PDA

View Full Version : 5870 su Milkyway e Collatz, ecco i tempi!


gabi.2437
05-10-2009, 14:16
La scheda è uscita, si è dimostrata da subito FENOMENALE con 2,7TeraFLOPS in Single precision e 550GFLOPS in Double precision :eek: :eek: :eek:

Ma come si comporta all'atto pratico nel calcolo distribuito? E rispetto alle sue precedenti?

Eccovi i dati

Per paragone, su milkyway, la mia 3870 ci mette per WU 2minuti e 15sec, ovvero 135sec, una 4890 overclockata ci mette sui 40sec

Ecco milkyway con la 5870, tempi di Hans-Ulrich Hugi (http://milkyway.cs.rpi.edu/milkyway/show_user.php?userid=62226)

Today i did some testing with the 5870 at different clock speeds (Milkyway and Collatz). All results are under Win7 Ultimate 64bit (Build 7600) with a Q9650 @ 3.75 GHz, Boinc Client 6.10.11 and the 0.20 Milkyway SW (no command line parameters changed). Under Collatz higher clocks greatly improve the performance (see my post there). Here are the results for Milkyway:

Clocks 850 / 1200 (@stock)
===========================

GPU load max. 99% (GPU-Z 0.3.5)

GPU core clock: 850 MHz, memory clock: 300 MHz (Wrong: 1200 MHz!)

predicted runtime per iteration is 62 ms(33.3333 ms are allowed), dividing each iteration in 2 parts
borders of the domains at 0 800 1600
Calculated about 8.22242e+012 floatingpoint ops on GPU, 1.23583e+008 on FPU. Approximate GPU time 20.7792 seconds

CPU time: 1.65361 seconds, GPU time: 20.7792 seconds, wall clock time: 21.793 seconds, CPU frequency: 3.7371 GHz
CPU time: 1.70041 seconds, GPU time: 20.7948 seconds, wall clock time: 21.833 seconds, CPU frequency: 3.7371 GHz
CPU time: 1.71601 seconds, GPU time: 20.7792 seconds, wall clock time: 21.844 seconds, CPU frequency: 3.7371 GHz

Clocks 850 / 1320 (GPU @stock / Memory + 10%)
=============================================

GPU load max. 99% (GPU-Z 0.3.5)

GPU core clock: 850 MHz, memory clock: 300 MHz (Wrong: 1320 MHz!)

predicted runtime per iteration is 62 ms(33.3333 ms are allowed), dividing each iteration in 2 parts
borders of the domains at 0 800 1600
Calculated about 8.22242e+012 floatingpoint ops on GPU, 1.23583e+008 on FPU. Approximate GPU time 20.7636 seconds

CPU time: 1.66921 seconds, GPU time: 20.7636 seconds, wall clock time: 21.831 seconds, CPU frequency: 3.7371 GHz
CPU time: 1.70041 seconds, GPU time: 20.8104 seconds, wall clock time: 21.907 seconds, CPU frequency: 3.7371 GHz
CPU time: 1.70041 seconds, GPU time: 20.8104 seconds, wall clock time: 21.847 seconds, CPU frequency: 3.7371 GHz

Clocks 935 / 1200 (GPU + 10% / Memory @stock)
==============================================

GPU core clock: 935 MHz, memory clock: 300 MHz (Wrong: 1200 MHz!)

predicted runtime per iteration is 56 ms (33.3333 ms are allowed), dividing each iteration in 2 parts
borders of the domains at 0 800 1600
Calculated about 8.22242e+012 floatingpoint ops on GPU, 1.23583e+008 on FPU. Approximate GPU time 20.1084 seconds

CPU time: 1.01401 seconds, GPU time: 20.1084 seconds, wall clock time: 21.15 seconds, CPU frequency: 3.7371 GHz
CPU time: 1.01401 seconds, GPU time: 20.1084 seconds, wall clock time: 21.15 seconds, CPU frequency: 3.7371 GHz
CPU time: 1.01401 seconds, GPU time: 20.0928 seconds, wall clock time: 21.125 seconds, CPU frequency: 3.7371 GHz

Clocks 935 / 1320 (both + 10%)
===============================

GPU load max. 99% (GPU-Z 0.3.5)

GPU core clock: 935 MHz, memory clock: 300 MHz (Wrong: 1320MHz!)

