Memory Ordering in Modern Microprocessors, Part I

As noted earlier, the good news is Linux's memory-ordering primitives and synchronization primitives make it unnecessary for most Linux kernel hackers to worry about memory barriers. This is especially good news given the large number of CPUs and systems that Linux supports and the resulting wide variety of memory-consistency models. However, there are times when knowing about memory barriers can be helpful, and I hope that this article has served as a good introduction to them.

I owe thanks to many CPU architects for patiently explaining the instruction- and memory-reordering features of their CPUs, particularly Wayne Cardoza, Ed Silha, Anton Blanchard, Tim Slegel, Juergen Probst, Ingo Adlung and Ravi Arimilli. Wayne deserves special thanks for his patience in explaining Alpha's reordering of dependent loads, a lesson that I resisted learning quite strenuously!

This work represents the view of the author and does not necessarily represent the view of IBM. IBM, zSeries and Power PC are trademarks or registered trademarks of International Business Machines Corporation in the United States, other countries, or both. Linux is a registered trademark of Linus Torvalds. i386 is a trademarks of Intel Corporation or its subsidiaries in the United States, other countries, or both. Other company, product, and service names may be trademarks or service marks of such companies. Copyright (c) 2005 by IBM Corporation.

Resources for this article: /article/8331.