Re: [PATCH v3 1/3] config/arm: avoid mcpu and march conflicts

[Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>]

> On Feb 5, 2024, at 10:10 PM, Wathsala Wathawana Vithanage <wathsala.vithanage@arm.com> wrote:
> 
> Hi Pavan,
> 
>> The compiler options march and mtune are a subset of mcpu and will lead to
>> conflicts if improper march is chosen for a given mcpu.
>> To avoid conflicts, force part number march when mcpu is available and is
>> supported by the compiler.
> 
> Why would one force the march specified in the part number when mcpu for
> that part number is also available and supported by the compiler?
> 
It would be good to explain the use case or the problem being faced.

>> 
>> Example:
>> march = armv9-a
>> mcpu = neoverse-n2
>> 
>> mcpu supported, march supported
>> machine_args = ['-mcpu=neoverse-n2', '-march=armv9-a']
> 
> -march restricts the compiler to baseline architecture of the -mcpu.
> For instance, Neoverse-n1's baseline architecture is armv8.2-a, 
> but it has some extensions from armv8.3-a, armv8.4-a, and armv8.5-a. 
> By setting -march to armv8.2-a the compiler will strictly omit extensions
> from 8.3, 8.4 and 8.5 resulting in a suboptimal outcome.
> 
>> 
>> mcpu supported, march not supported
>> machine_args = ['-mcpu=neoverse-n2']
> 
> This will result in the best outcome.
> 
>> 
>> mcpu not supported, march supported
>> machine_args = ['-march=armv9-a']
> 
> This too may result in a suboptimal outcome as optimization space
> is limited to the given march (not using extensions from later 
> architectures when available).
> 
>> 
>> mcpu not supported, march not supported
>> machine_args = ['-march=armv8.6-a']
> 
> Compiler knows nothing about the target CPU or the architecture.
> I think it's better to exit the build process with an error. 
> 
>> 
>> Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
>> ---
>> v2 Changes:
>> - Cleanup march inconsistencies. (Juraj Linkes)
>> - Unify fallback march selection. (Juraj Linkes)
>> - Tag along ARM WFE patch.
>> v3 Changes:
>> - Fix missing 'fallback_march' key check.
>> 
>> config/arm/meson.build | 108 +++++++++++++++++++++++++---------------
>> -
>> 1 file changed, 66 insertions(+), 42 deletions(-)
>> 
>> diff --git a/config/arm/meson.build b/config/arm/meson.build index
>> 36f21d22599a..ba859bd060b5 100644
>> --- a/config/arm/meson.build
>> +++ b/config/arm/meson.build
>> @@ -58,18 +58,18 @@ implementer_generic = {  }
>> 
>> part_number_config_arm = {
>> -    '0xd03': {'compiler_options':  ['-mcpu=cortex-a53']},
>> -    '0xd04': {'compiler_options':  ['-mcpu=cortex-a35']},
>> -    '0xd05': {'compiler_options':  ['-mcpu=cortex-a55']},
>> -    '0xd07': {'compiler_options':  ['-mcpu=cortex-a57']},
>> -    '0xd08': {'compiler_options':  ['-mcpu=cortex-a72']},
>> -    '0xd09': {'compiler_options':  ['-mcpu=cortex-a73']},
>> -    '0xd0a': {'compiler_options':  ['-mcpu=cortex-a75']},
>> -    '0xd0b': {'compiler_options':  ['-mcpu=cortex-a76']},
>> +    '0xd03': {'mcpu': 'cortex-a53'},
>> +    '0xd04': {'mcpu': 'cortex-a35'},
>> +    '0xd05': {'mcpu': 'cortex-a55'},
>> +    '0xd07': {'mcpu': 'cortex-a57'},
>> +    '0xd08': {'mcpu': 'cortex-a72'},
>> +    '0xd09': {'mcpu': 'cortex-a73'},
>> +    '0xd0a': {'mcpu': 'cortex-a75'},
>> +    '0xd0b': {'mcpu': 'cortex-a76'},
>>     '0xd0c': {
>>         'march': 'armv8.2-a',
>>         'march_features': ['crypto', 'rcpc'],
>> -        'compiler_options':  ['-mcpu=neoverse-n1'],
>> +        'mcpu': 'neoverse-n1',
>>         'flags': [
>>             ['RTE_MACHINE', '"neoverse-n1"'],
>>             ['RTE_ARM_FEATURE_ATOMICS', true], @@ -81,7 +81,7 @@
