typedef __builtin_neon_qi int8x8_t  __attribute__ ((__vector_size__ (8)));
typedef __builtin_neon_hi int16x4_t  __attribute__ ((__vector_size__ (8)));
typedef __builtin_neon_si int32x2_t  __attribute__ ((__vector_size__ (8)));
typedef __builtin_neon_di int64x1_t;
typedef __builtin_neon_sf float32x2_t  __attribute__ ((__vector_size__ (8)));
typedef __builtin_neon_poly8 poly8x8_t  __attribute__ ((__vector_size__ (8)));
typedef __builtin_neon_poly16 poly16x4_t  __attribute__ ((__vector_size__ (8)));
typedef __builtin_neon_uqi uint8x8_t  __attribute__ ((__vector_size__ (8)));
typedef __builtin_neon_uhi uint16x4_t  __attribute__ ((__vector_size__ (8)));
typedef __builtin_neon_usi uint32x2_t  __attribute__ ((__vector_size__ (8)));
typedef __builtin_neon_udi uint64x1_t;
typedef __builtin_neon_qi int8x16_t  __attribute__ ((__vector_size__ (16)));
typedef __builtin_neon_hi int16x8_t  __attribute__ ((__vector_size__ (16)));
typedef __builtin_neon_si int32x4_t  __attribute__ ((__vector_size__ (16)));
typedef __builtin_neon_di int64x2_t  __attribute__ ((__vector_size__ (16)));
typedef __builtin_neon_sf float32x4_t  __attribute__ ((__vector_size__ (16)));
typedef __builtin_neon_poly8 poly8x16_t  __attribute__ ((__vector_size__ (16)));
typedef __builtin_neon_poly16 poly16x8_t  __attribute__ ((__vector_size__ (16)));
typedef __builtin_neon_uqi uint8x16_t  __attribute__ ((__vector_size__ (16)));
typedef __builtin_neon_uhi uint16x8_t  __attribute__ ((__vector_size__ (16)));
typedef __builtin_neon_usi uint32x4_t  __attribute__ ((__vector_size__ (16)));
typedef __builtin_neon_udi uint64x2_t  __attribute__ ((__vector_size__ (16)));

typedef float float32_t;
typedef __builtin_neon_poly8 poly8_t;
typedef __builtin_neon_poly16 poly16_t;

typedef struct int8x8x2_t
{
 int8x8_t val[2];
} int8x8x2_t;

typedef struct int8x16x2_t
{
 int8x16_t val[2];
} int8x16x2_t;

typedef struct int16x4x2_t
{
 int16x4_t val[2];
} int16x4x2_t;

typedef struct int16x8x2_t
{
 int16x8_t val[2];
} int16x8x2_t;

typedef struct int32x2x2_t
{
 int32x2_t val[2];
} int32x2x2_t;

typedef struct int32x4x2_t
{
 int32x4_t val[2];
} int32x4x2_t;

typedef struct int64x1x2_t
{
 int64x1_t val[2];
} int64x1x2_t;

typedef struct int64x2x2_t
{
 int64x2_t val[2];
} int64x2x2_t;

typedef struct uint8x8x2_t
{
 uint8x8_t val[2];
} uint8x8x2_t;

typedef struct uint8x16x2_t
{
 uint8x16_t val[2];
} uint8x16x2_t;

typedef struct uint16x4x2_t
{
 uint16x4_t val[2];
} uint16x4x2_t;

typedef struct uint16x8x2_t
{
 uint16x8_t val[2];
} uint16x8x2_t;

typedef struct uint32x2x2_t
{
 uint32x2_t val[2];
} uint32x2x2_t;

typedef struct uint32x4x2_t
{
 uint32x4_t val[2];
} uint32x4x2_t;

typedef struct uint64x1x2_t
{
 uint64x1_t val[2];
} uint64x1x2_t;

typedef struct uint64x2x2_t
{
 uint64x2_t val[2];
} uint64x2x2_t;

typedef struct float32x2x2_t
{
 float32x2_t val[2];
} float32x2x2_t;

typedef struct float32x4x2_t
{
 float32x4_t val[2];
} float32x4x2_t;

typedef struct poly8x8x2_t
{
 poly8x8_t val[2];
} poly8x8x2_t;

