Re^4: Efficient bit-twiddling in Perl.

Your benchmark is not very realistic. As $n doesn't vary, you are completely ignoring the effect of the CPU cache misses that the lookup table may introduce.

The version of my benchmark I posted was the one I use -- in conjunction with -N=1 and uncommenting the print "@_"; -- to check that the output from all the methods is correct.

For timing runs, I operate on the loop counter $_, which when -N=10e6, is enough to exercise the full range of the table 38 times.

And I still get 20%+ improvement from the AoAs lookup:

Results

C:\test>1021064
Shift&and took: 0.000000606833 seconds
  Lookup  took: 0.000000485629 seconds
  Lookup2 took: 0.000000669586 seconds
(un)pack  took: 0.000007564075 seconds
[download]

In general, I've found it very difficult to detect, much less measure any discernible effect from cpu caching in perl code on my machine. It shows up readily in tight loops in C code, but Perl's memory allocation is so cache unfriendly that it rarely seems to come into play.

I would be interested to see the output from the above on your machine if you have a coupe of minutes.

With the rise and rise of 'Social' network sites: 'Computers are making people easier to use everyday'

Examine what is said, not who speaks -- Silence betokens consent -- Love the truth but pardon error.

"Science is about questioning the status quo. Questioning authority".

In the absence of evidence, opinion is indistinguishable from prejudice.

Comment on Re^4: Efficient bit-twiddling in Perl. Select or Download Code

Replies are listed 'Best First'.
Re^5: Efficient bit-twiddling in Perl. by salva (Canon) on Mar 01, 2013 at 13:25 UTC
`$ perl /tmp/1021241.pl Shift&and took: 0.000000844352 seconds Lookup took: 0.000000794679 seconds Lookup2 took: 0.000000945985 seconds (un)pack took: 0.000007257208 seconds` [download]	[reply] [d/l]
Re^6: Efficient bit-twiddling in Perl. by BrowserUk (Patriarch) on Mar 01, 2013 at 13:28 UTC
Less, but still a saving. Thanks. What cpu are you using?	[reply]
Re^7: Efficient bit-twiddling in Perl. by salva (Canon) on Mar 01, 2013 at 14:11 UTC
AMD Athlon(tm) 64 X2 Dual Core Processor 4000+ (IIRC, this is a 2GHz processor)	[reply]
Re^8: Efficient bit-twiddling in Perl. by BrowserUk (Patriarch) on Mar 01, 2013 at 14:30 UTC
Re^5: Efficient bit-twiddling in Perl. by Tux (Canon) on Mar 01, 2013 at 14:05 UTC
`tables generated sample data generated Shift&and took: 0.000000283640 seconds Lookup took: 0.000000553529 seconds Lookup3 took: 0.000000308301 seconds Lookup4 took: 0.000000435056 seconds Lookup5 took: 0.000000487484 seconds Lookup6 took: 0.000000454496 seconds Lookup7 took: 0.000000476669 seconds Linux 3.4.28-2.20-desktop [openSUSE 12.2 (Mantis)] x86_64 Xeon(R) CPU E5-1650 0 @ 3.20GHz/1200(12) x86_64 16009 Mb This is perl 5, version 16, subversion 2 (v5.16.2) built for x86_64-li +nux-ld` [download] I think that proves my point in Re^3: Efficient bit-twiddling in Perl. Enjoy, Have FUN! H.Merijn	[reply] [d/l]
Re^6: Efficient bit-twiddling in Perl. by BrowserUk (Patriarch) on Mar 01, 2013 at 14:49 UTC
I think that proves my point in Re^3: Efficient bit-twiddling in Perl. I am stunned by the 20% gain you get, and wonder if that would differ per perl version and/or architecture. It absolutely will, but as I said in the OP, this is for me, on my hardware. Not an exemplar for anyone else. With the rise and rise of 'Social' network sites: 'Computers are making people easier to use everyday' Examine what is said, not who speaks -- Silence betokens consent -- Love the truth but pardon error. "Science is about questioning the status quo. Questioning authority". In the absence of evidence, opinion is indistinguishable from prejudice.	[reply]
Re^5: Efficient bit-twiddling in Perl. by Tux (Canon) on Mar 01, 2013 at 14:07 UTC
`Shift&and took: 0.000000288148 seconds Lookup took: 0.000000252554 seconds Lookup2 took: 0.000000339390 seconds (un)pack took: 0.000002284377 seconds` [download] Enjoy, Have FUN! H.Merijn	[reply] [d/l]


We don't bite newbies here... much
	PerlMonks