What Is Amdahl’s Law?


A Brief Introduction to Amdahl’s Law

Have you ever wondered how improvements in processing speed can affect the overall performance of a system? This is where Amdahl’s Law comes into play. Developed by computer architect Gene Amdahl in 1967, Amdahl’s Law provides a formula to calculate the potential speedup of a system based on the fraction of the workload that can be parallelized.

Key Takeaways:

  • Amdahl’s Law calculates the potential speedup of a system.
  • It takes into account the fraction of the workload that can be parallelized.

So, what exactly is Amdahl’s Law? Let’s dive into the details.

Amdahl’s Law is a fundamental principle in computer architecture and performance analysis. It states that the overall speedup of a system is determined by the fraction of the workload that can be parallelized. In simple terms, it helps us understand how much faster a system can operate when we make certain parts of it run in parallel.

To better grasp the concept, let’s consider an example. Imagine you have a computer program that consists of two parts: Part A and Part B. Part A takes up 70% of the program’s execution time, while Part B accounts for the remaining 30%. If you implement parallelization techniques and manage to speed up Part A by 10 times, the overall speedup of the system wouldn’t be 10 times, but rather less due to Amdahl’s Law.

Amdahl’s Law is based on the following formula:

Speedup = 1 / [(1 – P) + (P / N)]


  • P represents the fraction of the workload that can be parallelized.
  • N represents the number of processors or cores.

By plugging in the values for ‘P’ and ‘N’, you can calculate the potential speedup of the system. However, it is important to note that Amdahl’s Law assumes a fixed problem size and workload distribution.

Now that we understand the basic concept of Amdahl’s Law, let’s explore its significance.

Amdahl’s Law serves as a guideline for system designers and architects. It emphasizes the importance of optimizing the non-parallelizable parts of a system to achieve significant performance gains. Simply throwing more processors at a problem may not always yield the expected speedup. System designers need to carefully analyze the workload and identify the parts that can be parallelized effectively.

Key Takeaways:

  • Amdahl’s Law is a guideline for system designers.
  • Optimizing non-parallelizable parts is crucial for significant performance gains.

In conclusion, Amdahl’s Law provides a formula to estimate the potential speedup of a parallel processing system. Understanding this law helps system designers make informed decisions regarding system architecture and optimization strategies. By carefully balancing the parallelizable and non-parallelizable parts, developers can unleash the full potential of a computing system and achieve efficient performance enhancement.