High Performance Computing Very Importany PDF

Preview

Summary

High Performance Computing most generally refers to the practice of aggregating computing power in a way that delivers much higher performance than one could get out of a typical desktop computer or workstation in order to solve large problems in science, engineering, or business.
It turns out...

Description

High Performance Computing Solved Mcqs set 10

226. ______ have been developed specifically for pipelined systems. A. utility software B. speed up utilities C. optimizing compilers D. none of the above Answer: C

227. Which of the following is a combination of several processors on a single chip? A. multicore architecture B. risc architecture C. cisc architecture D. subword parallelism Answer: A

228. The important feature of the VLIW is ..... A. ilp B. cost effectiveness C. performance D. none of the mentioned Answer: A

229. The parallel execution of operations in VLIW is done according to the schedule determined by ..... A. sk scheduler B. interpreter C. compiler D. encoder Answer: C

230. The VLIW processors are much simpler as they do not require of .....

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 10

A. computational register B. complex logic circuits C. ssd slots D. scheduling hardware Answer: D

231. The VLIW architecture follows ..... approach to achieve parallelism. A. misd B. sisd C. simd D. mimd Answer: D

232. Which of the following is not a Pipeline Conflicts? A. timing variations B. branching C. load balancing D. data dependency Answer: C

233. Which of the following statements is NOT TRUE for Internal Sorting algorithms A. usually deal with small number of elements B. no of elements must be able to fit in process\s main memory C. use auxilliary memory like tape or hard disk D. ususally are of type compare-exchange Answer: C

234. In sorting networks for INCREASING COMPARATOR with input x,y select the correct output X', Y' from the following options A. x\ = min { x , y } and y\ = min { x , y }

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 10

B. x\ = max { x , y } and y\ = min { x , y } C. x\ = min { x , y } and y\ = max{ x , y } D. x\ = max { x , y } and y\ = max { x , y } Answer: C

235. In sorting networks for DECREASING COMPARATOR with input x,y select the correct output X', Y' from the following options A. x\ = min { x , y } and y\ = min { x , y } B. x\ = max { x , y } and y\ = min { x , y } C. x\ = min { x , y } and y\ = max{ x , y } D. x\ = max { x , y } and y\ = max { x , y } Answer: B

236. Which of the following is TRUE for Bitonic Sequence a) Monotonically increasing b) Monotonically Decreasing c) With cyclic shift of indices d) First increasing then decreasing A. a) and b) B. a) and b) and d) C. a) and b) and c) D. a) and b) and c) and d) Answer: D

237. Which of the following is NOT a BITONIC Sequence A. {8, 6, 4, 2, 3, 5, 7, 9} B. {0, 4, 8, 9, 2, 1} C. {3, 5, 7, 9, 8, 6, 4, 2} D. {1, 2, 4, 7, 6, 0, 1} Answer: D

238. The procedure of sorting a bitonic sequence using bitonic splits is called A. bitonic merge

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 10

B. bitonic split C. bitonic divide D. bitonic series Answer: A

239. While mapping Bitonic sort on Hypercube, Compare-exchange operations take place between wires whose labels differ in A. one bit B. two bits C. three bits D. four bits Answer: A

240. Which of following is NOT A WAY of mapping the input wires of the bitonic sorting network to a MESH of processes A. row major mapping B. column major mapping C. row major snakelike mapping D. row major shuffled mapping Answer: B

241. Which is the sorting algorithm in below given steps - 1. procedure X_SORT(n) 2. begin 3. for i := n - 1 downto 1 do 4. for j := 1 to i do 5. compare-exchange(aj, aj + 1); 6. end X_SORT A. selection sort B. bubble sort C. parallel selcetion sort D. parallel bubble sort Answer: B

242. The odd-even transposition algorithm sorts n elements in n phases (n is even), each of which requires ------------compare-exchange operations

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 10

A. 2n B. n2 C. n/2 D. n Answer: C

243. What is TRUE about SHELL SORT A. moves elements only one position at a time B. moves elements long distance C. during second phase algorithm switches to odd even transposition sort D. both 2 and 3 Answer: D

