Re: [fluid-dev] Multi core support not so great

2009-09-28 Thread Kevin Fishburne
j...@resonance.org wrote: Yeah, I want one now too! :) CPU of champions for those on a budget: http://www.newegg.com/Product/Product.aspx?Item=N82E16819103674 This one's also good: http://www.newegg.com/Product/Product.aspx?Item=N82E16819103650 Kevin ___

Re: [fluid-dev] Multi core support not so great

2009-09-28 Thread josh
Quoting David Henningsson : j...@resonance.org skrev: I finished implementing a first pass at multi-core support. Oh, now I really must order a multi-core computer ;-) Yeah, I want one now too! :) While it was a fun task, it didn't really yield the kind of performance I was hoping for. F

Re: [fluid-dev] Multi core support not so great

2009-09-28 Thread David Henningsson
j...@resonance.org skrev: > I finished implementing a first pass at multi-core support. Oh, now I really must order a multi-core computer ;-) > While it > was a fun task, it didn't really yield the kind of performance I was > hoping for. For those interested here is a description of the curren

Re: [fluid-dev] Multi core support not so great

2009-09-28 Thread josh
For the iPhone, I'm considering having a build time option, that builds a single threaded FluidSynth, without glib support. This would probably also mean no shell or some API would need to be added to be able to use the shell in a non-blocking manner (so it could be called from within the

Re: [fluid-dev] Multi core support not so great

2009-09-28 Thread S. Christian Collins
Quick question: would that overhead end up being a factor on something like the iPhone, where the CPU power is quite limited? -~Chris j...@resonance.org wrote: I finished implementing a first pass at multi-core support. While it was a fun task, it didn't really yield the kind of performance I

[fluid-dev] Multi core support not so great

2009-09-28 Thread josh
I finished implementing a first pass at multi-core support. While it was a fun task, it didn't really yield the kind of performance I was hoping for. For those interested here is a description of the current logic: Added a synth.cpu-cores setting. Additional core threads are created in ne