檢測預處理器中的MOVBE可用性？

Question

我測試的第6代SKYLAKE微架構和CPU有movbe：

$ cat /proc/cpuinfo | grep movbe 
flags   : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 
clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art 
arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf tsc_known_freq pni 
pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid sse4_1 sse4_2 
x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch 
intel_pt tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 avx2 smep bmi2 
erms invpcid mpx rdseed adx smap clflushopt xsaveopt xsavec xgetbv1 xsaves dtherm 
ida arat pln pts hwp hwp_notify hwp_act_window hwp_epp 

我沒有看到下方的__MOVBE__預處理宏。即使在-mmovbe也不顯示。

我們使用哪個預處理器宏來確定movbe的可用性？

---

$ gcc -march=native -mmovbe -dM -E - </dev/null | sort 
#define __ABM__ 1 
#define __ADX__ 1 
#define __AES__ 1 
#define __amd64 1 
#define __amd64__ 1 
#define __ATOMIC_ACQ_REL 4 
#define __ATOMIC_ACQUIRE 2 
#define __ATOMIC_CONSUME 1 
#define __ATOMIC_HLE_ACQUIRE 65536 
#define __ATOMIC_HLE_RELEASE 131072 
#define __ATOMIC_RELAXED 0 
#define __ATOMIC_RELEASE 3 
#define __ATOMIC_SEQ_CST 5 
#define __AVX__ 1 
#define __AVX2__ 1 
#define __BIGGEST_ALIGNMENT__ 32 
#define __BMI__ 1 
#define __BMI2__ 1 
#define __BYTE_ORDER__ __ORDER_LITTLE_ENDIAN__ 
#define __CHAR16_TYPE__ short unsigned int 
#define __CHAR32_TYPE__ unsigned int 
#define __CHAR_BIT__ 8 
#define __CLFLUSHOPT__ 1 
#define __code_model_small__ 1 
#define __core_avx2 1 
#define __core_avx2__ 1 
#define __DBL_DECIMAL_DIG__ 17 
#define __DBL_DENORM_MIN__ ((double)4.94065645841246544177e-324L) 
#define __DBL_DIG__ 15 
#define __DBL_EPSILON__ ((double)2.22044604925031308085e-16L) 
#define __DBL_HAS_DENORM__ 1 
#define __DBL_HAS_INFINITY__ 1 
#define __DBL_HAS_QUIET_NAN__ 1 
#define __DBL_MANT_DIG__ 53 
#define __DBL_MAX_10_EXP__ 308 
#define __DBL_MAX__ ((double)1.79769313486231570815e+308L) 
#define __DBL_MAX_EXP__ 1024 
#define __DBL_MIN_10_EXP__ (-307) 
#define __DBL_MIN__ ((double)2.22507385850720138309e-308L) 
#define __DBL_MIN_EXP__ (-1021) 
#define __DEC128_EPSILON__ 1E-33DL 
#define __DEC128_MANT_DIG__ 34 
#define __DEC128_MAX__ 9.999999999999999999999999999999999E6144DL 
#define __DEC128_MAX_EXP__ 6145 
#define __DEC128_MIN__ 1E-6143DL 
#define __DEC128_MIN_EXP__ (-6142) 
#define __DEC128_SUBNORMAL_MIN__ 0.000000000000000000000000000000001E-6143DL 
#define __DEC32_EPSILON__ 1E-6DF 
#define __DEC32_MANT_DIG__ 7 
#define __DEC32_MAX__ 9.999999E96DF 
#define __DEC32_MAX_EXP__ 97 
#define __DEC32_MIN__ 1E-95DF 
#define __DEC32_MIN_EXP__ (-94) 
#define __DEC32_SUBNORMAL_MIN__ 0.000001E-95DF 
#define __DEC64_EPSILON__ 1E-15DD 
#define __DEC64_MANT_DIG__ 16 
#define __DEC64_MAX__ 9.999999999999999E384DD 
#define __DEC64_MAX_EXP__ 385 
#define __DEC64_MIN__ 1E-383DD 
#define __DEC64_MIN_EXP__ (-382) 
#define __DEC64_SUBNORMAL_MIN__ 0.000000000000001E-383DD 
#define __DEC_EVAL_METHOD__ 2 
#define __DECIMAL_BID_FORMAT__ 1 
#define __DECIMAL_DIG__ 21 
#define __ELF__ 1 
#define __F16C__ 1 
#define __FINITE_MATH_ONLY__ 0 
#define __FLOAT_WORD_ORDER__ __ORDER_LITTLE_ENDIAN__ 
#define __FLT_DECIMAL_DIG__ 9 
#define __FLT_DENORM_MIN__ 1.40129846432481707092e-45F 
#define __FLT_DIG__ 6 
#define __FLT_EPSILON__ 1.19209289550781250000e-7F 
#define __FLT_EVAL_METHOD__ 0 
#define __FLT_HAS_DENORM__ 1 
#define __FLT_HAS_INFINITY__ 1 
#define __FLT_HAS_QUIET_NAN__ 1 
#define __FLT_MANT_DIG__ 24 
#define __FLT_MAX_10_EXP__ 38 
