[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [amibroker] Re: Multi Core Optimization, L2 Cache & Optimization Run Times
|
PureBytes Links
Trading Reference Links
|
Interesting thread so
far. But wouldn't it be nice if we had some numerical yardsticks so
that different system configurations could be easily compared with one
another?
How about writing some benchmarks in afl? I assume the code wouldn't
have to be very complex, nor would it have to be for any sort of
'winning' system. Just something that everyone could run and we could
get some comparative speed results.
A few standard data sets would be necessary, each with a different
number of equities and bars/equity. I expect some to be upwards of a
GB or even larger. This could be a real distribution problem. Perhaps
a solution would be a small program, distributed with the benchmarks,
that generated fake (pseudo-random, but repeatable) data sets. These
sets could be generated and destroyed at will, but most importantly,
would provide for repeatable results.
-- Keith
Ton Sieverding wrote:
Yes in that case I understand your
reaction about overhead being far from constant. At least I assume it's
not ...
Regards, Ton.
-----
Original Message -----
Sent:
Thursday, June 19, 2008 7:00 PM
Subject:
Re: [amibroker] Re: Multi Core Optimization, L2 Cache &
Optimization Run Times
My point was that depending on the number of symbols and the
number of bars for each symbol that are being processed that you may
well find significantly different relationships between how long it
takes one processor versus several to deal with some task i.e.
different overhead when running multiple instances of AB simultaneously
with exactly the same conditions.
----- Original Message -----
From: Ton Sieverding
Date: Thursday, June 19, 2008 8:39 am
Subject: Re: [amibroker] Re: Multi Core Optimization, L2 Cache &
Optimization Run Times
To: amibroker@xxxxxxxxxps.com
> Sure ... But I was talking about 'all other things being equal'
> and doubling the core. Check your table. Same data or ?
>
> Regards, Ton.
>
> ----- Original Message -----
> From: Fred Tonetti
> To: amibroker@xxxxxxxxxps.com
> Sent: Thursday, June 19, 2008 2:06 PM
> Subject: RE: [amibroker] Re: Multi Core Optimization, L2 Cache
> & Optimization Run Times
>
>
>
> Data .
>
>
>
>
> -----------------------------------------------------------------
> -------------
>
> From: amibroker@xxxxxxxxxps.com
> [mailto:amibroker@yahoogroups.com] On Behalf Of Ton
Sieverding
> Sent: Thursday, June 19, 2008 1:55 AM
> To: amibroker@xxxxxxxxxps.com
> Subject: Re: [amibroker] Re: Multi Core Optimization, L2 Cache
> & Optimization Run Times
>
>
>
> For my information Fred, please mention one those things
> having such a influence on overhead that I cannot use it as a
> constant in a 'Rule of thumb' ...
>
>
>
> Regards, Ton.
>
>
>
> ----- Original Message -----
>
> From: Fred
>
> To: amibroker@xxxxxxxxxps.com
>
> Sent: Wednesday, June 18, 2008 7:49 PM
>
> Subject: [amibroker] Re: Multi Core Optimization, L2 Cache &
> Optimization Run Times
>
>
>
> Overhead is not a constant ... It is a function of a variety
> of
> things not all of which am I even aware of and some of which
> can be
> fairly significant ...
>
> --- In amibroker@xxxxxxxxxps.com, "Ton Sieverding"
> wrote:
> >
> > Of course not. You'll always keep the overhead as a
> constant. But
> as a rule of thumb it works fine for me in situations where
> time is
> the bottleneck ...
> >
> > Regards, Ton.
> >
> > ----- Original Message -----
> > From: Fred Tonetti
> > To: amibroker@xxxxxxxxxps.com
> > Sent: Wednesday, June 18, 2008 2:25 PM
> > Subject: RE: [amibroker] Multi Core Optimization, L2 Cache
> &
> Optimization Run Times
> >
> >
> >
> > The relationship isn't quite that clear .
> >
> >
> >
> > I'm still playing with this feature for IO but if you are
> using
> AB's exhaustive search for a variety of things and have a
> multiple
> CPU / Core machine try MCO on some of your optimization
> problems .
> >
> >
> >
> >
> > ----------------------------------------------------------
> ----------
> >
> > From: amibroker@xxxxxxxxxps.com
> [mailto:amibroker@yahoogroups.com] On Behalf Of Ton
Sieverding
> > Sent: Wednesday, June 18, 2008 4:29 AM
> > To: amibroker@xxxxxxxxxps.com
> > Subject: Re: [amibroker] Multi Core Optimization, L2 Cache
> &
> Optimization Run Times
> >
> >
> >
> > Fred does this show me that 'doubling the cores equals
> halving
> the time' -)
> >
> >
> >
> > Regards, Ton.
> >
> >
> >
> > ----- Original Message -----
> >
> > From: Fred Tonetti
> >
> > To: amibroker@xxxxxxxxxps.com
> >
> > Sent: Wednesday, June 18, 2008 1:10 AM
> >
> > Subject: RE: [amibroker] Multi Core Optimization, L2 Cache
> &
> Optimization Run Times
> >
> >
> >
> > Here are some results I got with my new toy .
