Extending Amdahl’s Law For the Cloud Computing Era

Abstract: By extending Amdahl’s law, software developers can weigh the pros and cons of moving their applications to the cloud. This is the era of Cloud Computing. A gradual change from centralized to distributed execution is taking place, but not without some practical issues related to process migrations (transparent middleware, efficient and secure data transmissions, …). Extending Amdahl’s law to Cloud Computing will provide a better understanding of the involved factors related to the offloading process such as the time and energy speedups, together with some hints about the future of this era.

Extending Amdahl's Law ForFig1

Figure 1. Centralized (red square) and Offloading computation (right and bottom) models.

Extending Amdahl's Law ForFig2a

Extending Amdahl's Law ForFig2b

Extending Amdahl's Law ForFig2c

Figure 2. Speedups of remote versus local execution (Nc,local=1, 4, 16) as a function of DI for different F and μ=1.

Extending Amdahl's Law ForFig3

Figure 3. Two-Roofline Model for GIPS (Giga Instructions Per Second) vs. DI for the Snapdragon 610 S4 Pro. The diminution of maximum device GIPS is marked with down arrows.

Full text: “Extending Amdahl’s Law For the Cloud Computing Era” IEEE Computer, vol 49 no.2, pp.14-22.