aws-ofi-rccl/66b3b31-cpeGNU-22.08 (aws-ofi-rccl-66b3b31-cpeGNU-22.08.eb)
This software is archived in the LUMI-EasyBuild-contrib GitHub repository as easybuild/easyconfigs/__archive__/a/aws-ofi-rccl/aws-ofi-rccl-66b3b31-cpeGNU-22.08.eb. The corresponding module would be aws-ofi-rccl/66b3b31-cpeGNU-22.08.
easyblock = 'ConfigureMake'
name = 'aws-ofi-rccl'
version = '66b3b31'
homepage = 'https://github.com/ROCmSoftwarePlatform/aws-ofi-rccl'
whatis = [
'Description: AWS OFI RCCL is a plug-in which enables EC2 developers to use libfabric as a network provider.'
]
description = """
Machine learning frameworks running on top of AMD GPUs use a library called
RCCL which provides standard collective communication routines for an arbitrary
number of GPUs installed across single or multiple nodes.
This module implements a plug-in which maps RCCLs connection-oriented transport
APIs to libfabric's connection-less reliable interface. This allows RCCL
applications to take benefit of libfabric's transport layer services like
reliable message support and operating system bypass.
"""
software_license_urls = ['https://github.com/ROCmSoftwarePlatform/aws-ofi-rccl/blob/cxi/LICENSE']
toolchain = {'name': 'cpeGNU', 'version': '22.08'}
sources = [{
'filename': '%(name)s-%(version)s.tar.gz',
'git_config': {
'url': 'https://github.com/ROCmSoftwarePlatform',
'repo_name': '%(name)s',
'commit': '%(version)s',
}
}]
dependencies = [
('rccl', '2.12.7')
]
preconfigopts = ' ./autogen.sh && '
configopts = (
' --with-libfabric=/opt/cray/libfabric/$(pkg-config --modversion libfabric) '
' --with-hip=$EBROOTROCM/hip '
' --with-rccl=$EBROOTRCCL '
)
sanity_check_paths = {
'files': ['lib/librccl-net.so.0.0.0'],
'dirs': ['bin', 'lib']
}
moduleclass = 'devel'