Hi Guys,
I have a ARM NEON Cortex-A8 based processor target. I was optimizing my code by making use of NEON. But when I compile my code I get this strange error. Don't know how to fix this.
I'm trying to compile the following code (PART 1) using Code Sourcery (PART2) on my host. And I get this strange error (PART3). Am I doing something wrong here? Can anyone else compile this and see if they also get the same compilation error?
The strange part is, in the code if I comment out the else if(step_size == 4)
part of the code, then the error vanishes. But, sadly my optimization is not complete with out it, so I must have it.
At first I thought its the problem with CodeSourcey compiler (on my host), so I compiled the program on my target directly (My target runs on Ubuntu). I used gcc there and once again, I get the same error and when I comment out the else if(step_size == 4)
part, then the error vanishes.
Help!
PART 1
#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);
}
PART 2
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"
PART 3
../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