Scribd
Upload
38 views

Shared Memory Architecture

1. The document appears to be an exam for an Advanced Computer Architecture course, covering 5 modules: non-uniform memory access, parallelism metrics, granularity in parallel computing, RISC vs CISC architectures, and multithreading architectures. 2. It contains 10 questions, with students required to answer 5 questions by choosing 1 full question from each module. Questions involve explaining concepts like NUMA, implicit/explicit parallelism, Amdahl's law, RISC/CISC differences, and multithreading parameters. 3. Students are advised not to reveal their identity or appeal to the evaluator, and to draw diagonal lines on blank pages when finishing their exam.

Uploaded by

Neethu Rajesh
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
38 views

Shared Memory Architecture

1. The document appears to be an exam for an Advanced Computer Architecture course, covering 5 modules: non-uniform memory access, parallelism metrics, granularity in parallel computing, RISC vs CISC architectures, and multithreading architectures. 2. It contains 10 questions, with students required to answer 5 questions by choosing 1 full question from each module. Questions involve explaining concepts like NUMA, implicit/explicit parallelism, Amdahl's law, RISC/CISC differences, and multithreading parameters. 3. Students are advised not to reveal their identity or appeal to the evaluator, and to draw diagonal lines on blank pages when finishing their exam.

Uploaded by

Neethu Rajesh
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

USN 16/17ELD154

First Semester M.Tech. Degree Examination, Dec.2018/Jan.2019


Advanced Computer Architecture

Time: 3 hrs. Max. Marks: 80

Note: Answer any FIVE full questions, choosing ONE full question from each module.
2. Any revealing of identification, appeal to evaluator and /or equations written eg, 42+8 = 50, will be treated as malpractice.

Module-1
1 a. Explain with neat diagram of non-uniform memory access (NUMA) of multiprocess model.
(08 Marks)
b. Explain :
(i) Implicit and Explicit parallelizing (06 Marks)
Important Note : 1. On completing your answers, compulsorily draw diagonal cross lines on the remaining blank pages.

(ii) Throughput Rate (02 Marks)

OR
2 a. Explain data dependencies and control dependencies. (08 Marks)
b. Explain in detail about hardware and software parallelism. (08 Marks)

Module-2
3 a. Define Grain size and fine grain. (04 Marks)
b. What do you mean by grain packing? Explain with an example. Also explain the advantages
of node duplication. (12 Marks)

OR
4 a. Define Amdahl’s law and explain in detail with fixed work load. (08 Marks)
b. Define the following basic metrics affecting the scalability of a computer system:
(i) Memory size
(ii) Problem size
(iii) CPU Time
(iv) I/O demand and communication overhead. (08 Marks)

Module-3
5 a. Compare RISC and CISC architecture in detail. (08 Marks)
b. Explain the power architecture of IBM RS/6000 in detail. (08 Marks)

OR
6 a. Explain collision-free scheduling. (08 Marks)
b. Explain with neat diagram about the instruction execution phases. (08 Marks)

Module-4
7 a. Discuss about various Branch handling technique. (10 Marks)
b. Explain on Hazard avoidance during Instruction pipelining. (06 Marks)

OR
8 a. Explain multiply pipeline design with the help of Carry Save Adder and Carry Propagate
Adder. (08 Marks)
b. Explain in detail about fixed-point and floating point numbers and its operation with
example. (08 Marks)
1 of 2
16/17ELD154

Module-5
9 a. List and explain on machine parameter of multithreading architecture. (08 Marks)
b. Explain different context-switching policies. (08 Marks)

OR
10 a. Explain with neat diagram on Stanford Bash multiprocessor. (10 Marks)
b. Write short notes on :
(i) Data flow graph
(ii) Static vs Dynamic data flow. (06 Marks)

*****

2 of 2

You might also like