32 bit faster than 64 bit

I ran a DAQ program on LabVIEW 2011 32 bit and it used 5-6% CPU according to the Task Manager.
I ran the same program under LabVIEW 2013 64 bit and it used 8-9% CPU according to the Task Manager.
I thought the 64 bit version would be more CPU effecient than the 32 bit version. What's up?
Thanks,
Mark
Solved!
Go to Solution.

mlevine wrote:
It wasn't the extended address space but the accumulator size that should get faster performance. I'd need less CPU cycles to do double precision math on a 64 bit processor than on a 32 bit processor. Of course if LabVIEW 32 bit uses the 64 bit accumulators than I wouldn't expect the CPU load to change. Anyway the sales guy said I'd see a 20% improvement in execution time. I don't see how that's possible with the CPU utilization has increased for the 64 bit version.
You seem to be throwing everything ( N bit processor, N bit LabVIEW, N bit OS, N bit address space, N bit accumulators, etc.) into one big blurry pile. We had a similar discussion a long time ago, see my comments here.
Except for the increased address space, using 64bit LabVIEW does not give you any significant advantage.
(Quite a while ago, I was doing some testing and recompiled my DLLs under 64bit intel Fortran and build a LabVIEW 64bit application of my EPR fitting program. The program contains an extensive benchmarking facility. The 64 bit application was nearly identical in speed (or even slightly slower) and thus I abandoned the idea of potentially moving to 64bit.)
Runing LabVIEW 32bit on a 64bit OS gives you access to a full 4GB of RAM, while running the same on a 32 bit OS gives you less (2 or 3GB max), so going to a 64bit OS for a 32 bit application has clear advantages (details). Upgrading to 64bit LabVIEW is typically not worth it and you get less support for certain drivers and toolkits.
LabVIEW Champion . Do more with less code and in less time .

Similar Messages

Is a binary on 32 bit faster than a 64 bit binary in solaris ?

I timed a program for both 64 bit and 32 bit . The code is something like this --
#include<stdio.h>
#include<string.h>
#include<stdlib.h>
int main (int argc,char **argv)
int count=0;
int count2=0;
int u=0;
int count3=0;
int sizeoffile=0;
int sizefile[5];
for(u=0;u<5;u++)
sizefile=1;
printf("%d\n",sizefile[u]);
char a='a';
char *b ;
FILE *file ;
b = (char *)malloc(512*sizeof(char));
while(count <512)
strncpy(b+count,&a,1);
count++;
for(u=0;u<2;u++)
sizeoffile=0;
if(u==0)
file=fopen("./writesize1","a");
else if (u==1)
file=fopen("./writesize2","a");
else if (u==2)
file=fopen("./writesize3","a");
else if (u==3)
file=fopen("./writesize4","a");
else if (u==4)
file=fopen("./writesize5","a");
while(sizeoffile<sizefile[u])
while(count2<(1024*1024))
count3=0;
while(count3 < 2)
fprintf(file,"%s",b);
fprintf(file,"\n");
fflush(file);
count3++;
count2++;
count2=0;
// count3++;
count3=0;
sizeoffile++;
fclose(file);
return 0;
The above code is crude code to write files of 1 GB.
I timed the above code binaries for 32 and 64 bit on a solaris 10 box . I got the following times :
for 32 bit : 2.16796for 64 bit : 2.5039466
Is this the expected behaviour or something I am missing ?
Edited by: rarpit on Mar 18, 2009 9:59 PM

Reasons a 64-bit program might be better:
* Can directly access more than 4GB of VM
* Has direct access to 64-bit math routines
* On x86, has access to more registers (big win for some code/compiler combinations) Shouldn't affect SPARC much.
Reasons a 32-bit program might be better:
* Can run on both 32-bit and 64-bit kernels
* Pointers are smaller. More code can fit in CPU cache, may run faster
* Memory footprint slightly smaller due to smaller pointers
So the general case is that unless you need the extra VM space, 64-bit math, have a special need to access 64-bit libraries, or your compiler is doing a great job of using the extra registers on x86, there's not much benefit to creating a 64-bit binary.
All that said, your program appears to be writing large files to disk. That task should be completely dominated by your I/O times. Did you run them more than once? I would imagine both versions to be identical because anything other than the disk writes will be in the noise.
Darren

MBP 13" not really faster than MB 13"

Hi
I want to upgrade my 4 year old MB 13". I really like the size... I waited a long time for the new processors to come. Now I discovered that the 13" model does not feature the i5 and i7 processors and I heard that the 13" MBP cannot be compared to the 15" model in terms of performance.
I will do more photo editing (photoshop) and video editing (final cut express) and my old MB is getting really slow...
Any advice on choice of Macbook - Pro or normal...
Thanks!

