Open fwyzard opened 3 hours ago
assign core,pdmv
New categories assigned: core,pdmv
@Dr15Jones,@AdrianoDee,@sunilUIET,@miquork,@makortel,@smuzaffar,@kskovpen you have been requested to review this Pull request/Issue and eventually sign? Thanks
cms-bot internal usage
A new Issue was created by @fwyzard.
@Dr15Jones, @antoniovilela, @makortel, @mandrenguyen, @rappoccio, @sextonkennedy, @smuzaffar can you please review it and eventually sign/assign? Thanks.
cms-bot commands are listed here
@sextonkennedy @srimanob @AdrianoDee FYI
@vlimant @malbouis FYI
@ckoraka FYI
runTheMatrix.py
has some GPU-related options:However, they affect only the creation of WMAgent (?) workflows, not the actual content of the workflow generated by
cmsDriver.py
and executed bycmsRun
.I would like to propose two changes:
--gpu
option fromforbidden
tooptional
;--gpu
option to cmsDriver, via the--accelerators
option.The first change is IMHO something we should do in its own right, but here it is motivated by minimising the impact of the second change on the cmsDriver workflows.
The second change proposes to map:
--gpu optional
to the current behaviour, that is, no extra cmsDriver options--gpu forbidden
tocmsDriver.py --accelerators cpu
--gpu required
tocmsDriver.py --accelerators gpu-*
By default cmsDriver does not impose any restrictions on the usage of GPUs. Passing
--accelerators cpu
sets the job'sprocess.options.accelerators
to[ 'cpu' ]
, which prevents the use of GPUs in a CUDA or Alpaka workflow. Passing--accelerators gpu-*
sets the job'sprocess.options.accelerators
to[ 'gpu-*' ]
, which requires the use of GPUs in a CUDA or Alpaka workflow.The advantage of this approach is that we no longer need to triplicate all Alpaka-related workflows: one version to run on any backend, one version to run only on CPU, one version to run only on GPUs.
As this change would affect O&C and PPD operations, what is their opinion ?