Frédéric Bastien

This isn't always good. If the optimization take times and the cache is full, then this will slow things down... The few good fixes I know: - The first time,...

The directory creation is atomic. In fact, it is the only posic atomic operation. This is why we use it. We needed that in the past as we where using...

The real problem is Suppose that if you have an empty cache and launch 1 job and it take it 10m to fill the cache. Then it happen frequently that...

We rescan each time we take the lock. This is needed to don't compile the same module multiple time. I don't think a listdir is slower then puthing that information...

Thanks for the timing. So we know now that the lock itself, in the best case (locally) don't cause slowdowns. Making the same timing on the cluster is a good...

The number are strange... The number in RAMDISK are slower then the first number with current Theano lock. On which cluster did you do those timing? I think you should...

I just pushed an update. Now it will refresh the cache content only when it take the lock the first time. On Fri, Feb 19, 2016 at 7:27 PM, Frédéric...

@bartvm did you had the time to redo the timing with your local computer? thanks On Fri, Feb 19, 2016 at 7:37 PM, Frédéric Bastien < [email protected]> wrote: > I...

I didn't do a PR, it is in a branch in my fork on github: https://github.com/nouiz/Theano/tree/lock On Thu, Feb 25, 2016 at 12:57 PM, Bart van Merriënboer < [email protected]> wrote:...

I think there is a way to manually start the worker. Is that right? If so, this allow to do that. But maybe it was removed. I don't know how...