typedef struct poly8x16x2_t
{
 poly8x16_t val[2];
} poly8x16x2_t;

typedef struct poly16x4x2_t
{
 poly16x4_t val[2];
} poly16x4x2_t;

typedef struct poly16x8x2_t
{
 poly16x8_t val[2];
} poly16x8x2_t;

typedef struct int8x8x3_t
{
 int8x8_t val[3];
} int8x8x3_t;

typedef struct int8x16x3_t
{
 int8x16_t val[3];
} int8x16x3_t;

typedef struct int16x4x3_t
{
 int16x4_t val[3];
} int16x4x3_t;

typedef struct int16x8x3_t
{
 int16x8_t val[3];
} int16x8x3_t;

typedef struct int32x2x3_t
{
 int32x2_t val[3];
} int32x2x3_t;

typedef struct int32x4x3_t
{
 int32x4_t val[3];
} int32x4x3_t;

typedef struct int64x1x3_t
{
 int64x1_t val[3];
} int64x1x3_t;

typedef struct int64x2x3_t
{
 int64x2_t val[3];
} int64x2x3_t;

typedef struct uint8x8x3_t
{
 uint8x8_t val[3];
} uint8x8x3_t;

typedef struct uint8x16x3_t
{
 uint8x16_t val[3];
} uint8x16x3_t;

typedef struct uint16x4x3_t
{
 uint16x4_t val[3];
} uint16x4x3_t;

typedef struct uint16x8x3_t
{
 uint16x8_t val[3];
} uint16x8x3_t;

typedef struct uint32x2x3_t
{
 uint32x2_t val[3];
} uint32x2x3_t;

typedef struct uint32x4x3_t
{
 uint32x4_t val[3];
} uint32x4x3_t;

typedef struct uint64x1x3_t
{
 uint64x1_t val[3];
} uint64x1x3_t;

typedef struct uint64x2x3_t
{
 uint64x2_t val[3];
} uint64x2x3_t;

typedef struct float32x2x3_t
{
 float32x2_t val[3];
} float32x2x3_t;

typedef struct float32x4x3_t
{
 float32x4_t val[3];
} float32x4x3_t;

typedef struct poly8x8x3_t
{
 poly8x8_t val[3];
} poly8x8x3_t;

typedef struct poly8x16x3_t
{
 poly8x16_t val[3];
} poly8x16x3_t;

typedef struct poly16x4x3_t
{
 poly16x4_t val[3];
} poly16x4x3_t;

typedef struct poly16x8x3_t
{
 poly16x8_t val[3];
} poly16x8x3_t;

typedef struct int8x8x4_t
{
 int8x8_t val[4];
} int8x8x4_t;

typedef struct int8x16x4_t
{
 int8x16_t val[4];
} int8x16x4_t;

typedef struct int16x4x4_t
{
 int16x4_t val[4];
} int16x4x4_t;

typedef struct int16x8x4_t
{
 int16x8_t val[4];
} int16x8x4_t;

typedef struct int32x2x4_t
{
 int32x2_t val[4];
} int32x2x4_t;

typedef struct int32x4x4_t
{
 int32x4_t val[4];
} int32x4x4_t;

typedef struct int64x1x4_t
{
 int64x1_t val[4];
} int64x1x4_t;

typedef struct int64x2x4_t
{
 int64x2_t val[4];
} int64x2x4_t;

typedef struct uint8x8x4_t
{
 uint8x8_t val[4];
} uint8x8x4_t;

typedef struct uint8x16x4_t
{
 uint8x16_t val[4];
} uint8x16x4_t;

typedef struct uint16x4x4_t
{
 uint16x4_t val[4];
} uint16x4x4_t;

typedef struct uint16x8x4_t
{
 uint16x8_t val[4];
} uint16x8x4_t;

typedef struct uint32x2x4_t
{
 uint32x2_t val[4];
} uint32x2x4_t;

typedef struct uint32x4x4_t
{
 uint32x4_t val[4];
} uint32x4x4_t;

typedef struct uint64x1x4_t
{
 uint64x1_t val[4];
} uint64x1x4_t;

typedef struct uint64x2x4_t
{
 uint64x2_t val[4];
} uint64x2x4_t;

