AMD or Intel as well as the memory brand - page 12
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
I have it on my old computer:
Test result:
Conclusion: RAM size and bus frequency affect speed more than the type of processor.
PS. Not an idle question. Is it really necessary to chase speed? Really, how crucial is this aspect for a single trader? If it is so important, can I somehow manage to get a supercomputer? They say that now there are some compact versions priced from $20,000.
Conclusion: RAM size and bus frequency have a greater influence on speed than the type of processor.
L2 cache size :)
L2 page cache size :)
>> Oh, yeah. And the cache. :-)How much should we weigh in grams? (с)
Quite an interesting article on the choice of power supply depending on configuration.
*
The idea is to add the following to the test:
- create objects, e.g. 100 labels
- move them, for example, one period of a sine wave, or simply change the coordinates 100 times
- delete the objects.
Accordingly, time from start to finish...
I have it on my old computer:
Test result:
Conclusion: RAM size and bus frequency have a stronger influence on speed than processor type.
PS. Not an idle question. Is it really necessary to chase speed? Really, how crucial is this aspect for a single trader? If it is so important, can I somehow manage to get a supercomputer? They say some compact versions are available now, with prices starting from $20,000.
I have another conclusion: Cache.
You can check it by "cutting" script to one section, it might fit to your 256kb.
Your memory is the same speed as mine, 1gb should be good enough for the test; the bus frequency is not supposed to affect this.
And now let's compare AMD Phenom X4 965 and Intel Core i7 940
AMD Phenom X4
Intel Core i7
Intel fans are nervously smoking. How can a 9k processor tear up a 21k CPU? (our prices are local, but I think price ratio is the same all over the country) And it turns out it can...
And now the question, why should I pay 21 thousand for lower performance, when I can buy a more efficient CPU for 9? At the same time it's less warm.
And now let's compare AMD Phenom X4 965 and Intel Core i7 940
AMD Phenom X4
Intel Core i7
Intel fans are nervously smoking. How can a 9k processor tear up a 21k CPU? (our prices are local, but I think price ratio is the same all over the country) And here it goes...
And now the question, why should I pay 21k for lower performance when I can buy a more efficient CPU for 9? At the same time it's less warm.
??? Have you read these tests and texts yourself???
Now comparing AMD Phenom X4 965 and Intel Core i7 940
AMD Phenom X4
Intel Core i7
Intel fans are nervously smoking. How is it that a 9k processor can beat a 21k processor? (The prices are ours, local, but I think the proportion of prices is the same all over the country) And here it goes...
And now the question, why should I pay 21 thousand for a lower performance processor when I can buy a higher performance processor for 9 thousand? At the same time it's less warm.
AMD releases world's first quad-core desktop processor for under $100
http://www.ixbt.com/news/hard/index.shtml?12/38/89
AMD Athlon II X4: four cores for $99
http://www.overclockers.com.ua/news/hardware/2009-09-16/104407/
Athlon II X4 620 and 630 processors officially launched
http://www.overclockers.ru/hardnews/34316.shtml
AMD low budget integrated graphics platforms outperform Intel at price/performance criterion.
AMD launches world's first quad-core desktop processor under $100
http://www.ixbt.com/news/hard/index.shtml?12/38/89
Nah, I can't do this anymore... I DON'T CARE IF IT'S A QUAD-CORE!
Look at the tests in the thread: my fucking single core Pentium for a rupee on a fucking three ruble laptop rips the multi-core ones in MQL calculations if they have a lower frequency. And in case of AMD even at equal frequency it rips.
Important:
- Core computational power. It mainly depends on frequency and on the number of operations per one clock. And also from peculiarities of float calculations of various implementations.
- Cache size. Very important parameter.
- Memory speed.
No, I can't... I DON'T CARE IF IT'S STONED!!!
Look at the tests in the thread: my shitty Pentium single core for a ruble on a shitty laptop for three rubles tears .multicore in calculations on MQL, if they have lower frequency. And in case of AMD even at equal frequency it rips.
It's important:
- Core computational power. It mainly depends on the frequency and on the number of operations per one clock cycle. And also from peculiarities of float calculations of various implementations.
- Cache size. Very important parameter.
- Memory speed.
You're right, mmm, even though I'm a supporter of the AMD camp. The first two tests in the script do a good job of showing just the computational capability of a single core in MT compiled applications. Both of these tests are very small in size and small in order not to "touch" the RAM for greater purity of the experiment. The third test is designed as a write memory test and has no special calculations.
In order to use all the processor cores, the test logic must allow paralleling the calculations and also, the compiler and the MT platform itself must allow this. As far as I know, I must be mistaken, the MQL5 language, like MQL4, does not provide features for building parallelism in code. I am sorry for that.
I'll post the updated script a bit later which shows the final performance index for my processor (AMD Atlon X2 3800) in a smoother way.
To Kombat -> graph objects processing doesn't really need the power of iron, because even processing tens of thousands of objects per second will not affect the trade, and in the tester, it is not needed. IMHO.