arm - ARM下编译NEON代码时出错

Question

我正在尝试将 SSE4 优化代码移植到使用以下 header 优化的 NEON:
https://github.com/jratcliff63367/sse2neon/blob/master/SSE2NEON.h

在 ODROID-xu4 上编译时出现编译错误此代码:
https://github.com/k06a/creepMiner/tree/feature/neon

[  2%] Building CXX object CMakeFiles/creepMiner.dir/src/shabal/mshabal/mshabal_neon.cpp.o
In file included from /root/creepMiner-neon/src/shabal/mshabal/sse2neon.hpp:123:0,
                 from /root/creepMiner-neon/src/shabal/mshabal/mshabal_neon.cpp:22:
/usr/lib/gcc/arm-linux-gnueabihf/7/include/arm_neon.h: In function '__m128i _mm_set1_epi32(int)':
/usr/lib/gcc/arm-linux-gnueabihf/7/include/arm_neon.h:6733:1: error: inlining failed in call to always_inline 'int32x4_t vdupq_n_s32(int32_t)': target specific option mismatch
 vdupq_n_s32 (int32_t __a)
 ^~~~~~~~~~~
In file included from /root/creepMiner-neon/src/shabal/mshabal/mshabal_neon.cpp:22:0:
/root/creepMiner-neon/src/shabal/mshabal/sse2neon.hpp:230:7: note: called from here
     (x)
       ^
/root/creepMiner-neon/src/shabal/mshabal/sse2neon.hpp:383:12: note: in expansion of macro 'vreinterpretq_m128i_s32'
     return vreinterpretq_m128i_s32(vdupq_n_s32(_i));
            ^~~~~~~~~~~~~~~~~~~~~~~
CMakeFiles/creepMiner.dir/build.make:878: recipe for target 'CMakeFiles/creepMiner.dir/src/shabal/mshabal/mshabal_neon.cpp.o' failed
make[2]: *** [CMakeFiles/creepMiner.dir/src/shabal/mshabal/mshabal_neon.cpp.o] Error 1
CMakeFiles/Makefile2:67: recipe for target 'CMakeFiles/creepMiner.dir/all' failed
make[1]: *** [CMakeFiles/creepMiner.dir/all] Error 2
Makefile:151: recipe for target 'all' failed
make: *** [all] Error 2

源文件有以下特定选项:

-marm -march=armv7-a+simd -mtune=cortex-a15.cortex-a7

CMakeLists.txt:

if (USE_NEON AND NOT MINIMAL_BUILD)
    add_definitions(-DUSE_NEON)
    set(SOURCE_FILES ${SOURCE_FILES} src/shabal/mshabal/mshabal_neon.cpp)
    if (UNIX OR APPLE)
        set_source_files_properties(src/shabal/mshabal/mshabal_neon.cpp PROPERTIES COMPILE_FLAGS -marm)
        set_source_files_properties(src/shabal/mshabal/mshabal_neon.cpp PROPERTIES COMPILE_FLAGS -march=armv7-a+simd)
        set_source_files_properties(src/shabal/mshabal/mshabal_neon.cpp PROPERTIES COMPILE_FLAGS -mtune=cortex-a15.cortex-a7)
    elseif (MSVC)
        set_source_files_properties(src/shabal/mshabal/mshabal_neon.cpp PROPERTIES COMPILE_FLAGS /arch:ARMv7)
    endif ()
endif ()

看起来当前架构不支持 vdupq_n_s32 ，但它应该，因为 armv7支持。

处理器信息:

