y-cruncher - A multi-threaded pi program [Archiv]

kruemelmonster

2014-03-24, 15:17:30

Das kürzliche Release des y-cruncher inkl. FMA4&XOP Support speziell für die Bulldozer Reihe ist wohl der beste Grund um mal einen passenden Benchthread zu eröffnen.

Download (http://www.numberworld.org/y-cruncher/) für Windows & Linux

Die y-cruncher.exe ist lediglich ein Loader welcher je nach CPU das beste Binary lädt, falls die Autoerkennung fehlschlägt oder man verschiedene Befehlssätze vergleichen will lassen sich die optimierten .exen wie unter Linux auch händisch aus dem Binaries-Ordner starten:

XOP Miyu -> Bulldozer (ausschließlich!)
AVX Hina -> Sandy / Ivy / Haswell
SSE4.1 Ushio -> Nehalem / Lynnfield
SSE4.1 Nagisa -> Yorkfield
SSE3 Kasumi -> Phenom & alles andere

Als Basisbench schlage ich mit Hinblick auf 4 GB Maschinen die Berechnung auf 500 Millionen Stellen mit 2,2 GB RAM-Verbrauch vor, erreichbar über das Hauptmenü mit 0->1->5.
Gewertet wird dann die Total Computation Time da die Total Time durch das Schreiben eines 500 MB Logfiles relativ plattenlastig ist.

kruemelmonster

2014-03-24, 15:18:30

i7 2600k @ 4.5 GHz / 4x 4 GB DDR3 1600 9-9-9-24-1T DualChannel / ASUS P8Z68-V Pro / Win 8.1 x64

http://abload.de/img/ycruncheri7dcodzep.jpg (http://abload.de/image.php?img=ycruncheri7dcodzep.jpg)

Total Computation Time: 113.100 sec
CPU Utilization: 765.664%
Multi-core Efficiency: 95.708%

---

i7 2600k @ 4.5 GHz / 3x 4 GB DDR3 1600 9-9-9-24-1T FlexMode / ASUS P8Z68-V Pro / Win 8.1 x64

http://abload.de/img/ycruncheri7vcsdd.png (http://abload.de/image.php?img=ycruncheri7vcsdd.png)

Total Computation Time: 126.790 sec
CPU Utilization: 710.19%
Multi-core Efficiency: 88.7738%

---

i5 750 @ 3.6 GHz / 1x 4 GB DDR3 1600 9-9-9-24-1T SingleChannel/ ASUS P7P55D-E LX / Win 8.1 x64

http://abload.de/img/ycruncheri5ygsps.png (http://abload.de/image.php?img=ycruncheri5ygsps.png)

Total Computation Time: 221.910 sec
CPU Utilization: 376.785%
Multi-core Efficiency: 94.1963%

(del676)

2014-03-24, 15:28:17

FX-8150 stock, 8 Kerne,16gb Ram 1333mhz, 335 laufende Prozesse,

Total Computation Time: 164.447 seconds ( 0.046 hours )
Total Time (with output + verify): 172.320 seconds ( 0.048 hours )

CPU Utilization: 744.576 %
Multi-core Efficiency: 93.072 %

Edit:
laeuft leider nur auf aktuellen Kernelversionen. Der von RHEL5 ist z.b. schon zu alt, RHEL6 funktioniert.

2x Xeon(R) CPU E5-2690, HTT disabled, 16 Kerne

Total Computation Time: 56.411 seconds ( 0.016 hours )
Total Time (with output + verify): 60.791 seconds ( 0.017 hours )

CPU Utilization: 1202.19 %
Multi-core Efficiency: 75.1366 %

Edit:
2x AMD Opteron(tm) Processor 6380, 24 Kerne
Total Computation Time: 132.435 seconds ( 0.037 hours )
Total Time (with output + verify): 140.467 seconds ( 0.039 hours )

CPU Utilization: 1899.21 %
Multi-core Efficiency: 59.3503 %

Eventuell stimmt mit der Maschine was nicht, das kommt mir schon elendslahm vor.

Edit: Ach, der skaliert mit der Kernanzahl nicht mehr anstaendig. :(

HarryHirsch

2014-03-24, 15:37:59

3960x @ 4500MHz, DDR3 2133

Total Computation Time: 84.989 seconds ( 0.024 hours )
Total Time (with output + verify): 90.644 seconds ( 0.025 hours )

CPU Utilization: 961.232 %
Multi-core Efficiency: 80.1027 %

atopisch

2014-03-24, 15:50:03

2 x Xeon E5-2670v2 Windows Server 2008R2

http://s7.directupload.net/images/140324/44ayfkoz.png (http://www.directupload.net)

Core i7-3667U 1 x 4GB RAM Windows 7 SP1 64bit

http://s1.directupload.net/images/140324/6pjybyyi.png (http://www.directupload.net)

Ronny G.

2014-03-24, 16:21:34

http://abload.de/img/123bnd9n.jpg

Computation Time: 115.298 seconds
Total Time: 125.014 seconds

CPU Utilization: 724.609 %
Multi-core Efficiency: 90.576 %

Mein System:
Intel Xeon e3-1230v3@4x3,7Ghz@1,010V, Ati R9 280x Sapphire Dual-X @ 1180/1600Mhz, AsRock Z87 Pro3, 2x4GB G.Skill DDD3 2133Mhz 10-11-10-27 2T ...Win 7 Prof. 64bit

Gammelobst

2014-03-24, 19:54:48

Core i7-4770k@4.5GHz / 24GB RAM 1333MHz / Win8.1u1

Radeonfreak

2014-03-24, 20:08:51

http://abload.de/img/unbenanntejsn6.png

Twodee

2014-03-24, 21:00:29

http://abload.de/img/unbenanntzpsst.jpg

Mcdave

2014-03-24, 21:18:04

System: i7 3770k @ 4.3GHZ, 8GB RAM 2133MHZ 11-11-11-27-1 & Windows 8.1 Pro x64

http://abload.de/img/cruncherl2uby.jpg (http://abload.de/image.php?img=cruncherl2uby.jpg)

Tyrann

2014-03-24, 21:27:32

http://i.imgur.com/W90MaoM.png

atopisch

2014-03-24, 21:51:10

Core i7-4770K@4.2GHz 2 x 4GB RAM 1866Mz 9-9-9-24-1T

http://s7.directupload.net/images/140324/vv7owdi3.png (http://www.directupload.net)

Core i7-4770K@4.3GHz

http://s1.directupload.net/images/140331/wyi4ldws.png (http://www.directupload.net)

kruemelmonster

2014-03-27, 17:36:10

Entgegen meiner Erwartungen kostet der Betrieb des Speichers im FlexMode doch mehr Leistung als gedacht, siehe Post #2. Dafür dass die ersten 8 GB im DC arbeiten sollen und nur die letzten 4 GB als SC angesprochen werden verlängert sich die Berechnungszeit um über 10%, und man sieht auch direkt an den Utilization und Efficiency Werten wie die Kerne nicht mehr ausreichend gefüttert werden.

