numam-dpdk/config/x86/meson.build
Liang Ma ba57777d7d build: check for broken AVX512 compiler support
GCC 6.3.0 has a known bug which related to _mm512_extracti64x4_epi64.
Please reference https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82887

Some DPDK PMD AVX512 version heavily use _mm512_extracti64x4_epi6,
which cause building failure with debug buildtype.

Therefore, it's helpful to check if compiler work with
_mm512_extracti64x4_epi6.

This patch check the compiler compile result against the test code
snippet. If the checking is failed then disable AVX512.

Bugzilla ID: 717
Fixes: e6a6a138919f ("net/i40e: add AVX512 vector path")
Fixes: 808a17b3c1e6 ("net/ice: add Rx AVX512 offload path")
Fixes: 4b64ccb328c9 ("net/iavf: fix VLAN extraction in AVX512 path")
Cc: stable@dpdk.org

Reported-by: Liang Ma <liangma@liangbit.com>
Signed-off-by: Liang Ma <liangma@bytedance.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
2021-07-22 20:04:24 +02:00

73 lines
2.1 KiB
Meson

# SPDX-License-Identifier: BSD-3-Clause
# Copyright(c) 2017-2020 Intel Corporation
# get binutils version for the workaround of Bug 97
if not is_windows
binutils_ok = run_command(binutils_avx512_check)
if binutils_ok.returncode() != 0 and cc.has_argument('-mno-avx512f')
machine_args += '-mno-avx512f'
warning('Binutils error with AVX512 assembly, disabling AVX512 support')
endif
endif
# check if compiler is working with _mm512_extracti64x4_epi64
# Ref: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82887
if cc.has_argument('-mavx512f')
code = '''#include <immintrin.h>
void test(__m512i zmm){
__m256i ymm = _mm512_extracti64x4_epi64(zmm, 0);}'''
result = cc.compiles(code, args : '-mavx512f', name : 'AVX512 checking')
if result == false
machine_args += '-mno-avx512f'
warning('Broken _mm512_extracti64x4_epi64, disabling AVX512 support')
endif
endif
# we require SSE4.2 for DPDK
if cc.get_define('__SSE4_2__', args: machine_args) == ''
message('SSE 4.2 not enabled by default, explicitly enabling')
machine_args += '-msse4'
endif
base_flags = ['SSE', 'SSE2', 'SSE3','SSSE3', 'SSE4_1', 'SSE4_2']
foreach f:base_flags
compile_time_cpuflags += ['RTE_CPUFLAG_' + f]
endforeach
optional_flags = [
'AES',
'AVX',
'AVX2',
'AVX512BW',
'AVX512CD',
'AVX512DQ',
'AVX512F',
'AVX512VL',
'PCLMUL',
'RDRND',
'RDSEED',
'VPCLMULQDQ',
]
foreach f:optional_flags
if cc.get_define('__@0@__'.format(f), args: machine_args) == '1'
if f == 'PCLMUL' # special case flags with different defines
f = 'PCLMULQDQ'
elif f == 'RDRND'
f = 'RDRAND'
endif
compile_time_cpuflags += ['RTE_CPUFLAG_' + f]
endif
endforeach
dpdk_conf.set('RTE_ARCH_X86', 1)
if dpdk_conf.get('RTE_ARCH_64')
dpdk_conf.set('RTE_ARCH_X86_64', 1)
dpdk_conf.set('RTE_ARCH', 'x86_64')
else
dpdk_conf.set('RTE_ARCH_I686', 1)
dpdk_conf.set('RTE_ARCH', 'i686')
endif
dpdk_conf.set('RTE_CACHE_LINE_SIZE', 64)