In a number of libraries and drivers we have multiple levels of checks
for enabling AVX2 support. In these cases:
* we first check for AVX2 support in the build-time ISA, i.e. through
the instruction-set/-march flag. If present, we add source file to the
list of sources.
* if not enabled at the minimum instruction-set level, i.e. a
default/generic build, we then check for compiler support for AVX2
and, if available, did a separate build of the AVX2 file using an
additional flag to enable the instruction set.
While this works, and was necessary in older releases, we no longer need
this level of complexity, as all supported DPDK compilers have support
for AVX2. This makes the second check unnecessary.
However, when we look at the effect of the second option above vs the
first, the only real difference is that in the second case, we add an
additional "-mavx2" to the build flags. This flag simply makes the
instruction set available for use, so should be harmless in the case
where the "march" flag already has that instruction set available.
Therefore, we can remove the check for the first case also, and always
use the fallback case with the extra flag.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
---
drivers/net/bnxt/meson.build | 27 ++++++++++-----------------
drivers/net/enic/meson.build | 10 +++-------
drivers/net/i40e/meson.build | 23 +++++++----------------
drivers/net/iavf/meson.build | 23 +++++++----------------
drivers/net/ice/meson.build | 22 +++++++---------------
lib/acl/meson.build | 24 ++++++------------------
6 files changed, 40 insertions(+), 89 deletions(-)
@@ -53,23 +53,16 @@ subdir('hcapi/cfa')
if arch_subdir == 'x86'
sources += files('bnxt_rxtx_vec_sse.c')
- # compile AVX2 version if either:
- # a. we have AVX supported in minimum instruction set baseline
- # b. it's not minimum instruction set, but supported by compiler
- if cc.get_define('__AVX2__', args: machine_args) != ''
- cflags += ['-DCC_AVX2_SUPPORT']
- sources += files('bnxt_rxtx_vec_avx2.c')
- elif cc.has_argument('-mavx2')
- cflags += ['-DCC_AVX2_SUPPORT']
- bnxt_avx2_lib = static_library('bnxt_avx2_lib',
- 'bnxt_rxtx_vec_avx2.c',
- dependencies: [static_rte_ethdev,
- static_rte_bus_pci,
- static_rte_kvargs, static_rte_hash],
- include_directories: includes,
- c_args: [cflags, '-mavx2'])
- objs += bnxt_avx2_lib.extract_objects('bnxt_rxtx_vec_avx2.c')
- endif
+ cflags += ['-DCC_AVX2_SUPPORT']
+ # build AVX2 code with instruction set explicitly enabled for runtime selection
+ bnxt_avx2_lib = static_library('bnxt_avx2_lib',
+ 'bnxt_rxtx_vec_avx2.c',
+ dependencies: [static_rte_ethdev,
+ static_rte_bus_pci,
+ static_rte_kvargs, static_rte_hash],
+ include_directories: includes,
+ c_args: [cflags, '-mavx2'])
+ objs += bnxt_avx2_lib.extract_objects('bnxt_rxtx_vec_avx2.c')
elif arch_subdir == 'arm' and dpdk_conf.get('RTE_ARCH_64')
sources += files('bnxt_rxtx_vec_neon.c')
endif
@@ -28,14 +28,10 @@ sources = files(
deps += ['hash']
includes += include_directories('base')
-# The current implementation assumes 64-bit pointers
-if cc.get_define('__AVX2__', args: machine_args) != '' and dpdk_conf.get('RTE_ARCH_64')
- sources += files('enic_rxtx_vec_avx2.c')
-# Build the avx2 handler if the compiler supports it, even though 'machine'
-# does not. This is to support users who build for the min supported machine
+# Build the avx2 handler for 64-bit X86 targets, even though 'machine'
