Abstract
We introduce Moore’s Law and Dennard scaling. They illustrate that further increases of compute capabilities will result from an increase in parallelism over the upcoming years; which implies that our codes have to be prepared to exploit this parallelism. We identify three levels of parallelism within a CPU (inter-node, intra-node and vector parallelism) and eventually characterise GPUs within these levels.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The “law” is so popular that Intel paid 10,000 USD for a copy of the original paper print in 2005.
- 2.
Some of these operations might require multiple cycles when expressing them by means of chip frequency, but the punchline is that there’s one operation per cycle sequence.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Weinzierl, T. (2021). Moore Myths. In: Principles of Parallel Scientific Computing. Undergraduate Topics in Computer Science. Springer, Cham. https://doi.org/10.1007/978-3-030-76194-3_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-76194-3_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-76193-6
Online ISBN: 978-3-030-76194-3
eBook Packages: Computer ScienceComputer Science (R0)