[v5] build: reduce use of AVX compiler flags

When doing a build for a target that already has the instruction sets
for AVX2/AVX512 enabled, skip emitting the AVX compiler flags, or the
x86-64-v4 '-march' flags, as they are unnecessary. Instead, when
the default flags produce the desired output, just use them unmodified,
and don't bother adding in extra enabling flags for AVX2 or AVX-512.

Depends-on: series-35421 ("doc/linux_gsg: update recommended compiler versions")

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
---
v5: Use "x86-64-v4" arch, when available, in place of "skylake-avx512"

V4: Fix error flagged by CI with clang builds without AVX512 - change
    "cc_avx512_args" to correct "cc_avx512_flags"

V3: put in version check to work around an issues with some meson
    versions, (hopefully) allowing builds to pass in all CIs. The
    printout of the extra flags now only happens with meson >= 0.60.2

V2: dropped the doc update for the minimum compiler version.  Based on
    discussion, that version bump is larger than proposed in RFC and is
    now a separate patch/series [series referenced above]
---
 config/x86/meson.build | 34 +++++++++++++++++++++++-----------
 drivers/meson.build    |  9 +--------
 lib/meson.build        |  9 +--------
 3 files changed, 25 insertions(+), 27 deletions(-)
  

[Public]

> -----Original Message-----
> From: Bruce Richardson <bruce.richardson@intel.com>
> Sent: Wednesday, June 11, 2025 4:23 PM
> To: dev@dpdk.org
> Cc: Varghese, Vipin <Vipin.Varghese@amd.com>; Bruce Richardson
> <bruce.richardson@intel.com>
> Subject: [PATCH v5] build: reduce use of AVX compiler flags
>
> Caution: This message originated from an External Source. Use proper caution
> when opening attachments, clicking links, or responding.
>
>
> When doing a build for a target that already has the instruction sets for
> AVX2/AVX512 enabled, skip emitting the AVX compiler flags, or the
> x86-64-v4 '-march' flags, as they are unnecessary. Instead, when the default flags
> produce the desired output, just use them unmodified, and don't bother adding in
> extra enabling flags for AVX2 or AVX-512.
>
> Depends-on: series-35421 ("doc/linux_gsg: update recommended compiler
> versions")
>
> Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
> ---
> v5: Use "x86-64-v4" arch, when available, in place of "skylake-avx512"
>
> V4: Fix error flagged by CI with clang builds without AVX512 - change
>     "cc_avx512_args" to correct "cc_avx512_flags"
>
> V3: put in version check to work around an issues with some meson
>     versions, (hopefully) allowing builds to pass in all CIs. The
>     printout of the extra flags now only happens with meson >= 0.60.2
>
> V2: dropped the doc update for the minimum compiler version.  Based on
>     discussion, that version bump is larger than proposed in RFC and is
>     now a separate patch/series [series referenced above]
> ---
>  config/x86/meson.build | 34 +++++++++++++++++++++++-----------
>  drivers/meson.build    |  9 +--------
>  lib/meson.build        |  9 +--------
>  3 files changed, 25 insertions(+), 27 deletions(-)
>
> diff --git a/config/x86/meson.build b/config/x86/meson.build index
> c3564b0011..e2ccfb6d12 100644
> --- a/config/x86/meson.build
> +++ b/config/x86/meson.build
> @@ -4,11 +4,13 @@
>  if is_ms_compiler
>      cc_avx2_flags = ['/arch:AVX2']
>  else
> -    cc_avx2_flags = ['-mavx2']
> +    cc_avx2_flags = []
> +    if cc.get_define('__AVX2__', args: machine_args) == ''
> +        cc_avx2_flags = ['-mavx2']
> +    endif
>  endif
>
>  cc_has_avx512 = false
> -target_has_avx512 = false
>
>  dpdk_conf.set('RTE_ARCH_X86', 1)
>  if dpdk_conf.get('RTE_ARCH_64')
> @@ -65,26 +67,36 @@ if is_linux or cc.get_id() == 'gcc'
>      endif
>  endif
>
> -cc_avx512_flags = ['-mavx512f', '-mavx512vl', '-mavx512dq', '-mavx512bw', '-
> mavx512cd'] -if (binutils_ok and cc.has_multi_arguments(cc_avx512_flags)
> +avx512_march_flag = '-march=x86-64-v4'
> +if not cc.has_argument(avx512_march_flag)
> +    avx512_march_flag = '-march=skylake-avx512'
> +endif
> +cc_avx512_flags = []
> +if (binutils_ok and cc.has_argument(avx512_march_flag)
>          and '-mno-avx512f' not in get_option('c_args'))
>      # check if compiler is working with _mm512_extracti64x4_epi64
>      # Ref: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82887
>      code = '''#include <immintrin.h>
>      void test(__m512i zmm){
>          __m256i ymm = _mm512_extracti64x4_epi64(zmm, 0);}'''
> -    result = cc.compiles(code, args : cc_avx512_flags, name : 'AVX512 checking')
> +    result = cc.compiles(code, args : [avx512_march_flag], name :
> + 'AVX512 checking')
>      if result == false
>          machine_args += '-mno-avx512f'
>          warning('Broken _mm512_extracti64x4_epi64, disabling AVX512 support')
>      else
>          cc_has_avx512 = true
> -        target_has_avx512 = (
> -                cc.get_define('__AVX512F__', args: machine_args) != '' and
> -                cc.get_define('__AVX512BW__', args: machine_args) != '' and
> -                cc.get_define('__AVX512DQ__', args: machine_args) != '' and
> -                cc.get_define('__AVX512VL__', args: machine_args) != ''
> -            )
> +        if cc.get_define('__AVX512F__', args: machine_args) == ''
> +            cc_avx512_flags = [avx512_march_flag]
> +            if cc.has_argument('-Wno-overriding-option')
> +                cc_avx512_flags += '-Wno-overriding-option'
> +            endif
> +        endif
> +    endif
> +endif
> +if developer_mode and meson.version().version_compare('>=0.60.2')
> +    message('Extra C flags needed for AVX2 output: @0@'.format(cc_avx2_flags))
> +    if cc_has_avx512
> +        message('Extra C flags needed for AVX512 output:
> +@0@'.format(cc_avx512_flags))
>      endif
>  endif
>
> diff --git a/drivers/meson.build b/drivers/meson.build index 7b7205dfac..b62880db02
> 100644
> --- a/drivers/meson.build
> +++ b/drivers/meson.build
> @@ -267,18 +267,11 @@ foreach subpath:subdirs
>              endif
>              if sources_avx512.length() > 0 and cc_has_avx512
>                  cflags += '-DCC_AVX512_SUPPORT'
> -                avx512_args = [cflags, cc_avx512_flags]
> -                if not target_has_avx512 and cc.has_argument('-march=skylake-
> avx512')
> -                    avx512_args += '-march=skylake-avx512'
> -                    if cc.has_argument('-Wno-overriding-option')
> -                        avx512_args += '-Wno-overriding-option'
> -                    endif
> -                endif
>                  avx512_lib = static_library(lib_name + '_avx512_lib',
>                          sources_avx512,
>                          dependencies: static_deps,
>                          include_directories: includes,
> -                        c_args: avx512_args)
> +                        c_args: [cflags, cc_avx512_flags])
>                  objs += avx512_lib.extract_objects(sources_avx512)
>              endif
>          endif
> diff --git a/lib/meson.build b/lib/meson.build index 1934cb4a29..0d56b2083b 100644
> --- a/lib/meson.build
> +++ b/lib/meson.build
> @@ -261,18 +261,11 @@ foreach l:libraries
>          endif
>          if sources_avx512.length() > 0 and cc_has_avx512
>              cflags += '-DCC_AVX512_SUPPORT'
> -            avx512_args = [cflags, cflags_avx512, cc_avx512_flags]
> -            if not target_has_avx512 and cc.has_argument('-march=skylake-avx512')
> -                avx512_args += '-march=skylake-avx512'
> -                if cc.has_argument('-Wno-overriding-option')
> -                    avx512_args += '-Wno-overriding-option'
> -                endif
> -            endif
>              avx512_lib = static_library(libname + '_avx512_lib',
>                      sources_avx512,
>                      dependencies: static_deps,
>                      include_directories: includes,
> -                    c_args: avx512_args)
> +                    c_args: [cflags, cflags_avx512, cc_avx512_flags])
>              objs += avx512_lib.extract_objects(sources_avx512)
>          endif
>      endif
> --
> 2.48.1