Hi niefl,
First of all (and I know this isn't quite what your are asking) although the new MBP isn't as fast as the new 15" model, it is a LOT quicker than a four year old MB. We have an early 2 GHz black CD MacBook (about the same generation as yours), a later , Core 2 Duo, MB, a SantaRosa 15" MBP from 2007, and a June 2009 13" MBP . Even the June 2009 13" model is much, much faster in any situation that requires processor power for things like photo editing or video editing than the early 2 GHz MB .
As far as comparison with the late 2009 polycarbonate MB goes, the benchmarks published by MacWorld (see http://www.macworld.com/article/147071/2010/04/13inchmacbookprobenchmarks.html) indicate that the new MBP 13 is a bit faster than the MB but not by a huge margin - maybe about 10% on most tasks.
But there are other very good reason to get the MBP if you can afford the extra couple of hundred dollars. For video work the huge difference is firewire. USB is better on recent Macs than it was in the days when your old MB was released, but it is still slower than FW400 and much, much slower than the Firewire 800 available on the MBP but not the MB.
Secondly the "standard" base configuration of the MBP comes with 4 gig of RAM, while the MB comes with just 2Gig. To do what you want to do efficiently you will need at least 4 gig of RAM. You will really notice the benefit of this with both photo editing and video work. Simply upgrading the RAM on the MB to 4 gig will cost you around half the difference in price between the two machines anyway!
Thirdly, the MBP comes with an illuminated keyboard. I never realised how useful this would be until I obtained my first MBP. Once you have been using one for a while it is hard to go back to the non-iluminated one.
Fourthly the MBP is a little lighter and slimmer than the MB.
Fifthly, our own experience has been that the aluminium MBPs are substantially tougher than the polycarbonate ones. Not only are they much more scratch resistant, but they are also less prone to case fractures through minor knocks.
Sixth, they have batteries / power management systems that give you longer battery charge life.
Seventh, they provide full sound output through the minidisplay port if you wish to hook up to an HDMI TV (unlike the MB)
Finally, they look better!
If you assume that you will have to upgrade the MB to 4 Gig of RAM anyway, then you get all the rest for just $100!
Pretty hard to beat when it comes to value IMHO!
Having said all of that, there is no doubt that the base model i5 MBP 15" is a very sweet computer, and ideal for the purposes you speak of, but if your budget, or demands for portability, means that you are choosing between the 13" MBP and the MB, I think the current model of the MBP13 wins hands down when it comes to overall value, and is a bit faster too.
Cheers
Rod

How can I download music from itunes store at a higher bit rate than 128k?

I have been able to import music from cd's at bit rates higher than 128kbs by clicking into the preferences item under the "edit" drop down menu. however, I have not been able to locate a similar command for itunes music downloads. is it possible to increase the bitrate of music downloads from itunes faster than 128kbps? if so, how?
gateway Windows XP AMD 64

No, store downloads have always been ONLY 128 kbps. With new deal between EMI & Apple, sometime next month you will be able to download EMI artists only at a higher bitrate without the DRM, for a slightly higher price. For now, though, all downloads are still 128 kbps. Your import settings only affect the CD's you rip your self. Hope this helps.

LR2 64-bit slower than 32-bit (Mac)

I ran a test a while back with Lightroom 1.3.1, generating 1:1 previews on a test directory of images:
http://www.rassoc.com/gregr/weblog/2008/02/24/mac-pro-performance/
On a Mac pro 2.8 GHz 8-core machine with 12GB of RAM, I found I could generate 211 1:1 previews for my directory in about 5:36, or 1.59 seconds/image.
I've found Lightroom 2, in 32-bit mode on the same machine, to run roughly the same speed.
However - running Lightroom 2 in 64-bit mode on this same machine takes 7:23, or 2.10 seconds per image. It's typically using >500% of CPU.
Why is it so much slower running 64-bit?