Auch krass zu sehen wie der Haswell von Gammelobst anscheinend am throtteln ist: atopisch kommt mit 13,5% mehr Takt ggü Ronny auf 12,2% kürzere Rechendauer, bei Gammelobst verlängert sich mit 21,6% mehr Takt ggü Ronny die Rechendauer um 11,3%.

Übrigens: Bitte immer den Takt mit angeben da bei CPUs mit aktivierter Turbofunktion nur der Basistakt ausgelesen wird.

Nuon

2014-03-27, 19:53:09

phenom2 955 @3.52GHz

Voodoo

2014-03-28, 11:31:13

Athlon 5350 / 8GB DDR3 1600 8-9-9-24

http://s7.directupload.net/images/140328/y6e92ppi.jpg (http://www.directupload.net)

sakul

2014-03-28, 19:37:36

Mein HTPC und ich hatten Langeweile :D

W7 x64 / VIA QuadCore L4700 @ 1.2+ GHz
2x 4 GB 1066 DDR3 7-7-7-20 @ 533 MHz

http://www.imgbox.de/users/public/images/gz321HCWnt.png

SSE4.1 Nagisa -> Yorkfield
Total Computation Time: 944.785 sec
CPU Utilization: 383.64%
Multi-core Efficiency: 95.91%

http://www.imgbox.de/users/public/images/Tj32wza9f2.png

SSE4.1 Ushio -> Nehalem / Lynnfield
Total Computation Time: 923.884 sec
CPU Utilization: 384.714%
Multi-core Efficiency: 96.1785%

Wie is das eigentlich mit der Multi-core Efficiency zu verstehen?
Genaugenomen is der VIA QuadCore garkein QuadCore sondern 2 DualCore die über einen FSB mit 266 MHz verbunden sind.
Sollte das nicht starke verluste bei der Multi-core Efficiency bedeuten?

Gebrechlichkeit

2014-03-29, 13:16:00

4670K@Stock , 2133Mhz 8Gb

Total Computation Time: 136.108 sec
CPU Utilization: 385.486%
Multi-core Efficiency: 96.3716%

http://saved.im/mtg0oda5ogvr/4670k3.png

-=Popeye=-

2014-03-29, 14:29:32

2600k @ 4500MHz, 16GB DDR3 1866 9-10-9-28-2T, Win7 x64

http://abload.de/img/y-crunchera0kk2.png

Total Computation Time: 112.627 sec
Total Time: 119.704 seconds

CPU Utilization: 761.395%
Multi-core Efficiency: 95.1744%

Loeschzwerg

2016-04-23, 16:13:30

VIA Quadcore E C4650 @ 2.0GHz:

Computation Time: 712.356 seconds
Total Time: 738.835 seconds

CPU Utilization: 359.546 %
Multi-core Efficiency: 89.887 %

Validation Version: 1.2

Program: y-cruncher - Gamma to the eXtReMe!!! ( www.numberworld.org )
Copyright 2008-2016 Alexander J. Yee ( a-yee@u.northwestern.edu )

User: None Specified - You can edit this in "Username.txt".

Processor(s): VIA QuadCore C4650@2.0GHz
Logical Cores: 4
Physical Memory: 8,562,429,952 bytes ( 8.00 GiB )
CPU Base Frequency: 2,000,038,173 Hz

Program Version: 0.6.9 Build 9464 (Windows - x64 AVX ~ Hina)
Constant: Pi
Algorithm: Chudnovsky Formula
Decimal Digits: 500,000,000
Hexadecimal Digits: Disabled
Threading Mode: Windows Thread Pool -> ? / 4
Computation Mode: Ram Only
Working Memory: 2,353,615,920 bytes ( 2.19 GiB )
Logical Disk Usage: 0 bytes ( 0 bytes )

Start Date: Sat Apr 23 15:34:53 2016
End Date: Sat Apr 23 15:47:12 2016

Computation Time: 712.356 seconds
Total Time: 738.835 seconds

CPU Utilization: 359.546 %
Multi-core Efficiency: 89.887 %

Last Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Dec Counts: {49995279,50000437,50011436,49992409,50005121,49990678,49998820,50000320,5000663 2,49998868}

Binary Hash: Floor(bin * 10^dec) mod (2^61 - 1) = 1095036223966448356

Timer Sanity Check: Passed
Frequency Sanity Check: Disabled in this version of y-cruncher
ECC Recovered Errors: 0

