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

Adca / Mca (Iii Year) 7t' Term-End Examination December, 2011 Cs-12: Computer Architecture

The document is a past exam paper for a Computer Architecture course. It contains 5 questions, with the first question having 4 parts (a-d). Question 1 asks students to analyze performance metrics like CPI, MIPS rate and execution time for a benchmark program run on a 150MHz processor. It also asks about limitations of superscalar design and characteristics of multi-threaded processor architectures. Questions 2-5 cover additional topics like instruction pipelining, cache organization, parallelism, and multiprocessor architectures.

Uploaded by

haider_ali980
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
30 views

Adca / Mca (Iii Year) 7t' Term-End Examination December, 2011 Cs-12: Computer Architecture

The document is a past exam paper for a Computer Architecture course. It contains 5 questions, with the first question having 4 parts (a-d). Question 1 asks students to analyze performance metrics like CPI, MIPS rate and execution time for a benchmark program run on a 150MHz processor. It also asks about limitations of superscalar design and characteristics of multi-threaded processor architectures. Questions 2-5 cover additional topics like instruction pipelining, cache organization, parallelism, and multiprocessor architectures.

Uploaded by

haider_ali980
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

No.

of Printed Pages : 3 ADCA / MCA (III Year) 7t' Term-End Examination December, 2011

I CS-12 I

CS-12 : COMPUTER ARCHITECTURE


Time : 3 hours Maximum Marks : 75

Note : Question no. 1 is compulsory. Answer any three questions from the rest.

1. (a) A 150 MHz processor was used to execute 9 a benchmar2k program with the following instruction and clock cycle counts.

Clock Instruction Instruction Type cycle count count Integer Arithmetic 60, 000 Data Transfer 40, 000 Floating Point 15, 000 Control transfer 8, 000
,--1 C1 Csi CA

Determine the effective CPI, MIPs rate and execution time for this program. CS-12 1 P.T.O.

(b) (c)

(d)

What are the factors limiting the degree of 5 Super Scalar design ? What is multi - threaded processor 8 architecture ? Explain its advantages and disadvantages in comparison to single threaded processors. Explain the architectural distinctions 8 between RISC and CLSC processors. Also, explain the concept of overlapping register windows in the SPARC architecture diagrammatically.

2. (a) Consider the following sequence of code and answer the following questions : : A =D + C S2 : C=E+B S3 : D=A+C S4 : E=F+D S5 : G=E+D S6 : D=A+F S7 : B=G+T (i) Use Bernsteins condition to detect the 5 maximum parallelism embedded in this code. Justify the portion that can be executed in parallel and the remaining portion that must be executed sequentially. (ii) Draw a dependency graph to show 5 all the dependences for the above code. CS-12 2

(b) Describe the differences between super - 5 scalar and VLIW architectures in terms of hardware and software requirements. 3. Explain the following as applied to multiprocessors and multicomputers. (a) A hierarchical cache/bus architecture for 5 designing a scalable multiprocessors. 5 (b) Network partitioning for multicast (c) communication. 5 Discard and Retransmission flow control.

4. (a) Explain the three mechanisms for 9 instruction pipelining, giving an example for each. (b) Explain the effect of block size, set number, 6 associativity and cache size on the performance of set associative cache organisation. 15 5. Compare and contrast the following : (a) Instruction and Trace scheduling (b) NUMA and COMA (c) Coarse gain and Medium grain parallelism

CS-12

You might also like