[PRL] Bob Harper's new blog
Matthias Felleisen
matthias at ccs.neu.edu
Thu Mar 17 14:18:54 EDT 2011
On Mar 17, 2011, at 2:12 PM, William D Clinger wrote:
>> That's from academic
>> compiler guys who parallelize for a living. Perhaps the
>> problem is 'academic' in that sentence.
>
> I think you're reporting a garbled message. If parallelism
> is the issue, then the cost of dynamic method dispatch is
> pretty far down in the noise.
Wait. You channeled Bob's argument about dynamic dispatch and killing parallelism into this discussion. All I can do is respond with "I can't imagine this is true" and it looks like we have wasted a whole lot of bandwidth to violently agree here.
More information about the PRL
mailing list