Sign inSign in
ConceptSystems & CS

Speedup

The ratio of the time of the sequential program running on one processor divided by the time of the parallel program running on P processors.
as Tim Mattson defines itIntelThe wording closest to all 6 definitions
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Execution time2Clock frequency and period relationship1CPI calculation1Execution time formula1Parallel processing1Parallel runtime modeling1Pipeline execution cycles1Runtime modeling1

Opens up

Concepts that name this one as a prerequisite.

Lecturers

4

Each in their own terms, from the easiest level.

  • Tim Mattson

    Intel · Undergraduate

    • 3:50Programming Clusters (MPI) and GPUs
  • Onur Mutlu

    ETH Zürich · Undergraduate

    Calculated as the old number of cycles divided by the new number of cycles after adding a read port.
    • 2:06:06Digital Design and Computer Architecture: Problem Solving II (ETH Zürich, Spring 2025, Lecture 27)
    • 3:13:42Digital Design and Computer Architecture: Problem Solving VI (ETH Zürich, Spring 2025, Lecture 31)
  • Charles Leiserson & Julian Shun

    MIT · Undergraduate

    T1/TpT_1 / T_p on P processors, categorized into sublinear, linear, and superlinear.
    • 38:07Races and Parallelism
  • Kayvon Fatahalian & Kunle Olukotun

    Stanford University · Undergraduate

    The ratio of the execution time using one processor to the execution time using P processors for a given problem.
    • 13:30Parallel Computing: Why Parallelism? Why Efficiency?

Lectures that assume it

4

Connections

14

The lectures that define it or assume it, and the concepts next to it.

4 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.