Bug 152255 – We should not employ the snippet code in the DFG if no OSR exit was previously encountered.

• Status: RESOLVED
• Resolution: FIXED
• Component: JavaScriptCore

[Mark Lam]

We already tried to do this but was doing it wrong.  The is what we do now:

     if (Node::shouldSpeculateUntypedForArithmetic(leftChild.node(), rightChild.node())
         || m_graph.hasExitSite(node->origin.semantic, BadType)) {
         fixEdge<UntypedUse>(leftChild);
         fixEdge<UntypedUse>(rightChild);
         ...

The || should be a &&.  We only want to employ the snippet code if we have actually encountered an OSR exit due to untyped operands not being supported.

[Mark Lam]

Created attachment 267301 [details]
proposed patch.

[Mark Lam]

Created attachment 267302 [details]
x86_64 benchmark result.

[Mark Lam]

With this change, we see the following progression in JSRegress:

   arguments-out-of-bounds                           12.9152+-1.3205     ^     10.2297+-0.3642        ^ definitely 1.2625x faster

[Saam Barati]

Comment on attachment 267301 [details]
proposed patch.

r=me

[Mark Lam]

Thanks for the review.  Landed in r194040: <http://trac.webkit.org/r194040>.

[Filip Pizlo]

Comment on attachment 267301 [details]
proposed patch.

This is the wrong policy.  We usually only rely on exit sites as a last resort.

Why did you do this?

[Mark Lam]

(In reply to comment #6)
> Comment on attachment 267301 [details]
> proposed patch.
> 
> This is the wrong policy.  We usually only rely on exit sites as a last
> resort.
> 
> Why did you do this?

This was suggested by Geoff, and was implemented this way since the first op_sub snippet.  The only issue was that I had a bug in how I implemented it.