Comparing the C FFI overhead on various languages

Another major caveat to this benchmark is it doesn't include any significant marshalling costs. For example, passing strings or arrays from Java to C is much, much slower than passing a single integer. Same is going to be true for a lot (all?) of the GC'd languages, and especially true for strings when the language isn't utf8 natively (as in, even though Java can store in utf8 internally, it doesn't expose that publicly so JNI doesn't benefit)

Some of the results look outdated. The Dart results look bad (25x slower than C), but looking at the code (<a href="https:&#x2F;&#x2F;github.com&#x2F;dyu&#x2F;ffi-overhead&#x2F;tree&#x2F;master&#x2F;dart" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;dyu&#x2F;ffi-overhead&#x2F;tree&#x2F;master&#x2F;dart</a>) it appears to be five years old. Dart has a new FFI as of Dart 2.5 (2019): <a href="https:&#x2F;&#x2F;medium.com&#x2F;dartlang&#x2F;announcing-dart-2-5-super-charged-development-328822024970" rel="nofollow">https:&#x2F;&#x2F;medium.com&#x2F;dartlang&#x2F;announcing-dart-2-5-super-charge...</a> I&#x27;m curious how the new FFI would fare in these benchmarks.

There is no Python benchmark but you can find a PR claiming it has 123,198ms. That would be a worst one by a wide margin.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;dyu&#x2F;ffi-overhead&#x2F;pull&#x2F;18" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;dyu&#x2F;ffi-overhead&#x2F;pull&#x2F;18</a>

So why isn&#x27;t C the baseline (and zig and rust being pretty close to it quite expected), but both luajit and julia are significantly faster??

The D programming language has literally a zero overhead to interface with C. The same calling conventions are used, the types are the same.<p>D can also access C code by simply importing a .c file:<p><pre><code> import foo; &#x2F;&#x2F; call functions from foo.c </code></pre> analogously to how you can `#include &quot;foo.h&quot;` in C++.

I had to run it to believe, I confirm it&#x27;s 183 seconds(!) for python3 on my laptop<p>Also, OCaml because I was interested (milliseconds):<p><pre><code> ocaml(int,noalloc,native) = 2022 ocaml(int,alloc,native) = 2344 ocaml(int,untagged,native) = 1912 ocaml(int32,noalloc,native) = 1049 ocaml(int32,alloc,native) = 1556 ocaml(int32,boxed,native) = 7544</code></pre>

It seems Rust has basically no overhead versus C, but it could have <i>negative</i> overhead if you use cross-language LTO. Of course, you can do LTO between C files too, so that would be unfair. But I think this sets it apart from languages that, even with a highly optimised FFI, don&#x27;t have compiler support for LTO with C code.

Just a caveat, not sure if it matters in practice, but this benchmark is using very old versions of many languages it&#x27;s comparing (5 year old ones).

I developed a terminal emulator, file manager and text editor Deodar 8 years ago in JavaScript&#x2F;V8 with native C++ calls, it worked but I was extremely disappointed by speed, it felt so slow like you need to do a passport control each time you call a C++ function.

This ia a cool concept, but the implementation is contrived (as many others describe). e.g. JNI array marshalling&#x2F;unmarshalling has a lot of overhead. The Nim version is super outdated too (not sure about the other languages).

For a game scripting language, Wren posts a pretty bad result here. Think it has isn&#x27;t explicitly game focused though. The version tested is quite old however, having released in 2016.

Needs LTO, with that it will have 0 overhead in the compiled languages.<p>D can actually compile the C code in this test now.

I guess it is better to measure CPU time instead of wall time (e.g. using clock() ).

What about Common Lisp?

That Nim version has just left kindergarten and is prepping for elementary.

&gt; - julia 0.6.3<p>That&#x27;s an ancient version, the current version is v1.7.2.

Java has a new API for FFI called the foreign memory interface

Any idea why mono is used rather than .NET here?

Go looks horribly slow, I thought segmented stacks have gone away to improve this?

Java has project Panama coming that may improve things a little.

n.b. this is using an absolutely ancient version of node, though i&#x27;m not sure that would change anything, worth nothing

Can you try PHP?

Missing 2014, or 2018 in the title.

this benchmark is afwul (which is expected)