuf/3.21.9-GCCcore-12.3.0 && ' | ||
| local_preinstallopts = 'export DP_ENABLE_PYTORCH=1 && export DP_ENABLE_TENSORFLOW=0 && ' | ||
| local_preinstallopts += 'export PYTORCH_ROOT=$EBROOTPYTORCH && ' | ||
|
|
||
| exts_list = [ | ||
| ('dargs', '0.4.10', { | ||
| 'checksums': ['2b39e0a93dcd323d0affb3f54ee2c11a439084d718934df08f38692dfbadddf8'], | ||
| }), | ||
| ('wcmatch', '8.5.2', { | ||
| 'checksums': ['a70222b86dea82fb382dd87b73278c10756c138bd6f8f714e2183128887b9eb2'], | ||
| }), | ||
| ('mendeleev', '0.20.1', { | ||
| 'checksums': ['26f27099f0587cab82dd7f84ee31a5c48e994eb478ea2a92756c5fd50764f7da'], | ||
| }), | ||
| ('array_api_compat', '1.10.0', { | ||
| 'checksums': ['eb98056fa4993e7e98860b7a1ca73c9ae1c77f1ef95366a5ebd5dec8e6d55bad'], | ||
| }), | ||
| ('dpdata', '0.2.21', { | ||
| 'checksums': ['55dcec61bdc8707fb6b3e57406fb7c07b6ccb7a0ac763a1407cc1c3222bf58b1'], | ||
| }), | ||
| ('deepmd_kit', version, { | ||
| 'preinstallopts': "export DP_ENABLE_PYTORCH=1 && export DP_ENABLE_TENSORFLOW=0 && export PYTORCH_ROOT=$EBROOTPYTORCH && ", | ||
| 'checksums': ['10d4443c6fe31a9a4573ed6eda73b6a669dae572cf2bc43f45e9a63aaae02cff'], | ||
| }), | ||
| ] | ||
|
|
||
| # sanity_check_paths = { | ||
| # 'files': ['bin/%(name)s'], | ||
| # 'dirs': ['lib/python%(pyshortver)s/site-packages'], | ||
| # } | ||
|
|
||
| # sanity_check_commands = ['%(name)s --help'] | ||
|
|
||
| moduleclass = 'ai' |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,52 @@ | ||
| easyblock = 'PythonBundle' | ||
|
|
||
| name = 'Horovod' | ||
| version = '0.28.1' | ||
| local_tf_version = '2.15.1' | ||
| local_cuda_suffix = '-CUDA-%(cudaver)s' | ||
| versionsuffix = local_cuda_suffix + '-TensorFlow-%s' % local_tf_version | ||
|
|
||
| homepage = 'https://github.com/uber/horovod' | ||
| description = "Horovod is a distributed training framework for TensorFlow." | ||
|
|
||
| toolchain = {'name': 'foss', 'version': '2023a'} | ||
|
|
||
| builddependencies = [ | ||
| ('CMake', '3.26.3'), | ||
| # ('protobuf', '3.21.9'), | ||
| ] | ||
| dependencies = [ | ||
| ('Python', '3.11.3'), | ||
| ('PyYAML', '6.0'), | ||
| ('CUDA', '12.1.1', '', SYSTEM), | ||
| ('NCCL', '2.18.3', local_cuda_suffix), | ||
| ('TensorFlow', local_tf_version, local_cuda_suffix), | ||
| ] | ||
|
|
||
| use_pip = True | ||
| sanity_pip_check = True | ||
|
|
||
| preinstallopts = 'module swap protobuf/3.21.9-GCCcore-12.3.0 && HOROVOD_WITH_MPI=1 HOROVOD_GPU_ALLREDUCE=NCCL HOROVOD_GPU_BROADCAST=NCCL ' | ||
| preinstallopts += 'HOROVOD_WITH_TENSORFLOW=1 HOROVOD_WITHOUT_PYTORCH=1 HOROVOD_WITHOUT_MXNET=1 ' | ||
