Scribd
Upload
179 views6 pages

High Performance Computing (HPC) (80-Marks Sem8 - 2022)

Its a Final Question Paper of High Performance Computing [HPC]

Uploaded by

Shubham Patil
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
179 views6 pages

High Performance Computing (HPC) (80-Marks Sem8 - 2022)

Its a Final Question Paper of High Performance Computing [HPC]

Uploaded by

Shubham Patil
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
You are on page 1/ 6
Sem V7 Oe eee COMP OP: ABFAS HPC 26]os] vo22— University of Mumbai Examinations Summer 2022 Time: 2 hour 30 minutes ‘Max, Marks: 80 Q1. {Choose the correct option for following questions. All the Questions are compulsory and carry equal marks classified the computers on the basis of organization of the 1. ‘constituent elements in the computer. Flynn Option A: Handler Option B: Shore Option C: Feng Option D: ‘Two stage instruction pipeline has. : 2. fetch and Execute instruction Option A: * Fetch and Write Instruction Option B: Fetch and Decode Option c: Fetch and Memory Excess Option D: 28664C990148DE74AAA48B94567067DC Control hazards occurs due to. 3. ADD instruction Option A: MUL instruction Option B: DIV instruction Option c: ee Branch instruction Option D: 4, We anticipate which pages we are going to browse ahead of time and issue requests for them in advance are known as Option A: | Prefetching Option B: | Multithreading Option c: | Multitasking Option D: | Latency 5 Messages in Cut through routing are divided into? 28664C990148DE7444448894567067DC Packets. Option A: Segments Option B: Flits Option C: smaller units Option D: 6 The number and size of tasks into which a problem is decomposed determines the. of the decomposition. Option A: | Concurrency Option B: | Task dependency Option C: | Granularity Option D: | Efficiency suited to problems that are solved using the divide-and-conquer 7. strategy exploratory decomposition Option A: : Recursive Decomposition Option B: 28664C990148DE744A.A48B94567067DC speculative decomposition Option C: data decomposition Option D: 8. Which speedup could be achieved according to Amdahl’s law for infinite number of processors if 5% of a program is sequential and the remaining part is ideally parallel? Option A: | Infinite speedup Options: |5 Optionc: | 20 Option D: | 50 Non-blocking Message Passing Operations are generally 9. accompanied by a___ operation. Send Buffer Option A: Buffer Option B: check-status Option c: Receive Buffer Option D: 28664C990148DE74AAA48B94567067DC Which MPI function is used to determine the label of calling 10. | process? L MPLInit Option A: MPLComm_world Option B: MPI_Comm_size Option C: MPI_Comm_rank Option D: Qa. Solve any Two Questions out of Three 10 marks each (20 Marks Each) Discuss the categories of computers based on Flynn's A classification. Discuss in detail Pipeline hazards with its types. B c What are the limitations of Memory System Performance? 28664C990148DE74AAA48B94567067DC Q3. Solve any Two Questions out of Three 10 marks each (20 Marks Each) A Explain high performance computing platforms and their applications, Explain the different mapping techniques that are used for B load balancing. c Explain the Decomposition techniques in parallel computing. Q4. Solve any Two Questions out of Three 10 marks each (20 Marks Each) A State and expiain Amdahl’s law. What is the relevance of Amdahl's law in HPC? Write a MPI program to find sum of N numbers. B c Explain blocking and non-blocking communication using MPI. 28664C990148DE744AA48894567067DC.

You might also like