Warning: foreach() argument must be of type array|object, bool given in /var/www/html/web/app/themes/studypress-core-theme/template-parts/header/mobile-offcanvas.php on line 20

Question: 6.17 Benchmarking is field of study that involves identifying representative workloads to run on specific computing platforms in order to be able to objectively compare performance of one system to another. In this exercise we will compare two classes of benchmarks: the Whetstone CPU benchmark and the PARSEC Benchmark suite. Select one program from PARSEC. All programs should be freely available on the Internet. Consider running multiple copies of Whetstone versus running the PARSEC Benchmark on any of systems described in Section 6.11.

6.17.1 [60] what is inherently different between these two classes of workload when run on these multi-core systems?

6.17.2 [60] In terms of the Roofline Model, how dependent will the results you obtain when running these benchmarks be on the amount of sharing and synchronization present in the workload used?

Short Answer

Expert verified

6.17.1

The two differences between these two suites:

  • Whetstone

  • PARSEC

6.17.2

The benchmark of the “PARSEC” should be only impacted by the synchronization and the sharing.

Step by step solution

01

Define the concept.

6.17.1

Whetstone is referred to a test of the benchmark whose purpose is for measuring the performance of the floating-point operations in the computer. The performance is computed by calculating the speed and the efficiency. The outcome of the test is provided in "KWIPS" units. This unit is known as also the "kilo-whetstones-per-second".

6.17.2

The "PARSEC" is referred to as a benchmark suite. The purpose is to study the "CMPs". These “Cmps” are basically Chip-Multiprocessors. This suit is also including mining and synthesis. Also, the emerged applications in recognition are included with this. One of the characteristics of this is to cover the broad spectrum of data sharing, synchronization working sets, locality, and so on.

02

Determine the calculation.

6.17.1

The first difference describes the design for the performance of the floating point. And the second one is for the workloads of those, which are determined by the programs of multithread. The purpose of whetstone is for measuring the performance of the floating-point operations in the computer. The performance is computed by calculating the speed and the efficiency. The outcome of the test is provided in "KWIPS" units. This unit is known as also the "kilo-whetstones-per-second".

6.17.2

The benchmark of the “PARSEC” should be only impacted by the synchronization and the sharing. But this should not be a factor of the “Whetstone”. The purpose of the "PARSEC” is to study the "CMPs". These “Cmps” are basically Chip-Multiprocessors. This suit is also including mining and synthesis. Also, the emerged applications in recognition are included with this. One of the characteristics of this is to cover the broad spectrum of data sharing, synchronization working sets, locality, and so on.

Unlock Step-by-Step Solutions & Ace Your Exams!

  • Full Textbook Solutions

    Get detailed explanations and key concepts

  • Unlimited Al creation

    Al flashcards, explanations, exams and more...

  • Ads-free access

    To over 500 millions flashcards

  • Money-back guarantee

    We refund you if you fail your exam.

Over 30 million students worldwide already upgrade their learning with Vaia!

One App. One Place for Learning.

All the tools & learning materials you need for study success - in one app.

Get started for free

Most popular questions from this chapter

B.28 [10] <§B.6> Now calculate the relative performance of adders. Assume that hardware corresponding to any equation containing only OR or AND terms, such as the equations for pi and gi on page B-40, takes one time unit T. Equations that consist of the OR of several AND terms, such as the equations for c1, c2, c3, and c4 on page B-40, would thus take two time units, 2T. The reason is it would take T to produce the AND terms and then an additional T to produce the result of the OR. Calculate the numbers and performance ratio for 4-bit adders for both ripple carry and carry lookahead. If the terms in equations are further defined by other equations, then add the appropriate delays for those intermediate equations, and continue recursively until the actual input bits of the adder are used in an equation. Include a drawing of each adder labeled with the calculated delays and the path of the worst-case delay highlighted.

A.6 [5] Using SPIM, write and test an adding machine program that repeatedly reads in integers and adds them into a running sum. The program should stop when it gets an input that is 0, printing out the sum at that point. Use the SPIM system calls described on pages A-43 and A-45.

We would like to execute the loop below as efficiently as possible. We have two different machines, a MIMD machine and a SIMD machine.

for (i=0;i<2000;i++)

for(j=0;j<3000;j++)

X_array[i][j] = Y_array[j][i] + 200;

6.11.1 [10] For a 4 CPU MIMD machine, show the sequence of MIPS instructions that you would execute on each CPU. What is the speedup for this MIMD machine?

6.11.2 [10] For an 8-wide SIMD machine (i.e.,8 parallel SIMD functional units), write an assembly program in using your own SIMD extensions to MIPS to execute the loop. Compare the number of instructions executed on the SIMD machine to MIMD machine.

Assume that X consists of 3 bits, x2 x1 x0, and Y consists of 3 bits, y2 y1 y0. Write logic functions that are true if and only if

■X<Y , where X and Y are thought of as unsigned binary numbers

■ X<Y , where X and Y are thought of as signed (two’s complement) numbers

■ X = Y

Use a hierarchical approach that can be extended to larger numbers of bits. Show how can you extend it to 6-bit comparison.

Derive the product-of-sums representation for Eshown on page B-11 starting with the sum-of-products representation. You will need to use DeMorgan’s theorems.

See all solutions

Recommended explanations on Computer Science Textbooks

View all explanations

What do you think about this solution?

We value your feedback to improve our textbook solutions.

Study anywhere. Anytime. Across all devices.

Sign-up for free