Event Log:
Sat Apr 23 15:34:53 2016 0.097 Reserving Working Memory
Sat Apr 23 15:34:55 2016 2.329 Constructing Twiddle Tables
Sat Apr 23 15:34:55 2016 2.341 Allocating I/O Buffers
Sat Apr 23 15:34:55 2016 2.347 Begin Computation
Sat Apr 23 15:34:55 2016 2.353 Series: ( 34 ) 0.000%
Sat Apr 23 15:34:55 2016 2.366 Series: ( 33 ) 0.002%
Sat Apr 23 15:34:55 2016 2.368 Series: ( 32 ) 0.003%
Sat Apr 23 15:34:55 2016 2.372 Series: ( 31 ) 0.004%
Sat Apr 23 15:34:55 2016 2.377 Series: ( 30 ) 0.006%
Sat Apr 23 15:34:55 2016 2.384 Series: ( 29 ) 0.008%
Sat Apr 23 15:34:55 2016 2.392 Series: ( 28 ) 0.011%
Sat Apr 23 15:34:55 2016 2.402 Series: ( 27 ) 0.015%
Sat Apr 23 15:34:55 2016 2.417 Series: ( 26 ) 0.021%
Sat Apr 23 15:34:55 2016 2.434 Series: ( 25 ) 0.028%
Sat Apr 23 15:34:55 2016 2.458 Series: ( 24 ) 0.039%
Sat Apr 23 15:34:55 2016 2.494 Series: ( 23 ) 0.053%
Sat Apr 23 15:34:55 2016 2.543 Series: ( 22 ) 0.072%
Sat Apr 23 15:34:55 2016 2.613 Series: ( 21 ) 0.099%
Sat Apr 23 15:34:56 2016 2.709 Series: ( 20 ) 0.135%
Sat Apr 23 15:34:56 2016 2.844 Series: ( 19 ) 0.184%
Sat Apr 23 15:34:56 2016 3.049 Series: ( 18 ) 0.252%
Sat Apr 23 15:34:56 2016 3.346 Series: ( 17 ) 0.344%
Sat Apr 23 15:34:57 2016 3.789 Series: ( 16 ) 0.471%
Sat Apr 23 15:34:57 2016 4.367 Series: ( 15 ) 0.643%
Sat Apr 23 15:34:58 2016 5.215 Series: ( 14 ) 0.879%
Sat Apr 23 15:34:59 2016 6.484 Series: ( 13 ) 1.202%
Sat Apr 23 15:35:01 2016 8.198 Series: ( 12 ) 1.643%
Sat Apr 23 15:35:04 2016 10.822 Series: ( 11 ) 2.246%
Sat Apr 23 15:35:07 2016 14.455 Series: ( 10 ) 3.070%
Sat Apr 23 15:35:12 2016 19.462 Series: ( 9 ) 4.196%
Sat Apr 23 15:35:19 2016 26.464 Series: ( 8 ) 5.738%
Sat Apr 23 15:35:29 2016 36.416 Series: ( 7 ) 7.846%
Sat Apr 23 15:35:44 2016 51.017 Series: ( 6 ) 10.732%
Sat Apr 23 15:36:04 2016 71.388 Series: ( 5 ) 14.685%
Sat Apr 23 15:36:34 2016 101.338 Series: ( 4 ) 20.104%
Sat Apr 23 15:37:20 2016 146.970 Series: ( 3 ) 27.543%
Sat Apr 23 15:38:21 2016 207.806 Series: ( 2 ) 37.778%
Sat Apr 23 15:39:48 2016 295.264 Series: ( 1 ) 51.913%
Sat Apr 23 15:41:49 2016 416.434 Series: ( 0 ) 71.591%
Sat Apr 23 15:44:50 2016 597.522 Finishing Series
Sat Apr 23 15:44:51 2016 598.059 Division
Sat Apr 23 15:45:22 2016 628.739 InvSqrt
Sat Apr 23 15:45:41 2016 647.944 Final Multiply
Sat Apr 23 15:45:54 2016 661.680 Base Converting
Sat Apr 23 15:46:48 2016 714.716 Writing Decimal Digits
Sat Apr 23 15:46:54 2016 720.952 Verifying Base Conversion
Sat Apr 23 15:47:12 2016 738.923 End Computation

----

Checksum: 6aa9a38ea279a660142258470ed5f705cbc6abb07c638d481d274be5ffeb621d

Achill

2016-04-23, 20:36:56

5820k@4.4Ghz, UC@3.4Ghz, DDR4@2400Mhz

Computation Time: 40.463 seconds
Total Time: 45.377 seconds

Validation Version: 1.2

Program: y-cruncher - Gamma to the eXtReMe!!! ( www.numberworld.org )
Copyright 2008-2016 Alexander J. Yee ( a-yee@u.northwestern.edu )

User: None Specified - You can edit this in "Username.txt".

Processor(s): Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz
Logical Cores: 12
Physical Memory: 17,000,013,824 bytes ( 16.0 GiB )
CPU Base Frequency: 3,299,992,847 Hz

Program Version: 0.6.9 Build 9464 (Windows - x64 AVX2 ~ Airi)
Constant: Pi
Algorithm: Chudnovsky Formula
Decimal Digits: 500,000,000
Hexadecimal Digits: Disabled
Threading Mode: Windows Thread Pool -> ? / 12
Computation Mode: Ram Only
Working Memory: 2,773,649,224 bytes ( 2.58 GiB )
Logical Disk Usage: 0 bytes ( 0 bytes )

Start Date: Sat Apr 23 20:30:12 2016
End Date: Sat Apr 23 20:30:58 2016

Computation Time: 40.463 seconds
Total Time: 45.377 seconds

CPU Utilization: 1001.985 %
Multi-core Efficiency: 83.499 %

Last Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Dec Counts: {49995279,50000437,50011436,49992409,50005121,49990678,49998820,50000320,5000663 2,49998868}

Binary Hash: Floor(bin * 10^dec) mod (2^61 - 1) = 1095036223966448356

Timer Sanity Check: Passed
Frequency Sanity Check: Disabled in this version of y-cruncher
ECC Recovered Errors: 0

Event Log:
Sat Apr 23 20:30:12 2016 0.076 Reserving Working Memory
Sat Apr 23 20:30:13 2016 0.643 Constructing Twiddle Tables
Sat Apr 23 20:30:13 2016 0.666 Allocating I/O Buffers
Sat Apr 23 20:30:13 2016 0.668 Begin Computation
Sat Apr 23 20:30:13 2016 0.669 Series: ( 34 ) 0.000%
Sat Apr 23 20:30:13 2016 0.672 Series: ( 33 ) 0.002%
Sat Apr 23 20:30:13 2016 0.672 Series: ( 32 ) 0.003%
Sat Apr 23 20:30:13 2016 0.673 Series: ( 31 ) 0.004%
Sat Apr 23 20:30:13 2016 0.674 Series: ( 30 ) 0.006%
Sat Apr 23 20:30:13 2016 0.674 Series: ( 29 ) 0.008%
Sat Apr 23 20:30:13 2016 0.675 Series: ( 28 ) 0.011%
Sat Apr 23 20:30:13 2016 0.677 Series: ( 27 ) 0.015%
Sat Apr 23 20:30:13 2016 0.678 Series: ( 26 ) 0.021%
Sat Apr 23 20:30:13 2016 0.681 Series: ( 25 ) 0.028%
Sat Apr 23 20:30:13 2016 0.683 Series: ( 24 ) 0.039%
Sat Apr 23 20:30:13 2016 0.687 Series: ( 23 ) 0.053%
Sat Apr 23 20:30:13 2016 0.691 Series: ( 22 ) 0.072%
Sat Apr 23 20:30:13 2016 0.698 Series: ( 21 ) 0.099%
Sat Apr 23 20:30:13 2016 0.706 Series: ( 20 ) 0.135%
Sat Apr 23 20:30:13 2016 0.716 Series: ( 19 ) 0.184%
Sat Apr 23 20:30:13 2016 0.730 Series: ( 18 ) 0.252%
Sat Apr 23 20:30:13 2016 0.750 Series: ( 17 ) 0.344%
Sat Apr 23 20:30:13 2016 0.776 Series: ( 16 ) 0.471%
Sat Apr 23 20:30:13 2016 0.812 Series: ( 15 ) 0.643%
Sat Apr 23 20:30:13 2016 0.861 Series: ( 14 ) 0.879%
Sat Apr 23 20:30:13 2016 0.931 Series: ( 13 ) 1.202%
Sat Apr 23 20:30:13 2016 1.025 Series: ( 12 ) 1.643%
Sat Apr 23 20:30:14 2016 1.166 Series: ( 11 ) 2.246%
Sat Apr 23 20:30:14 2016 1.363 Series: ( 10 ) 3.070%
Sat Apr 23 20:30:14 2016 1.649 Series: ( 9 ) 4.196%
Sat Apr 23 20:30:14 2016 2.084 Series: ( 8 ) 5.738%
Sat Apr 23 20:30:15 2016 2.700 Series: ( 7 ) 7.846%
Sat Apr 23 20:30:16 2016 3.539 Series: ( 6 ) 10.732%
Sat Apr 23 20:30:17 2016 4.713 Series: ( 5 ) 14.685%
Sat Apr 23 20:30:19 2016 6.440 Series: ( 4 ) 20.104%
Sat Apr 23 20:30:21 2016 8.899 Series: ( 3 ) 27.543%
Sat Apr 23 20:30:25 2016 12.355 Series: ( 2 ) 37.778%
Sat Apr 23 20:30:29 2016 17.099 Series: ( 1 ) 51.913%
Sat Apr 23 20:30:36 2016 23.955 Series: ( 0 ) 71.591%
Sat Apr 23 20:30:46 2016 34.026 Finishing Series
Sat Apr 23 20:30:46 2016 34.146 Division
Sat Apr 23 20:30:48 2016 36.092 InvSqrt
Sat Apr 23 20:30:50 2016 37.319 Final Multiply
Sat Apr 23 20:30:50 2016 38.095 Base Converting
Sat Apr 23 20:30:53 2016 41.134 Writing Decimal Digits
Sat Apr 23 20:30:56 2016 43.990 Verifying Base Conversion
Sat Apr 23 20:30:58 2016 45.446 End Computation

