If you have a runtime penalty when running 2 independent AB jobs on a Core Duo CPU it might be caused by too less memory (swapping to disk) or other tasks which are also running (e.g. a web browser, audio streamer or whatever). You can check this with a process explorer which shows each tasks CPU utilisation. Similar, 4 AB jobs on a Core Quad should have nearly no penalty in runtime.
Tomasz stated that multi-thread optimization does not scale good with the CPU number, but it is not clear to me why this is the case. In my understanding, AA optimization is a sequential process of running the same AFL script with different parameters. If I have an AFL with significantly long runtime per optimization step (e.g. 1 minute) the overhead for the multi-threading should become quite small and independent tasks should scale nearly with the number of CPUs (as long as there is sufficient memory, n threads might need n-times more memory than a single thread). For sure the situation is different if my single optimization run takes only a few millisecs or seconds, then the overhead for multi-thread-managment goes up ... Maybe Tomasz can give some detailed comments on that issue? Best regards, Markus --- In [email protected], "dloyer123" <[EMAIL PROTECTED]> wrote: > > Running on my core 2 laptop, running two copies of AB, doing > optimizatios will slow down both, but not by half. So, running on 1 > core, might take 1 minute per pass, two cores can run 2 passes in 1.5 > minutes. > > But... The two passes are independent and dont know about each other > and are not part of the same optimization run. > > Also... The dual cores can be had at 3GHz, the quad cores at less. > > So, it is hard to keep 4 cores busy and the contention will be worse. > > I just ordered a new optimization system myself. I went with the 3Ghz > Core 2 dual, with 4GB of DDR2(800) ram. There is faster ram available, > but at a much higher cost and benchmarks dont show much benifit. > > --- In [email protected], "Steve Dugas" <sjdugas@> wrote: > > > > Hi - OK, I decided to get a new computer for optimizations. I can get > either a dual-core or a quad-core. I know TJ has run tests and decided > not to rewrite AB's optimizer for multi-core, but I think I remember > someone saying that they were getting a speed boost by running 2 > instances of AB on a dual-core machine? So, if I got a quad-core and > ran 4 instances, would they each use a different core and give me a 4X > speed increase? If not, could it possibly be *slower* to get a quad- > core if all instances of AB are trying to use only one core ( 1/4 of > computer's power, vs 1/2 for a dual-core )? Sorry for the stupid > questions, I hope someone knows more about it than me. 8 - ) > > Thanks! > > > > Steve > > >
