Other
Workshop4 p2
- Course
- Institution
Workshop questions/answers for preparing for exams
[Show more]
Seller
Follow
mj_1
Content preview
Workshop 4 Part 2 – Parallel systems and PerformanceParallel Architecture
1.Explain the concept of pipelining. What is a theoretical maximum speedup possible for a 6-stage
pipeline? What does prevent the pipelines to achieve the maximum performance?
Pipelining is the process of fetch-decode-execute , Pipelining is the ability to overlap execution of
different instructions at the same time. It exploits parallelism among instructions and is NOT visible
to the programmer, allowing a higher number of instructions to be executed in a given time.
- max possible speed is 6 times speed up.
- Structural hazards, Data hazards and Control hazards stop maximum performance
2. Explain the difference between the CPU’s and GPU’s architectures. Which one is better suited for
real-time applications and why?
The main difference between CPU and GPU architecture is that a CPU is designed to handle a wide-
range of tasks quickly (as measured by CPU clock speed), but are limited in the concurrency of tasks
that can be running. A GPU is designed to quickly render high-resolution images and video
concurrently tend to have high throughput meaning more instructions at a time.
-GPU is better for crypto mining, medical imaging, computer vision and data science (optimized for
parallel tasks)
-CPU is better for multitasking and real time applications (optimised for low latency computations
and faster clock speeds)
3.The 5 equal stages (Fetch, Decode, Execute, Memory, Write-back) of the two processors A and B
have the latencies of 350ps and 100ps, respectively (Pico- (symbol p) is a unit prefix in the metric
system denoting one trillionth, a factor of 10−12). Assume that when pipelining, each pipeline stage
costs 20ps extra time for the registers between pipeline stages. What is the latency and throughput
for non-pipelined and pipelined processing for each of the processors?
Throughput = 1 second / how many fetch-decode-execute-memory-write instruction cycles
A - Non-Pipeline : Latency = 350 * 5 (stages) = 1750 ps (each stage is 350 ps)
Throughput = 10^12 (1 second in pico seconds) / 1750
A - Pipeline: Latency = 370 * 5 = 1850 ps
Throughput = 10^
B – Non-Pipeline : Latency = 100 * 5 = 500 ps
Throughput = 10^12ps / 500ps
B – Pipeline : Latency = 120 * 5 = 600 ps
Throughput = 10^
The benefits of buying summaries with Stuvia:
Guaranteed quality through customer reviews
Stuvia customers have reviewed more than 700,000 summaries. This how you know that you are buying the best documents.
Quick and easy check-out
You can quickly pay through credit card or Stuvia-credit for the summaries. There is no membership needed.
Focus on what matters
Your fellow students write the study notes themselves, which is why the documents are always reliable and up-to-date. This ensures you quickly get to the core!
Frequently asked questions
What do I get when I buy this document?
You get a PDF, available immediately after your purchase. The purchased document is accessible anytime, anywhere and indefinitely through your profile.
Satisfaction guarantee: how does it work?
Our satisfaction guarantee ensures that you always find a study document that suits you well. You fill out a form, and our customer service team takes care of the rest.
Who am I buying these notes from?
Stuvia is a marketplace, so you are not buying this document from us, but from seller mj_1. Stuvia facilitates payment to the seller.
Will I be stuck with a subscription?
No, you only buy these notes for $4.50. You're not tied to anything after your purchase.
Can Stuvia be trusted?
4.6 stars on Google & Trustpilot (+1000 reviews)
67474 documents were sold in the last 30 days
Founded in 2010, the go-to place to buy study notes for 14 years now