----

Checksum: 015a6cc64681a6301ea05f6d7eacac54dd99b87e0a4e178800c459884d5843b4

Der CPU-Lüfter dreht 3 mal auf 100% hoch, dass passiert bei rund 74°C und schafft sonst nur das böse prime95...

Darkman.X

2016-04-23, 21:17:49

Was erwartest du denn? Es wird ja immerhin das noch bösere AVX2 genutzt :D

---------------------------

i7-5930K @ 4 GHz
4 x 4 GiB DDR4-2666 (15-15-15-35-2T-1.2V)

Computation Time: 42.783 seconds
Total Time: 47.097 seconds

CPU Utilization: 1026.7 %
Multi-core Efficiency: 85.5586 %

Tralalak

2016-04-23, 21:29:19

Intel Core i3 2367M 1.4GHz (Sandy Bridge, 2C/4T, 3MB L3 cache)

http://i669.photobucket.com/albums/vv53/Artthurko/Ci3_zpsilbhla9c.jpg (http://s669.photobucket.com/user/Artthurko/media/Ci3_zpsilbhla9c.jpg.html)

Tralalak

2016-04-23, 22:27:59

VIA QuadCore E C4650 2.0GHz (Isaiah - CNR, 4C/4T, 2MB L2 cache)
16GB SO-DIMM DDR3 1600MHz @ 1333MHz

http://i669.photobucket.com/albums/vv53/Artthurko/y_cruncher%20C4650_zps5bss5epd.jpg (http://s669.photobucket.com/user/Artthurko/media/y_cruncher%20C4650_zps5bss5epd.jpg.html)

-=Popeye=-

2016-04-23, 23:15:31

5820k @ stock / 16GB DDR4 2666 15-15-15-35 2T

Computation Time: 46.977 seconds
Total Time: 53.150 seconds

CPU Utilization: 1005.29 %
Multi-core Efficiency: 83.7741 %

sakul

2016-04-23, 23:57:32

VIA QuadCore E C4650 2.0GHz (Isaiah - CNR, 4C/4T, 2MB L2 cache)
16GB SO-DIMM DDR3 1600MHz @ 1333MHz

Win 7 X64 im Vergleich zu Loeschzwerg und Tralalak mit nur SSE4.1 Erweiterung.

Computation Time: 677.450 seconds
Total Time: 720.907 seconds

CPU Utilization: 363.655 %
Multi-core Efficiency: 90.9138 %

Der Unterschied von SSE4.1 zu AVX ist kleiner als ich erwartet hatte aber er ist da :)
Wobei mich der Test schon etwas verwirrt denn wenn ich das richtig interpretiere war mein Ergebnis leicht besser als das eure ? ? ?

Tralalak

2016-04-24, 01:59:50

VIA QuadCore E C4650 2.0GHz (Isaiah - CNR, 4C/4T, 2MB L2 cache)

SSE4.1
http://i669.photobucket.com/albums/vv53/Artthurko/y_cruncher_SSE4_1_%20C4650_zpsek3dfbss.jpg (http://s669.photobucket.com/user/Artthurko/media/y_cruncher_SSE4_1_%20C4650_zpsek3dfbss.jpg.html)

x64 SSE4.1 - Ushio vs x64 AVX - Hina

Computation Time: 675.207 seconds vs 745.754 seconds (+10,45% fur SSE4.1)
Total Time: 703.041 seconds vs 774.904 seconds (+10,22% fur SSE4.1)

:eek::

Darkman.X

2016-04-24, 02:41:20

Da schmeckt den VIA-CPUs wohl das AVX nicht so sehr. Ich habe eben mal aus Langeweile mit meiner Intel-CPU getestet: Dort gibt's keine Überraschungen, die Ergebnisse sind wie erwartet. Je neuer das Feature-Set, umso schneller der Benchmark. Wobei der Wechsel von AVX1 zu AVX2 schon heftig ist:

SSE3|SSE4.1|AVX1|AVX2
109.696|106.822|85.222|47.895

Die Frage ist nun: Woran liegt es? Hat VIA vielleicht nur eine 128Bit-AVX-Einheit wie die AMD-Bulldozers? Denen soll das Intel-256Bit-AVX ja auch nicht so gut schmecken. Vielleicht kann ja ein AMD-User mal AVX1 mit SSE4.1 vergleichen.

EDIT: hmm....laut Google soll eure CPU sogar AVX2 können. Wieso nimmt der Benchmark dann nur AVX1? Fragen über Fragen...

BlackArchon

2016-04-24, 09:21:17

Hier mit einem AMD Carrizo (AMD Pro A12-8800B, unterstützt erstmalig bei AMD AVX2!) mit 500m Digits:

SSE3|SSE4.1|AVX1|AVX2|XOP (default)
427,0|401,6|398,5|366,0|370,5

sakul

2016-04-24, 10:03:43

Da schmeckt den VIA-CPUs wohl das AVX nicht so sehr. Ich habe eben mal aus Langeweile mit meiner Intel-CPU getestet: Dort gibt's keine Überraschungen, die Ergebnisse sind wie erwartet. Je neuer das Feature-Set, umso schneller der Benchmark. Wobei der Wechsel von AVX1 zu AVX2 schon heftig ist:

SSE3|SSE4.1|AVX1|AVX2
109.696|106.822|85.222|47.895

Die Frage ist nun: Woran liegt es? Hat VIA vielleicht nur eine 128Bit-AVX-Einheit wie die AMD-Bulldozers? Denen soll das Intel-256Bit-AVX ja auch nicht so gut schmecken. Vielleicht kann ja ein AMD-User mal AVX1 mit SSE4.1 vergleichen.

