[PATCH v2] build: reduce use of AVX compiler flags

[Bruce Richardson]

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
skylake-avx512 '-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-35006 ("doc/linux_gsg: update recommended compiler versions")

Signed-off-by: Bruce Richardson <bruce.richardson at intel.com>
---

V2: dropped the doc update for the minimum meson version. Based on
    discussion, that version bump is larger than proposed in RFC and
    is now a separate patch/series [series 35006 referenced above]

---
 config/x86/meson.build | 31 ++++++++++++++++++++-----------
 drivers/meson.build    |  9 +--------
 lib/meson.build        |  9 +--------
 3 files changed, 22 insertions(+), 27 deletions(-)

diff --git a/config/x86/meson.build b/config/x86/meson.build
index c3564b0011..97f790b0d4 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 +67,33 @@ 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=skylake-avx512'
+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_args += '-Wno-overriding-option'
+            endif
+        endif
+    endif
+endif
+if developer_mode
+    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 b0850bbb24..51c824ea40 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 41fd98f4e9..16389b9c34 100644
--- a/lib/meson.build
+++ b/lib/meson.build
@@ -260,18 +260,11 @@ 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