|
|
||
| exts_list = [ | ||
| ('cloudpickle', '2.2.1', { | ||
| 'checksums': ['d89684b8de9e34a2a43b3460fbca07d09d6e25ce858df4d5a44240403b6178f5'], | ||
| }), | ||
| ('horovod', version, { | ||
| 'patches': ['Horovod-0.28.1_support_flatbuffers_2.0.6.patch'], | ||
| 'checksums': [ | ||
| '92a43f5a94c43907a56805bad15f19700c62ffc83b7ca483f9e104e229f67ef0', | ||
| '9696ffb3b2bad1d6dd5a9f37bc58078ca7c585f933bcbec037036ad9fc0b297d', | ||
| ], | ||
| }), | ||
| ] | ||
|
|
||
| sanity_check_paths = { | ||
| 'files': ['bin/horovodrun'], | ||
| 'dirs': ['lib/python%(pyshortver)s/site-packages'], | ||
| } | ||
|
|
||
| sanity_check_commands = ["horovodrun --help"] | ||
|
|
||
| moduleclass = 'tools' |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,52 @@ | ||
| easyblock = 'PythonBundle' | ||
|
|
||
| name = 'Horovod' | ||
| version = '0.28.1' | ||
| local_tf_version = '2.15.1' | ||
| # local_cuda_suffix = '-CUDA-%(cudaver)s' | ||
| # versionsuffix = local_cuda_suffix + '-TensorFlow-%s' % local_tf_version | ||
| versionsuffix = '-TensorFlow-%s' % local_tf_version | ||
|
|
||
| homepage = 'https://github.com/uber/horovod' | ||
| description = "Horovod is a distributed training framework for TensorFlow." | ||
|
|
||
| toolchain = {'name': 'foss', 'version': '2023a'} | ||
|
|
||
| builddependencies = [ | ||
| ('CMake', '3.26.3'), | ||
| # ('protobuf', '3.21.9'), | ||
| ] | ||
| dependencies = [ | ||
| ('Python', '3.11.3'), | ||
| ('PyYAML', '6.0'), | ||
| ('TensorFlow', local_tf_version), | ||
| ] | ||
|
|
||
| use_pip = True | ||
| sanity_pip_check = True | ||
|
|
||
| local_preinstallopts = 'module swap protobuf/3.21.9-GCCcore-12.3.0 && HOROVOD_WITH_MPI=1 ' | ||
| local_preinstallopts += 'HOROVOD_WITH_TENSORFLOW=1 HOROVOD_WITHOUT_PYTORCH=1 HOROVOD_WITHOUT_MXNET=1 ' | ||
|
|
||
| exts_list = [ | ||
| ('cloudpickle', '2.2.1', { | ||
| 'checksums': ['d89684b8de9e34a2a43b3460fbca07d09d6e25ce858df4d5a44240403b6178f5'], | ||
| }), | ||
| ('horovod', version, { | ||
| 'preinstallopts': local_preinstallopts, | ||
| 'patches': ['Horovod-0.28.1_support_flatbuffers_2.0.6.patch'], | ||
| 'checksums': [ | ||
| '92a43f5a94c43907a56805bad15f19700c62ffc83b7ca483f9e104e229f67ef0', | ||
| '9696ffb3b2bad1d6dd5a9f37bc58078ca7c585f933bcbec037036ad9fc0b297d', | ||
| ], | ||
| }), | ||
| ] | ||
|
|
||
| sanity_check_paths = { | ||
| 'files': ['bin/horovodrun'], | ||
| 'dirs': ['lib/python%(pyshortver)s/site-packages'], | ||
| } | ||
|
|
||
| sanity_check_commands = ["horovodrun --help"] | ||
|
|
||
| moduleclass = 'tools' |
Oops, something went wrong.