Re: [dpdk-dev] [EXT] Re: [PATCH v3 0/9] GPU library

[Jerin Jacob Kollanukkaran <jerinj@marvell.com>]

> -----Original Message-----
> From: dev <dev-bounces@dpdk.org> On Behalf Of Thomas Monjalon
> Sent: Wednesday, October 20, 2021 12:42 AM
> To: Jerin Jacob <jerinjacobk@gmail.com>
> Cc: Elena Agostini <eagostini@nvidia.com>; techboard@dpdk.org; dpdk-dev
> <dev@dpdk.org>
> Subject: [EXT] Re: [dpdk-dev] [PATCH v3 0/9] GPU library
> 
> External Email
> 
> ----------------------------------------------------------------------
> 19/10/2021 20:47, Jerin Jacob:
> > > As I stated multiple times, let’s start with something simple that
> > > works and then think about how to enhance the library/driver.
> >
> > I have submitted RFC[1] to abstract in a generic way so that
> > workload-specific _driver_ aspects are NOT EXPOSED to the application.
> >
> > The RFC explains with application code, how any workload can be used
> > by the application without exposing the driver details.
> > Also, shows how to enable a framework to abstract a different form of
> > workload acceletor(DPU, GPU, XPU, IPU....)
> >
> > In order to map to this discussion with RFC:
> > You may need to add a new host port for GPU which as
> > lib/dwa/rte_dwa_port_host_xxxxx.h and adding new workload as
> > lib/dwa/rte_dwa_profile_xxxx.h(Which can be reused by all dataplane
> > workload accelerator)
> >
> > [1]
> > https://urldefense.proofpoint.com/v2/url?u=http-3A__mails.dpdk.org_arc
> > hives_dev_2021-
> 2DOctober_226070.html&d=DwIFaQ&c=nKjWec2b6R0mOyPaz7xtfQ
> >
> &r=1DGob4H4rxz6H8uITozGOCa0s5f4wCNtTa4UUKvcsvI&m=8RtZAL1mpqAKtA
> i3Fpryk
> >
> gq7CJ_9Xlb_cnR8gVPZPAc&s=aWBFPWzbVCCBZ9HSTIwBD5Mw9wdBYje1ad8zY
> j7oeiI&e
> > =
> 
> That's really 2 different points of view:
> 	- expose only some predefined dataplane workloads
> 	- or allow to build any custom workload

That’s one way to look at. Other way to look at, If you split the workload as quantifiable piece.
We could chain the workload to create any custom workload.
Another aspect is how can application writer  custom Dataplane workload which is not
specific to acceletor HW rather it express what need to do for the application .


> 
>