244. Which is the fastest sorting algorithm A. bubble sort B. odd-even transposition sort C. shell sort D. quick sort Answer: D

245. Quicksort's performance is greatly affected by the way it partitions a sequence. A. true B. false Answer: A

246. Pivot in Quick sort can be selected as A. always first element B. always last element C. always middle index element D. randomly selected element

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 10

Answer: D

247. Quick sort uses Recursive Decomposition A. true B. false Answer: A

248. In first step of parallelizing quick sort for n elements to get subarrays, which of the following statement is TRUE A. only one process is used B. n processes are used C. two processes are used D. none of the above Answer: A

249. In Binary tree representation created by execution of Quick sort, Pivot is at A. leaf node B. root of tree C. any internal node D. none of the above Answer: B

250. What is the worst case time complexity of a quick sort algorithm? A. o(n) B. o(n log n) C. o(n2) D. o(log n) Answer: C

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 11

251. What is the average running time of a quick sort algorithm? A. o(n) B. o(n log n) C. o(n2) D. o(log n) Answer: B

252. Odd-even transposition sort is a variation of A. quick sort B. shell sort C. bubble sort D. selection sort Answer: C

253. What is the average case time complexity of odd-even transposition sort? A. o(n log n) B. o(n) C. o(log n) D. o(n2) Answer: D

254. Shell sort is an improvement on A. quick sort B. bubble sort C. insertion sort D. selection sort Answer: C

255. In parallel Quick Sort Pivot is sent to processes by

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 11

A. broadcast B. multicast C. selective multicast D. unicast Answer: A

256. In parallel Quick Sort each process divides the unsorted list into A. n lists B. 2 lists C. 4 lists D. n-1 lists Answer: B

257. Time Complexity of DFS is? (V – number of vertices, E – number of edges) A. o(v + e) B. o(v) C. o(e) D. o(v*e) Answer: A

258. A person wants to visit some places. He starts from a vertex and then wants to visit every vertex till it finishes from one vertex, backtracks and then explore other vertex from same vertex. What algorithm he should use? A. bfs B. dfs C. prim\s D. kruskal\s Answer: B

259. Given an array of n elements and p processes, in the message-

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 11

passing version of the parallel quicksort, each process stores --------elements of array A. n*p B. n-p C. p/n D. n/p Answer: D

260. In parallel quick sort Pivot selecton strategy is crucial for A. maintaing load balance B. maintaining uniform distribution of elements in process groups C. effective pivot selection in next level D. all of the above Answer: D

261. In execution of the hypercube formulation of quicksort for d = 3, split along -----------dimention to partition sequence into two big blocks, one greater than pivot and other smaller than pivot as shown in diagram A. first B. scond C. third D. none of above Answer: C

262. Which Parallel formulation of Quick sort is possible A. shared-address-space parallel formulation B. message passing formulation C. hypercube formulation D. all of the above Answer: D

263. Which formulation of Dijkstra's algorithm exploits more parallelism

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 11

A. source-partitioned formulation B. source-parallel formulation C. partitioned-parallel formulation D. all of above Answer: B

264. In Dijkstra's all pair shortest path each process compute the singlesource shortest paths for all vertices assigned to it in SOURCE PARTITIONED FORMULATION A. true B. false Answer: A

265. A complete graph is a graph in which each pair of vertices is adjacent A. true B. false Answer: A

266. The space required to store the adjacency matrix of a graph with n vertices is A. in order of n B. in order of n log n C. in order of n squared D. in order of n/2 Answer: C

267. Graph can be represented by A. identity matrix B. adjacency matrix C. sprse list D. sparse matrix

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 11

Answer: B

268. to solve the all-pairs shortest paths problem which algorithm/s is/are used a) Floyd's algorithm b) Dijkstra's single-source shortest paths c) Prim's Algorithm d) Kruskal's Algorithm A. a) and c) B. a) and b) C. b) and c) D. c) and d) Answer: B

269. Simple backtracking is a depth-first search method that terminates upon finding the first solution. A. true B. false Answer: A

