diff options
| author | Paul E. McKenney <paulmck@kernel.org> | 2023-08-11 10:41:08 -0700 |
|---|---|---|
| committer | Paul E. McKenney <paulmck@kernel.org> | 2023-08-11 10:41:08 -0700 |
| commit | 11e363b6d3d9c6df03067807beff2262d0654a69 (patch) | |
| tree | 15dbd2dd7b2ee736e653b694f9afb6c7555e9bc6 | |
| parent | 4902b3edb43cb671d736f8c59fb17d991a0fcefd (diff) | |
| download | perfbook-11e363b6d3d9c6df03067807beff2262d0654a69.tar.gz | |
count: Solicit hard evidence for/against hardware atomic_inc
Reported-by: Yariv Aridor <yariv.aridor@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
| -rw-r--r-- | count/count.tex | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/count/count.tex b/count/count.tex index e2c5885d..c82e7333 100644 --- a/count/count.tex +++ b/count/count.tex @@ -418,7 +418,11 @@ avoids the delays inherent in such circulation. where $N$ is the number of CPUs, as shown in \cref{fig:count:Data Flow For Global Combining-Tree Atomic Increment}. Some say that a few CPUs with this sort of hardware optimization - were in production use in the 1990s and started to reappear in 2011. + were in production use in the 1990s and started to reappear in + 2011.\footnote{ + The first reader to send a citable reference confirming + or invalidating this statement will be mentioned in a + future version of this footnote.} This is a great improvement over the $\O{N}$ performance of current hardware shown in |