(25 points) Performance of a MIPS program

(The following code fragment processes two single-precision floating-point arrays A and B, and modifies the array B.

Each array consists of 500 single-precision floats.

The addresses of A and B are stored in $a0 and $a1 respectively.

Note that there is an outer loop and an inner loop in the MIPS assembly language code.

(Say thank you! you dont have to write these MIPS codes)

li move	$a2, 500 $t0, $a0	# #	$a2 = 500 $t0 = address of array A
move	$t4, $zero	#	$t4 = 0
mtc1	$zero, $f4	#	$f4 = 0 (move to coprocessor 1)
outer: lwc1	$f0, ($t0)	# #	outer loop load single-precision float
add.s move	$f4, $f4, $f0 $t1, $a1	#	$t1 = address of Array B
move	$t5, $zero	#	$t5 = 0
inner: lwc1	$f1, ($t1)	# #	inner loop load single-precision float
mul.s div.s swc1 addi addi bne	$f2, $f1, $f0 $f3, $f2, $f4 $f3, ($t1) $t1, $t1, 4 $t5, $t5, 1 $t5, $a2, inner	# #	store single-precision float end of inner loop
addi addi bne	$t0, $t0, 4 $t4, $t4, 1 $t4, $a2, outer	#	end of outer loop

The above code is executed on a processor with a 2 GHz clock that requires the following number of cycles for each instruction:

Instructions	Cycles
Li, move, mtc1, addi	3
Lwc1, swc1	5
Add.s, mul.s	10
div.s	20
bne	4

(5 pts) Count the total number of instructions executed by the above code fragment, including those executed outside the outer loop.

(8 pts) How many cycles does it take to execute the above code?

(4 pts) What is the execution time in nanoseconds?

(4 pts) What is the average CPI for the above code?

(4 pts) What is the MIPS rate for the above code?