predicted runtime per iteration is 56 ms(33.3333 ms are allowed), dividing each iteration in 2 parts
borders of the domains at 0 800 1600
Calculated about 8.22242e+012 floatingpoint ops on GPU, 1.23583e+008 on FPU. Approximate GPU time 20.0772 seconds

CPU time: 1.04521 seconds, GPU time: 20.0772 seconds, wall clock time: 21.144 seconds, CPU frequency: 3.7371 GHz
CPU time: 0.998406 seconds, GPU time: 20.0928 seconds, wall clock time: 21.122 seconds, CPU frequency: 3.7371 GHz
CPU time: 0.998406 seconds, GPU time: 20.0928 seconds, wall clock time: 21.122 seconds, CPU frequency: 3.7371 GHz

20 secondi per WU :sbavvv: :sbavvv: :sbavvv:

E, sempre suoi, i tempi su Collatz


(per paragone, la mia 3870 per WU ci mette sui 2000 secondi)

Clocks 850 / 1200 (@stock)
===========================

GPU load max. 50% (GPU-Z 0.3.5)

GPU core clock: 850 MHz, memory clock: 300 MHz (Wrong: 1200 MHz!)

predicted runtime per iteration is 34 ms (33.3333 ms are allowed), dividing each iteration in 2 parts
borders of the domains at 0 2048 4096
needed 1674 steps for 2361224431037583010991
72615528055281 total executed steps for 137438953472 numbers

CPU time: 0.358802 seconds, GPU time: 512.367 seconds, wall clock time: 512.773 seconds, CPU frequency: 3.7371 GHz
CPU time: 0.358802 seconds, GPU time: 512.757 seconds, wall clock time: 513.149 seconds, CPU frequency: 3.7371 GHz
CPU time: 0.343202 seconds, GPU time: 512.399 seconds, wall clock time: 512.79 seconds, CPU frequency: 3.7371 GHz

Clocks 935 / 1320 (both + 10%)
===============================

GPU load max. 99% (GPU-Z 0.3.5)

GPU core clock: 935 MHz, memory clock: 300 MHz (Wrong: 1320 MHz!)

predicted runtime per iteration is 31 ms (33.3333 ms are allowed)
borders of the domains at 0 4096
needed 1679 steps for 2361218053894194294923
76789984427940 total executed steps for 137438953472 numbers

CPU time: 0.561604 seconds, GPU time: 256.979 seconds, wall clock time: 257.348 seconds, CPU frequency: 3.7371 GHz
CPU time: 2.32441 seconds, GPU time: 263.585 seconds, wall clock time: 264.059 seconds, CPU frequency: 3.7371 GHz
CPU time: 1.06081 seconds, GPU time: 257.785 seconds, wall clock time: 258.158 seconds, CPU frequency: 3.7371 GHz

The higher clock speed nearly doubles the load and the calaculation time is half. So i want to know it is the GPU clock or the memory clock that gives this advantage:

Clocks 850 / 1320 (GPU @stock / Memory + 10%)
=============================================

GPU load max. 54% (GPU-Z 0.3.5)

GPU core clock: 850 MHz, memory clock: 300 MHz (Wrong: 1320 MHz!)

predicted runtime per iteration is 34 ms (33.3333 ms are allowed), dividing each iteration in 2 parts
borders of the domains at 0 2048 4096
needed 1674 steps for 2361211536082181078012
70073165112471 total executed steps for 137438953472 numbers

CPU time: 0.358802 seconds, GPU time: 512.445 seconds, wall clock time: 512.776 seconds, CPU frequency: 3.7371 GHz
CPU time: 0.327602 seconds, GPU time: 512.352 seconds, wall clock time: 512.704 seconds, CPU frequency: 3.7371 GHz
CPU time: 0.358802 seconds, GPU time: 512.398 seconds, wall clock time: 512.81 seconds, CPU frequency: 3.7371 GHz

Clocks 935 / 1200 (GPU + 10% / Memory @stock)
==============================================

GPU load max. 98% (GPU-Z 0.3.5)

GPU core clock: 935 MHz, memory clock: 300 MHz (Wrong: 1200 MHz!)

predicted runtime per iteration is 31 ms (33.3333 ms are allowed)
borders of the domains at 0 4096
needed 1723 steps for 2361229808201720130217
64635609237816 total executed steps for 137438953472 numbers