$ cat /proc/cpuinfo

给出以下:

processor   : 0
model name  : ARMv7 Processor rev 3 (v7l)
BogoMIPS    : 90.00
Features    : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae 
CPU implementer : 0x41
CPU architecture: 7
CPU variant : 0x0
CPU part    : 0xc07
CPU revision    : 3

processor   : 1
model name  : ARMv7 Processor rev 3 (v7l)
BogoMIPS    : 90.00
Features    : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae 
CPU implementer : 0x41
CPU architecture: 7
CPU variant : 0x0
CPU part    : 0xc07
CPU revision    : 3

processor   : 2
model name  : ARMv7 Processor rev 3 (v7l)
BogoMIPS    : 90.00
Features    : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae 
CPU implementer : 0x41
CPU architecture: 7
CPU variant : 0x0
CPU part    : 0xc07
CPU revision    : 3

processor   : 3
model name  : ARMv7 Processor rev 3 (v7l)
BogoMIPS    : 90.00
Features    : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae 
CPU implementer : 0x41
CPU architecture: 7
CPU variant : 0x0
CPU part    : 0xc07
CPU revision    : 3

processor   : 4
model name  : ARMv7 Processor rev 3 (v7l)
BogoMIPS    : 120.00
Features    : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae 
CPU implementer : 0x41
CPU architecture: 7
CPU variant : 0x2
CPU part    : 0xc0f
CPU revision    : 3

processor   : 5
model name  : ARMv7 Processor rev 3 (v7l)
BogoMIPS    : 120.00
Features    : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae 
CPU implementer : 0x41
CPU architecture: 7
CPU variant : 0x2
CPU part    : 0xc0f
CPU revision    : 3

processor   : 6
model name  : ARMv7 Processor rev 3 (v7l)
BogoMIPS    : 120.00
Features    : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae 
CPU implementer : 0x41
CPU architecture: 7
CPU variant : 0x2
CPU part    : 0xc0f
CPU revision    : 3

processor   : 7
model name  : ARMv7 Processor rev 3 (v7l)
BogoMIPS    : 120.00
Features    : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae 
CPU implementer : 0x41
CPU architecture: 7
CPU variant : 0x2
CPU part    : 0xc0f
CPU revision    : 3

Hardware    : ODROID-XU4
Revision    : 0100
Serial      : 0000000000000000

获得原生拱:

gcc -march=native -v

给出以下内容:

Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/usr/lib/gcc/arm-linux-gnueabihf/7/lto-wrapper
Target: arm-linux-gnueabihf
Configured with: ../src/configure -v --with-pkgversion='Ubuntu/Linaro 7.3.0-16ubuntu3' --with-bugurl=file:///usr/share/doc/gcc-7/README.Bugs --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++ --prefix=/usr --with-gcc-major-version-only --with-as=/usr/bin/arm-linux-gnueabihf-as --with-ld=/usr/bin/arm-linux-gnueabihf-ld --program-suffix=-7 --program-prefix=arm-linux-gnueabihf- --enable-shared --enable-linker-build-id --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --libdir=/usr/lib --enable-nls --with-sysroot=/ --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --with-default-libstdcxx-abi=new --enable-gnu-unique-object --disable-libitm --disable-libquadmath --disable-libquadmath-support --enable-plugin --enable-default-pie --with-system-zlib --with-target-system-zlib --enable-objc-gc=auto --enable-multiarch --enable-multilib --disable-sjlj-exceptions --with-arch=armv7-a --with-fpu=vfpv3-d16 --with-float=hard --with-mode=thumb --disable-werror --enable-multilib --enable-checking=release --build=arm-linux-gnueabihf --host=arm-linux-gnueabihf --target=arm-linux-gnueabihf
Thread model: posix
gcc version 7.3.0 (Ubuntu/Linaro 7.3.0-16ubuntu3)

也许这是一个问题？我只看到 --with-arch=armv7-a --with-fpu=vfpv3-d16支持，但应该是vfpv4支持。是吗？我应该重新配置 GCC 吗？这会有帮助吗？

Answer 1

-mfpu=neon应该可以解决问题。

顺便说一句，你真的希望只包含头文件就行吗？

NEON 有大量在 Intel 机器上不可用的指令，尤其是在排列方面。

你会得到很多 vtbl到处都有令人讨厌的延迟的指令，这些指令像疯了一样消耗周期。

仅仅依靠别人的通用解决方案不能称为优化 IMO。