Issue #16487 has been updated by shevegen (Robert A. Heiler).


I wanted to add just a short comment - while byroot is quite possibly corre=
ct in regards to most users
using pre-packaged binaries (probably), there are also folks (like me, and =
others) who compile ruby
from source. These could benefit from significant speed improvement, e. g. =
via a configure switch
for building (such as --enable-simd and/or --enable-simd-optimizations and/=
or --optimizations=3DLIST).

So perhaps the primary issue is about code maintainability/complexity as su=
ch. If only we could write
ruby in ... ruby, then ugly #ifdef macros may not have to be used. :)

----------------------------------------
Misc #16487: Potential for SIMD usage in ruby-core
https://bugs.ruby-lang.org/issues/16487#change-83723

* Author: byroot (Jean Boussier)
* Status: Open
* Priority: Normal
* Assignee: =

----------------------------------------
### Context

There are several ruby core methods that could be optimized with the use of=
 SIMD instructions.

I experimented a bit on `coderange_scan` https://github.com/Shopify/ruby/pu=
ll/2, and Pavel Rosick=FD experimented on `String#strip` https://github.com=
/ruby/ruby/pull/2815.

### Problem

The downside of SIMD instructions is that they are not universally availabl=
e.
So it means maintaining several versions of the same code, and switching th=
em either statically or dynamically.

And since most Ruby users use precompiled binaries from repositories and su=
ch, it would need to be dynamic if we want most users to benefit from it.

So it's not exactly "free speed", as it means a complexified codebase.

### Question

So the question is to know wether ruby-core is open to patches using SIMD i=
nstructions ? And if so under which conditions.

cc @shyouhei





-- =

https://bugs.ruby-lang.org/

Unsubscribe: <mailto:ruby-core-request / ruby-lang.org?subject=3Dunsubscribe>
<http://lists.ruby-lang.org/cgi-bin/mailman/options/ruby-core>