Catch up on stories from the past week (and beyond) at the Slashdot story archive

 



Forgot your password?
typodupeerror
×
Software

Are 64-bit Binaries Slower than 32-bit Binaries? 444

JigSaw writes "The modern dogma is that 32-bit applications are faster, and that 64-bit imposes a performance penalty. Tony Bourke decided to run a few of tests on his SPARC to see if indeed 64-bit binaries ran slower than 32-bit binaries, and what the actual performance disparity would ultimately be."
This discussion has been archived. No new comments can be posted.

Are 64-bit Binaries Slower than 32-bit Binaries?

Comments Filter:
  • Re: OSNews (Score:5, Funny)

    by duffbeer703 ( 177751 ) * on Saturday January 24, 2004 @12:06AM (#8072821)
    In case anyone hasn't realized it yet, this article proves that OSNews is the most retarded website on the planet.

    The typical story is titled like "A comprehensive review of the Atari ST". The contents are typically something like... "I found an old Atari ST, but my cdrom wouldn't fit in the 5.25" disk drive and mozilla wouldn't compile. So the Atari sucks"

    I benchmarked a skilled Chinese abacus user against a C-programmer implementing an accounting system. The chinese dude figured out that 1+1=2 before the C-programmer loaded his editor, so the abacus is faster.
  • by paul248 ( 536459 ) on Saturday January 24, 2004 @12:07AM (#8072830) Homepage
    It all depends on how many of those 64 bits are 1's. 1's are a lot heavier than 0's, so too many of them will slow your program down a lot. If you compare a 32-bit program with all 1's, it will run significantly slower than a 64-bit program with only a few 1's. It's simple, really.
  • by Ken Broadfoot ( 3675 ) on Saturday January 24, 2004 @12:08AM (#8072832) Homepage Journal
    From the article:

    I create a very simple C file, which I call hello.c:

    main()
    {
    printf("Hello!\n");
    }

    Watch out... SCO owns this bit of code too...

    --ken
  • by Anonymous Coward on Saturday January 24, 2004 @12:10AM (#8072843)
    How do you figure? CMOS only uses energy when transitioning between one and zero, when both transistors are in the ohmic region (drawing current). I don't see how 1 is any more heavy than 0.
  • by Anonymous Coward on Saturday January 24, 2004 @12:11AM (#8072848)
    Here on planet Jokeania, we laugh at his statement.
  • by Anonymous Coward on Saturday January 24, 2004 @12:14AM (#8072871)
    Pointy haired boss: Dilbert! My laptop is awfully heavy. Is there anything I can do?

    Dilbert: Sure! Just start randomly deleting things. All that data can be pretty heavy!!!!

    (later)
    Pointy haired boss: Hmmm...Windows? My house already has all I need! *click* Yes! That's gotta be like 5 pounds!
  • by Anonymous Coward on Saturday January 24, 2004 @12:16AM (#8072887)
    does that mean you can optimize your code by constantly xoring variables with themselves?
  • by jusdisgi ( 617863 ) on Saturday January 24, 2004 @12:16AM (#8072888)
    Hey...that's funny...I just called a post off-topic that was a direct quote from the artical.

    Cool.

    Of course, the funny thing is that I'm right (in a way).
  • by momerath2003 ( 606823 ) * on Saturday January 24, 2004 @12:18AM (#8072894) Journal
    ...because otherwise the computer physically has to move twice as much data around for each operation it does.

    64-bit computers have to physically move data around? I suppose I'll have to buy a grappling arm attachment for my G5 to get it to work. :(
  • by archen ( 447353 ) on Saturday January 24, 2004 @12:19AM (#8072899)
    The same tricks that boost the performance of their CPU model numbers 20-30% over their clockspeed? =P
  • by HardCase ( 14757 ) on Saturday January 24, 2004 @12:21AM (#8072908)
    Makes me wonder what tricks AMD has managed to pull out of their hat to increase 64 bit performance by 20-30%...


    They didn't use an obsolete UltraSparc chip? ;-)

  • by CatGrep ( 707480 ) on Saturday January 24, 2004 @12:27AM (#8072931)
    Then 16bit binaries should be even faster then 32.

    And why stop there?

    8bits should really scream.

    I can see it now: 2GHz 6502 processors, retro computing. The 70's are back.
  • Benchmarks (Score:3, Funny)

    by Anonymous Coward on Saturday January 24, 2004 @12:33AM (#8072964)
    As it needs to be said for any benchmarking story:

    There are 3 types lies. Lies. Damned Lies. ...and benchmarks.
  • by Anonymous Coward on Saturday January 24, 2004 @12:41AM (#8073009)
    No one had tested it before to my knowledge, so predicting the outcome was impossible.

    yes, right. we predict only on things we've seen someone else do in the past.

    you've got the right idea, mate...
  • by Uncle Gropey ( 542219 ) on Saturday January 24, 2004 @12:48AM (#8073035) Journal
    It's not that the 1's are heavier, it's that they tend to snag in the system bus and take longer to travel than the smoother 0's.
  • by paul248 ( 536459 ) on Saturday January 24, 2004 @12:50AM (#8073052) Homepage
    That's why I modded my CPU to handle 0's and 8's instead. I call it the 8thlon XP.
  • by Frymaster ( 171343 ) on Saturday January 24, 2004 @12:55AM (#8073068) Homepage Journal
    There are 3 types lies. Lies. Damned Lies. ...and benchmarks.

    i've got some specint stats that show that damned lies are up to 30% faster.

