-----Original Message----- From: Anton Aylward <opensuse@antonaylward.com> To: opensuse@opensuse.org Subject: Re: [opensuse] 64 bit vs 32 bit RAM consumption Date: Tue, 23 Jul 2013 19:35:51 -0400 Carlos E. R. said the following on 07/23/2013 07:01 PM:
-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA256
El 2013-07-23 a las 15:44 -0400, Anton Aylward escribió:
Werner Flamme said the following on 07/23/2013 02:45 PM:
If you have to add 2 and 3 it will take the same time on both archs. 64 bit is not faster, it is larger. Compare a road truck of 6 wheels to another of 12 wheels and double length.
Huh? That doesn't make sense to me? Can you explain it it detail - and drop the analogy.
Give op-code example. Doesn't have to be from a real machine, just hypothetical.
No, I will not bother. If you don't understand it, I will not bother to explain.
I think we're out of sequence here, Carlos. I'm in agreement with you, it was Werner's post I was questioning. It doesn't matter if the "2" and the "3" are in registers or memory, if its a register-to-register, register-to-memory or memory-to-memory operation. These are small integers. The issue is the op-code set. I couldn't figure what Werner's bit about 'zeros' had to do with it. The only reason I can' assert all this for an 8-bit machine is that it probably won't have op-codes for all those classes of operations. But yes, 64, 32 and 16 bit machines certainly. (I get to pick and choose, mind.) -----Original Message----- Let me chime in, Indeed the question if your dealing with mem or reg isn't that important. More relevant is the size on the variable you are working on. In one of my lab exercises we had to write a arithmetic-lib. When operating on uint128 with an 8-bit cpu, it takes quite more time and code, compared with a cpu with broader registers. The other way round, assuming a 64-bit datapath between cpu-and mem, fetching a 64-bit variable is as expensive as an 8-bit one. Between those obvious extremes, the is a large grey area. Secondly, the number of application (no number-crunching benchmarks) that uses var larger than 32-bit is very limited. It is more the OS that is using large numbers (mem, disk) _IF_ (!) programmers never used variables larger than they really needed, i would say that 32-bit would save time&mem. (i mean using 32-bit virtual machines inside a 64-bit KVM/XEN) As explained above using vars (data/pointers) larger than your internal architecture is costly. In those cases using 32-bit is contra-productive. Early on the thread, PAE was mentioned, i dare say it is an anachronism. Ten years ago, machines started to appear that could hold more than 4GB mem, but few applications were built for it. If you have 4GB or more installed, just go for a 64-bit OS. Personally, i use mostly use 32bit. Also because i have also to deal with much older hardware. hw -- To unsubscribe, e-mail: opensuse+unsubscribe@opensuse.org To contact the owner, e-mail: opensuse+owner@opensuse.org