My results are repeatable; 1:1 preview generation takes about 30% longer using 64-bit than 32-bit. I opened a support ticket on this (case number 180331555) - here is the response from Adobe:
I understand that Lightroom# takes longer to render previews in 64-bit
mode than in 32-bit mode.
I am able to duplicate this basic behavior when rendering a relatively
small batch of previews in Lightroom.
It is not expected that all operations in 64-bit mode will perform
faster. Memory access generally takes longer in 64-bit mode due to
having to address a larger memory space.
Performance benefit should be most noticeable when performing operations
that use more than 4GB of memory. At this point, the 32-bit application
will experience a large performance penalty due to increased hard drive
access.
Hmm. Sounds like they were able to reproduce the behavior I see, but I can't think of why memory access should be slower in 64-bit.

ITunes will not open and tells me to use the "information" to open in 32 bit rather than 64. but the information pane does not offer that option ...

I am trying to open my iTune 10.4 on my mac mini which is running OS 10.6.8, and I get the message that I need to use the information pane to open in 32-bit rather than 64. But the information pane does not offer this option. I'm in a vicious circle of opening, getting this message, then having to close. Did this come about after the June update of iTunes? And if so, why haven't they fixed it? And what can I do? You'd think Apple would want be to be able to spend my money in their store ...

Try following steps and test one at a time:
1. Restart computer, right mouse click iTunes icon and select "Run As Administrator"
2. If that does not work, check to see if this file APSDaemon.exe is the problem here.
Close your iTunes.
Press Ctrl-Alt-Del key and choose Task Manager. In the "Processes" Tab, select the file APSDaemon.exe and click End Prosses button, then close the task manager window.
Now open itunes and see if it is working?
If that works, to prevent having to do the same process everytime you restart Windows, go to. START button, type in
MSCONFIG
Hit ENTER
Click STARTUP Tab, Uncheck "Apple Push", click OK.
Restart Windows.
3. If that fails or you don't see ApsDaemon.exe in the Processes, refer to following article to remove SC files:
http://support.apple.com/kb/TS2363
4. If that fails, repair or reinstall your Quicktime. START / CONTROL PANEL / PROGRAMS N FEATURES / hightlight QUICKTIME and click REPAIR.

Adobe always quits unexpectedly in Mac when I read a bit fast. How can i deal with it, plz?

Adobe always quits unexpectedly in Mac when I read a bit fast.
It is the latest update.
How can i deal with it, plz?

You posted in the forum for iPad and iPhone (different app). I've moved your question to the Reader forum for desktop/laptop computers.

My serial number is not valid anymore ? I bought my photoshop and I have been using it for a little bit more than one year...

Hello,
I bought my Photoshop Extended (PC) last year in the US. I have been using it for a bit more than a year. Today, opening Photoshop, Adobe asks me to pay or enter my serial number. So I enter the number (again), and it says that the number is invalid.
My version is an official version, I paid for it.
What I am supposed to do now ?
Thx

We are basically users and can't really help with activation. So unless a staff member can check in, you need to speak to Customer Service.
http://helpx.adobe.com/x-productkb/global/service1.html
Serial number and activation chat
or
800-833-6687
Monday—Friday, 5am—7pm PT

Hi,have you ever met such problem- one side of the display a bit lower than another,it is new, what should i do ?

Hi,have you ever met such problem- one side of the display a bit lower than another,it is new, what should i do ?

Call Apple Support

Query of query - running slower on 64 bit CF than 32 bit CF

Greetings...
I am seeing behavior where pages that use query-of-query run slower on 64-bit Coldfusion 9.01 than on 32-bit Coldfusion 9.01.
My server specs are : dual processer virtual machine, 4 GIG ram, Windows 2008 Datacenter Server r2 64-bit, Coldfusion 9.01. Note that the coldfusion is literally "straight out of the box", and is using all default settings - the only thing I configured in CF is a single datasource.
The script I am using to benchmark this runs a query that returns 20,000 rows with fields id, firstname, lastname, email, city, datecreated. I then loop through all 20,000 records, and for each record, I do a query-of-query (on the same master query) to find any other record where the lastname matches that of the record I'm currently on. Note that I'm only interested in using this process for comparative benchmarking purposes, and I know that the process could be written more efficiently.
Here are my observed execution times for both 64-bit and 32-bit Coldfusion (in seconds) on the same machine.
64 bit CF 9.01: 63,49,52,52,52,48,50,49,54 (avg=52 seconds)
32 bit CF 9.01: 47,45,43,43,45,41,44,42,46 (avg=44 seconds)
It appears from this that 64-bit CF performs worse than 32-bit CF when doing query-of-query operations. Has anyone made similar observations, and is there any way I can tune the environment to improve 64 bit performance?
Thanks for any help you can provide!
By the way, here's the code that is generating these results:

