100% satisfaction guarantee Immediately available after payment Both online and in PDF No strings attached
logo-home
Previously searched by you
Previously searched by you
logo
CISC 360 Final Exam Questions & Answers 2024/2025 $9.49   Add to cart
Quickly navigate to
Preview
  2.  
  3. CISC 360
  4.  
  5. CISC 360

Exam (elaborations)

CISC 360 Final Exam Questions & Answers 2024/2025
 13 views  0 purchase
  • Course
  • CISC 360
  • Institution
  • CISC 360

CISC 360 Final Exam Questions & Answers 2024/2025 What is Data Level Parallelism? - ANSWERSParallelism due to executing essentially the same code on a large number of objects. How is DLP linked to Flynn's Taxonomy? - ANSWERSLinked to SIMD and SIMT. When you have lots of cores and make co...

[Show more]

Preview 3 out of 17  pages

Document information

  • August 7, 2024
  • 17
  • 2024/2025
  • Exam (elaborations)
  • Questions & answers

Subjects

  • cisc 360 final exam questions answers

Written for

  • CISC 360
  • CISC 360

Seller

avatar-seller
Bensuda

Reviews received

Content preview

CISC 360 Final Exam Questions &
Answers 2024/2025

What is Data Level Parallelism? - ANSWERSParallelism due to executing essentially the same code on a
large number of objects.



How is DLP linked to Flynn's Taxonomy? - ANSWERSLinked to SIMD and SIMT.



When you have lots of cores and make computations go faster, you would call this____? -
ANSWERSLatency Oriented or Throughput Oriented.



What type of unit is Latency Oriented? - ANSWERSCPU.



What type of unit is Throughput Oriented? - ANSWERSGPU.



What are the characteristics of Latency Oriented designs? - ANSWERSPowerful ALU which reduces
operation latency.



Large caches that convert long latency memory accesses to short latency cache accesses.



Sophisticated control which includes Branch Prediction for reduced branch latency and Data Forwarding
for reduced data latency.



What are the characteristics of Throughput Oriented designs? - ANSWERSSmall caches that boost
Memory Throughput.



Simple control that feature no branch prediction, and data forwarding, but has more ALU devoted to
floating point computation.

,Energy efficient ALUs that have long latency, but are heavily pipelined for high throughput.



Require massive number of threads to tolerate latencies. These threads include Threading Logic and
Thread State.



What are the best applications for a CPU? - ANSWERSFor sequential parts where latency matters.



What are the best applications for a GPU? - ANSWERSFor parallel parts where throughput matters.



Can be 10x faster than CPUs for parallel code.



What is the SIMT model? - ANSWERSSingle Instruction Multiple Thread.



What is the GPU chip design? - ANSWERSGPU core is the Stream Processor.



Stream Processors are grouped in Stream Multiprocessors.



Stream Processors are basically SIMD processors.



What is a PCI Express Bus? - ANSWERSAllows transfer between chip and the GPU.



What were the versions of PCI Express? - ANSWERS1.) PCI Express (PCI-E) delivered 250MB/s per lane,
giving a total of 8GB/s for a 16 lane bus.



2.) PCI-E delivered 16GB/s for a 16 lane bus.



3.) PCI-3 Delivered 32GB/s for a 16 lane bus.



What happens when there are more lanes in a bus? - ANSWERSThe more lanes, the faster the transfer.

, What are the features of a CPU memory hierarchy? - ANSWERS1.) Big caches.



2.) Few threads.



3.) Modest memory bandwidth.



4.) Rely mainly on caches and prefetching.



What are the features of a GPU memory hierarchy? - ANSWERS1.) Small caches.



2.) Many threads.



3.) Huge memory bandwidth.



4.) Rely mainly on multi-threading.



What is the roofline model? - ANSWERSThe core perimeter is "arithmetic Intensity".



Arithmetic Intensity is the ratio of total floating-point operations to total data movement (bytes).



How do you calculate Theoretical Bandwidth? - ANSWERS(Memory Frequency x [Bus Width] / 8) x
Operations per Cycle = Bandwidth in GB/s



What do the number of operations per cycle depend on? - ANSWERSOn the core.



What is the major drawback of a CPU + GPU model? - ANSWERSData movement cost, which is when
computations are offloaded from CPU to GPU.

The benefits of buying summaries with Stuvia:

Guaranteed quality through customer reviews

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

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

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 Bensuda. Stuvia facilitates payment to the seller.

Will I be stuck with a subscription?

No, you only buy these notes for $9.49. You're not tied to anything after your purchase.

Can Stuvia be trusted?

4.6 stars on Google & Trustpilot (+1000 reviews)

81989 documents were sold in the last 30 days

Founded in 2010, the go-to place to buy study notes for 14 years now

Start selling
$9.49
  • (0)
  Add to cart