Acked-by: Vipin Varghese <vipin.varghese@amd.com>
  

On Wed, Jun 11, 2025 at 11:53:10AM +0100, Bruce Richardson wrote:
> When doing a build for a target that already has the instruction sets
> for AVX2/AVX512 enabled, skip emitting the AVX compiler flags, or the
> x86-64-v4 '-march' flags, as they are unnecessary. Instead, when
> the default flags produce the desired output, just use them unmodified,
> and don't bother adding in extra enabling flags for AVX2 or AVX-512.
> 
> Depends-on: series-35421 ("doc/linux_gsg: update recommended compiler versions")
> 
> Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
> ---
> v5: Use "x86-64-v4" arch, when available, in place of "skylake-avx512"
> 
> V4: Fix error flagged by CI with clang builds without AVX512 - change
>     "cc_avx512_args" to correct "cc_avx512_flags"
> 
> V3: put in version check to work around an issues with some meson
>     versions, (hopefully) allowing builds to pass in all CIs. The
>     printout of the extra flags now only happens with meson >= 0.60.2
> 
> V2: dropped the doc update for the minimum compiler version.  Based on
>     discussion, that version bump is larger than proposed in RFC and is
>     now a separate patch/series [series referenced above]
> ---
>  config/x86/meson.build | 34 +++++++++++++++++++++++-----------
>  drivers/meson.build    |  9 +--------
>  lib/meson.build        |  9 +--------
>  3 files changed, 25 insertions(+), 27 deletions(-)
>
Recheck-request: rebase=main, iol-unit-amd64-testing
  

> > When doing a build for a target that already has the instruction sets for
> > AVX2/AVX512 enabled, skip emitting the AVX compiler flags, or the
> > x86-64-v4 '-march' flags, as they are unnecessary. Instead, when the default flags
> > produce the desired output, just use them unmodified, and don't bother adding in
> > extra enabling flags for AVX2 or AVX-512.
> >
> > Depends-on: series-35421 ("doc/linux_gsg: update recommended compiler
> > versions")
> >
> > Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
> 
> Acked-by: Vipin Varghese <vipin.varghese@amd.com>

Applied, thanks.