AMD or Intel as well as the memory brand - page 49
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 am posting my table with the new data from HideYourRichess. The criterion remains the same - ff. four2one, your speciality is the time*price criterion.
Conditionally, both configurations could be referred to blue by colour :) But still waiting for more optimizations, HideYourRichess.
joo
Athlon 64 X2 3800+ (2000 MHz), cache 2x512 KB L2
DDR2 PC-5360 2GB
82.07*2(?)=164.14
310*2=620
Mathemat
Core 2 Duo E7200@2.53, cache 3 MB L2
4GB RAM PC-6400
46.27*2.53=117.06
213*2.53=538.89
Svinozavr
Celeron 900 @ 2.20 GHz, cache 1 MB L2
DDR2 PC-6400 2GB
52.18*2.2=114.8
206*2.2=453.2
benik
Celeron 325 @ 2.53 GHz, cache 256 K L2
DDR2 PC-6400 1GB
103.3*2.53=261.35
438*2.53=1108.14
begemot61
Pentium 4 670 @ 3.8 GHz, cache 2 MB L2
DDR2 PC-4266 2GB
78.57*3.8=298.57
169*3.8=642.2
BLACK_BOX
Athlon 64 X2 4200+ @ 2.2 GHz, cache 2x512 KB L2
DDR1 PC-3200 (?) 3 GB
77.84*2.2=171.25
forex-k
Core 2 Duo Q8200 @ 2.33 GHz, cache 2x2 MB L2
RAM 4 GB PC-6400
46.84*2.33=109.14
189*2.33=440.37
Phenom II X3 720 @ 3.72 GHz, cache 3x512 KB L2 + 6 MB L3
113*3.72=420.36
four2one
Athlon 64 X2 5050e @ 2.6 GHz, cache 2x512 KB L2
RAM 4 (8) GB PC-5970
60*2.6=156.0
134*2.6=348.4
begemot61
6-Core Opteron 2439 SE @ 2.8 GHz, cache 6x512 KB L2 + 6 MB L3
DDR2 4 GB PC-5333
42.33*2.8=118.52
95*2.8=266
begemot61
Xeon W5590 @ 3.47 GHz, cache 4x256 KB L2 + 8 MB L3
DDR3 PC-10670 12GB
27,53*3,47=95.53
62*3.47=215.14
Dmido
Pentium 4 @ 3 GHz, cache 512 KB L2
DDR1 PC-3200 1.15 GB
64.49*3=193.47
315*3 = 945
TorBar
Intel Celeron 331 @ 2.66 GHz, cache 256 KB L2
DDR1 (PC-3200) 1.5GB
105.49*2.66=280.60
386*2.66=1026.76
imp120
Athlon 64 X2 3800+ @ 2 GHz, cache 2x512 KB L2
DDR1(?) PC-3200 2 GB
90*2.0=180
318*2.0=636
Docent
Core 2 Duo E6550 @ 3 GHz, cache 4 MB L2
DDR2 PC-6864 2 GB
40.35*3.0=121.05
174*3.0=522
imp120
Mobile Core 2 Duo P8600 @ 2.4 GHz, cache 3 MB L2
DDR2 4GB PC-6400
44.99*2.4=107.98
201*2.4=482.4
Vinin
Core 2 Duo E8400 @ 3.00 GHz, cache 6 MB L2
DDR2 4GB PC-6400
36.99*3.0=110.97
152*3.0=456
HideYourRichess
Mobile Core 2 Duo T9800 @ 2.93 GHz, cache 6 MB L2
DDR3 8 GB PC-8510
36.21*2.93=106.1
161*2.93=471.73
HideYourRichess
Xeon 5355 @ 2.66 GHz, cache 2x4 MB L2
DDR2 32 GB PC-5320
42.2*2.66=112.25
188*2.66=500.08
Here is my result of the new script. If we now want to get a characteristic similar to ff, since rating is the inverse of time, we just need to calculate Freq/Rating. It is probably not necessary to normalize to the previous ff.
But the test has become much harder, as can be seen from the figures.
I do!
Thank you, Alexey. Yes, the rating is inverse of the time value reduced to prcentage ratio of my "reference" processor. Your result means +109% speed gain relative to AMD Atlon 64 X2 3800, or in other words 2.094 times faster.
As you can see, the result is different from the one in the table below, as my memory is probably not 2+ times slower than yours, but only 1.77 times slower. Here you can see more clearly the difference in computing speed between processors on the same core.
>> I got this!
there you go! the difference with Mathemat is almost 15%! and the table is 1.23%!
There you go! The difference with Mathemat is almost 15%! and the table shows 1.23%!
even though the first time this test showed 200 and the second time 194
although the first time this test showed 200 and the second time 194
The accuracy of the test results (of any kind) increases if you disconnect from the internet, turn off the firewall and antivirus, etc. I had a difference of up to 5%. Or in other words, 5% of "power" was eaten up by the service programs.
I'm afraid to disappoint you, but the performance results of this script are even less relevant than those of the first script. The point is that most compilers calculate expressions of the kind you see here at compile time (since there's no point in evaluating what can be evaluated ahead of time). I.e. code inside loops is equivalent to something like this: Int = 120 and Double = 120.0. That is, nothing useful is done at all. And if you replace the code inside loops with what I have written, the result will remain the same (check it for yourself). In fact, it measures the overhead of loop organization. The result in the second case is a bit smaller because entering Double (8 bytes) is a bit longer than entering Int (4 bytes).
And if in the first script array handling (the longest part) at least somehow reflected performance of memory subsystem (and bus with caches), this test in general measures "spherical horses in vacuum" and shows results not so much in parrots.
joo, I hope no offence. :)
I'm afraid to disappoint you, but the performance results of this script are even less relevant than those of the first script. The point is that most compilers calculate expressions of the kind you see here at compile time (since there's no point in evaluating what can be evaluated ahead of time). I.e. code inside loops is equivalent to something like this: Int = 120 and Double = 120.0. That is, nothing useful is done at all. And if you replace the code inside loops with what I have written, the result will remain the same (check it for yourself). In fact, it measures the overhead of loop organization. That in the second case the result is a bit smaller because entering Double (8 bytes) is a bit longer than entering Int (4 bytes).
But do we care what the CPU spends its resources on? We should measure it more accurately. :)
Yes, I too was surprised by such a small difference in speed between integer and real.