Amdahl's and Gustafson-Barsis laws revisited
Andrzej Karbowski

TL;DR
This paper demonstrates that the Gustafson-Barsis law can be simply derived from Amdahl's law, clarifying their relationship and correcting misconceptions about their implications for parallel application speedup limits.
Contribution
It provides a straightforward derivation showing that Gustafson-Barsis law is not separate from Amdahl's law, but can be obtained from it, clarifying their connection.
Findings
Gustafson-Barsis law can be derived from Amdahl's law in a few lines.
The claim that Gustafson-Barsis law overthrows Amdahl's law is incorrect.
The derivation treats the sequential execution time as a constant.
Abstract
The paper presents a simple derivation of the Gustafson-Barsis law from the Amdahl's law. In the computer literature these two laws describing the speedup limits of parallel applications are derived separately. It is shown, that treating the time of the execution of the sequential part of the application as a constant, in few lines the Gustafson-Barsis law can be obtained from the Amdahl's law and that the popular claim, that Gustafson-Barsis law overthrows Amdahl's law is a mistake.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Queuing Theory Analysis