<CFQUERY NAME="ALLRECS" DATASOURCE="MyDsn">
    SELECT * FROM MyTBL
</CFQUERY>
<CFLOOP QUERY="ALLRECS">
    <CFQUERY NAME="SAMELASTNAME" DBTYPE="QUERY">
        SELECT * FROM ALLRECS
        WHERE LN=<CFQUERYPARAM VALUE="#ALLRECS.LN#" CFSQLTYPE="CF_SQL_VARCHAR">
        AND ID<><CFQUERYPARAM VALUE="#AllRecs.ID#" CFSQLTYPE="CF_SQL_INTEGER">
    </CFQUERY>
    <CFIF SameLastName.RecordCount GT 20>
        #AllRecs.LN#, #AllRecs.FN# : #SameLastName.RecordCount# other records with same lastname<BR>
    </CFIF>
</CFLOOP>

BoBear2681 wrote:
..follow-up: ..Thanks for the follow-up. I'll be interested to hear the progress (or otherwise, as the case may be).
As an aside. I got sick of trying to deal with Clip because it could only handle very small Clip sizes. AFAIR it was 1 second of 44.1 KHz stereo. From that point, I developed BigClip.
Unfortunately BigClip as it stands is even less able to fulfil your functional requirement than Clip, in that only one BigClip can be playing at a time. Further, it can be blocked by other sound applications (e.g. VLC Media Player, Flash in a web page..) or vice-versa.

Keyboard sound issue / camera overheats a bit faster once again after 5.1.1

Let us know when you do

i dunno i think there is an issue with the keyboard sound. Like for example when you type "Hello" supposedly you will hear 5 clicks right!? but for some reason you will only hear 4. Its like the phone is having hard time catching up on what you are typing. Its not synchronize. Also camera overheat a bit faster again. not happening with the previous version done hard reset and reupdate using pc companion still the same.

I bought my iphone 5 a bit more than a month ago. Few days ago it is broken (not my fault). Is it possible to completely return it and get money back?

I bought my iphone 5 a bit more than a month ago. Few days ago it is broken (not my fault). Is it possible to completely return it and get money back?

No, you cannot get your money back.
If you have tried the basics restart, reset, restore, then make an appointment at the genius bar. If the iphone is defective then they will replace it.

Intel Core 2 Duo: 64-bit or 32-bit?

Just a short question: is Intel Core 2 Duo a 64-bit processor, or a 32-bit one? I know that according to Wikipedia it's a 64-bit processor, but I have heard (rumors?) that it only "emulates" 64-bit mode, and in fact it is a 32-bit processor.
I have such a processor and I'd like to know what version of Arch should I install: i686 or x86_64 (in order to get the best performance)?

Thank you all for your answers, they were very helpful!
chicha wrote:All the people I know using a 64 bit architecture did not notice a real performance improvement which could justify to change your 32 bit system to a 64 bit system. More ever a 64 bit system consumes more memory than a 32 bit one (the binaries are bigger).
Quite interesting. But there are also other issues, mentioned later...
chicha wrote:
Here are 3 situations I would recommand a 64 bit system :
1 - For the fun and curiosity
2 - You have a big memory ( >= 2Go )
3 - You have a specific need which justify the 64 bit (special software, research, advanced use such as cluster ...)
Ad.1) I use my system for work, not fun. I need a tool, not a toy.
Ad.2) My new machine has 2 GB RAM. Moreover, one of the reasons to buy the machine was the ability to install total of 4 GB RAM. I'm a developer and it is possible that in the future (1, 2 years) I will need more RAM than I need now.
Ad.3) Not my case.
chicha wrote:
Here are 3 situations I would not recommand a 64 bit system :
1 - You think your system will be faster than a 32 bit one.
2 - You do not know what a 64 bit system is against a 32 bit system and its consequences on programming stuffs
3 - You do not want to bother with recompiling stuffs or change some software you use because they do not support 64 bit.
Ad.1) I don't think so; I didn't think so. But I'm not a "hardware guy", so I wanted to make myself sure...
Ad.2) I'm a developer, but my target is desktop. I use Java and Python, cross-platform languages. Do I really need to care about it? Isn't it the JVM's and Python's developers' problem? (Or, perhaps, I'm missing the point here?)
Ad.3) I don't want to bother...
Let's sum it up:
1) Since there is no noticable performance improvement of 64-bit OS over 32-bit one, using 32-bit OS is recommended (lower memory consumption).
2) Since my machine has 2 GB RAM, and it will be upgraded to 4 GB in 1-2 years, 64-bit OS is recommended.
The conclusion: I should install 64-bit OS.
Am I right?

