[dpdk-dev] [PATCH v1 01/12] mldev: introduce machine learning device library

Shivah Shankar Shankar Narayan Rao sshankarnara at marvell.com
Thu Feb 2 06:26:50 CET 2023


> -----Original Message-----
> From: jerinj at marvell.com <jerinj at marvell.com>
> Sent: Monday, November 14, 2022 5:32 PM
> To: dev at dpdk.org; Thomas Monjalon <thomas at monjalon.net>; Bruce
> Richardson <bruce.richardson at intel.com>; Srikanth Yalavarthi
> <syalavarthi at marvell.com>
> Cc: ferruh.yigit at xilinx.com; ajit.khaparde at broadcom.com;
> aboyer at pensando.io; andrew.rybchenko at oktetlabs.ru;
> beilei.xing at intel.com; chas3 at att.com; chenbo.xia at intel.com;
> ciara.loftus at intel.com; Devendra Singh Rawat <dsinghrawat at marvell.com>;
> ed.czeck at atomicrules.com; evgenys at amazon.com; grive at u256.net;
> g.singh at nxp.com; zhouguoyang at huawei.com; haiyue.wang at intel.com;
> Harman Kalra <hkalra at marvell.com>; heinrich.kuhn at corigine.com;
> hemant.agrawal at nxp.com; hyonkim at cisco.com; igorch at amazon.com; Igor
> Russkikh <irusskikh at marvell.com>; jgrajcia at cisco.com;
> jasvinder.singh at intel.com; jianwang at trustnetic.com;
> jiawenwu at trustnetic.com; jingjing.wu at intel.com; johndale at cisco.com;
> john.miller at atomicrules.com; linville at tuxdriver.com;
> keith.wiles at intel.com; Kiran Kumar Kokkilagadda
> <kirankumark at marvell.com>; oulijun at huawei.com; Liron Himi
> <lironh at marvell.com>; longli at microsoft.com; mw at semihalf.com;
> spinler at cesnet.cz; matan at nvidia.com; matt.peters at windriver.com;
> maxime.coquelin at redhat.com; mk at semihalf.com; humin29 at huawei.com;
> Pradeep Kumar Nalla <pnalla at marvell.com>; Nithin Kumar Dabilpuram
> <ndabilpuram at marvell.com>; qiming.yang at intel.com;
> qi.z.zhang at intel.com; Radha Chintakuntla <radhac at marvell.com>;
> rahul.lakkireddy at chelsio.com; Rasesh Mody <rmody at marvell.com>;
> rosen.xu at intel.com; sachin.saxena at oss.nxp.com; Satha Koteswara Rao
> Kottidi <skoteshwar at marvell.com>; Shahed Shaikh
> <shshaikh at marvell.com>; shaibran at amazon.com;
> shepard.siegel at atomicrules.com; asomalap at amd.com;
> somnath.kotur at broadcom.com; sthemmin at microsoft.com;
> steven.webster at windriver.com; Sunil Kumar Kori <skori at marvell.com>;
> mtetsuyah at gmail.com; Veerasenareddy Burru <vburru at marvell.com>;
> viacheslavo at nvidia.com; xiao.w.wang at intel.com;
> cloud.wangxiaoyun at huawei.com; yisen.zhuang at huawei.com;
> yongwang at vmware.com; xuanziyang2 at huawei.com; Prasun Kapoor
> <pkapoor at marvell.com>; Nadav Haklai <nadavh at marvell.com>; Satananda
> Burla <sburla at marvell.com>; Narayana Prasad Raju Athreya
> <pathreya at marvell.com>; Akhil Goyal <gakhil at marvell.com>;
> mdr at ashroe.eu; dmitry.kozliuk at gmail.com; anatoly.burakov at intel.com;
> cristian.dumitrescu at intel.com; honnappa.nagarahalli at arm.com;
> mattias.ronnblom at ericsson.com; ruifeng.wang at arm.com;
> drc at linux.vnet.ibm.com; konstantin.ananyev at intel.com;
> olivier.matz at 6wind.com; jay.jayatheerthan at intel.com; Ashwin Sekhar T K
> <asekhar at marvell.com>; Pavan Nikhilesh Bhagavatula
> <pbhagavatula at marvell.com>; eagostini at nvidia.com; Derek Chickles
> <dchickles at marvell.com>; Shivah Shankar Shankar Narayan Rao
> <sshankarnara at marvell.com>; Jerin Jacob Kollanukkaran
> <jerinj at marvell.com>
> Subject: [dpdk-dev] [PATCH v1 01/12] mldev: introduce machine learning
> device library
> 
> From: Jerin Jacob <jerinj at marvell.com>
> 
> Add mldev API specification to standardize and use the machine learning
> device and inference operations in vendor neutral way.
> 
> Following operations are abstracted through APIs
> 
> - ML device capability probe
> - ML device configuration
> - ML device queue pair configuration
> - ML device state management
> - ML device stat/xstat operations
> - ML model load/unload/start/stop operations
> - ML model information probe
> - ML IO operations to find size for input and output buffers
> - ML quantize and dequantize operations
> - ML ops pool creation and free operations
> - ML device enqueue/dequeue fastpath interference operations
> 
> Also added programming guide.
> 
> Signed-off-by: Jerin Jacob <jerinj at marvell.com>
> Signed-off-by: Srikanth Yalavarthi <syalavarthi at marvell.com>
> ---
>  MAINTAINERS                              |    5 +
>  config/rte_config.h                      |    3 +
>  doc/api/doxy-api-index.md                |    1 +
>  doc/api/doxy-api.conf.in                 |    1 +
>  doc/guides/prog_guide/img/mldev_flow.svg |  714 ++++++++++++++
>  doc/guides/prog_guide/index.rst          |    1 +
>  doc/guides/prog_guide/mldev.rst          |  186 ++++
>  lib/eal/common/eal_common_log.c          |    1 +
>  lib/eal/include/rte_log.h                |    1 +
>  lib/meson.build                          |    1 +
>  lib/mldev/meson.build                    |   18 +
>  lib/mldev/rte_mldev.c                    |    5 +
>  lib/mldev/rte_mldev.h                    | 1092 ++++++++++++++++++++++
>  lib/mldev/version.map                    |    3 +
>  14 files changed, 2032 insertions(+)
>  create mode 100644 doc/guides/prog_guide/img/mldev_flow.svg
>  create mode 100644 doc/guides/prog_guide/mldev.rst
>  create mode 100644 lib/mldev/meson.build
>  create mode 100644 lib/mldev/rte_mldev.c
>  create mode 100644 lib/mldev/rte_mldev.h
>  create mode 100644 lib/mldev/version.map
> 
Acked-by: Shivah Shankar S <sshankarnara at marvell.com>



More information about the dev mailing list