Unexpected behaviour calling an assembly function from c code. Is a bug?

#include <stdio.h>
#include <time.h>
#include <stdint.h>
#include <stdlib.h>
#include <string.h>

extern void move32b_LDM(uint32_t *ori, uint32_t size, uint32_t *dest);
extern void move32b_LDR(uint32_t *ori, uint32_t size, uint32_t *dest);

int main(int argc, char* argv[])
{
    uint32_t *origen = malloc(1 << 27);
    uint32_t *destino = malloc(1<<27);
    if (origen == 0 || destino == 0)
        return -1;
    for (unsigned int i=0;i< (1<<25);i++)
        *(origen+i) = i;
    
    clock_t start = clock();
    memcpy(destino,origen, 1 << 27);
    clock_t finish = clock();
    printf("Time of memcpy: %f\n", ((double)(finish - start))/CLOCKS_PER_SEC);

    start = clock();
    move32b_LDM(origen,1<<27,destino);
    finish = clock();
    printf("Time of LDM: %f\n", ((double)(finish - start))/CLOCKS_PER_SEC);


    start = clock();
    move32b_LDR(origen,1<<27,destino);
    finish = clock();
    printf("Time of LDR: %f\n", ((double)(finish - start))/CLOCKS_PER_SEC);

    return 0;
}

    .global   move32b_LDM
    .global move32b_LDR
    .p2align 2
    .type    move32b_LDM,%function

    .section .text

move32b_LDM:
.func
push {R4,R5,R6,R7,R8}
ADD R8,R2,R1
loop: LDMIA R0!,{R4,R5,R6,R7}
    STMIA R2!, {R4,R5,R6,R7}
    CMP R8,R2
    BNE loop
pop {R4,R5,R6,R7,R8}
MOV PC,LR
.endfunc

    .type   move32b_LDR,%function
move32b_LDR:
.func
push {R4,R5,R6,R8}
MOV R5,#0
MOv R6,R5
ADD R8,R2,R6
loop2: LDR R4,[R0],#4
    STR R4,[R2],#4
    CMP R8,R2
    BNE loop2
pop {R4,R5,R6,R8}
MOV PC,LR
.endfunc