![]() The average clock per instructions (CPI) would be computed with the following formula:ĬPI = (step 1 cost) + (steps 2,3,5 cost) + (step 4 cost) To get good processor performance the average times to fetch instructions and to access data from memory must be reduced.Īssume that every instruction needs to be fetched from memory, every memory reference instruction needs one memory access, and one third of the instructions are a memory reference, and step 4 for instruction that do not have a memory reference takes one cycle. Thus, an access to main memory is very expensive, over 100 clock cycles. Modern processors typically have a clock cycle of 0.5ns while accesses to main memory are 50ns or more. However, for steps 1 and 4 accessing main memory may take much longer than one cycle. Decode instruction and fetch register operandsĪt a minimum it takes one processor clock cycle to do each step.The simple programmer's model of processor executing machine language instruction is a loop of the following steps each step finished before moving on the the next step:
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |