-----Original Message-----
From: Thomas Monjalon <redacted>
Sent: Wednesday, July 15, 2020 1:45 PM
To: Medvedkin, Vladimir <redacted>
Cc: Kinsella, Ray <redacted>; Stephen Hemminger
[off-list ref]; dev@dpdk.org; david.marchand@redhat.com;
jerinj@marvell.com; Ananyev, Konstantin [off-list ref];
Richardson, Bruce [off-list ref]; Mcnamara, John
[off-list ref]; O'Driscoll, Tim [off-list ref]
Subject: Re: [dpdk-dev] [PATCH v6 0/8] fib: implement AVX512 vector lookup

15/07/2020 14:29, Medvedkin, Vladimir:

quoted

On 15/07/2020 12:59, Thomas Monjalon wrote:

quoted

15/07/2020 12:35, Medvedkin, Vladimir:

quoted

On 15/07/2020 10:47, Thomas Monjalon wrote:

quoted

14/07/2020 16:38, Stephen Hemminger:

quoted

"Kinsella, Ray" [off-list ref] wrote:

quoted

On 13/07/2020 23:19, Stephen Hemminger wrote:

quoted

Did anyone else see the recent AVX512 discussion from Linus:
    "I hope AVX512 dies a painful death, and that Intel starts

fixing real problems

quoted

quoted

quoted

quoted

quoted

quoted

quoted

     instead of trying to create magic instructions to then

create benchmarks that they can look good on.

quoted

quoted

quoted

quoted

quoted

quoted

Yup - I saw this one.
Sweeping statements like these are good to provoke debate, the

truth is generally more nuanced.

quoted

quoted

quoted

quoted

quoted

quoted

If you continue to read the post, Linus appears to be mostly

questioning microprocessor design decisions.

quoted

quoted

quoted

quoted

quoted

quoted

That is an interesting discussion, however the reality is that the

technology does exists and may be beneficial for Packet Processing.

quoted

quoted

quoted

quoted

quoted

quoted

I would suggest, we continue to apply the same logic governing

adoption of any technology by DPDK.

quoted

quoted

quoted

quoted

quoted

quoted

When the technology is present and a clear benefit is shown, we

use it with caution.

quoted

quoted

quoted

quoted

quoted

quoted

In the case of Vladimir's patch, the user has to explicitly
switch on the AVX512 lookup with RTE_FIB_DIR24_8_VECTOR_AVX512.

Using what is available makes sense in DPDK.

Why does it require explicit  enabling in application?
AVX512 is not reliable enough to be automatically used when

available?

quoted

quoted

quoted

It is reliable enough. User have to explicitly trigger to avx512
lookup because using avx512 instructions can reduce the frequency
of your cores. The user knows their environment better. So the
scalar version is used so as not to affect the frequency.

So the user must know which micro-optimization is better for a code
they don't know. Reminder: an user is not a developper.
I understand we have no better solution though.
Can we improve the user experience with some recommendations, numbers,

etc?

quoted

quoted

In case where a user is a developer (dpdk users are mostly devs,
aren't
they?) who uses the fib library in their app may decide to switch to
avx512 lookup using rte_fib_set_lookup_fn() when they know that their
code is already using avx512 (ifdef, startup check, etc).
In other case an app developer, for example, could provide to user
command line option or some interactive command to switch lookup

function.

quoted

I'd recommend to run testfib app with various "-v" options to evaluate
lookup performance on a target system to make a decision.

I think this is the difference between a library for hackers, and a
product for end-users.
We are not building a product, but we can make a step in that direction by
documenting some knowledge.
I don't know exactly what it means in this case, so I'll let others
suggest some doc improvements (if anyone cares).

We have got a patchset in the works to try and make AVX-512 use simpler for 20.11,
by providing both developer APIs and end-user cmdline flags to control this
centrally for DPDK, rather than having each library provide its own magic hooks
to optionally enable this support. As part of that set, we'll see about what
doc updates need to be made also - again covering both developer and end-app user.

Hopefully we can get that set out soon to get early feedback and reach a good
conclusion.

/Bruce