Using one loop(for ,e.g. 1 X 16) instead of two(for-for, e.g. 4X4) for performance stuffs

for_loop_asm.c

/**
#compile: 
gcc -S -fverbose-asm -g -O0 <<FILE>>.c -O <<FILE>>.s
#asm
as -alhnd <<FILE>>.s > <<FILE>>.lst
#related course
https://www.youtube.com/watch?v=ulJm7_aTiQM
*/

/*using one loop instead of two (nested loop)*/
void loop_2d(void){
	/*tmp var to hold the res*/
	int v=0;
	/*const the first loop iteration len*/
	const int l=4;
	/*index for triggering event*/
	int i=0;
	/*for a lxl (16) loop*/
	for(int a=0;
		a<(l*l);
			a++){
		/*if index of first loop is equal to index of second loop*/
		if(i==a){
			/*update the res*/
			v = v + a;
			/*update the trigger index*/
			i = i + l 
				  + 1;
		}
	}
}

/*using nested loop*/
void loop_2d2d(void) {
	/*tmp var to hold the res*/
	int v=0;
	/*const the first loop iteration len*/
	const int l=4;
	/*for a li(4) loop*/
	for(int a=0;
			a<l;
				a++){
		/*for another li(4) loop(performance hit?)*/
		for(int b=0;
				b<l;
					b++){
			/*if index of first loop is equal to index of second loop*/
			if(b==a){
				/*update the trigger index*/
				v = v + a;
			}
		}
	}
	
}