#define __FLT_MAX__ 3.40282346638528859812e+38F 
#define __FLT_MAX_EXP__ 128 
#define __FLT_MIN_10_EXP__ (-37) 
#define __FLT_MIN__ 1.17549435082228750797e-38F 
#define __FLT_MIN_EXP__ (-125) 
#define __FLT_RADIX__ 2 
#define __FMA__ 1 
#define __FP_FAST_FMA 1 
#define __FP_FAST_FMAF 1 
#define __FSGSBASE__ 1 
#define __FXSR__ 1 
#define __GCC_ASM_FLAG_OUTPUTS__ 1 
#define __GCC_ATOMIC_BOOL_LOCK_FREE 2 
#define __GCC_ATOMIC_CHAR16_T_LOCK_FREE 2 
#define __GCC_ATOMIC_CHAR32_T_LOCK_FREE 2 
#define __GCC_ATOMIC_CHAR_LOCK_FREE 2 
#define __GCC_ATOMIC_INT_LOCK_FREE 2 
#define __GCC_ATOMIC_LLONG_LOCK_FREE 2 
#define __GCC_ATOMIC_LONG_LOCK_FREE 2 
#define __GCC_ATOMIC_POINTER_LOCK_FREE 2 
#define __GCC_ATOMIC_SHORT_LOCK_FREE 2 
#define __GCC_ATOMIC_TEST_AND_SET_TRUEVAL 1 
#define __GCC_ATOMIC_WCHAR_T_LOCK_FREE 2 
#define __GCC_HAVE_DWARF2_CFI_ASM 1 
#define __GCC_HAVE_SYNC_COMPARE_AND_SWAP_1 1 
#define __GCC_HAVE_SYNC_COMPARE_AND_SWAP_16 1 
#define __GCC_HAVE_SYNC_COMPARE_AND_SWAP_2 1 
#define __GCC_HAVE_SYNC_COMPARE_AND_SWAP_4 1 
#define __GCC_HAVE_SYNC_COMPARE_AND_SWAP_8 1 
#define __GCC_IEC_559 2 
#define __GCC_IEC_559_COMPLEX 2 
#define __GNUC__ 6 
#define __GNUC_MINOR__ 3 
#define __GNUC_PATCHLEVEL__ 1 
#define __GNUC_RH_RELEASE__ 1 
#define __GNUC_STDC_INLINE__ 1 
#define __gnu_linux__ 1 
#define __GXX_ABI_VERSION 1010 
#define __has_include_next(STR) __has_include_next__(STR) 
#define __has_include(STR) __has_include__(STR) 
#define __haswell 1 
#define __haswell__ 1 
#define __INT16_C(c) c 
#define __INT16_MAX__ 0x7fff 
#define __INT16_TYPE__ short int 
#define __INT32_C(c) c 
#define __INT32_MAX__ 0x7fffffff 
#define __INT32_TYPE__ int 
#define __INT64_C(c) C## L 
#define __INT64_MAX__ 0x7fffffffffffffffL 
#define __INT64_TYPE__ long int 
#define __INT8_C(c) c 
#define __INT8_MAX__ 0x7f 
#define __INT8_TYPE__ signed char 
#define __INT_FAST16_MAX__ 0x7fffffffffffffffL 
#define __INT_FAST16_TYPE__ long int 
#define __INT_FAST32_MAX__ 0x7fffffffffffffffL 
#define __INT_FAST32_TYPE__ long int 
#define __INT_FAST64_MAX__ 0x7fffffffffffffffL 
#define __INT_FAST64_TYPE__ long int 
#define __INT_FAST8_MAX__ 0x7f 
#define __INT_FAST8_TYPE__ signed char 
#define __INT_LEAST16_MAX__ 0x7fff 
#define __INT_LEAST16_TYPE__ short int 
#define __INT_LEAST32_MAX__ 0x7fffffff 
#define __INT_LEAST32_TYPE__ int 
#define __INT_LEAST64_MAX__ 0x7fffffffffffffffL 
#define __INT_LEAST64_TYPE__ long int 
#define __INT_LEAST8_MAX__ 0x7f 
#define __INT_LEAST8_TYPE__ signed char 
#define __INT_MAX__ 0x7fffffff 
#define __INTMAX_C(c) C## L 
#define __INTMAX_MAX__ 0x7fffffffffffffffL 
#define __INTMAX_TYPE__ long int 
#define __INTPTR_MAX__ 0x7fffffffffffffffL 
#define __INTPTR_TYPE__ long int 
#define __LDBL_DENORM_MIN__ 3.64519953188247460253e-4951L 
#define __LDBL_DIG__ 18 
#define __LDBL_EPSILON__ 1.08420217248550443401e-19L 
#define __LDBL_HAS_DENORM__ 1 
#define __LDBL_HAS_INFINITY__ 1 
#define __LDBL_HAS_QUIET_NAN__ 1 
#define __LDBL_MANT_DIG__ 64 
#define __LDBL_MAX_10_EXP__ 4932 
#define __LDBL_MAX__ 1.18973149535723176502e+4932L 
#define __LDBL_MAX_EXP__ 16384 
#define __LDBL_MIN_10_EXP__ (-4931) 
#define __LDBL_MIN__ 3.36210314311209350626e-4932L 
#define __LDBL_MIN_EXP__ (-16381) 
#define __linux 1 
#define __linux__ 1 
#define linux 1 
#define __LONG_LONG_MAX__ 0x7fffffffffffffffLL 
#define __LONG_MAX__ 0x7fffffffffffffffL 
#define __LP64__ 1 
#define _LP64 1 
#define __LZCNT__ 1 
#define __MMX__ 1 
#define __NO_INLINE__ 1 