CPU time: 0.842405 seconds, GPU time: 310.285 seconds, wall clock time: 311.448 seconds, CPU frequency: 3.7371 GHz
CPU time: 0.748805 seconds, GPU time: 306.697 seconds, wall clock time: 310.218 seconds, CPU frequency: 3.7371 GHz
CPU time: 0.702005 seconds, GPU time: 305.527 seconds, wall clock time: 307.559 seconds, CPU frequency: 3.7371 GHz

:eek: :eek: :eek:

FENOMENALE!

nn020
08-10-2009, 20:54
Sto aspettando che questo signore aggiorni i sistemi:
http://atlasfolding.com/

Sarà interessante vedere la 5870X2

nongio
09-10-2009, 12:14
Mamma mia che tempi!!!
Pazzesca....voglio vedere poi una 5850, che come prezzo può essere la mia prossima scheda video

gabi.2437
09-10-2009, 12:48
Sto aspettando che questo signore aggiorni i sistemi:
http://atlasfolding.com/

Sarà interessante vedere la 5870X2
Di interessante c'è solo da vedere quanto schifo fa Folding sulle ATI :(

Le 5xxx ci girano già ;) una 5870 va il 35% più veloce di una 4870 (che già rispetto alle nvidia faceva schifo)

Perchè? Colpa del client che è programmato male, l'han dichiarato loro.

CYRANO
17-10-2009, 16:54
che driver ha usato la 5870 per milkyway ?


C'.a'.z'.a

gabi.2437
17-10-2009, 21:34
Ah boh, i 9.9 forse

CYRANO
19-10-2009, 05:30
e perchè allora a loro vanno ed a me crashano ? :cry: :cry: :cry: :cry:



Cò.aò.zò.a

gabi.2437
20-10-2009, 18:57
metti gli 8.12 :D

forse i 9.9 vanno bene con 7, io non lo so :D

CYRANO
20-10-2009, 22:20
arridaje :D
io gli 8.12 non li metto nel modo piu' assoluto :D


C;,a;,z;,a

gabi.2437
21-10-2009, 06:15
io ce li ho e vanno bene :D se no prova windows 7 :O

CYRANO
23-10-2009, 02:07
io ce li ho e vanno bene :D se no prova windows 7 :O

beh il passaggio da xp32 a 7-64 è in programma as soon as possible :O



C.àòa.àòz.àaza

gabi.2437
23-10-2009, 06:19
Cmq la situazione è questa, o 8.12 o gli ultimi se hai fortuna :D

CYRANO
23-10-2009, 16:57
Oh collapse funzia !
coi 9.9
unico problema è che mi manda la 4870 a quasi 80°c :asd:
la cosa mi preoccupa un pochetto in effetti...
cioè tenerla così 24h al giorno... :D
ci devo riflettere su :D



C,òaò,z,òa

gabi.2437
23-10-2009, 17:03
Collatz o collapse? :asd:

80° sono pochi, stai tranquillo ;) Fosse oltre i 100 mi preoccuperei un pelino, ma 80 su una 4870 è normale

Milkyway la farà salire di più :D (ma anche Collatz se imposti i parametri giusti nell'app_info)

CYRANO
23-10-2009, 18:44
Si ok ma 80°C 24h al giorno con la ventola sparata al 90% non è il max... anche perchè ci devo dormire ad un 1mt di distanza :asd:



C,òaò,z,òaza

gabi.2437
23-10-2009, 18:47
Ah beh se è per il rumore ti capisco :D Per il resto non c'è problema, è fatta apposta per elaborare, se volevi un soprammobile compravi un soprammobile, non una scheda video con supporto CAL :O

Vabbè dai, anche in idle la ventola macina non poco :D

CYRANO
23-10-2009, 19:45
i sogni di gloria con collatz son durati una manciata di minuti.
Poi ho aggiornato ai 9.10 ed ora non va più nulla :asd:
ossia mi dà:

23/10/2009 20.31.23|Collatz Conjecture|Output file collatz_1256131244_55011_0_0 for task collatz_1256131244_55011_0 absent

insomma fallisce tutte le wu .. sob ...


C,òa,òz,òa

gabi.2437
23-10-2009, 20:23
Si ma mica è colpa di driver lì... intanto metti l'ultimo client di collatz :D