memcpy 速度太慢？掌握这个技术让内存拷贝效率成倍提升

封面出自：板栗懒得很

使用neon指令

#ifdef  __ARM__
static void neon_memcpy(volatile unsigned char *dst, volatile unsigned char *src, int sz)
{
    if (sz & 63)
        sz = (sz & -64) + 64;
    asm volatile (
    "NEONCopyPLD: \n"
            " VLDM %[src]!,{d0-d7} \n"
            " VSTM %[dst]!,{d0-d7} \n"
            " SUBS %[sz],%[sz],#0x40 \n"
            " BGT NEONCopyPLD \n"
    : [dst]"+r"(dst), [src]"+r"(src), [sz]"+r"(sz) : : "d0", "d1", "d2", "d3", "d4", "d5", "d6", "d7", "cc", "memory");
}
#endif

  由于并不是所有的armv7架构cpu都支持neon，所以这里增加cpufeatures库用来判断是否支持neon。下面是正确的使用方式。

#ifdef  __ARM__
    if (android_getCpuFamily() == ANDROID_CPU_FAMILY_ARM &&
        (android_getCpuFeatures() & ANDROID_CPU_ARM_FEATURE_NEON) != 0){//支持NEON
        neon_memcpy(destBuffer, src, length);
    }else{
        memcpy(destBuffer, src, length);
    }
#else
//其它架构使用memcpy
     memcpy(destBuffer, src, length);
#endif

Android mk开启neon

#arm架构增加neon支持
ifeq ($(TARGET_ARCH_ABI),armeabi-v7a)
LOCAL_CFLAGS := -D__cpusplus -g -mfloat-abi=softfp -mfpu=neon -march=armv7-a -mtune=cortex-a8 -DHAVE_NEON=1
endif
#开启两个架构的neon支持（x86可以通过将neon转为sse间接支持）
ifeq ($(TARGET_ARCH_ABI),$(filter $(TARGET_ARCH_ABI), armeabi-v7a x86))
LOCAL_ARM_NEON := true
endif
LOCAL_STATIC_LIBRARIES := cpufeatures

include $(BUILD_SHARED_LIBRARY)
$(call import-module,android/cpufeatures)

Cmake开启neon

# 引入cpufeatures模块
include_directories(${ANDROID_NDK}/sources/android/cpufeatures)

if (${ANDROID_ABI} STREQUAL "armeabi-v7a")
    set_property(SOURCE ${SOURCES} APPEND_STRING PROPERTY COMPILE_FLAGS " -mfpu=neon")
    add_definitions("-DHAVE_NEON=1")
elseif (${ANDROID_ABI} STREQUAL "x86")
    set_property(SOURCE ${SOURCES} APPEND_STRING PROPERTY COMPILE_FLAGS
            " -mssse3  -Wno-unknown-attributes \
                   -Wno-deprecated-declarations \
                   -Wno-constant-conversion \
                   -Wno-static-in-inline")
    add_definitions(-DHAVE_NEON_X86=1 -DHAVE_NEON=1)
endif ()
add_library(
        yourLibrary
        SHARED
        ${ANDROID_NDK}/sources/android/cpufeatures/cpu-features.c
)

  事实上并不是只有arm架构才支持SIMD，x86也是支持的（SSE），并且Android也提供了适用于x86的NEON_2_SSE.h。x86并不直接支持neon指令，而是通过这个头文件将其转为sse指令，以提供与neon相同的api。有兴趣的同学可以研究一下。