1. Piplelining

Assume each instruction will divide into IF, Decode, EXE, MEM, and WB stages. Consider executing the following code on the pipelined datapath of figure on slide 21 of handout12.

add $2, $3, $1

sub $4, $3, $5

add $5, $3, $7

add $7, $6, $1

add $8, $2, $6

At the end of the 5th cycle of execution, which registers are being read and which register will be written?

1. Benchmark.

The table below shows the number of floating-point operations executed in three different programs and the runtime for those programs on three different computers:

Program

Floating-point
opeations

Execution time in seconds

Computer A

Computer B

Computer C

Program 1

5*10^9

2

5

10

Program 2

20*10^9

20

20

20

Program 3

40*10^9

200

50

15

Which computer is fastest according to total execution time? How many times as fast is it compared to the other two computers?



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *