## High Performance Computing Multiple Choice Questions |High Performance Computing Solved MCQ Questions with Answer PDF

High Performance Computing MCQs:  HPC has been a integral part of academic research & industry innovation for decades. It helps engineers, data scientists, designers, and other researchers solve large, complex problems in far less time and at less cost than traditional computing. High Performance Computing have three key components namely compute, network, and storage. Here you will get the High Performance Computing MCQ quiz and PDF format are also given below. Read the below High performance Computing questions with confident to prepare the competitive exams, entrance exams and interview. These all are most important questions, so candidate study for this topic thoroughly. Practice this kind of MCQ quiz daily it will definitely improve your knowledge, skills, reading ability etc.

### High Performance MCQ Quiz and online Test

1. constant
2. decreases
3. increase
4. None

#### 2. In DNS algorithm of matrix multiplication it used_________________

1. 2d partition
2. 3d partition
3. 1d partition
4. All of above

#### 3. The load imbalance problem in Parallel Gaussian Elimination: can be alleviated by using a _________ mapping

1. cyclic
2. acyclic
3. All of above
4. None of above

#### 4. Speedup tends to saturate and efficiency _____ as a consequence of Amdahl’s law.

1. constant
2. increase
3. decreases
4. None of these

1. 3
2. 1
3. 4
4. 2

#### 6. Efficient implementation of basic communication operation can improve ____________

1. communication
2. performance
3. algorithm
4. None of above

#### 7. Wimple at way to send p-1 messages from source to the other p-1 processors________

1. communication
2. algorithm
4. concurrency

#### 8. Group communication operations are built using _____ Messaging primitives

1. one-to-all
2. point-to-point
3. all-to-one
4. None

#### 9. The processors compute _________ product of the vector element and the local matrix.

1. global
2. local
3. All of above
4. None of above

#### 10. The performance of quicksort depends critically on the quality of the ______

1. pivot
2. center element
3. non-pivote
4. Len of array

#### 11. One processor has a piece of data and it need to send to everyone is __________

1. all-to-one
2. point -to-point
3. one -to-all
4. All of above

#### 12. The fundamental operation of comparison-based sorting is ________

1. sorting
2. searching
3. compare-exchange
4. swapping

#### 13. Which of the following is not a stable sorting algorithm in its typical implementation.

1. merge sort
2. insertion sort
3. bubble sort
4. quick sort

#### 14. ______ can be comparison-based or non comparison-based.

1. sorting
2. searching
3. All of above
4. None of above

#### 15. Breadth First Search is equivalent to which of the traversal in the Binary Trees?

1. level-order traversal
2. pre-order traversal
3. post-order traversal
4. in-order traversal

1. searching
2. sorting
3. lookup
4. none

#### 17. ______________ algorithms use auxiliary storage (such as tapes and hard disks) for sorting because the number of elements to be sorted is too large to fit into memory.

1. internal searching
2. internal sorting
3. external searching
4. external sorting

#### 18. Which of the following is not an application of Breadth First Search?

1. when the graph is a linked list
2. when the graph is a binary tree
3. All of above
4. None of above

#### 19. In ___________, the number of elements to be sorted is small enough to fit into the process’s main memory

1. internal sorting
2. external sorting
3. external searching
4. internal searching

#### 20. In CUDA, a single invoked kernel is referred to as a ____________

1. grid
3. block
4. None of mentioned above

#### 21. A CUDA program is comprised of two primary components: a host and a ____________.

1. CPU kernel
2. GPU kernel
3. OS
4. None of above

#### 22. A grid is comprised of ________ of threads.

1. bunch
2. block
3. host
4. All of above

#### 23. The computer cluster architecture emerged as an alternative for ____________

1. super computers
2. workstation
3.  isa
4. distributed systems

#### 24. CUDA supports ____________ in which code in a single thread is executed by all other threads.

4. All of above

#### 25.  _____ method is used in centralized systems to perform out of order execution.

1. score boarding
2. optimizing
3. scorecard
4. redundancy

#### 26. _______ became the first language specifically designed by a GPU Company to facilitate general purpose computing on __________.

1. c, cpus
2. java, cpus
3. python, gpus
4. cuda c, gpus

#### 27. Each warp of GPU receives a single instruction and “broadcasts” it to all of its threads. It is a ____________ operation.

1. simt (single instruction multiple thread)
2. simd (single instruction multiple data)
3. sist (single instruction single thread)
4. sisd (single instruction single data)

#### 28. ______ is Callable from the host.

1. __global__
2. _host_
3.  _device_
4. None of these

#### 29. The CUDA architecture consists of ___________ for parallel computing kernels and functions.

1. cisc instruction set architecture
2. zisc instruction set architecture
3. risc instruction set architecture
4. ptx instruction set architecture

#### 30. CUDA stands for__________ designed by NVIDIA

1. complex unstructured distributed architecture
2. compute unified device architecture
3. common union discrete architecture
4. complex unidentified device architecture

#### 31. The time lost due to branch instruction is often referred to as ___________.

1. delay
2. latency
3. branch penalty
4. None

1. __global__
2. void
3.  _host_
4. _device_

#### 33. Triple angle brackets mark in a statement inside main function, what does it indicates?

1. a call from device code to host code
2. a call from host code to device code
3. greater than comparison
4. less than comparison

Answer: a call from host code to device code

#### 34. Any condition that causes a processor to stall is called as _________.

1. page fault
2. system error
3. hazard
4. None

#### 35. What makes a CUDA code runs in parallel?

1. first parameter value inside triple angle bracket (n) indicates execution’s of kernel n times in parallel
2. kernel name outside triple angle bracket indicates execution’s of kernel n times in parallel
3. All of above
4. None of above

Answer: first parameter value inside triple angle bracket (n) indicates execution’s of kernel n times in parallel

1. bunch
3. host
4. None

#### 37. _________ is Callable from the device only.

1.  _device_
2. _host_
3. __global__
4. None of above

#### 38. Calling a kernel is typically referred to as _________.

1. kernel termination
2. kernel initialization
4. kernel invocation

1. cuda
2. cda
3. cud
4. pta