A computer architect needs to design the pipeline of a new microproces.docx
A computer architect needs to design the pipeline of a new microprocessor. She has an example program with 106 instructions. Each instruction takes 600 ps to finish. a. How long does it take to execute this program on a non-pipelined, single-cycle processor? b. Assume the current state-of-the-art pipeline has 30 stages. Assume also that the stages are perfectly balanced. How much speedup will it achieve compared to the non-pipelined processor? c. Realistically, we cannot achieve ideal speedup due to the overhead of implementing pipelining stages (e.g. imperfectly balanced stages, adding pipeline registers, etc). Does this overhead affect the instruction latency, instruction throughput, or both? For each metric affected, is the effect significant? Why or why not? Solution a) Answer:It takes 100 ps × 106instructions = 100 microseconds to execute on a nonpipelined processor. b) Answer:A perfect 20-stage pipeline would speed up the execution by 20 times (ignoring start and end transientsin the pipeline). c) Answer:Pipeline overhead impacts both latency and throughput .
A computer architect needs to design the pipeline of a new microproces.docx
A computer architect needs to design the pipeline of a new microprocessor. She has an example program with 106 instructions. Each instruction takes 600 ps to finish. a. How long does it take to execute this program on a non-pipelined, single-cycle processor? b. Assume the current state-of-the-art pipeline has 30 stages. Assume also that the stages are perfectly balanced. How much speedup will it achieve compared to the non-pipelined processor? c. Realistically, we cannot achieve ideal speedup due to the overhead of implementing pipelining stages (e.g. imperfectly balanced stages, adding pipeline registers, etc). Does this overhead affect the instruction latency, instruction throughput, or both? For each metric affected, is the effect significant? Why or why not? Solution a) Answer:It takes 100 ps × 106instructions = 100 microseconds to execute on a nonpipelined processor. b) Answer:A perfect 20-stage pipeline would speed up the execution by 20 times (ignoring start and end transientsin the pipeline). c) Answer:Pipeline overhead impacts both latency and throughput .
More Related Content
Similar to A computer architect needs to design the pipeline of a new microproces.docx
Similar to A computer architect needs to design the pipeline of a new microproces.docx(20)
More from tkathryn
More from tkathryn(20)
Recently uploaded
Recently uploaded(20)
A computer architect needs to design the pipeline of a new microproces.docx
- 1. A computer architect needs to design the pipeline of a new microprocessor. She has an example program with 106 instructions. Each instruction takes 600 ps to finish. a. How long does it take to execute this program on a non-pipelined, single-cycle processor? b. Assume the current state-of-the-art pipeline has 30 stages. Assume also that the stages are perfectly balanced. How much speedup will it achieve compared to the non-pipelined processor? c. Realistically, we cannot achieve ideal speedup due to the overhead of implementing pipelining stages (e.g. imperfectly balanced stages, adding pipeline registers, etc). Does this overhead affect the instruction latency, instruction throughput, or both? For each metric affected, is the effect significant? Why or why not? Solution a) Answer:It takes 100 ps × 106instructions = 100 microseconds to execute on a nonpipelined processor. b) Answer:A perfect 20-stage pipeline would speed up the execution by 20 times (ignoring start and end transientsin the pipeline). c) Answer:Pipeline overhead impacts both latency and throughput