1 / 10

Amdahl’s Law

Amdahl’s Law. The performance improvement to be gained from using some faster mode of execution is limited by the fraction of the time the faster mode can be used Speedup tells us how much faster a task will run using the machine with the enhancement as apposed to the original machine.

leis
Download Presentation

Amdahl’s Law

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Amdahl’s Law • The performance improvement to be gained from using some faster mode of execution is limited by the fraction of the time the faster mode can be used • Speedup tells us how much faster a task will run using the machine with the enhancement as apposed to the original machine 240-530 Digital System Architecture : IO

  2. Amdahl’s Law: cont’d • An alternative equation: • Fractionenhanced: fraction of computation time in the original machine that can be converted to take advantage of the enhancement (<=1) • Speedupenhanced: how much faster the task would run if the enhanced mode were used for the entire program 240-530 Digital System Architecture : IO

  3. Example 1 • Suppose that we are considering an enhancement that run 10 times faster than the original machine but is only usable 40% of the time. What is the overall speedup gained by incorporating the enhancement? • Answer 240-530 Digital System Architecture : IO

  4. Example 2 • Implementations of floating-point (FP) square root vary significantly in performance. Suppose FP square root (FPSQR) is responsible for 20% of the execution time of a critical benchmark on a machine. One proposal is to add FPSQR hardware that will speed up this operation by a factor of 10. The other alternative is to just try make all FP instructions run faster; FP instructions are responsible for a total of 50% of the execution time. The design team believes that they can make all FP instructions run two times faster with the same effort as required for the fast square root. Compare these two design alternatives. 240-530 Digital System Architecture : IO

  5. Magnetic Disks • Platters, arm, read/write head • Track, sector, cylinder • constant bit density/variable bit density • seek, seek time, average seek time • transfer time, controller time • rotation latency (rotational delay) for a drive that spins at 3600 RPM 240-530 Digital System Architecture : IO

  6. Example • What is the average time to read or write a 512-byte sector for a typical disk? The advertised average seek time is 9ms, the transfer rate is 4MB/s, it rotates at 7200RPM, and the controller overhead is 1ms. Assume the disk is idle so that there is no queuing delay. Answer: Average disk access is equal to average seek time + average rotational delay + transfer time + controller overhead. The answer is Assume the measured seek time is 33% of the calculated average, the answer is 3ms + 4.2ms + 0.1ms + 1ms = 8.3ms 240-530 Digital System Architecture : IO

  7. 240-530 Digital System Architecture : IO

  8. 240-530 Digital System Architecture : IO

  9. Other types of storage • Magneto-optical disks • Optical disks • CD-ROM (used to be a “read-only device”) • Magnetic tapes • Solid state disks • FLASH memory 240-530 Digital System Architecture : IO

  10. Homework 1 • Read Section 6.1-6.4 (pg. 485-521) • Exercise 6.9 and 6.19 240-530 Digital System Architecture : IO

More Related