Hi all,
It is a well known fact that performing an aligned vector load with an unaligned memory address should lead to segmentation fault.
However, when I do try to run code segment below using the same, i do not see any segmentation fault.
------------------------------------------------------------------------------------------------
#include <stdio.h>#include <stdlib.h>#include <time.h>#include "arm_neon.h"void add (uint32x4_t *data_a,uint32x4_t *data_b) { /* Set each sixteen values of the vector to 3. * * Remark: a 'q' suffix to intrinsics indicates * the instruction run for 128 bits registers. */ *data_a = vaddq_u32 (*data_a, *data_b);}int main (int argc,char** argv) { unsigned int n = atoi(argv[1]); /* Create custom arbitrary data. */ uint32_t uint32_data_a[n]; uint32_t uint32_data_b[n]; uint32_t uint32_data_c[n]; struct timespec start,end; for(uint32_t i = 1; i <= n ; i+=1) { uint32_data_a[i-1] = i; uint32_data_b[i-1] = i; uint32_data_c[i-1] = i; } /* Create the vector with our data. */ uint32x4_t data_a; uint32x4_t data_b; clock_gettime(CLOCK_MONOTONIC,&start); for(int count = 0; count < 10; count++) { for(int i = 1; i < n ; i+=4) { /* Load our custom data into the vector register. */ data_a = vld1q_u32 (uint32_data_a + i); data_b = vld1q_u32 (uint32_data_b + i); /* Call of the add3 function. */ add(&data_a,&data_b); vst1q_u32(uint32_data_c + i,data_a); } } clock_gettime(CLOCK_MONOTONIC,&end); double time_usec=(((double)end.tv_sec * 1000000 + (double)end.tv_nsec/1000) - ((double)start.tv_sec *1000000 + (double)start.tv_nsec/1000)); printf("Time taken for aligned load is : %fus and count is %d \n", time_usec/10,n ); for(uint32_t i = 0; i < n ; i++) printf("%2d ",uint32_data_c[i]); printf("\n"); return 0;}
----------------------------------------------------------------------------------------------------
Clearly almost every access to memory in this case is unaligned? is there any reason for this inconsistent behavior? Thanks in advance.
Aketh TM