From: Florian Weimer <fw@deneb.enyo.de>
To: Prem Mallappa via Libc-alpha <libc-alpha@sourceware.org>
Cc: codonell@redhat.com, Michael Matz <matz@suse.de>,
Prem Mallappa <Premachandra.Mallappa@amd.com>,
Prem Mallappa <prem.mallappa@gmail.com>,
schwab@suse.com
Subject: Re: [PATCH 0/3] RFC: Platform Support for AMD Zen and AVX2/AVX
Date: Tue, 17 Mar 2020 10:02:17 +0100 [thread overview]
Message-ID: <87wo7je4me.fsf@mid.deneb.enyo.de> (raw)
In-Reply-To: <20200317044646.29707-1-PMallappa@amd.com> (Prem Mallappa via Libc-alpha's message of "Tue, 17 Mar 2020 10:16:43 +0530")
* Prem Mallappa via Libc-alpha:
> From: Prem Mallappa <Premachandra.Mallappa@amd.com>
>
> Hello Glibc Community,
>
> == (cross posting to libc-alpha, apologies for the spam) ==
>
> This is in response to
>
> [1] https://sourceware.org/bugzilla/show_bug.cgi?id=24979
> [2] https://sourceware.org/bugzilla/show_bug.cgi?id=24080
> [3] https://sourceware.org/bugzilla/show_bug.cgi?id=23249
>
> It is clear that there is no panacea here. However,
> here is an attempt to address them in parts.
>
> From [1], enable customers who already have
> "haswell" libs and has seen perf benifits by loading
> them on AMD Zen.
> (Load libraries by placing them in LD_LIBRARY_PATH/zen
> or by a symbolic link zen->haswell)
>
> From [2] and [3]
> And, A futuristic generic-avx2/generic-avx libs,
> enables OS vendors to supply an optimized set.
> And haswell/zen are really a superset, hence
> keeping it made sense.
>
> By this we would like to open it up for discussion
> The haswell/zen can be intel/amd
> (or any other name, and supply ifunc based loading
> internally)
I think we cannot use the platform subdirectory for that because there
is just a single one. If we want a Intel/AMD split, we need to
enhance the dynamic loader to try the CPU vendor directory first, and
then fallback to a shared subdirectory. Most distributions do not
want to test and ship binaries specific to Intel or AMD CPUs.
That's a generic loader change which will need some time to implement,
but we can work on something else in the meantime:
We need to check for *all* relevant CPU flags such code can use and,
and only enable a subdirectory if they are present. This is necessary
because virtualization and microcode updates can disable individual
CPU features.
For the new shared subdirectory, I think we should not restrict
ourselves just to AVX2, but we should also include useful extensions
that are in practice always implemented in silicon along with AVX2,
but can be separately tweaked.
This seems to be a reasonable list of CPU feature flags to start with:
3DNOW
3DNOWEXT
3DNOWPREFETCH
ABM
ADX
AES
AVX
AVX2
BMI
BMI2
CET
CLFLUSH
CLFLUSHOPT
CLWB
CLZERO
CMPXCHG16B
ERMS
F16C
FMA
FMA4
FSGSBASE
FSRM
FXSR
HLE
LAHF
LZCNT
MOVBE
MWAITX
PCLMUL
PCOMMIT
PKU
POPCNT
PREFETCHW
RDPID
RDRAND
RDSEED
RDTSCP
RTM
SHA
SSE3
SSE4.1
SSE4.2
SSE4A
SSSE3
TSC
XGETBV
XSAVE
XSAVEC
XSAVEOPT
XSAVES
You (as in AMD) need to go through this list and come back with the
subset that you think should be enabled for current and future CPUs,
based on your internal roadmap and known errata for existing CPUs. We
do not need a rationale for how you filter down the list, merely the
outcome.
(I already have the trimmed-down list from Intel.)
next prev parent reply other threads:[~2020-03-17 9:03 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-17 4:46 [PATCH 0/3] RFC: Platform Support for AMD Zen and AVX2/AVX Prem Mallappa via Libc-alpha
2020-03-17 4:46 ` [PATCH 1/3] x86: Refactor platform support in cpu_features Prem Mallappa via Libc-alpha
2020-03-17 4:46 ` [PATCH 2/3] x86: Add AMD Zen and AVX2/AVX platform support Prem Mallappa via Libc-alpha
2020-03-17 4:46 ` [PATCH 3/3] x86: test to load from PLATFORM path Prem Mallappa via Libc-alpha
2020-03-17 9:02 ` Florian Weimer [this message]
2020-03-17 13:17 ` [PATCH 0/3] RFC: Platform Support for AMD Zen and AVX2/AVX Carlos O'Donell via Libc-alpha
2020-03-17 19:27 ` Adhemerval Zanella via Libc-alpha
2020-03-17 21:37 ` Carlos O'Donell via Libc-alpha
2020-03-27 14:26 ` Florian Weimer
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
List information: https://www.gnu.org/software/libc/involved.html
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=87wo7je4me.fsf@mid.deneb.enyo.de \
--to=fw@deneb.enyo.de \
--cc=Premachandra.Mallappa@amd.com \
--cc=codonell@redhat.com \
--cc=libc-alpha@sourceware.org \
--cc=matz@suse.de \
--cc=prem.mallappa@gmail.com \
--cc=schwab@suse.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 read-only IMAP folder(s) and NNTP newsgroup(s).