On 09/16/2016 04:54 PM, Emilio G. Cota wrote:
On Fri, Sep 16, 2016 at 10:46:48 -0700, Richard Henderson wrote:
From: "Emilio G. Cota" <c...@braap.org>
With this microbenchmark we can measure the overhead of emulating atomic
instructions with a configurable degree of contention.
The benchmark spawns $n threads, each performing $o atomic ops (additions)
in a loop. Each atomic operation is performed on a different cache line
(assuming lines are 64b long) that is randomly selected from a range [0, $r).
[ Note: each $foo corresponds to a -foo flag ]
As I mentioned yesterday I have an updated version of this
[ The major change is to run for a certain number of seconds, instead
of a fixed number of operations. ]
I'll send the full updated patch as a reply to this message to make
it easier to pick up.