how to initialize and process arrays in arm neon assembly -

i want convert c program arm neon assembly:

int main() {     int str1[]={1,2,3,4,5,6,7,8,9,10};     int str2[]={11,12,3,4,8,1,4,5,8,3};     int str3[10],i;      for(i=0;i<10;i++)     {         str3[i] = str1[i]+str2[i];     } } 

thanks.

let's cheat , use <arm_neon.h> in gcc , see code gcc generates (neon-add.c):

#include <assert.h> #include <stdio.h> #include <arm_neon.h>  #define array_len(a) (sizeof(a)/sizeof((a)[0]))  __attribute__((noinline, noclone)) static void print(int r[]) {     int i;     (i = 0; < 10; i++) {         printf("%d: %d\n", i, r[i]);     } }  int main() {     int i, j;     int str1[]={1,2,3,4,5,6,7,8,9,10};     int str2[]={11,12,3,4,8,1,4,5,8,3};     int result[10];     enum {         width = 2,     };     int *s1, *s2, *res;      (i = 0, j = 0, s1 = str1, s2 = str2, res = result; < array_len(str1);             i+= width, j++, s1 += width, s2 += width, res += width) {         int32x2_t t1, t2;         t1 = vld1_s32(s1);         t2 = vld1_s32(s2);         t2 = vadd_s32(t2, t1);         vst1_s32(res, t2);     }      print(result);      return 0; } 

ask gcc assembly with:

$ arm-linux-gnueabihf-gcc -os -mfpu=neon -s neon-add.c  

and arm assembly in unified syntax:

    .syntax unified     .arch armv7-a     .eabi_attribute 27, 3     .eabi_attribute 28, 1     .fpu neon     .eabi_attribute 20, 1     .eabi_attribute 21, 1     .eabi_attribute 23, 3     .eabi_attribute 24, 1     .eabi_attribute 25, 1     .eabi_attribute 26, 2     .eabi_attribute 30, 4     .eabi_attribute 34, 1     .eabi_attribute 18, 4     .thumb     .file   "neon-add.c"     .text     .align  1     .thumb     .thumb_func     .type   print, %function print:     @ args = 0, pretend = 0, frame = 0     @ frame_needed = 0, uses_anonymous_args = 0     push    {r3, r4, r5, lr}     mov r5, r0     movs    r4, #0 .l2:     mov r1, r4     ldr r2, [r5, r4, lsl #2]     ldr r0, .l4     adds    r4, r4, #1     bl  printf     cmp r4, #10     bne .l2     pop {r3, r4, r5, pc} .l5:     .align  2 .l4:     .word   .lc2     .size   print, .-print     .section    .text.startup,"ax",%progbits     .align  1     .global main     .thumb     .thumb_func     .type   main, %function main:     @ args = 0, pretend = 0, frame = 120     @ frame_needed = 0, uses_anonymous_args = 0     push    {r4, r5, lr}     sub sp, sp, #124     ldr r4, .l9     mov r5, sp     ldmia   r4!, {r0, r1, r2, r3}     stmia   r5!, {r0, r1, r2, r3}     ldmia   r4!, {r0, r1, r2, r3}     stmia   r5!, {r0, r1, r2, r3}     ldmia   r4, {r0, r1}     adds    r4, r4, #8     stmia   r5, {r0, r1}     add r5, sp, #40     ldmia   r4!, {r0, r1, r2, r3}     stmia   r5!, {r0, r1, r2, r3}     ldmia   r4!, {r0, r1, r2, r3}     stmia   r5!, {r0, r1, r2, r3}     movs    r3, #0     ldmia   r4, {r0, r1}     stmia   r5, {r0, r1}     b   .l7 .l8:     vld1.32 {d16}, [r2]     vld1.32 {d17}, [r1]     vadd.i32    d16, d17, d16     vst1.32 {d16}, [r0] .l7:     add r4, sp, #40     add r2, sp, #80     adds    r1, r3, r4     add r4, sp, #0     adds    r0, r3, r2     adds    r2, r3, r4     adds    r3, r3, #8     cmp r3, #48     bne .l8     add r0, sp, #80     bl  print     movs    r0, #0     add sp, sp, #124     pop {r4, r5, pc} .l10:     .align  2 .l9:     .word   .lanchor0     .size   main, .-main     .section    .rodata     .align  2 .lanchor0 = . + 0 .lc0:     .word   1     .word   2     .word   3     .word   4     .word   5     .word   6     .word   7     .word   8     .word   9     .word   10 .lc1:     .word   11     .word   12     .word   3     .word   4     .word   8     .word   1     .word   4     .word   5     .word   8     .word   3     .section    .rodata.str1.1,"ams",%progbits,1 .lc2:     .ascii  "%d: %d\012\000"     .ident  "gcc: (crosstool-ng linaro-1.13.1-4.7-2013.02-01-20130221 - linaro gcc 2013.02) 4.7.3 20130205 (prerelease)"     .section    .note.gnu-stack,"",%progbits