#define __ORDER_BIG_ENDIAN__ 4321 
#define __ORDER_LITTLE_ENDIAN__ 1234 
#define __ORDER_PDP_ENDIAN__ 3412 
#define __PCLMUL__ 1 
#define __POPCNT__ 1 
#define __PRAGMA_REDEFINE_EXTNAME 1 
#define __PRFCHW__ 1 
#define __PTRDIFF_MAX__ 0x7fffffffffffffffL 
#define __PTRDIFF_TYPE__ long int 
#define __RDRND__ 1 
#define __RDSEED__ 1 
#define __REGISTER_PREFIX__ 
#define __SCHAR_MAX__ 0x7f 
#define __SEG_FS 1 
#define __SEG_GS 1 
#define __SHRT_MAX__ 0x7fff 
#define __SIG_ATOMIC_MAX__ 0x7fffffff 
#define __SIG_ATOMIC_MIN__ (-__SIG_ATOMIC_MAX__ - 1) 
#define __SIG_ATOMIC_TYPE__ int 
#define __SIZE_MAX__ 0xffffffffffffffffUL 
#define __SIZEOF_DOUBLE__ 8 
#define __SIZEOF_FLOAT128__ 16 
#define __SIZEOF_FLOAT__ 4 
#define __SIZEOF_FLOAT80__ 16 
#define __SIZEOF_INT128__ 16 
#define __SIZEOF_INT__ 4 
#define __SIZEOF_LONG__ 8 
#define __SIZEOF_LONG_DOUBLE__ 16 
#define __SIZEOF_LONG_LONG__ 8 
#define __SIZEOF_POINTER__ 8 
#define __SIZEOF_PTRDIFF_T__ 8 
#define __SIZEOF_SHORT__ 2 
#define __SIZEOF_SIZE_T__ 8 
#define __SIZEOF_WCHAR_T__ 4 
#define __SIZEOF_WINT_T__ 4 
#define __SIZE_TYPE__ long unsigned int 
#define __SSE__ 1 
#define __SSE2__ 1 
#define __SSE2_MATH__ 1 
#define __SSE3__ 1 
#define __SSE4_1__ 1 
#define __SSE4_2__ 1 
#define __SSE_MATH__ 1 
#define __SSSE3__ 1 
#define __STDC__ 1 
#define __STDC_HOSTED__ 1 
#define __STDC_IEC_559__ 1 
#define __STDC_IEC_559_COMPLEX__ 1 
#define __STDC_ISO_10646__ 201605L 
#define __STDC_NO_THREADS__ 1 
#define _STDC_PREDEF_H 1 
#define __STDC_UTF_16__ 1 
#define __STDC_UTF_32__ 1 
#define __STDC_VERSION__ 201112L 
#define __tune_core_avx2__ 1 
#define __tune_haswell__ 1 
#define __UINT16_C(c) c 
#define __UINT16_MAX__ 0xffff 
#define __UINT16_TYPE__ short unsigned int 
#define __UINT32_C(c) C## U 
#define __UINT32_MAX__ 0xffffffffU 
#define __UINT32_TYPE__ unsigned int 
#define __UINT64_C(c) C## UL 
#define __UINT64_MAX__ 0xffffffffffffffffUL 
#define __UINT64_TYPE__ long unsigned int 
#define __UINT8_C(c) c 
#define __UINT8_MAX__ 0xff 
#define __UINT8_TYPE__ unsigned char 
#define __UINT_FAST16_MAX__ 0xffffffffffffffffUL 
#define __UINT_FAST16_TYPE__ long unsigned int 
#define __UINT_FAST32_MAX__ 0xffffffffffffffffUL 
#define __UINT_FAST32_TYPE__ long unsigned int 
#define __UINT_FAST64_MAX__ 0xffffffffffffffffUL 
#define __UINT_FAST64_TYPE__ long unsigned int 
#define __UINT_FAST8_MAX__ 0xff 
#define __UINT_FAST8_TYPE__ unsigned char 
#define __UINT_LEAST16_MAX__ 0xffff 
#define __UINT_LEAST16_TYPE__ short unsigned int 
#define __UINT_LEAST32_MAX__ 0xffffffffU 
#define __UINT_LEAST32_TYPE__ unsigned int 
#define __UINT_LEAST64_MAX__ 0xffffffffffffffffUL 
#define __UINT_LEAST64_TYPE__ long unsigned int 
#define __UINT_LEAST8_MAX__ 0xff 
#define __UINT_LEAST8_TYPE__ unsigned char 
#define __UINTMAX_C(c) C## UL 
#define __UINTMAX_MAX__ 0xffffffffffffffffUL 
#define __UINTMAX_TYPE__ long unsigned int 
#define __UINTPTR_MAX__ 0xffffffffffffffffUL 
#define __UINTPTR_TYPE__ long unsigned int 
#define __unix 1 
#define __unix__ 1 
#define unix 1 
#define __USER_LABEL_PREFIX__ 
#define __VERSION__ "6.3.1 20161221 (Red Hat 6.3.1-1)" 
#define __WCHAR_MAX__ 0x7fffffff 
#define __WCHAR_MIN__ (-__WCHAR_MAX__ - 1) 
#define __WCHAR_TYPE__ int 
#define __WINT_MAX__ 0xffffffffU 
#define __WINT_MIN__ 0U 
#define __WINT_TYPE__ unsigned int 
#define __x86_64 1 
#define __x86_64__ 1 
#define __XSAVE__ 1 
#define __XSAVEC__ 1 
#define __XSAVEOPT__ 1 
#define __XSAVES__ 1 

