0% found this document useful (0 votes)
18 views

Jan 2018

Uploaded by

murthyvc
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
0% found this document useful (0 votes)
18 views

Jan 2018

Uploaded by

murthyvc
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/ 2
Save trees use e-Question Paper Go green DOWNLOAD THIS FREE AT www.viuresource.com ow [TTT Seventh Semester B.E. Degree Examination, Dec.2017/Jan.2013 Advanced Computer Architectures : lacie PPT ain oti i at least TWO questions from each, a PART-A ee ee 48? ies pee ee ees ie 7 E i ‘Assume a disk subsystem wth the lowing compagens yl MITE. 3 Tks each rated at 1,000,000 he MITE i * 1 SCSI controfier, $00,000 —hour F ae * {Power supply, 200,000 hour MTT ae 31 Pan 200,000 —bour MTT. is +1 SeSt cable, 1,000,000 ~ hour Using the simplifying sssumptions th are exponentially distributed and that uy fil we nope spe he amar nol cnr) {__ © Wrtemicenteperimnes a 7 (eimariy | 12 a Enlist the ppetine hazards. Also . aoa Ee 7 8 Withan ad of « eat tnctiona [scuss the classic 5 stage pipeline for a Rise iz processor, that highlight rygghffiows through the data path (loNeia) $2 3 a. What do you mean Qe? Explain the significance of it. Further, discuss the bY various types of limi inset can be achieved by Soop uncoling. (10 Marks) a s b. What is dynamic ion” ‘the state transition diagram for a 2-bit prediction scheme i aud explain. (or Maris . bgycatng predictors and Tournament predictors. (09 ri) z fps the dient strategies employed to exploit Instruction Level Parallelism i and state dynamic scheduling ‘io Maris) Ho. Fc a sc aretha in exhancog the pavers ot PEs butters FE i) culation i prediction. omar a5 ean i 5 Supe you want to achieve a speedup of 80 with 100 processors. What fraction of the computation canbe sequonta!? (omar) j Bae SES Ga tana amiable? i tiprocesor, indicating the sat ransition diagram explicitly. (o7Maris) a What do you understand by memory consistently? Explain furthermore, discuss how relaxed consistently modes allow reads ond wre to complets out of order orMars) Lor BRANCHES | ALL SEMESTERS | NOTES | QUESTON PAPERS | LAB MANUALS A Viuresource Go Green initiative Save trees use e-Question Paper Go green DOWNLOAD THIS FREE AT www.viuresource.com Ic 6 a. Briefly explain the six basic cache optimization employed to impy mance. (9 Maris) b. Indicate the distinguish features of the following techniques embbygffto finprove cache behavior i) Compulsory misses i) Capacity misses 4if)_ Conflict misses (06 Marks) , Inbricf, discuss the four memory hierarchy questions fo 1 (os marks) 7a. Briefly explain the eleven advanced optimizations. ormance, (2 Maris) Explain how the protection of processes is accompli via We following : ) Virtual memory it) Virtual machines. re (08 Marks) fechniques are useful in uncovering sequences of straight sine code. (Oo Marks) the TA-64 architecture, that hold the ao Marks) 8a. Discuss how software pipelining and 1 the parallelism among instructions by c1 . Explain the five dierene execu comreponding mG 2of2 BRANCHES | ALL SEMESTERS | NOTES | QUESTON PAPERS | LAB MANUALS A Viuresource Go Green initiative

You might also like