Oops. Linked an old benchmark version. https://www.refheap.com/92391
Reid
On 10/27/2014 03:13 PM, Reid McKenzie wrote:
For grins I slapped together this benchmark
<https://www.refheap.com/92385>, which tries to compare calls with
callsite static arity to application both for fully unrolled and
partially unrolled functions. The results I see indicate that in both
cases the cost of |apply| is almost equal for all arities. For
invocations/call sites with statically known arities, there seems to
be a factor of ~5x speedup compared to function application. The fully
unrolled function seems to do ~2x better than the “base” function for
all call site arities. This suggests that |apply| is immensely
expensive in general, and that such arity unrolling even for trivial
functions would be a good thing. Albeit hard to build.
Reid
--
You received this message because you are subscribed to the Google
Groups "Clojure" group.
To post to this group, send email to clojure@googlegroups.com
Note that posts from new members are moderated - please be patient with your
first post.
To unsubscribe from this group, send email to
clojure+unsubscr...@googlegroups.com
For more options, visit this group at
http://groups.google.com/group/clojure?hl=en
---
You received this message because you are subscribed to the Google Groups "Clojure" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to clojure+unsubscr...@googlegroups.com.
For more options, visit https://groups.google.com/d/optout.