> >
> > This is using a reasonably complex system on ~500 symbols
> over
> 10 years i.e. ~2500 bars ...
> >
> > Cores Time Percent
> >
> > 1
> 218
> >
> > 2 114 52.29%
> >
> > 3 79 36.24%
> >
> > 4 62 28.44%
> >
> > 5 52 23.85%
> >
> > 6 46 21.10%
> >
> > 7 41 18.81%
> >
> > 8 37 16.97%
> >
> > As expected the higher you go the more overhead there is .
> but
> improvements like this are still well worth the effort .
> Especially
> on a single box .
> >
> >
> > ----------------------------------------------------------
> --------
> >
> > From: amibroker@xxxxxxxxxps.com
> [mailto:amibroker@yahoogroups.com] On Behalf Of Steve
Dugas
> > Sent: Saturday, June 14, 2008 7:00 PM
> > To: amibroker@xxxxxxxxxps.com
> > Subject: Re: [amibroker] Multi Core Optimization, L2 Cache
> &
> Optimization Run Times
> >
> > Very interesting Fred, thanks! This looks encouraging, at
> least for us EOD guys.
> >
> > One thing I notice - at 32 tickers, it looks like the
> curve
> has "recovered" to what you might expect to see even if
> there was no
> dent at 16. And also, after 32 the curve seems to get a
> second wind,
> i.e. it "inverts" and the time per symbol decreases *more*
> rapidly as
> more tickers are added. What do you think might account for
> that? Is
> it just due to the log nature of the chart? Thanks!
> >
> > Steve
> >
> > ----- Original Message -----
> >
> > From: Fred Tonetti
> >
> > To: amibroker@xxxxxxxxxps.com
> >
> > Sent: Saturday, June 14, 2008 5:49 PM
> >
> > Subject: [amibroker] Multi Core Optimization, L2 Cache &
> Optimization Run Times
> >
> > Given TJ's comments about:
> >
> > - The amount of memory utilized in processing
> symbols of data
> >
> > - Whether or not this would fit in the L2 cache
> >
> > - The effect it would have on optimizations when it
> didn't
> >
> > I finally got around to running a little benchmark for
> Multi
> Core Optimization using the program I wrote and posted ( MCO
> ) which
> I'll be posting a new version of shortly .
> >
> > These tests were run under the following conditions:
> >
> > - A less than state of the art laptop with
> >
> > o Core 2 Duo 1.86 Ghz processor
> >
> > o 2 MB of L2 Cache
> >
> > - Watch Lists of symbols each of which
> >
> > o Contains the next power of two number of symbols of
> the previous i.e. 1, 2, 4, 8, 16, 32, 64, 128, 256
> >
> > o Contains Symbols containing ~5000 bars of data .
> >
> > Given the above:
> >
> > - Each symbol should require 160,000 bytes i.e.
> ~5,000 bars * 32 bytes per bar
> >
> > - Loading more than 13 symbols should cause L2 cache
> misses to occur
> >
> > Results:
> >
> > - See the attached data & chart
> >
> > There are several interesting things I find regarding the
> results .
> >
> > - The "dent" in the cu rve looking left to right
> occurs right where you'd think it would, between 8 symbols
> and 16
> symbols i.e. from the point at which all data can be loaded
> to and
> accessed from the L2 cache to the point where it no longer
> can .
> >
> > - The "dent" occurs in the same place running either
> one or two instances of AB
> >
> > - The "dent" while clearly visible is hardly
> traumatic in terms of run times
> >
> > - The relationship of run times between running one
> and two instances of AB is consistent at 40% savings in
> terms of run
> times regardless of the number of symbols.
> >
> > - This is also in line when one looks at how much
> CPU is utilized when running one instance of AB which on the
> test
> machine is typically in the 54 - 60% range.
> >
> > I have a new toy that I'll be trying these benchmarks on
> again shortly i.e. a dual core 2 duo quad 3.0 ghz .
> >
> >
> >
> >
> > ----------------------------------------------------------
> --------
> >
> > I am using the free version of SPAMfighter for private users.
> > It has removed 480 spam emails to date.
> > Paying users do not have this message in their emails.
> > Try SPAMfighter for free now!
> >
> >
> >
> >
> >
> >
> > ----------------------------------------------------------
> ----------
> > I am using the free version of SPAMfighter for private users.
> > It has removed 480 spam emails to date.
> > Paying users do not have this message in their emails.
> > Try SPAMfighter for free now!
> >
>
>
>
>
> ---------------------- -------------------------------------------
> -------------
> I am using the free version of SPAMfighter for private users.
> It has removed 480 spam emails to date.
> Paying users do not have this message in their emails.
> Try SPAMfighter for free now!
>
>
>
>
__._,_.___
Please note that this group is for discussion between users only.
To get support from AmiBroker please send an e-mail directly to
SUPPORT {at} amibroker.com
For NEW RELEASE ANNOUNCEMENTS and other news always check DEVLOG:
http://www.amibroker.com/devlog/
For other support material please check also:
http://www.amibroker.com/support.html
![]()
__,_._,___
|
|
|
|
|