64-bit or 32-bit Intel?

I am assuming these new Intel machines are still the old 32-bit style. Is this correct? What are we sacrificing for back stepping? I work in a PC environment office with my G5 and it's amazing how much clearer and brigher my monitor (we all have the same one) looks next to the others.

Jim,
As as software engineer who has worked in various application and systems areas and over the era of transition from 16-bit to 32-bit hardware, I can only agree with you that choice of hardware must be dictated by the needs of the use to which it will be put. So clearly for today's desktops (and even more so for laptops), 32-bit hardware is certainly adequate. Whether or not disk speeds are a factor also depends on the application. Obviously, database-intensive applications typically run the mass storage devices ragged. Other applications barely touch the disk once the program and its data are loaded.
Anyway, what I really wanted to point out, though you're probably aware of this already, is that the new iMac (Intel dual-core model) and the MacBook Pro both use faster memory and memory buses than any of their predecessors (with the possible exception of the heavy-duty G4 or G5 desktops--I'm not really familiar with their hardware details).
To give you an idea of a result I found surprising (pleasantly so), a theorem prover I've written in Java (a very CPU- and memory-intensive application) runs much faster (about 50% faster) on the iMac with its dual-core 2 GHz processor(s) than it does on the Linux box with an Intel P4 HyperThreading CPU running at 3 GHz. The reason? The RAM and FSB bus on that Linux box are a lot slower than the ones on the iMac. So even though this application, which currently is principally single-threaded (Java apps can always use a processor core for garbage collection), benefits more from the faster FSB and RAM on the iMac than it is hurt by having a processor running only two thirds the speed of the on in the Linux box.
Randall Schulz
iMac 20" Core Duo; MacBook Pro Mac OS X (10.4.5)

How can floating point division be faster than integer division?

Hello,
I don't know if this is a Java quirk, or if I am doing something wrong. Check out this code:
public class TestApp
     public static void main(String args[])
          long lngOldTime;
          long lngNewTime;
          long lngTimeDiff;
          int Tmp;
          lngOldTime = System.currentTimeMillis();
          for( int A=1 ; A<=20000 ; A++)
               for( int B=1 ; B<=20000 ; B++)
                    Tmp = A / B;
          lngNewTime = System.currentTimeMillis();
          lngTimeDiff = lngNewTime - lngOldTime;
          System.out.println(lngTimeDiff);
}It reports that the division operations took 18,116 milliseconds.
Now check out this code (integers replaced with doubles):
public class TestApp
     public static void main(String args[])
          long lngOldTime;
          long lngNewTime;
          long lngTimeDiff;
          double Tmp;
          lngOldTime = System.currentTimeMillis();
          for( double A=1 ; A<=20000 ; A++)
               for( double B=1 ; B<=20000 ; B++)
                    Tmp = A / B;
          lngNewTime = System.currentTimeMillis();
          lngTimeDiff = lngNewTime - lngOldTime;
          System.out.println(lngTimeDiff);
}It runs in 11,276 milliseconds.
How is it that the second code snippet could be so much faster than the first? I am using jdk1.4.2_04
Thanks in advance!

I'm afraid you missed several key points. I only used
Longs for measuring the time (System.currentTimeMillis
returns a long). Sorry you are correct I did miss that.
However, even if I had, double is
also a 64-bit data type - so technically that would
have been a more fair test. The fact that 64-bit
floating point divisions are faster than 32-bit
integer divisions is what confuses me.
Oh, just in case you're interested, using float's in
that same snippet takes only 7,471 milliseconds to
execute!Then the other explaination is that the Hotspot compiler is optimizing the floating point code to use the cpu floating point instructions but it is not optimizing the integer divide in the same way.

32 bit faster than 64 bit

Similar Messages

Maybe you are looking for