Scribd
Upload
59 views2 pages

MTech QB

The document contains 12 questions related to parallel computing concepts. The questions cover topics like approaches for parallelism, MIPS rate calculation, CPI and execution time determination, matrix multiplication scheduling on fine-grained and coarse-grained processors, parameters of static networks, characteristics of different computer generations, architectural operations of SIMD and MIMD computers, definitions of key parallel computing terms, differences between string reduction and graph reduction machines, data dependence analysis, vector supercomputer architecture, and elements of modern computers.

Uploaded by

Raj Kumar Singh
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
59 views2 pages

MTech QB

The document contains 12 questions related to parallel computing concepts. The questions cover topics like approaches for parallelism, MIPS rate calculation, CPI and execution time determination, matrix multiplication scheduling on fine-grained and coarse-grained processors, parameters of static networks, characteristics of different computer generations, architectural operations of SIMD and MIMD computers, definitions of key parallel computing terms, differences between string reduction and graph reduction machines, data dependence analysis, vector supercomputer architecture, and elements of modern computers.

Uploaded by

Raj Kumar Singh
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 2

UNIT-1 Q.01 What two approaches for parallelism? [2] Q.02 Derive the formula for MIPS rate.

[4] Q.03 A 40 MHz processor was used to execute a bench mark program with the following instruction mix and clock cycle counts. [5] Instruction type count Integer arithmetic Data transfer Floating Point Control Transfer Instruction count 4500 32000 15000 8000 Clock cycle 1 2 2 2

Determine CPI, MIPS rate and execution time for this program. Q.04 Consider matrix multiplication problem: [9] A11 A12 A21 A22

B11 B21

B12 B22

C11 C21

C12 C22

Compute C=C11+C12+C21+C22. Using fine grain and course grain also do the scheduling for fine and course grain. Assume: (1)Each multiplication require 101 cycle. (2)Each addition required 8 cycle. (3)Communication delay between any two node is 212 cycle. (4)No. of processor in fine grain=8 (5)No. Of processor in coarse grain=4 Q.05 Calculate the following parameter for below given static network: [9] (i) Node degree (ii) Network diameter (iii) No. Of links (iv) Network size for ring, chordal ring, binary tree and star. Q.06 Name three distinct characteristics that exist in ith generation computers for i=1, 2, 3 and 4 but not jth generation for j=0, 1, 2......i-1 where the zeroth generation corresponds to prior electronic computers. Q.07 Characterize the architectural operations of SIMD and MIMD computers. Distinguish between multiprocessor and Multi Computers. Q.08 Define the following terms: (a) Bernsteins Conditions (b) Degree of parallelism (c) Computation granularity (d) Cross bar networks (e) Bisection bandwidth Q.09 What are the difference between string reduction and graph reduction

Machines? Also

explain software and hardware parallelism.

Q.10 Perform a data dependence analysis on each of the following FORTRAN program fragments. Show the dependence graph among the statements with justification. (a) (b) S1 : A = B+D S1 : X = SIN (Y) S2 : C = A*3 S2 : Z = X+W S3 : A = A+C S3 : Y = -2.5*W S4 : A/2 S4 : X = Cos (Z) Q.11 Show the architecture of a vector super computer and differentiate between register to register and memory to memory architecture. Q.12 What are the different elements of modern computer? Explain each in brief.

You might also like