270. Best-first search (BFS) algorithms can search both graphs and trees. A. true B. false Answer: A

271. A* algorithm is a A. bfs algorithm B. dfs algorithm C. prim\s algorithm D. kruskal\s algorithm Answer: A

272. identify Load-Balancing Scheme/s A. asynchronous round robin B. global round robin

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 11

C. random polling D. all above methods Answer: D

273. important component of best-first search (BFS) algorithms is A. open list B. closed list C. node list D. mode list Answer: A

274. A CUDA program is comprised of two primary components: a host and a _____. A. gpu kernel B. cpu kernel C. os D. none of above Answer: A

275. The kernel code is dentified by the ________qualifier with void return type A. _host_ B. __global__ C. _device_ D. void Answer: B

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 12

276. the BlockPerGrid and ThreadPerBlock parameters are related to the ________ model supported by CUDA. A. host B. kernel C. thread abstraction D. none of above Answer: C

277. _________ is Callable from the device only A. _host_ B. __global__ C. _device_ D. none of above Answer: C

278. ______ is Callable from the host A. _host_ B. __global__ C. _device_ D. none of above Answer: B

279. ______ is Callable from the host A. _host_ B. __global__ C. _device_ D. none of above Answer: A

280. Cache memory works on the principle of

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 12

A. locality of data B. locality of memory C. locality of reference D. locality of reference & memory Answer: C

281. SIMD represents an organization that ______________. A.

refers to a computer system capable of processing

B. represents organization of single computer containing memory unit. C.

includes many processing units under the supervision

D.

none of the above.

several programs at the same time. a control unit, processor unit and a of a common control unit

Answer: C

282. Select different aspects of parallelism A. server applications utilize high aggregate network bandwidth B. scientific applications typically utilize high processing and memory system performance C. all of the above D. data intensive applications utilize high aggregate throughput Answer: D

283. Select correct answer: DRAM access times have only improved at the rate of roughly % per year over this interval. A. 20 B. 40 C. 50 D. 10 Answer: A

284. Analyze, if the second instruction has data dependencies with the first, but the third instruction does not, the first

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 12

A. out-of-order B. both of the above C. none of the above D. in-order Answer: B

285. Select the parameters which captures Memory system performance A. bandwidth B. both of the above C. none of the above D. latency Answer: C

286. Consider the example of a fire- hose. If the water comes out of the hose five seconds after the hydrant is turned on. Once the water starts flowing, if the hydrant delivers water at the rate of 15 gallons/second. Analyze the bandwidth and latency. A. bandwidth: 5*15 gallons/second and latency: 15 seconds B. bandwidth: 15 gallons/second and latency: 5 seconds C. bandwidth: 3 gallons/second and latency: 5 seconds D. bandwidth: 5 gallons/second and latency: 15 seconds Answer: C

287. Select alternate approaches for Hiding Memory Latency A. multithreading B. spatial locality C. all of the above D. prefeching Answer: D

288. Select which clause in OpenMP is similar to the private, except values of variables are initialized to corresponding values before the

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 12

A. firstprivate B. shared C. all of the above D. private Answer: B

289. Which of the following projects of Blue Gene is not in development? A. blue gene / m B. blue gene / p C. blue gene / q D. blue gene / l Answer: B

290. A decomposition can be illustrated in the form of a directed graph with nodes corresponding to tasks and edges indicating that the result of one task is required for processing the next. Such graph is called as A. task dependency graph B. task interaction graph C. process interaction graph D. process dependency graph Answer: B

291. In which case, the owner computes rule implies that the output is computed by the process to which the output data is assigned? A. output data decomposition B. both of the above C. none of the above D. input data decomposition Answer: B

292. Select relevant task characteristics from the options given below:

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 12

A. task sizes B. size of data associated with tasks C. all of the above D. task generation Answer: D

293. A classic example of game playing - each 15 puzzle board is the example of A. dynamic task generation B. none of the above C. all of the above D. static task generation Answer: B

294. Which model is equally suitable to shared-address- space or messagepassing paradigms, since the interaction is naturally two ways. A. master slave model B. data parallel model C. producer consumer or pipeline model D. work pool model Answer: B