  • Re: OSNews (Score:5, Funny)

    by DNS-and-BIND ( 461968 ) on Saturday January 24, 2004 @12:57AM (#8073080) Homepage
    Are you kidding? This guy is a genius. Not only did he actually figure out that the UltraSPARC-II processor is 64-bit, but he can actually use the file and time utilities! Most of the "linux admin" types I know who buy old Sparcs for the novelty factor end up putting linux on them anyway..."This Solaris stuff is too hard".
  • by Frymaster ( 171343 ) on Saturday January 24, 2004 @12:59AM (#8073085) Homepage Journal
    it's that they tend to snag in the system bus and take longer to travel than the smoother 0's.

    this reminds of "back in the day" when we ran a token ring network. when end users would complain about net outage we'd simply tell them that the token got stuck or, worse yet lost. fortunately, we have a backup token on floppy back in the systems room. it's an fddi token, mind you, so it's a bit bigger but if you don't kink the cabling it should work fine for now.

  • by appleLaserWriter ( 91994 ) on Saturday January 24, 2004 @12:59AM (#8073089)
    1's are a lot heavier than 0's

    On early systems, particularly before the 286, the mass differential between 0 and 1 was a serious issue. However, the 286's innovative pipeline system introduced a shift in focus from mass to width. As pipelines became increasingly narrow, words composed primarily of "1"s began to execute at a more rapid pace than those with a heavy weighting of "0"s.
  • by Art Tatum ( 6890 ) on Saturday January 24, 2004 @01:02AM (#8073103)
    Did you ever have them look for the token under their desks? More fun than telling them where the "any" key is. :-)
  • by Anonymous Coward on Saturday January 24, 2004 @01:52AM (#8073289)
    2^32 bytes of memory should be enough for anyone!
    -new bill gates quote
  • Re: OSNews (Score:2, Funny)

    by S.Lemmon ( 147743 ) on Saturday January 24, 2004 @01:57AM (#8073318) Homepage
    Ha! Shows what you know! Atari-STs came with a built-in 3.5" drive - not a 5.25" so I say nya! to your feeble attempt at computer critic criticism.
  • by fucksl4shd0t ( 630000 ) on Saturday January 24, 2004 @02:15AM (#8073402) Homepage Journal

    Man, I'm going offtopic, but back in my oil-changing days...

    Some new guy had started working, and his neck was redder than desert sand. He told me that his girlfriend's car had a blinker out on the left and he replaced the bulb and the light didn't come back on. I asked him if he checked his blinker fluid. He said he didn't know what blinker fluid was. I told him that blinker fluid sits in a reservoir in the middle of the car, and when you make a turn the fluid flows in the opposite direction of the turn, into the blinkers, to make sure that the electrical connection is good.

    He spent 3 hours the next morning, on his day off, calling up parts stores and asking them if they had any blinker fluid. Poor guy. I had to break it to him slowly...

  • by CaptainCarrot ( 84625 ) on Saturday January 24, 2004 @02:55AM (#8073500)
    Yeah, like that one time when I tripped over a coax while walking behind a row of Apollo DN660s and yanked it clean out of the connector. Yeesh! Tokens everywhere! I had to get the mop out, and here I was not even in the janitors' union. That by itself could have gotten me fired. As it was I didn't get caught for that, but the network went down and everyone knew it was my fault because of all the squashed token guts on the bottom of my shoes.

    We were finding the damn things in the ventilators for weeks afterward.

  • by scottgfx ( 68236 ) on Saturday January 24, 2004 @04:33AM (#8073806) Journal
    At a TV station I used to work at, we used to send people on searches for "Liquid Video". Pretty much the same results! It's amazing the people that get hired at TV stations. Mr. Blinker-Fluid would be a genius compared to some in my industry of choice.

    At the station I'm at now, they send PA's to ask the engineers for the "ChromaKey for the Genlock". :)
  • by ari_j ( 90255 ) on Saturday January 24, 2004 @07:11AM (#8074162)
    In high school, we put a girl up to getting her blinker fluid topped off at a service station. She went and asked about it, and the next day was quite irate with us. But that didn't stop us - within a week, we sent the same girl to go have the summer air taken out of her tires, to be replaced with winter air. Apparently she went back to the same shop to have them take care of this for her.

    That's the difference between a natural blonde and a dyed blonde.

This file will self-destruct in five minutes.

Working...