|
![]() |
Overclock.net - Overclocking.net > Software, Programming and Coding > Operating Systems > Windows | |
Windows XP x64 and arithmetic performance?
|
||
![]() |
|
|
LinkBack | Thread Tools |
|
|
#1 (permalink) | ||||||
|
New to Overclock.net
|
I was wondering if I would see any increase in computational speeds by running a 64bit mathematical application on Windows XP x64? Basically would arithmetic be inherently faster in a 64bit environment/application? I know 64bit allows better memory allocation but I can't seem to find an answer to the arithmetic question.
__________________Thanks!
|
||||||
|
|
|
|
|
#2 (permalink) | |||||||||||||
|
Case Modder
|
it wil be faster yes
but you will only notice it in really big calculations
__________________
Looking for cheap compressors for phase change
|
|||||||||||||
|
|
|
|
#3 (permalink) | |||||||
|
New to Overclock.net
|
Quote:
My codes take about 3 hours to complete.
|
|||||||
|
|
|
|
|
#4 (permalink) | |||||||||||||
|
Turing Test is Overrated
|
Then yes, you should notice a decent performance increase. Instead of breaking apart large numbers into 32+32 bits, the CPU could just process the 64 bit value and reducing overhead. What kind of code?
__________________
WANTED: Socket M Core/Core 2 CPU, SUGO-02 Black, quality 802.11b/g PCI Card To answer most of your questions: (1) a fridge cannot cool a PC (2) 64-bit OS for over 3.4GB (3) If a PCIe card fits, it will work (4) Resolution, not screen size (5) If you have a question, it is not news (6) Report, not respond to Spam (7) Single/Non-Modular Rail PSUs are NOT better than Multi-Rail/Modular
|
|||||||||||||
|
|
|
|
#6 (permalink) | |||||||||||||
|
Windows Wrangler
|
I would think you would, as stated above, 32 bit cpus break up numbers that are bigger than a 32 bit
__________________
|
|||||||||||||
|
|
|
|
|
#7 (permalink) | |||||||||||||
|
Turing Test is Overrated
|
I can't search many forums with any benchmarks (work filters) but I can provide links that may help you.
http://www.google.com/group/comp.sof...ct=result&cd=1 http://www.google.com/group/comp.sof...ct=result&cd=2 http://www.google.com/group/comp.sof...ct=result&cd=3 The best thing is just to test it!
__________________
WANTED: Socket M Core/Core 2 CPU, SUGO-02 Black, quality 802.11b/g PCI Card To answer most of your questions: (1) a fridge cannot cool a PC (2) 64-bit OS for over 3.4GB (3) If a PCIe card fits, it will work (4) Resolution, not screen size (5) If you have a question, it is not news (6) Report, not respond to Spam (7) Single/Non-Modular Rail PSUs are NOT better than Multi-Rail/Modular
|
|||||||||||||
|
|
|
|
#8 (permalink) | ||||||||
|
New to Overclock.net
|
Quote:
Quote:
|
||||||||
|
|
|
|
|
#9 (permalink) | |||||||||||||
|
Turing Test is Overrated
|
Geeeeez.... that's a huge increase. What type of calculation was in that benchmark? Basically, it can't hurt and will only improve.
__________________
WANTED: Socket M Core/Core 2 CPU, SUGO-02 Black, quality 802.11b/g PCI Card To answer most of your questions: (1) a fridge cannot cool a PC (2) 64-bit OS for over 3.4GB (3) If a PCIe card fits, it will work (4) Resolution, not screen size (5) If you have a question, it is not news (6) Report, not respond to Spam (7) Single/Non-Modular Rail PSUs are NOT better than Multi-Rail/Modular
|
|||||||||||||
|
|
|
|
#10 (permalink) | ||||||
|
New to Overclock.net
|
well I just got done installing everything and I ran some benchmarks
__________________All I can say is WOW I have a benchmark which basically calculates the inverse of a random 5000x5000 matrix which in 32bit would take 47 sec, it now takes 19 seconds under 64bit! In fact all of the benchmarks directly related to math operations improved by at least twice as fast. Sick!
|
||||||
|
|
|
![]() |
| Currently Active Users Viewing This Thread: 1 (0 members and 1 guests) | |
| Thread Tools | |
|
|