295. In which type of the model, tasks are dynamically assigned to the processes for balancing the load? A. master slave model B. data parallel model C. producer consumer or pipeline model D. work pool model Answer: A

296. Select the appropriate stage of GPU Pipeline which receives commands from CPU and also pulls geometry information from system

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 12

memory. A. vertex processing B. memory interface C. host interface D. pixel processing Answer: D

297. In all-to-one reduction, data items must be combined piece-wise and the result made available at a processor. A. last B. target C. n-1 D. first Answer: C

298. Analyze the Cost of Scatter and Gather . A. t=ts log p + tw m (p-1) B. t=ts log p - tw m (p-1) C. t=tw log p - ts m (p-1) D. t=tw log p + ts m (p-1) Answer: B

299. All-to-all personalized communication is also known as . A. total exchange B. both of the above C. none of the above D. partial exchange Answer: B

300. All-to-all personalized communication is performed independently in each row with clustered messages of size on a mesh.

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 12

A. p B. m?p C. p?m D. m Answer: C

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 13

301. In All-to-All Personalized Communication on a Ring, the size of the message reduces by at each step A. p B. m-1 C. p-1 D. m Answer: A

302. All-to-All Broadcast and Reduction algorithm on a Ring terminates in steps. A. p+1 B. p-1 C. p*p D. p Answer: C

303. In All-to-all Broadcast on a Mesh, operation performs in which sequence? A. rowwise, columnwise B. columnwise, rowwise C. columnwise, columnwise D. rowwise, rowwise Answer: B

304. Messages get smaller in and stay constant in . A. gather, broadcast B. scatter , broadcast C. scatter, gather D. broadcast, gather Answer: C

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 13

305. The time taken by all-to- all broadcast on a ring is . A. t= (ts + twm)(p-1) B. t= ts logp + twm(p-1) C. t= 2ts(?p – 1) - twm(p-1) D. t= 2ts(?p – 1) + twm(p-1) Answer: B

306. The time taken by all-to- all broadcast on a mesh is . A. t= (ts + twm)(p-1) B. t= ts logp + twm(p-1) C. t= 2ts(?p – 1) - twm(p-1) D. t= 2ts(?p – 1) + twm(p-1) Answer: A

307. The time taken by all-to- all broadcast on a hypercube is . A. t= (ts + twm)(p-1) B. t= ts logp + twm(p-1) C. t= 2ts(?p – 1) - twm(p-1) D. t= 2ts(?p – 1) + twm(p-1) Answer: C

308. The prefix-sum operation can be implemented using the kernel A. all-to-all broadcast B. one-to-all broadcast C. all-to-one broadcast D. all-to-all reduction Answer: B

309. Select the parameters on which the parallel runtime of a program depends.

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 13

A. number of processors B. communication parameters of the machine C. all of the above D. input size Answer: D

310. The time that elapses from the moment the first processor starts to the moment the last processor finishes execution is called as

.

A. parallel runtime B. overhead runtime C. excess runtime D. serial runtime Answer: B

311. Select how the overhead function (To) is calculated. A. to = p*n tp - ts B. to = p tp - ts C. to = tp - pts D. to = tp - ts Answer: C

312. What is is the ratio of the time taken to solve a problem on a single processor to the time required to solve the same problem on a parallel computer with p identical processing elements? A. overall time B. speedup C. scaleup D. efficiency Answer: C

313. Which is alternative options for latency hiding?

Download more sets at McqMate.com

High Performance Computing Solved Mcqs set 13

A. increase cpu frequency B. multithreading C. increase bandwidth D. increase memory Answer: B

314. ______ Communication model is generally seen in tightly coupled system. A. message passing B. shared-address space C. client-server D. distributed network Answer: B

315. The principal parameters that determine the communication latency are as follows: A. startup time (ts) per-hop time (th) per-word transfer time (tw) B. startup time (ts) per-word transfer time (tw) C. startup time (ts) per-hop time (th) D. startup time (ts) message-packet-size(w) Answer: A

316. The number and size of tasks into which a problem is decomposed determines the __ A. granularity B. task C. dependency graph D. decomposition Answer: A

31...