EDIT: hmm....laut Google soll eure CPU sogar AVX2 können. Wieso nimmt der Benchmark dann nur AVX1? Fragen über Fragen...

Das mit dem AVX2 wundert mich auch das es nicht benutzt wird hmm. . .
Was ich mit Bestimmtheit sagen kann ist das weder AVX noch AVX2 in Windows 7 x64 SP1 mit den VIA's verwendet werden kann. Die CPU's werden dort zwar als AVX/AVX2 Klasse erkannt, das Features wird aber vom BS. deaktiviert.
Die AVX-Tests der VIA's hier stammen vermutlich alle aus einem Windows 8/10 wo das AVX/AVX2 Feature aktiviert ist.

Achill

2016-04-24, 11:11:45

@VIA-Besitzer, ihr könntet schauen ob sich etwas ändert, wenn ihr den Vendor-String von eurem Prozessor ändert zu "GenuineIntel": http://www.agner.org/optimize/blog/read.php?i=49#73

Tralalak

2016-04-24, 12:03:44

Intel Core i3 2367M 1.4GHz (Sandy Bridge, 2C/4T, 3MB L3 cache)

http://i669.photobucket.com/albums/vv53/Artthurko/y_cruncher%20SSE4.1%20Ci3_zpsuqglbsth.png (http://s669.photobucket.com/user/Artthurko/media/y_cruncher%20SSE4.1%20Ci3_zpsuqglbsth.png.html)

x64 AVX - Hina vs x64 SSE4.1 - Ushio

Computation Time: 703.977 seconds vs 859.687 seconds (+22,12% fur AVX)
Total Time: 741.090 seconds vs 899.192 seconds (+21,33% fur AVX)

I think that problem can by also with detection VIA CNR processor (many benchmark CPU-Z, AIDA64, Cinebench R15) dont know this processor a there benchmark cant exploit the potential CNR processor.

Morpheus2200

2016-04-24, 18:52:45

Xeon 1230 v2
8Gb@ 1600mhz

Darkman.X

2016-04-25, 03:39:23

Hier mit einem AMD Carrizo (AMD Pro A12-8800B, unterstützt erstmalig bei AMD AVX2!) mit 500m Digits:

SSE3|SSE4.1|AVX1|AVX2|XOP (default)
427,0|401,6|398,5|366,0|370,5

Der Vorteil von AVX2 gegenüber AVX1 ist ja nicht so toll. Hat AMD wieder eine andere Implementierung als Intel? Oder spielen da andere Dinge mit rein (Cache, RAM, usw.)?

I think that problem can by also with detection VIA CNR processor (many benchmark CPU-Z, AIDA64, Cinebench R15) dont know this processor a there benchmark cant exploit the potential CNR processor.

Do you have Win8 or Win10? Can you run the AVX2-binary?

HisN

2016-04-25, 10:38:07

Intel 5960X@4.4Ghz DDR4 2400

http://abload.de/img/ycruncher_5960x4.4ghzzvs5w.jpg (http://abload.de/image.php?img=ycruncher_5960x4.4ghzzvs5w.jpg)

Der Bench hat irgendwie auch zugelegt, zwischen der Version 6.6 und der 6.9 liegen gute 15 Sekunden bei 0-1-5 und gute 8 Sekunden bei 0-1-4

sakul

2016-04-25, 14:16:43

@VIA-Besitzer, ihr könntet schauen ob sich etwas ändert, wenn ihr den Vendor-String von eurem Prozessor ändert zu "GenuineIntel": http://www.agner.org/optimize/blog/read.php?i=49#73

Die Software ist 6 Jahre alt und für die alten Einkern Nanos nicht für die Modernen Quadcores.

Ich denke Tralalak hat das gut erkannt.
AVX braucht explizite Unterstützung durch das Betriebssystem und angepassten Code der auf die Neuen 256Bit Register der jeweiligen Prozessoren abgestimmt sein muss. Wie ich das verstanden habe werden die alten 128Bit SSE Befehle ja im unteren 128Bit Teil des neuen 256Bit AVX Register verarbeitet.
Da AVX ein Drei-Operanden-SIMD-Befehlsformat im Gegensatz zur alten SSE Zwei-Operanden-Form verwendet benötige man eine Softwareunterstützung. Damit die neuen Register bei einem Kontextwechsel korrekt gespeichert und wiederhergestellt werden.

Ich denke das hier bei VIA und AMD noch nicht das Volle Potenzial ausgeschöpft wurde. Daher die z.T bescheidenden und im Falle von VIA sogar vernichtenden werte beim abschneiden von AVX/AVX2.

Hier noch ein Spaß Bench mit meinem alten VIA und der neuen y-cruncher Version :)

W7 x64 / VIA QuadCore L4700 @ 1.2+ GHz
2x 4 GB 1066 DDR3 7-7-7-20 @ 533 MHz

BlackArchon

2016-04-25, 20:25:50

Der Vorteil von AVX2 gegenüber AVX1 ist ja nicht so toll. Hat AMD wieder eine andere Implementierung als Intel? Oder spielen da andere Dinge mit rein (Cache, RAM, usw.)?
Ich weiß es nicht. Wer könnte etwas mehr Licht ins Dunkle bringen?

Mcdave

2016-04-25, 20:37:54

4790K @ 4.6GHz (1.20V), NB @ 4.3GHz (1.10V), 16GB 2400Mhz RAM 10-12-11-30-1, Win 10 x64 Pro

http://666kb.com/i/d8eh046ijc9asnpkj.gif

tdon

2016-04-25, 21:22:17

i7-6700k @ 4.0 Ghz
DDR4-3200 CL14 16GB
Win 10 x64

http://abload.de/img/cruncher20pq7.png

BlackArchon

2016-04-25, 22:13:17

Intel Core i3-2350M (Sandy Bridge, 2x 2,3 GHz, HT, 35W):

SSE3|SSE4.1|AVX1|AVX2
518,4|502,0|426,3|-

Der HeinZ

2016-04-25, 23:33:16

Ich bekomm meinen vishera nicht crunch-stable!;D;D;D;D
Ich glaube er ist zu sehr untertaktet. Allerdings ist das der erste Benchmark, der nicht durchläuft.
Gruss Matthias

dildo4u

2016-04-25, 23:39:36

Ich bekomm meinen vishera nicht crunch-stable!;D;D;D;D
Ich glaube er ist zu sehr untertaktet. Allerdings ist das der erste Benchmark, der nicht durchläuft.
Gruss Matthias
Schätze mal es gibt sonst kaum Programme die XOP nutzen bei mir kackt er auch ab zieht auch noch mal 20 Watt mehr als andere Last Programme.

