2

我有一个基于 ARM NEON Cortex-A8 的处理器目标。我正在通过使用 NEON 来优化我的代码。但是当我编译我的代码时，我得到了这个奇怪的错误。不知道如何解决这个问题。

我正在尝试在我的主机上使用 Code Sourcery (PART2) 编译以下代码 (PART 1)。我得到了这个奇怪的错误（第 3 部分）。我在这里做错了吗？其他人可以编译这个，看看他们是否也得到相同的编译错误？

奇怪的是，在代码中，如果我注释掉代码的else if(step_size == 4)一部分，那么错误就会消失。但是，遗憾的是，没有它我的优化是不完整的，所以我必须拥有它。

起初我认为这是 CodeSourcey 编译器（在我的主机上）的问题，所以我直接在我的目标上编译了程序（我的目标在 Ubuntu 上运行）。我在那里再次使用 gcc，我得到了同样的错误，当我注释掉该else if(step_size == 4)部分时，错误消失了。

帮助！

第1部分

#include<stdio.h>
#include"arm_neon.h"

#define IMAGE_HEIGHT 480
#define IMAGE_WIDTH  640

float32_t integral_image[IMAGE_HEIGHT][IMAGE_WIDTH];

float32x4_t box_area_compute3(int, int , int , int , unsigned int , float);

inline int min(int, int);

int main()
{

 box_area_compute3(1, 1, 4, 4, 2, 0);

 return 0;
}

float32x4_t box_area_compute3(int row, int col, int num_rows, int num_cols, unsigned int step_size, float three)
{
 unsigned int height = IMAGE_HEIGHT;
 unsigned int width = IMAGE_WIDTH;

 int temp_row = row + num_rows;
 int temp_col = col + num_cols;

 int r1 = (min(row, height))- 1 ;
 int r2 = (min(temp_row, height)) - 1;

 int c1 = (min(col, width)) - 1;
 int c2 = (min(temp_col, width)) - 1;

 float32x4_t v128_areas;

 if(step_size == 2)
 {
  float32x4x2_t top_left, top_right, bottom_left, bottom_right;
  top_left    = vld2q_f32((float32_t *)integral_image[r1] + c1);
  top_right   = vld2q_f32((float32_t *)integral_image[r1] + c2);
  bottom_left  = vld2q_f32((float32_t *)integral_image[r2] + c1);
  bottom_right  = vld2q_f32((float32_t *)integral_image[r2] + c2);

  v128_areas = vsubq_f32(vsubq_f32(vaddq_f32(top_left.val[0], bottom_right.val[0]), top_right.val[0]), bottom_left.val[0]);


 }
 else if(step_size == 4)
 {
  float32x4x4_t top_left, top_right, bottom_left, bottom_right;
  top_left   = vld4q_f32((float32_t *)integral_image[r1] + c1);
  top_right   = vld4q_f32((float32_t *)integral_image[r1] + c2);
  bottom_left  = vld4q_f32((float32_t *)integral_image[r2] + c1);
  bottom_right  = vld4q_f32((float32_t *)integral_image[r2] + c2);

  v128_areas = vsubq_f32(vsubq_f32(vaddq_f32(top_left.val[0], bottom_right.val[0]), top_right.val[0]), bottom_left.val[0]);

 }

 if(three == 3.0)
  v128_areas = vmulq_n_f32(v128_areas, three);

 return v128_areas;

}

inline int min(int X, int Y)
{
 return (X < Y ? X : Y);
}

第2部分

arm-none-linux-gnueabi-gcc -O0 -g3 -Wall -c -fmessage-length=0 -fcommon -MMD -MP -MF"main.d" -MT"main.d" -mcpu=cortex-a8 -marm -mfloat-abi=hard -mfpu=neon-vfpv4 -o"main.o" "../main.c"

第三部分

../main.c: In function 'box_area_compute3':
../main.c:65: error: unable to find a register to spill in class 'GENERAL_REGS'
../main.c:65: error: this is the insn:
(insn 226 225 227 5 c:\program files\codesourcery\sourcery g++\bin\../lib/gcc/arm-none-linux-gnueabi/4.4.1/include/arm_neon.h:9863 (parallel [
           (set (reg:XI 148 [ D.17028 ])
               (unspec:XI [
                       (mem:XI (reg:SI 3 r3 [301]) [0 S64 A64])
                       (reg:XI 148 [ D.17028 ])
                       (unspec:V4SF [
                               (const_int 0 [0x0])
                           ] 191)
                   ] 111))
           (set (reg:SI 3 r3 [301])
               (plus:SI (reg:SI 3 r3 [301])
                   (const_int 32 [0x20])))
       ]) 1605 {neon_vld4qav4sf} (nil))
../main.c:65: confused by earlier errors, bailing out
cs-make: *** [main.o] Error 1
4

4 回答 4

2

我无法对此进行测试，因为我没有它的工具链，但这种类型的错误通常可以通过稍微改写代码来解决。通常这不应该发生，它应该被报告为一个错误，但是您正在使用处理器特定的功能，这可能不如编译器的其余部分经过测试和完善。