+# may not. This is to support users who build for the min supported machine
# and need to run the binary on newer CPUs too.
-# This part is from i40e meson.build
-elif cc.has_argument('-mavx2') and dpdk_conf.get('RTE_ARCH_64')
+if dpdk_conf.has('RTE_ARCH_X86_64')
enic_avx2_lib = static_library('enic_avx2_lib',
'enic_rxtx_vec_avx2.c',
dependencies: [static_rte_ethdev, static_rte_bus_pci],
@@ -49,22 +49,13 @@ if arch_subdir == 'x86'
cflags += ['-fno-asynchronous-unwind-tables']
endif
- # compile AVX2 version if either:
- # a. we have AVX supported in minimum instruction set baseline
- # b. it's not minimum instruction set, but supported by compiler
- if cc.get_define('__AVX2__', args: machine_args) != ''
- cflags += ['-DCC_AVX2_SUPPORT']
- sources += files('i40e_rxtx_vec_avx2.c')
- elif cc.has_argument('-mavx2')
- cflags += ['-DCC_AVX2_SUPPORT']
- i40e_avx2_lib = static_library('i40e_avx2_lib',
- 'i40e_rxtx_vec_avx2.c',
- dependencies: [static_rte_ethdev,
- static_rte_kvargs, static_rte_hash],
- include_directories: includes,
- c_args: [cflags, '-mavx2'])
- objs += i40e_avx2_lib.extract_objects('i40e_rxtx_vec_avx2.c')
- endif
+ cflags += ['-DCC_AVX2_SUPPORT']
+ i40e_avx2_lib = static_library('i40e_avx2_lib',
+ 'i40e_rxtx_vec_avx2.c',
+ dependencies: [static_rte_ethdev, static_rte_kvargs, static_rte_hash],
+ include_directories: includes,
+ c_args: [cflags, '-mavx2'])
+ objs += i40e_avx2_lib.extract_objects('i40e_rxtx_vec_avx2.c')
i40e_avx512_cpu_support = (
cc.get_define('__AVX512F__', args: machine_args) != '' and
@@ -29,22 +29,13 @@ if arch_subdir == 'x86'
cflags += ['-fno-asynchronous-unwind-tables']
endif
- # compile AVX2 version if either:
- # a. we have AVX supported in minimum instruction set baseline
- # b. it's not minimum instruction set, but supported by compiler
- if cc.get_define('__AVX2__', args: machine_args) != ''
- cflags += ['-DCC_AVX2_SUPPORT']
- sources += files('iavf_rxtx_vec_avx2.c')
- elif cc.has_argument('-mavx2')
- cflags += ['-DCC_AVX2_SUPPORT']
- iavf_avx2_lib = static_library('iavf_avx2_lib',
- 'iavf_rxtx_vec_avx2.c',
- dependencies: [static_rte_ethdev,
- static_rte_kvargs, static_rte_hash],
- include_directories: includes,
- c_args: [cflags, '-mavx2'])
- objs += iavf_avx2_lib.extract_objects('iavf_rxtx_vec_avx2.c')
- endif
+ cflags += ['-DCC_AVX2_SUPPORT']
+ iavf_avx2_lib = static_library('iavf_avx2_lib',
+ 'iavf_rxtx_vec_avx2.c',
+ dependencies: [static_rte_ethdev, static_rte_kvargs, static_rte_hash],
+ include_directories: includes,
+ c_args: [cflags, '-mavx2'])
+ objs += iavf_avx2_lib.extract_objects('iavf_rxtx_vec_avx2.c')
iavf_avx512_cpu_support = (
cc.get_define('__AVX512F__', args: machine_args) != '' and
@@ -28,21 +28,13 @@ if arch_subdir == 'x86'
cflags += ['-fno-asynchronous-unwind-tables']
endif
- # compile AVX2 version if either:
- # a. we have AVX supported in minimum instruction set baseline
- # b. it's not minimum instruction set, but supported by compiler
- if cc.get_define('__AVX2__', args: machine_args) != ''
- cflags += ['-DCC_AVX2_SUPPORT']
- sources += files('ice_rxtx_vec_avx2.c')
- elif cc.has_argument('-mavx2')
- cflags += ['-DCC_AVX2_SUPPORT']
- ice_avx2_lib = static_library('ice_avx2_lib',
- 'ice_rxtx_vec_avx2.c',
- dependencies: [static_rte_ethdev, static_rte_kvargs, static_rte_hash],
- include_directories: includes,
- c_args: [cflags, '-mavx2'])
- objs += ice_avx2_lib.extract_objects('ice_rxtx_vec_avx2.c')
- endif
+ cflags += ['-DCC_AVX2_SUPPORT']
+ ice_avx2_lib = static_library('ice_avx2_lib',
+ 'ice_rxtx_vec_avx2.c',
+ dependencies: [static_rte_ethdev, static_rte_kvargs, static_rte_hash],
+ include_directories: includes,
+ c_args: [cflags, '-mavx2'])
+ objs += ice_avx2_lib.extract_objects('ice_rxtx_vec_avx2.c')
ice_avx512_cpu_support = (
cc.get_define('__AVX512F__', args: machine_args) != '' and
@@ -14,24 +14,12 @@ headers = files('rte_acl.h', 'rte_acl_osdep.h')
if dpdk_conf.has('RTE_ARCH_X86')
sources += files('acl_run_sse.c')
- # compile AVX2 version if either:
- # a. we have AVX supported in minimum instruction set baseline
- # b. it's not minimum instruction set, but supported by compiler
- #
- # in former case, just add avx2 C file to files list
- # in latter case, compile c file to static lib, using correct compiler
- # flags, and then have the .o file from static lib linked into main lib.
- if cc.get_define('__AVX2__', args: machine_args) != ''
- sources += files('acl_run_avx2.c')
- cflags += '-DCC_AVX2_SUPPORT'
- elif cc.has_argument('-mavx2')
- avx2_tmplib = static_library('avx2_tmp',
- 'acl_run_avx2.c',
- dependencies: static_rte_eal,
- c_args: cflags + ['-mavx2'])
- objs += avx2_tmplib.extract_objects('acl_run_avx2.c')
- cflags += '-DCC_AVX2_SUPPORT'
- endif
+ cflags += '-DCC_AVX2_SUPPORT'
+ avx2_tmplib = static_library('avx2_tmp',
+ 'acl_run_avx2.c',
+ dependencies: static_rte_eal,
+ c_args: cflags + ['-mavx2'])
+ objs += avx2_tmplib.extract_objects('acl_run_avx2.c')
# compile AVX512 version if:
# we are building 64-bit binary AND binutils can generate proper code