Der HeinZ

2016-04-25, 23:43:39

Ich weiß es nicht. Wer könnte etwas mehr Licht ins Dunkle bringen?

AVX 2 wird doch bei AMD Carizzo noch über 256 bit Register ausgeführt, bei Intel über 512 bit register (so war es angedacht). Dadurch sind die intel cpus viel schneller.
Erst "Zen" wird 512 Bit nutzen (glaub ich).
Gruß Matthias
Alles Quark! Carrizo 256 Bit AVX2 ;Bulldozer und Vishera AVX 128 Bit

Der HeinZ

2016-04-26, 07:31:08

Vishera 4,0 Ghz 1866 Speicher NB @ 2,2 Ghz
SSE3 - SSE4.1 - XOP - AVX - Run 1 - AVX Run 2

Das System throttled nicht, Temps liegen bei max. 57 grad (XOP). AVX 2 läuft langsam. Woran liegts?
Gruss Matthias

EDIT: Auffällig ist allerdings das die Berechnung unter SSE3,SSE4.1 + XOP beinahe so schnell wie auf einer Sandy Bridge abläuft,
die output + Verify aber viel langsamer sind. Ich denke das kommt dadurch das beim letzteren wieder nur ein Kern genutzt wird.
Ich kanns´ allerdings gerade nicht testen. Das liegt an der USB Festplatte auf dem das Programm installiert ist. Von der SSD gestartet sinkt der Wert auf übliche Werte ~135.
Komisch ist auch das SSE3 und SSE4.1 beim Vishera praktisch keinen Unterschied macht.
Das ist gegenläufig zu anderen Programmen wo die Unterschiede meist eklatant sind (z.B. H.264,H.265 Benchmark)

BlackArchon

2016-04-26, 20:29:35

Hm, auf dem Vishera ist AVX nur halb so schnell wie XOP, während bei Carrizo beides ähnlich schnell ist. Wie kommt denn das?

MikePayne

2016-04-26, 20:30:34

A10-7800 Kaveri (2 Module / 4 Threads / APU-Grafik deaktiviert)
2x 4 GB DDR3 2133
Win 10 Pro x64

45W: 3 - 3,5 GHz
XOP: 289.572 s
AVX: 335.792 s

65W: 3,5 - 3,8 GHz
XOP: 259.078 s
AVX: 294.997 s

Nuon

2016-04-26, 21:04:04

I5 6600K@4.2GHz 16GB DDR4 2133

Tralalak

2016-04-27, 20:33:52

Do you have Win8 or Win10? Can you run the AVX2-binary?

Win 10

http://i669.photobucket.com/albums/vv53/Artthurko/x265%20VIA%20C4650_AVX2_stopped_zpsrgygjsx5.jpg (http://s669.photobucket.com/user/Artthurko/media/x265%20VIA%20C4650_AVX2_stopped_zpsrgygjsx5.jpg.html)

Der HeinZ

2016-04-28, 15:40:18

Ich teste beim Vishera später die Auswirkung der NB/3rd Level Cache und der Speichergeschwindkeit auf den Bench.
Da Carrizo trotz 256 implentierung von AVX2 auch nicht schneller wird liegts wohl an was anderem als der reinen Implentierung des Befehlsatzes.
Carrizo hat dafür einen größeren Unterschied beim Wechsel von SSE3 auf SSE4.1 als der Vishera.
Gruß Matthias

Darkman.X

2016-04-28, 16:50:25

Laut den 2 Beiträgen hier (http://www.forum-3dcenter.org/vbulletin/showthread.php?p=11013239#post11013239) läuft auch AVX2 bei AMD wohl über die 128Bit-Schiene. Daher der geringe Nutzen von AVX2.

Der HeinZ

2016-04-29, 07:44:42

Ich hab mal vor der Arbeit ein bisschen gebencht:

Vishera @ 4,0 Ghz + 2,0 Ghz NB

DDR3 - 800
AVX XOP SSE4.1 SSE3
253,044 147,846 186,711 188,587
264,329 156,537 196,485 198,108

DDR3 - 1333
AVX XOP SSE4.1 SSE3
234,683 127,452 167,196 168,432
244,447 135,089 175,798 176,849

DDR3 - 1866
AVX XOP SSE4.1 SSE3
227,141 122,785 163,383 keine Lust gehabt
236,585 130,200 171,753 keine Lust gehabt

Desweiteren habe ich die NB auf 2,6 Ghz gezogen, es gab dabei keinerlei Veränderungen.
Das gleiche Ergebniss erfolgt wenn man den HT Bus von 2,2 auf 2,6 ändert.

Das XOP soviel schneller ist als AVX ist für mich daher nicht nachvollziehbar erklärbar.

Interessant ist aber das man bei diesem Bench mit schnellem Speicher sehr viel Zeit gutmachen kann. Das ist mittlerweile eher seltener der Fall als früher.
Gruss Matthias

sakul

2016-04-29, 11:55:41

Win 10

http://i669.photobucket.com/albums/vv53/Artthurko/x265%20VIA%20C4650_AVX2_stopped_zpsrgygjsx5.jpg (http://s669.photobucket.com/user/Artthurko/media/x265%20VIA%20C4650_AVX2_stopped_zpsrgygjsx5.jpg.html)

that's interesting the X265 test program that also uses AVX2 on VIA Cpu crashes to. http://www.forum-3dcenter.org/vbulletin/showpost.php?p=11001746&postcount=132

Der HeinZ

2016-04-30, 07:33:25

T9300 Penryn @ 2,5 Dualcore

SSE4.1 SSE3

Hobby

2016-04-30, 10:06:49

FX 8350 - 4200 MHz (21x200)
16 GB Mem 1600
WIN 10 Pro - 64

Test: 0-1-5

y-cruncher v0.6.9 Build 9464
-------------------

Total Computation Time: 114.443 seconds ( 0.032 hours )
Total Time (with output + verify): 121.642 seconds ( 0.034 hours )

CPU Utilization: 754.336 %
Multi-core Efficiency: 94.292 %

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Version: 0.6.9.9464 (Windows - x64 XOP ~ Miyu)
Processor(s): AMD FX(tm)-8350 Eight-Core Processor
Logical Cores: 8
Physical Memory: 17,160,142,848 (16.0 GiB)
CPU Base Frequency: 4,228,230,671 Hz

Result File: Validation - Pi - 500,000,000.txt

Benchmark Successful. The digits appear to be OK.

