Question: 5. [20 marks] Arithmetic Intensity. The Intel Core i7 920 has a peak floating-point performance of 42.66 GFs/s, and a peak memory bandwidth of 16.4

 5. [20 marks] Arithmetic Intensity. The Intel Core i7 920 has

5. [20 marks] Arithmetic Intensity. The Intel Core i7 920 has a peak floating-point performance of 42.66 GFs/s, and a peak memory bandwidth of 16.4 GB/s. The Nvidia GTX 2880 has a peak floating-point performance of 78 GFs/s, and a peak memory bandwidth of 127 GBs/s. Every program has an arithmetic intensity (ai), measured in flops/byte, that indicates how much performance is achievable for a given peak bandwidth. The equation is: sustained GFs/s min{ ai*bw, peak GFs/s a) Suppose an application has a arithmetic intensity of 0.5 Fs/B. what sustained performance will it have on the Intel machine? What is the bottleneck? b) Suspose an application has an arithmetic intensity of 4 Fs/B. What sustained performance will it have on the Intel machine? What is the bottleneck? c) Suppose an application has a arithmetic intensity of 0.5 Fs/B. what sustained performance will it have on the Nvidia machine? What is the bottleneck? d) Suppose an application has an arithmetic intensity of 1 F/B. On which machine would you achieve greater sustained performance? Justify your answer. 5. [20 marks] Arithmetic Intensity. The Intel Core i7 920 has a peak floating-point performance of 42.66 GFs/s, and a peak memory bandwidth of 16.4 GB/s. The Nvidia GTX 2880 has a peak floating-point performance of 78 GFs/s, and a peak memory bandwidth of 127 GBs/s. Every program has an arithmetic intensity (ai), measured in flops/byte, that indicates how much performance is achievable for a given peak bandwidth. The equation is: sustained GFs/s min{ ai*bw, peak GFs/s a) Suppose an application has a arithmetic intensity of 0.5 Fs/B. what sustained performance will it have on the Intel machine? What is the bottleneck? b) Suspose an application has an arithmetic intensity of 4 Fs/B. What sustained performance will it have on the Intel machine? What is the bottleneck? c) Suppose an application has a arithmetic intensity of 0.5 Fs/B. what sustained performance will it have on the Nvidia machine? What is the bottleneck? d) Suppose an application has an arithmetic intensity of 1 F/B. On which machine would you achieve greater sustained performance? Justify your

Step by Step Solution

There are 3 Steps involved in it

1 Expert Approved Answer
Step: 1 Unlock blur-text-image
Question Has Been Solved by an Expert!

Get step-by-step solutions from verified subject matter experts

Step: 2 Unlock
Step: 3 Unlock

Students Have Also Explored These Related Databases Questions!