Re: [amibroker] Multi Core Optimization, L2 Cache & Optimization Run Times

["Steve Dugas" <sjdugas@xxxxxxxxxxx>]

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@xxxxxxxxxxxxxxx

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 curve 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 ?

__._,_.___

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

Your email settings: Individual Email|Traditional
Change settings via the Web (Yahoo! ID required)
Change settings via email: Switch delivery to Daily Digest | Switch to Fully Featured
Visit Your Group | Yahoo! Groups Terms of Use | Unsubscribe

__,_._,___