BlackArchon

2016-04-30, 10:15:15

Kabini-Power: Hier mit einem AMD A4-5000, 8 GB DDR3-1600 mit 500m Digits:

SSE3 (default)|SSE4.1|AVX1|AVX2|XOP
764,5|776,4|709,4|-|-

Der HeinZ

2016-04-30, 15:34:41

Jeder post Piledriver AMD Prozessor ist unter AVX effektiver als Vishera.
Scheint so als habe man die Umsetzung der AVX 256 BIT Befehle irgendwie verkackt und das bei den neueren verbessert.
Gruss Matthias

Achill

2016-04-30, 16:02:42

Hmm... ich hatte das ja schon angedeutet mit dem VIA-Prozessor und den Vendor-String der CPU.

y-cruncher verwendet für >= AVX-256 den Intel Compiler 15, siehe: http://www.numberworld.org/y-cruncher/algorithms.html

All binaries that use 256-bit AVX or larger are compiled using Intel Compiler 15

M.W. hat sich nichts daran geändert, dass der Intel-Compiler für nicht Intel-CPUs andere Code-Pfade erzeugt und hier u.U. auch nicht die best mögliche SIMD verwendet wird. Mich würde ein Vergleich unter Linux interessieren, da hier der GCC zum Einsatz kommt.

sakul

2016-04-30, 16:56:38

Hmm... ich hatte das ja schon angedeutet mit dem VIA-Prozessor und den Vendor-String der CPU.

y-cruncher verwendet für >= AVX-256 den Intel Compiler 15, siehe: http://www.numberworld.org/y-cruncher/algorithms.html

M.W. hat sich nichts daran geändert, dass der Intel-Compiler für nicht Intel-CPUs andere Code-Pfade erzeugt und hier u.U. auch nicht die best mögliche SIMD verwendet wird. Mich würde ein Vergleich unter Linux interessieren, da hier der GCC zum Einsatz kommt.

Ich habe auch schon versuche mit Linux Mint 17.3 gemacht.
Leider wird der VIA QuadCore E C4650 2.0GHz als unbekannte CPU erkannt und läuft nur in einer art Kompatibilität Modus.
Sonst funktioniert aber alles vergleichbar zu einem Win7 ich konnte da keine Geschwindigkeit Vor/Nachteile entdecken. Es wird auch alles andere soweit richtig erkannt nur eben die CPU nicht. Ich bin jetzt aber auch nicht so der Linux Fachmann um da spezielle CPU Microcode von Hand selber nach zu installieren wenn es überhaupt welche für die VIA CPU geben sollte.

Interessant finde ich das es wohl mittlerweile auch andere Varianten der VIA CPU ohne AVX/AVX2 Anbindung zu geben scheint. Siehe hier http://www.forum-3dcenter.org/vbulletin/showpost.php?p=11016781&postcount=117

BlackArchon

2016-05-01, 10:01:57

Ich habe mit dem Autor von y-cruncher u.a. über den VIA-Prozessor gesprochen. Das hat er zu dem Thema VIA und AVX2 geschrieben:

I've seen that one about the VIA C4650. It can't run the AVX2 binary because it needs more than that. You need AVX, AVX2, FMA3, BMI2, and ABM. Haswell and Excavator have all of them. I believe the VIA is missing the last 3.

So the naming may be a bit deceptive. Generally speaking these instructions sets are linear in that a new one implies all the old ones and the ones that come out simultaneously on the same generation. AVX2, and BMI2 all came out at the same time on Haswell. FMA3 came slightly earlier with Piledriver. And all processors with AVX2 have FMA3. So without knowledge of the VIA processor, everyone who targets Haswell will use all of them.

The good thing is that y-cruncher actually checks for everything before using the binary. And it correctly detected the lack of FMA3 and BMI2 and decided not to use the AVX2 binary. Otherwise, it would just crash.(Mit Einwilligung des Autors veröffentlicht)

Achill

2016-05-01, 11:06:27

Ich habe mit dem Autor von y-cruncher u.a. über den VIA-Prozessor gesprochen. Das hat er zu dem Thema VIA und AVX2 geschrieben:

I've seen that one about the VIA C4650. It can't run the AVX2 binary because it needs more than that. You need AVX, AVX2, FMA3, BMI2, and ABM. Haswell and Excavator have all of them. I believe the VIA is missing the last 3.

So the naming may be a bit deceptive. Generally speaking these instructions sets are linear in that a new one implies all the old ones and the ones that come out simultaneously on the same generation. AVX2, and BMI2 all came out at the same time on Haswell. FMA3 came slightly earlier with Piledriver. And all processors with AVX2 have FMA3. So without knowledge of the VIA processor, everyone who targets Haswell will use all of them.

The good thing is that y-cruncher actually checks for everything before using the binary. And it correctly detected the lack of FMA3 and BMI2 and decided not to use the AVX2 binary. Otherwise, it would just crash.

(Mit Einwilligung des Autors veröffentlicht)

Finde es toll das der Autor geantwortet hat. Ich glaube aber, dass es der Intel Compiler ist (mit Target:Haswell) der diese Abhängigkeit erzeugt.
Es würde kein Sinn machen, noch würde ich so einen Lapsus von Intel/AMD/VIA erwarten, dass eine SIMD ABI umsetzt wird, die andere nicht verfügbare ABIs vorausetzt.
Leider kann man nicht den Quellcode überfliegen, ob der Autor Assembler nutz oder Hints via Präprozessor-Direktiven und die Umsetzung dem Comipler überlässt. Wenn es der letztere Fall ist, ist der Bench zum Vergleich von CPU-Arch aus meiner Sicht nicht mehr so gut geeignet.

sakul

2016-05-01, 11:25:54

Ich habe mit dem Autor von y-cruncher u.a. über den VIA-Prozessor gesprochen. Das hat er zu dem Thema VIA und AVX2 geschrieben:

(Mit Einwilligung des Autors veröffentlicht)

Sehr interessant FMA3 scheint dem Via wirklich zu fehlen. ich hab das auch nochmal mit AIDA64 gegengeprüft.
Das würde auch erklären weshalb mein Win7 x64 SP1, AVX/AVX2 Deaktiviert hat. Es Checkt wohl die CPU Feature Liste der Reihe nach ab und da wo der Erste fehlt wird der Cut gemacht in meinem Fall geht es dann nur bis SSE4.2.

