Reputation: 181
I was studying for my architecture final and came across the following lines of code:
for(i = 0; i <= N ;i++){
a[i] = b[i] + c[i];
}
The question is: "How does this code snippet demonstrate examples of temporal and spatial locality? Be sure to consider memory references for both data and instructions."
In terms of spatial locality I believe the code demonstrates it by accessing contiguous memory locations (a[0] then a[i] etc). However, my confusion comes with temporal locality. I'm not sure how this snippet of code references the same location within a small period of time? Any sort of help would be greatly appreciated.
Upvotes: 3
Views: 1542
Reputation: 2866
I'm not sure how this snippet of code references the same location within a small period of time.
In addition to txtechhelp's answer, the instructions that make up that for loop are also stored in memory. These instructions are "fetched" from memory/cache each time they are executed. Since each of these instructions is executed N+1 times in a very short time frame, this demonstrates temporal locality.
Upvotes: 0
Reputation: 6777
I'm not sure how this snippet of code references the same location within a small period of time?
As has been commented, the variable i
is accessed quite frequently, take the following line of code in your example:
a[i] = b[i] + c[i];
In this example, a
, b
and c
all presumably refer to array types pointing to different memory locations (even if contiguous, still different); however, the variable i
is read each time it is referenced to then determine the location of the array to reference.
Think of it this way:
get i from memory and store value in register x.
get value of b + [value in register x] from memory, store in register b.
get i from memory and store value in register y
get value of c + [value in register y] from memory, store in register c.
get i from memory and store value in register z
add value of [register b] to value in [register c] and store in memory location a + [value in register z]
An optimizing compiler would likely see this temporal locality and instead do something similar to the following:
get i from memory and store value in register i.
get value of b + [value in register i] from memory, store in register b.
get value of c + [value in register i] from memory, store in register c.
add value of [register b] to value in [register c] and store in memory location a + [value in register i]
It is in this way that i
has a temporal proximity between adjacent references.
I hope that can help.
Upvotes: 3