siddhant

Knowledge / Computer Science

Parallel Computing

Executing multiple computations simultaneously to increase throughput or reduce execution time.

By Siddhant Krishna · Published 2026-10-06 · Updated 2026-10-06

01

Forms of Parallelism

  • Instruction-level parallelism overlaps processor instructions.
  • Data parallelism applies the same operation across many data elements.
  • Task parallelism executes different tasks concurrently.
  • Thread-level parallelism distributes work among execution threads.
  • Distributed parallelism coordinates work across networked machines.

02

Amdahl's Law

speedup ≤ 1 / (s + (1-s)/N)

If fraction s of a workload is inherently serial, increasing the number of parallel workers N has a bounded benefit.

References

  1. ACM, IEEE Computer Society, and AAAI, CS2023 Final Report.
    https://csed.acm.org/
  2. Nisan & Schocken, MIT Press; NAND2Tetris computational systems approach.
    https://www.nand2tetris.org/

Related

Contact

Get in Touch

Want to chat? Just shoot me a dm with a direct question on twitter and I'll respond whenever I can. I will ignore all soliciting.