>> part_number_config_arm = {
>>     '0xd40': {
>>         'march': 'armv8.4-a',
>>         'march_features': ['sve'],
>> -        'compiler_options':  ['-mcpu=neoverse-v1'],
>> +        'mcpu': 'neoverse-v1',
>>         'flags': [
>>             ['RTE_MACHINE', '"neoverse-v1"'],
>>             ['RTE_ARM_FEATURE_ATOMICS', true], @@ -92,8 +92,9 @@
>> part_number_config_arm = {
>>         'march': 'armv8.4-a',
>>     },
>>     '0xd49': {
>> +        'march': 'armv9-a',
>>         'march_features': ['sve2'],
>> -        'compiler_options': ['-mcpu=neoverse-n2'],
>> +        'mcpu': 'neoverse-n2',
>>         'flags': [
>>             ['RTE_MACHINE', '"neoverse-n2"'],
>>             ['RTE_ARM_FEATURE_ATOMICS', true], @@ -127,21 +128,23 @@
>> implementer_cavium = {
>>     ],
>>     'part_number_config': {
>>         '0xa1': {
>> -            'compiler_options': ['-mcpu=thunderxt88'],
>> +            'mcpu': 'thunderxt88',
>>             'flags': flags_part_number_thunderx
>>         },
>>         '0xa2': {
>> -            'compiler_options': ['-mcpu=thunderxt81'],
>> +            'mcpu': 'thunderxt81',
>>             'flags': flags_part_number_thunderx
>>         },
>>         '0xa3': {
>> -            'compiler_options': ['-march=armv8-a+crc', '-mcpu=thunderxt83'],
>> +            'march': 'armv8-a',
>> +            'march_features': ['crc'],
>> +            'mcpu': 'thunderxt83',
>>             'flags': flags_part_number_thunderx
>>         },
>>         '0xaf': {
>>             'march': 'armv8.1-a',
>>             'march_features': ['crc', 'crypto'],
>> -            'compiler_options': ['-mcpu=thunderx2t99'],
>> +            'mcpu': 'thunderx2t99',
>>             'flags': [
>>                 ['RTE_MACHINE', '"thunderx2"'],
>>                 ['RTE_ARM_FEATURE_ATOMICS', true], @@ -153,7 +156,7 @@
>> implementer_cavium = {
>>         '0xb2': {
>>             'march': 'armv8.2-a',
>>             'march_features': ['crc', 'crypto', 'lse'],
>> -            'compiler_options': ['-mcpu=octeontx2'],
>> +            'mcpu': 'octeontx2',
>>             'flags': [
>>                 ['RTE_MACHINE', '"cn9k"'],
>>                 ['RTE_ARM_FEATURE_ATOMICS', true], @@ -176,7 +179,7 @@
>> implementer_ampere = {
>>         '0x0': {
>>             'march': 'armv8-a',
>>             'march_features': ['crc', 'crypto'],
>> -            'compiler_options':  ['-mtune=emag'],
>> +            'mcpu': 'emag',
>>             'flags': [
>>                 ['RTE_MACHINE', '"eMAG"'],
>>                 ['RTE_MAX_LCORE', 32],
>> @@ -186,7 +189,7 @@ implementer_ampere = {
>>         '0xac3': {
>>             'march': 'armv8.6-a',
>>             'march_features': ['crc', 'crypto'],
>> -            'compiler_options':  ['-mcpu=ampere1'],
>> +            'mcpu': 'ampere1',
>>             'flags': [
>>                 ['RTE_MACHINE', '"AmpereOne"'],
>>                 ['RTE_MAX_LCORE', 320], @@ -206,7 +209,7 @@
>> implementer_hisilicon = {
>>         '0xd01': {
>>             'march': 'armv8.2-a',
>>             'march_features': ['crypto'],
>> -            'compiler_options': ['-mtune=tsv110'],
>> +            'mcpu': 'tsv110',
>>             'flags': [
>>                 ['RTE_MACHINE', '"Kunpeng 920"'],
>>                 ['RTE_ARM_FEATURE_ATOMICS', true], @@ -695,11 +698,21 @@ if
>> update_flags
>> 
>>     machine_args = [] # Clear previous machine args
>> 
>> +    candidate_mcpu = ''
>> +    if part_number_config.has_key('mcpu')
>> +        mcpu = part_number_config['mcpu']
>> +        if (cc.has_argument('-mcpu=' + mcpu))
