-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
____/ GreyCloud on Friday 01 Jan 2010 18:51 : \____
> Roy Schestowitz wrote:
>> ____/ GreyCloud on Thursday 31 Dec 2009 18:44 : \____
>>
>>> Roy Schestowitz wrote:
>>>> -----BEGIN PGP SIGNED MESSAGE-----
>>>> Hash: SHA1
>>>>
>>>> ____/ GreyCloud on Wednesday 30 Dec 2009 23:30 : \____
>>>>
>>>>> Roy Schestowitz wrote:
>>>>>> -----BEGIN PGP SIGNED MESSAGE-----
>>>>>> Hash: SHA1
>>>>>>
>>>>>> ____/ Peter KÃhlmann on Wednesday 30 Dec 2009 20:47 : \____
>>>>>>
>>>>>>> Roy Schestowitz wrote:
>>>>>>>
>>>>>>>> -----BEGIN PGP SIGNED MESSAGE-----
>>>>>>>> Hash: SHA1
>>>>>>>>
>>>>>>>> Ubuntu 32-bit, 32-bit PAE, 64-bit Kernel Benchmarks
>>>>>>>>
>>>>>>>> ,----[ Quote ]
>>>>>>>> | For this comparison we used Ubuntu 9.10 on a
>>>>>>>> | Lenovo ThinkPad T61 notebook running an Intel
>>>>>>>> | Core 2 Duo T9300 processor, 4GB of system
>>>>>>>> | memory, a 100GB Hitachi HTS7220 SATA HDD, and a
>>>>>>>> | NVIDIA Quadro NVS 140M. We were using the
>>>>>>>> | Ubuntu-supplied kernels that are based off the
>>>>>>>> | Linux 2.6.31 kernel in Ubuntu Karmic. Other
>>>>>>>> | packages that were maintained included GNOME
>>>>>>>> | 2.28.1, X Server 1.6.4, NVIDIA 195.22 display
>>>>>>>> | driver, GCC 4.4.1, and we were using the
>>>>>>>> | default EXT4 file-system with all other
>>>>>>>> | defaults. With Ubuntu to properly address 4GB
>>>>>>>> | or greater of system memory you need to use a
>>>>>>>> | PAE kernel as the Physical Address Extension
>>>>>>>> | support through the kernel's high-mem
>>>>>>>> | configuration options are not enabled in the
>>>>>>>> | default 32-bit kernels.
>>>>>>>> `----
>>>>>>>>
>>>>>>>> http://www.phoronix.com/scan.php?page=article&item=ubuntu_32_pae&num=1
>>>>>>>>
>>>>>>> Oh, oh, now our resident 64bit "specialist" Hadron Snot Quark has some
>>>>>>> heavy explanation to do why, totally different from his ascertions, the
>>>>>>> 64bit linux trounced the 32bit counterpart on *every* test.
>>>>>>>
>>>>>>> Which was maintained as fact all along from linux users who actually use
>>>>>>> linux *and* especially in the 64bit version, and which was all the time
>>>>>>> naysaid by Hadron and comrades (after all, 64bit windows is actually
>>>>>>> *slower* than 32bit windows, as there are practically no 64bit apps.
>>>>>>> Can't have that, can we?)
>>>>>>>
>>>>>>> And here we have *again* a benchmark where 64bit linux was faster, in in
>>>>>>> several cases *dramatically* faster than 32bit
>>>>>>>
>>>>>>> I guess Hadrons "explanation" will be that those guys are "lying
>>>>>>> freetards"
>>>>>> Microsoft has to throw mud at 64-bit because it's still struggling to get
>>>>>> it working.
>>>>> I'd say that the biggest improvements to performance when moving to
>>>>> 64-bit is the utilization of the general purpose registers and the
>>>>> elimination of the saving of the BP register and movement of addresses
>>>>> on every function call. All one has to do to verify this is to compile
>>>>> a simple hello world program in C and to utilize the generate assembly
>>>>> instructions only in 32-bit mode and compare the code generated in
>>>>> 64-bit code. This is the way Intel processors work. I don't get a
>>>>> speed advantage when the same code is compiled on a G5 (IBMs 970FX) in
>>>>> 64-bit mode. I get better speed in 32-bit mode as there are 32 general
>>>>> purpose registers available and it these same gp registers are there in
>>>>> 64-bit mode as well.
>>>> Microsoft recommended 64-bit only because it temporarily renders some
>>>> viruses incompatible. Not performance, not memory addressing...
>>>>
>>> It should've gave them performance, but then maybe they pissed away the
>>> performance on some other background process.
>>
>> Maybe their compiler sucks.
>>
>
> I haven't used any of their compilers since VS6.0.
> That one was fairly useful, but the IDE had a few bugs in it and the
> documentation didn't cover one item in regards to symbolic ID names that
> had to be in upper case, else the programs just didn't work even tho
> they compiled correctly.
> I just don't have enough money to spend on them right now.
gcc is inheriting from icc, so it'll get better. But anyway, does Microsoft
have /incentive/ to improve for 64-bit?
- --
~~ Best of wishes
Roy S. Schestowitz | "Far away from home, robots build people"
http://Schestowitz.com | GNU is Not UNIX | PGP-Key: 0x74572E8E
http://iuron.com - proposing a non-profit search engine
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.9 (GNU/Linux)
iEYEARECAAYFAks+fK0ACgkQU4xAY3RXLo4c/QCfRXkidNlFZw+GOxbi6u2GAAMw
y7MAmQGsOO3yrv1tACsEruku1cBpLMAX
=ESSd
-----END PGP SIGNATURE-----
|
|