---

如果需要的話：

skylake:~$ gcc -v 
Using built-in specs. 
COLLECT_GCC=gcc 
COLLECT_LTO_WRAPPER=/usr/libexec/gcc/x86_64-redhat-linux/6.3.1/lto-wrapper 
Target: x86_64-redhat-linux 
Configured with: ../configure --enable-bootstrap --enable-languages=c,c++,objc,obj-c++,fortran,ada,go,lto --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --with-bugurl=http://bugzilla.redhat.com/bugzilla --enable-shared --enable-threads=posix --enable-checking=release --enable-multilib --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-gnu-unique-object --enable-linker-build-id --with-linker-hash-style=gnu --enable-plugin --enable-initfini-array --disable-libgcj --with-isl --enable-libmpx --enable-gnu-indirect-function --with-tune=generic --with-arch_32=i686 --build=x86_64-redhat-linux 
Thread model: posix 
gcc version 6.3.1 20161221 (Red Hat 6.3.1-1) (GCC) 

---

這裏有一些相關的堆棧溢出的問題，但他們沒有討論的話題：

• Which CPUs support MOVBE instruction?
• Operations and endianess
• ASM usage of memory location operands
• Why does the ia32/x64 opcode map document 0x66 and 0xF2 as a double mandatory prefix for opcode 0x0F38F1
• How to make GCC generate bswap instruction for big endian store without builtins

Answer 1

正如我敢肯定你已經得出結論，沒有規定這個。簡單地比較-mmovbe與-mno-movbe的輸出清楚地表明瞭這一點。

一些替代方法：

• 如果你知道足夠-mmovbe添加到命令行，你也可以添加自己的定義。
• 您可能能夠從其他定義的一個（_ _的Haswell _ _彈簧記）推斷，但不能處理明確-mmovbe案件。或AMD。看看gcc的docs，他們在那裏談論每種體系結構支持的內容，如果你決定採用這種方式，可能會有所幫助。
• 也許你最好的選擇是通過cpuid在運行時檢查它。傳遞eax = 1會在ecx的位22（基於零）中返回此功能。