>> +            candidate_mcpu = mcpu
>> +        endif
>> +    endif
>> +
>>     # probe supported archs and their features
>>     candidate_march = ''
>>     if part_number_config.has_key('march')
>> -        if part_number_config.get('force_march', false)
>> -            candidate_march = part_number_config['march']
>> +        if part_number_config.get('force_march', false) or candidate_mcpu != ''
>> +            if cc.has_argument('-march=' +  part_number_config['march'])
>> +                candidate_march = part_number_config['march']
>> +            endif
>>         else
>>             supported_marchs = ['armv8.6-a', 'armv8.5-a', 'armv8.4-a', 'armv8.3-
>> a',
>>                                 'armv8.2-a', 'armv8.1-a', 'armv8-a'] @@ -717,32 +730,43
>> @@ if update_flags
>>                 endif
>>             endforeach
>>         endif
>> -        if candidate_march == ''
>> -            error('No suitable armv8 march version found.')
>> -        endif
>> +
>>         if candidate_march != part_number_config['march']
>> -            warning('Configuration march version is ' +
>> -                    '@0@, but the compiler supports only @1@.'
>> -                    .format(part_number_config['march'], candidate_march))
>> +            warning('Configuration march version is @0@, not supported.'
>> +                    .format(part_number_config['march']))
>> +            if candidate_march != ''
>> +                warning('Using march version @0@.'.format(candidate_march))
>> +            endif
>>         endif
>> -        candidate_march = '-march=' + candidate_march
>> 
>> -        march_features = []
>> -        if part_number_config.has_key('march_features')
>> -            march_features += part_number_config['march_features']
>> -        endif
>> -        if soc_config.has_key('extra_march_features')
>> -            march_features += soc_config['extra_march_features']
>> +        if candidate_march == '' and candidate_mcpu == ''
>> +            error('No suitable ARM march/mcpu version found.')
>>         endif
>> -        foreach feature: march_features
>> -            if cc.has_argument('+'.join([candidate_march, feature]))
>> -                candidate_march = '+'.join([candidate_march, feature])
>> -            else
>> -                warning('The compiler does not support feature @0@'
>> -                    .format(feature))
>> +
>> +        if candidate_march != ''
>> +            candidate_march = '-march=' + candidate_march
>> +            march_features = []
>> +            if part_number_config.has_key('march_features')
>> +                march_features += part_number_config['march_features']
>>             endif
>> -        endforeach
>> -        machine_args += candidate_march
>> +            if soc_config.has_key('extra_march_features')
>> +                march_features += soc_config['extra_march_features']
>> +            endif
>> +            foreach feature: march_features
>> +                if cc.has_argument('+'.join([candidate_march, feature]))
>> +                    candidate_march = '+'.join([candidate_march, feature])
>> +                else
>> +                    warning('The compiler does not support feature @0@'
>> +                        .format(feature))
>> +                endif
>> +            endforeach
>> +            machine_args += candidate_march
>> +        endif
>> +    endif
>> +
>> +    if candidate_mcpu != ''
>> +        candidate_mcpu = '-mcpu=' + candidate_mcpu
>> +        machine_args += candidate_mcpu
>>     endif
>> 
>>     # apply supported compiler options
>> --
>> 2.43.0
>