Re: Music Synthesis

Thanks for responding, Rob.

> What are your target platforms, specifically? 


Yes, that was exactly my question:  What are our target platforms?  That is a question for the whole group, not just me.  We have to decide that.  IMHO characterizing our target platforms, plus deciding what our target functionality requirements are, would be a significantly better place to start deliberations than to begin by asking which of a few pre-existing proposals we want to go with.  Then we could evaluate specific proposals against the requirements, and either modify them or create a new one to satisfy the requirements.


> We should do experiments on a mobile device and report back.


The characterization would have to be somewhat more complicated than that.  Even within mobile devices with web browsers there is a huge range of capability, it's not just a single data point.


> Anyway, we need to plan for the future, and it seems safe to assume that JS optimization techniques will spread to every platform where they're useful.

The more important the project, the more closely any assumptions should be examined.  So I would ask that a little differently: Are any of our target platforms too limited to implement those techniques?

Also, that response doesn't address the possibility that some of our target platforms may be too underpowered to do anything useful even if its JS implementation is optimized.  (Corollary: We could decide to make the ability to do some basic set of realtime audio processing functionality our baseline for what's an acceptable target platform.)

	-- Chris G.


On 2010Jun 15, at 1:49 p, Robert O'Callahan wrote:
> On Wed, Jun 16, 2010 at 8:22 AM, Chris Grigg <chris@chrisgrigg.org> wrote:
> Further to my comment on the separate "Target platforms?" thread, on what range of target platforms did you find the performance to be equivalent?  Are there any of our target platforms that are not capable of realtime performance with that FFT implementation?  I would worry about very skinny clients not only for FFT but for any compute intensive operations.
> 
> Vlad's tests were on a desktop machine. We should do experiments on a mobile device and report back. However, I see no fundamental reason why the observed closeness in performance between JS and C would be unattainable in lower-end devices. Our ARM backend is less mature but that will improve.
> 
> Asking another way: Are these accelerated JS implementation techniques you reference deployed for all of our target platforms?
> 
> What are your target platforms, specifically? Anyway, we need to plan for the future, and it seems safe to assume that JS optimization techniques will spread to every platform where they're useful.
> 
> Rob
> -- 
> "He was pierced for our transgressions, he was crushed for our iniquities; the punishment that brought us peace was upon him, and by his wounds we are healed. We all, like sheep, have gone astray, each of us has turned to his own way; and the LORD has laid on him the iniquity of us all." [Isaiah 53:5-6]