From: "Varghese, Vipin" <vipin.varghese@amd.com>
To: "Burakov, Anatoly" <anatoly.burakov@intel.com>,
ferruh.yigit@amd.com, dev@dpdk.org
Subject: Re: [RFC 0/2] introduce LLC aware functions
Date: Mon, 2 Sep 2024 06:38:20 +0530 [thread overview]
Message-ID: <65f3dc80-2d07-4b8b-9a5c-197eb2b21180@amd.com> (raw)
In-Reply-To: <288d9e9e-aaec-4dac-b969-54e01956ef4e@intel.com>
[-- Attachment #1: Type: text/plain, Size: 2391 bytes --]
<Snipped>
Thank you Antaloy for the response. Let me try to share my understanding.
> I recently looked into how Intel's Sub-NUMA Clustering would work within
> DPDK, and found that I actually didn't have to do anything, because the
> SNC "clusters" present themselves as NUMA nodes, which DPDK already
> supports natively.
yes, this is correct. In Intel Xeon Platinum BIOS one can enable
`Cluster per NUMA` as `1,2 or4`.
This divides the tiles into Sub-Numa parition, each having separate
lcores,memory controllers, PCIe
and accelerator.
>
> Does AMD's implementation of chiplets not report themselves as separate
> NUMA nodes?
In AMD EPYC Soc, this is different. There are 2 BIOS settings, namely
1. NPS: `Numa Per Socket` which allows the IO tile (memory, PCIe and
Accelerator) to be partitioned as Numa 0, 1, 2 or 4.
2. L3 as NUMA: `L3 cache of CPU tiles as individual NUMA`. This allows
all CPU tiles to be independent NUMA cores.
The above settings are possible because CPU is independent from IO tile.
Thus allowing 4 combinations be available for use.
These are covered in the tuning gudie for the SoC in 12. How to get best
performance on AMD platform — Data Plane Development Kit 24.07.0
documentation (dpdk.org)
<https://doc.dpdk.org/guides/linux_gsg/amd_platform.html>.
> Because if it does, I don't really think any changes are
> required because NUMA nodes would give you the same thing, would it not?
I have a different opinion to this outlook. An end user can
1. Identify the lcores and it's NUMA user `usertools/cpu-layout.py`
2. But it is core mask in eal arguments which makes the threads
available to be used in a process.
3. there are no API which distinguish L3 numa domain. Function
`rte_socket_id
<https://doc.dpdk.org/api/rte__lcore_8h.html#a7c8da4664df26a64cf05dc508a4f26df>`
for CPU tiles like AMD SoC will return physical socket.
Example: In AMD EPYC Genoa, there are total of 13 tiles. 12 CPU tiles
and 1 IO tile. Setting
1. NPS to 4 will divide the memory, PCIe and accelerator into 4 domain.
While the all CPU will appear as single NUMA but each 12 tile having
independent L3 caches.
2. Setting `L3 as NUMA` allows each tile to appear as separate L3 clusters.
Hence, adding an API which allows to select available lcores based on
Split L3 is essential irrespective of the BIOS setting.
>
> --
> Thanks,
> Anatoly
>
[-- Attachment #2: Type: text/html, Size: 7994 bytes --]
next prev parent reply other threads:[~2024-09-02 1:08 UTC|newest]
Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-08-27 15:10 Vipin Varghese
2024-08-27 15:10 ` [RFC 1/2] eal: add llc " Vipin Varghese
2024-08-27 17:36 ` Stephen Hemminger
2024-09-02 0:27 ` Varghese, Vipin
2024-08-27 20:56 ` Wathsala Wathawana Vithanage
2024-08-29 3:21 ` 答复: " Feifei Wang
2024-09-02 1:20 ` Varghese, Vipin
2024-09-03 17:54 ` Wathsala Wathawana Vithanage
2024-09-04 8:18 ` Bruce Richardson
2024-09-06 11:59 ` Varghese, Vipin
2024-09-12 16:58 ` Wathsala Wathawana Vithanage
2024-08-27 15:10 ` [RFC 2/2] eal/lcore: add llc aware for each macro Vipin Varghese
2024-08-27 21:23 ` [RFC 0/2] introduce LLC aware functions Mattias Rönnblom
2024-09-02 0:39 ` Varghese, Vipin
2024-09-04 9:30 ` Mattias Rönnblom
2024-09-04 14:37 ` Stephen Hemminger
2024-09-11 3:13 ` Varghese, Vipin
2024-09-11 3:53 ` Stephen Hemminger
2024-09-12 1:11 ` Varghese, Vipin
2024-09-09 14:22 ` Varghese, Vipin
2024-09-09 14:52 ` Mattias Rönnblom
2024-09-11 3:26 ` Varghese, Vipin
2024-09-11 15:55 ` Mattias Rönnblom
2024-09-11 17:04 ` Honnappa Nagarahalli
2024-09-12 1:33 ` Varghese, Vipin
2024-09-12 6:38 ` Mattias Rönnblom
2024-09-12 7:02 ` Mattias Rönnblom
2024-09-12 11:23 ` Varghese, Vipin
2024-09-12 12:12 ` Mattias Rönnblom
2024-09-12 15:50 ` Stephen Hemminger
2024-09-12 11:17 ` Varghese, Vipin
2024-09-12 11:59 ` Mattias Rönnblom
2024-09-12 13:30 ` Bruce Richardson
2024-09-12 16:32 ` Mattias Rönnblom
2024-09-12 2:28 ` Varghese, Vipin
2024-09-11 16:01 ` Bruce Richardson
2024-09-11 22:25 ` Konstantin Ananyev
2024-09-12 2:38 ` Varghese, Vipin
2024-09-12 2:19 ` Varghese, Vipin
2024-09-12 9:17 ` Bruce Richardson
2024-09-12 11:50 ` Varghese, Vipin
2024-09-13 14:15 ` Burakov, Anatoly
2024-09-12 13:18 ` Mattias Rönnblom
2024-08-28 8:38 ` Burakov, Anatoly
2024-09-02 1:08 ` Varghese, Vipin [this message]
2024-09-02 14:17 ` Burakov, Anatoly
2024-09-02 15:33 ` Varghese, Vipin
2024-09-03 8:50 ` Burakov, Anatoly
2024-09-05 13:05 ` Ferruh Yigit
2024-09-05 14:45 ` Burakov, Anatoly
2024-09-05 15:34 ` Ferruh Yigit
2024-09-06 8:44 ` Burakov, Anatoly
2024-09-09 14:14 ` Varghese, Vipin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=65f3dc80-2d07-4b8b-9a5c-197eb2b21180@amd.com \
--to=vipin.varghese@amd.com \
--cc=anatoly.burakov@intel.com \
--cc=dev@dpdk.org \
--cc=ferruh.yigit@amd.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).