typedef struct float32x2x4_t
{
 float32x2_t val[4];
} float32x2x4_t;

typedef struct float32x4x4_t
{
 float32x4_t val[4];
} float32x4x4_t;

typedef struct poly8x8x4_t
{
 poly8x8_t val[4];
} poly8x8x4_t;

typedef struct poly8x16x4_t
{
 poly8x16_t val[4];
} poly8x16x4_t;

typedef struct poly16x4x4_t
{
 poly16x4_t val[4];
} poly16x4x4_t;

typedef struct poly16x8x4_t
{
 poly16x8_t val[4];
} poly16x8x4_t;

 CC [M] /work/platform-zynq/drivers/zynq_fpga_driver/mmi_neon/lcd_hw_fs8812_neon.o
In file included from /home/liuwanpeng/lin/lib/gcc/arm-xilinx-linux-gnueabi/4.8.3/include/arm_neon.h:39:0,
         from /work/platform-zynq/drivers/zynq_fpga_driver/mmi_neon/lcd_hw_fs8812_neon.c:8:
/home/liuwanpeng/lin/lib/gcc/arm-xilinx-linux-gnueabi/4.8.3/include/stdint.h:9:26: error: no include path in which to search for stdint.h
 # include_next <stdint.h>
 没有使用-ffreestanding编译选项时，在内核态下使用出现此编译错误。             

未使能“Support for NEON in kernel mode”时会报错：
mmi_module_amp: Unknown symbol kernel_neon_begin (err 0)
mmi_module_amp: Unknown symbol kernel_neon_end (err 0)

CFLAGS_MODULE += -O3 -mfpu=neon -mfloat-abi=softfp -ffreestanding 

#include <linux/module.h> 
#include <linux/printk.h>
#include <arm_neon.h>　　// 来自GCC的头文件，必须用-ffreestanding编译选徐昂

int fs8812_cvt_buf( uint8 * dst, uint8 * src )
{

  uint8x16_t V_src[8];
  uint8x16_t V_tmp[8];
  uint8x16_t V_dst[8];
  uint8x16_t V_msk;
  int8x16_t V_shift;
  int8 RSHL_bits[8] = {0,1,2,3,4,5,6,7};
  int8 row,bit;
  uint8 page;
  uint8 * fb_page_x = NULL;  

  // convert the frame_buf for fs8812
  for( page=0;page<4;page++ ){
    fb_page_x = src + page*LCD_PAGE_BYTES;
    for( row=0;row<LCD_8812_PAGE_ROWS;row++ )
      V_src[row] = vld1q_u8( fb_page_x + row*LCD_8812_ROW_BYTES );
　　　　　　　for( bit=0;bit<8;bit++){
      　　V_msk = vdupq_n_u8(1<<bit);
      　　for( row=0;row<LCD_8812_PAGE_ROWS;row++){
        　　V_tmp[row] = vandq_u8(V_src[row],V_msk);  // only process the desire bit
        　　V_shift = vdupq_n_s8( RSHL_bits[row]-bit );
        　　V_tmp[row] = vshlq_u8( V_tmp[row],V_shift );
      　　}  
      　　V_dst[bit] = vorrq_u8(V_tmp[0],V_tmp[1]);   // all bit_x convert to one row
      　　V_dst[bit] |= vorrq_u8(V_tmp[2],V_tmp[3]);
      　　V_dst[bit] |= vorrq_u8(V_tmp[4],V_tmp[5]);
      　　V_dst[bit] |= vorrq_u8(V_tmp[6],V_tmp[7]);        
    　　}
    　　// store to ram
    　　fb_page_x = dst + page*LCD_PAGE_BYTES;
    　　for( row=0;row<LCD_8812_PAGE_ROWS;row++ ){
      　　 vst1q_u8(fb_page_x,V_dst[row]);
      　　fb_page_x += LCD_8812_ROW_BYTES;
    　　}
  }
　　return 0;
}

EXPORT_SYMBOL_GPL(fs8812_cvt_buf);

  // convert the frame_buf for fs8812
  kernel_neon_begin();
  fs8812_cvt_buf( g_tmp_buf, frame_buf );
  kernel_neon_end();