由于这是一个寄存器溢出错误，并且您涉及多个指针，因此我高度怀疑编译器可能会尝试将更多数据加载到寄存器中，而不是担心可能会发生一些混叠（这可能是t 实际发生）。下面我将处理这种可能性，并做一些其他的事情，从编译器的角度来看，这可能会降低代码的复杂性（尽管看起来可能并非如此）。

#include<stdio.h>
#include"arm_neon.h"

#define IMAGE_HEIGHT 480
#define IMAGE_WIDTH  640

float32_t integral_image[IMAGE_HEIGHT][IMAGE_WIDTH];

float32x4_t box_area_compute3(int, int , int , int , unsigned int , float);

inline int min(int, int);

int main()
{

 box_area_compute3(1, 1, 4, 4, 2, 0);

 return 0;
}

/* By putting these in separate functions the compiler will initially
 * think about them by themselves, without the complications of the
 * surrounding code.  This may give it the abiltiy to optimise the
 * code somewhat before trying to inline it.
 * This may also serve to make it more obvious to the compiler that
 * the local variables are dead after their use (since they are
 * dead after the call returns, and that the lifetimes of some variable
 * cannot actually overlap (hopefully reducing the register needs).
 */
static inline float32x4_t do_it2(float32_t *tl, float32_t *tr, float32_t *bl, float32_t * br) {
    float32x4x2_t top_left, top_right, bottom_left, bottom_right;
    float32x4_t A, B;

    top_left = vld2q_f32(tl);
    top_right = vld2q_f32(tr);
    bottom_left = vld2q_f32(bl);
    bottom_right = vld2q_f32(br);

    /* By spreading this across several statements I have created several
     * additional sequence points.  The compiler does not think that it
     * has to dereference all of the pointers before doing any of the
     * computations.... maybe. */
    A = vaddq_f32(*top_left.val, *bottom_right.val);
    B = vsubq_f32(A, *top_right.val);
    return vsubq_f32(B, *bottom_left);
}

static inline float32x4_t do_it4(float32_t *tl, float32_t *tr, float32_t *bl, float32_t * br) {
    float32x4x4_t top_left, top_right, bottom_left, bottom_right;
    float32x4_t A, B;

    top_left = vld4q_f32(tl);
    top_right = vld4q_f32(tr);
    bottom_left = vld4q_f32(bl);
    bottom_right = vld4q_f32(br);

    A = vaddq_f32(*top_left.val, *bottom_right.val);
    B = vsubq_f32(A, *top_right.val);
    return vsubq_f32(B, *bottom_left);
}

float32x4_t box_area_compute3(int row, int col, int num_rows, int num_cols, unsigned int step_size, float three)
{
 unsigned int height = IMAGE_HEIGHT;
 unsigned int width = IMAGE_WIDTH;

 int temp_row = row + num_rows;
 int temp_col = col + num_cols;

 int r1 = (min(row, height))- 1 ;
 int r2 = (min(temp_row, height)) - 1;

 int c1 = (min(col, width)) - 1;
 int c2 = (min(temp_col, width)) - 1;

 float32x4_t v128_areas;

     float32_t *tl = (float32_t *)integral_image[r1] + c1;
 float32_t *tr = (float32_t *)integral_image[r1] + c2;
 float32_t *bl = (float32_t *)integral_image[r2] + c1;
 float32_t *br = (float32_t *)integral_image[r2] + c2;


 switch (step_size) {
    case 2:
      v128_areas = do_it2(tl, tr, bl, br);
      break;

 case 4:
      v128_areas = do_it4(tl, tr, bl, br);
      break;
 }

 if(three == 3.0)
  v128_areas = vmulq_n_f32(v128_areas, three);

 return v128_areas;

}

inline int min(int X, int Y)
{
 return (X < Y ? X : Y);
}

我希望这会有所帮助，并且我没有引入任何错误。

于 2010-09-28T16:22:47.587 回答
1

好吧，我已经就这个问题联系了 Code Sourcery，他们认为这是 GCC 编译器中的一个错误。所以我在汇编中编写了 do_it4(){.....} 函数，而不是使用内在函数。现在效果很好！

于 2010-10-28T09:18:05.900 回答
0

该行： 

float32x4x4_t top_left, top_right, bottom_left, bottom_right;

使用所有 16 个 q 寄存器！编译器不能处理这个并不奇怪。您可能可以通过重写以使用更少的寄存器来解决此问题。

于 2011-03-23T18:41:25.500 回答
0

ARM NEON Cortex-A8 支持 vfpv3，Cortex-A5 支持 vfpv4 和 neon2，（至于：如果您使用 -mfloat-abi=hard，您将跳过在软件缺失指令中进行模拟的能力，因此您无法生成可以优化的代码对于 vfpv4，但将在 vfpv3 上运行软件仿真）

于 2012-04-20T19:05:59.247 回答