All of lore.kernel.org
 help / color / mirror / Atom feed
From: Thomas Monjalon <thomas@monjalon.net>
To: bruce.richardson@intel.com
Cc: dev@dpdk.org
Subject: Re: [PATCH 0/3] lib: fix AVX2 checks and macro exposure
Date: Thu, 18 Sep 2025 10:10:59 +0200	[thread overview]
Message-ID: <24958055.6Emhk5qWAg@thomas> (raw)
In-Reply-To: <20250918073135.1273767-1-thomas@monjalon.net>

18/09/2025 09:28, Thomas Monjalon:
> These are fixes for AVX2 in efd and member libraries.
> While at it, I've hidden a macro which was wrongly exported in the API
> without having a correct prefix.
> 
> Thomas Monjalon (3):
>   efd: fix AVX2 support
>   member: remove AVX2 build-time checks
>   member: hide internal macro

The AVX2 changes break the compilation of "x86-generic" with these messages:

lib/member/rte_member_x86.h: In function 'search_bucket_single_avx':
lib/member/rte_member_x86.h:35:28: error: AVX vector return without AVX enabled changes the ABI [-Werror=psabi]
   35 |         uint32_t hitmask = _mm256_movemask_epi8((__m256i)_mm256_cmpeq_epi16(

lib/efd/rte_efd_x86.h: In function 'efd_lookup_internal_avx2':
lib/efd/rte_efd_x86.h:24:17: error: AVX vector return without AVX enabled changes the ABI [-Werror=psabi]
   24 |         __m256i vhash_val_a = _mm256_set1_epi32(hash_val_a);

AVX2 must be forced on these headers.
The solution is probably to move these functions in .c files
declared as sources_avx2 in meson.build.



  parent reply	other threads:[~2025-09-18  8:11 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-09-18  7:28 [PATCH 0/3] lib: fix AVX2 checks and macro exposure Thomas Monjalon
2025-09-18  7:28 ` [PATCH 1/3] efd: fix AVX2 support Thomas Monjalon
2025-09-18  7:48   ` Bruce Richardson
2025-09-18  8:16     ` Thomas Monjalon
2025-09-18  7:28 ` [PATCH 2/3] member: remove AVX2 build-time checks Thomas Monjalon
2025-09-18  7:49   ` Bruce Richardson
2025-09-18  7:28 ` [PATCH 3/3] member: hide internal macro Thomas Monjalon
2025-09-18  7:50   ` Bruce Richardson
2025-09-18  8:10 ` Thomas Monjalon [this message]
2025-09-18  8:59   ` [PATCH 0/3] lib: fix AVX2 checks and macro exposure Bruce Richardson
2025-09-18  9:08 ` [PATCH v2 0/4] " Thomas Monjalon
2025-09-18  9:08   ` [PATCH v2 1/4] efd: fix AVX2 support Thomas Monjalon
2025-09-18  9:40     ` Thomas Monjalon
2025-09-18  9:47       ` Thomas Monjalon
2025-09-18  9:08   ` [PATCH v2 2/4] efd: remove AVX2 build-time check Thomas Monjalon
2025-09-18  9:08   ` [PATCH v2 3/4] member: remove AVX2 build-time checks Thomas Monjalon
2025-09-18  9:08   ` [PATCH v2 4/4] member: hide internal macro Thomas Monjalon
2025-09-24 15:43 ` [PATCH v3 0/2] lib: fix AVX2 checks and macro exposure Thomas Monjalon
2025-09-24 15:43   ` [PATCH v3 1/2] efd: fix AVX2 support Thomas Monjalon
2025-09-24 15:49     ` Bruce Richardson
2025-09-24 15:43   ` [PATCH v3 2/2] member: hide internal macro Thomas Monjalon
2025-09-24 16:50   ` [PATCH v3 0/2] lib: fix AVX2 checks and macro exposure Thomas Monjalon

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=24958055.6Emhk5qWAg@thomas \
    --to=thomas@monjalon.net \
    --cc=bruce.richardson@intel.com \
    --cc=dev@dpdk.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.