Chapter 6, Problem 6.34HW

Program Plan Intro

Given Information:

The following matrix transpose routine is given:

//array declaration

typedef int array[4][4];

//function to transpose array

void transpose2(array dst, array src)

{

//variable declaration

int i,j;

//iterate through first array

for(i=0;i<4;i++)

{

//iterate through second array

for(j=0;j<4;j++)

{

//transpose matrix

dst[j][i]=src[i][j];

}

}

}

The machine that runs the code has the following properties:

• The size of integer is “4”.
• The “src” array starts at address “0” and “dst” array starts at address “64”.
• There is a single L1 data cache that is direct-mapped, write-through and write allocate with a block size of 16 bytes.
• The cache has a total size of “32” bytes and the cache is initially empty.
• The only sources of read and write misses are accesses to the “src” and “dst” array.