Wenn ich das richtig verstehe kann AVX/AVX2 ja dann praktisch nicht genutzt werden mit dem VIA C4650. Schlimmer noch falls eine Software nicht erkennt das dem VIA FMA3 fehlt und versucht wird AVX2 zu starten, es zu einen Crash kommt. Das würde auch erklären weshalb der X265 Benchmark hier aus dem Forum abschmiert auf dem VIA C4650. In Windows 10 ist nämlich AVX/AVX2 nicht standardmäßig deaktiviert und es wird versucht AVX2 zu nutzen.

Wenn ich das alles so richtig verstanden habe wäre das aber schon ein dicker Patzer seitens Centaur Technology. Das die nicht gemerkt haben das ihrem chip design ein entscheidender Baustein fehlt kann ich garnicht glauben.
Hier der Beitrag zum X265 Benchmark CPU Feature Liste vergleichen auch hier fehlt dem VIA FMA3 http://www.forum-3dcenter.org/vbulletin/showpost.php?p=11001576&postcount=131

BlackArchon

2016-05-01, 11:35:33

Ich denke eher, dass VIA/Centaur nicht die Rechte besitzt bzw. nicht eingekauft hat, um FMA3 und Co. zu nutzen.

Schau doch mal, ob du so etwas wie x265 selbst mit dem GCC übersetzen kannst und dabei AVX2 aktivierst, aber die anderen Features abschaltest, die der VIA-Prozessor nicht kann. Dann sollte das so erzeugte Binary ja funktionieren.

sakul

2016-05-01, 11:59:27

Ich denke eher, dass VIA/Centaur nicht die Rechte besitzt bzw. nicht eingekauft hat, um FMA3 und Co. zu nutzen.

Schau doch mal, ob du so etwas wie x265 selbst mit dem GCC übersetzen kannst und dabei AVX2 aktivierst, aber die anderen Features abschaltest, die der VIA-Prozessor nicht kann. Dann sollte das so erzeugte Binary ja funktionieren.
Leider habe ich nicht so die Technischen Kenntnisse um so etwas selber zu machen vielleicht können das ja Loeschzwerg oder Tralalak mal versuchen.

Aber das würde ja das eigentliche Problem nicht lösen, da quasi jede Software die AVX/AVX2 nutzt erst auf den VIA abgestimmt werden muss.
Ich dachte eigentlich das diese Dinge der Vergangenheit angehören und heute alles von sich aus kompatibel zueinander ist.
Ich denke aus Kompatibilität Gründen hätte Centaur Technology besser die Rechte an FMA3 Lizenziert oder eben ganz auf AVX/AVX2 verzichtet.

Edit. Selbst wenn ich Dinge mit GCC übersetzen könnte würde das nix bringe da standardmäßig in Win7 x64 SP1 AVX/AVX2 deaktiviert ist beim VIA C4650 und mir keine Möglichkeit bekannt ist dies zu Aktivieren.

kruemelmonster

2016-05-01, 14:05:30

Zumindest AVX1 sollte auf dem VIA aber doch laufen wenn ich mir die Ausgabe meines Sandy Bridge anschau:

sakul

2016-05-01, 14:11:01

Zumindest AVX1 sollte auf dem VIA aber doch laufen wenn ich mir die Ausgabe meines Sandy Bridge anschau:

Tut es ja auch aber 10% langsamer als mit SSE4.1

http://www.forum-3dcenter.org/vbulletin/showpost.php?p=11011505&postcount=23

http://www.forum-3dcenter.org/vbulletin/showpost.php?p=11011610&postcount=26

dildo4u

2016-05-01, 14:51:01

Bei mir crasht AVX2 auch auf einem FX 8320e und Win 10.

sakul

2016-05-01, 15:06:31

Bei mir crasht AVX2 auch auf einem FX 8320e und Win 10.
joah. . . laut Wiki fehlt ihm ja auch BMI2 um reibungslos zu funktionieren

http://www.forum-3dcenter.org/vbulletin/showpost.php?p=11018020&postcount=58

BlackArchon

2016-05-01, 15:32:24

Bei mir crasht AVX2 auch auf einem FX 8320e und Win 10.
Deiner CPU fehlt vor allem AVX2. ;)

Carrizo ist die erste Architektur bei AMD, die AVX2 überhaupt unterstützt. Vorher gibt es nur AVX.

dildo4u

2016-05-01, 15:38:01

Ah schade hoffe das wird nicht so schnell zum Nachteil,ich schätze mal Games werden höstens AVX 1 nutzen da die Konsolen Jaguar Core's nutzen.

Der HeinZ

2016-05-01, 16:42:37

Ah schade hoffe das wird nicht so schnell zum Nachteil,ich schätze mal Games werden höstens AVX 1 nutzen da die Konsolen Jaguar Core's nutzen.
Dafür ist die Umsetzung von AVX 256 Bit auf unseren FX eher fragwürdig bzw. laaangsam. Das schränkt die Zukunftssicherheit des FX dann irgendwie noch weiter ein. Mist!
XOP wird wohl keiner nutzen, das ist wie damals mit SSE4a.

BlackArchon

2016-05-01, 22:12:01

Weil mich die schwankende Performance etwas verwundert hat, und weil Carrizo die einzige CPU ist, die ALLE Befehlssätze unterstützt, hier 5 Durchläufe bei 500m Digits (AMD Pro A12-8800B, 2x 8 GB DDR3-1600 Dualchannel):

Run|SSE3|SSE4.1|AVX|AVX2|XOP (default)
1|493,9|421,6|399,1|360,2|387,2
2|420,6|424,4|413,3|371,9|391,9
3|432,4|425,0|420,3|374,5|404,6
4|432,4|421,1|416,4|369,6|400,3
5|420,1|422,9|415,6|371,4|387,8

Fett markiert: Bestwert pro Befehlssatz

Habt ihr auch solche Schwankungen oder liegt das an der Notebook-Kühlung?

sakul

2016-05-01, 23:32:15

Weil mich die schwankende Performance etwas verwundert hat, und weil Carrizo die einzige CPU ist, die ALLE Befehlssätze unterstützt, hier 5 Durchläufe bei 500m Digits (AMD Pro A12-8800B, 2x 8 GB DDR3-1600 Dualchannel):

Run|SSE3|SSE4.1|AVX|AVX2|XOP (default)
1|493,9|421,6|399,1|360,2|387,2
2|420,6|424,4|413,3|371,9|391,9
3|432,4|425,0|420,3|374,5|404,6
4|432,4|421,1|416,4|369,6|400,3
5|420,1|422,9|415,6|371,4|387,8

Fett markiert: Bestwert pro Befehlssatz

Habt ihr auch solche Schwankungen oder liegt das an der Notebook-Kühlung?

Interessanterweise scheinen die Schwankungen bei dir unter SSE4.1 am geringsten und unter SSE3 am höchsten zu sein wenn man mal die 5 Durchgänge miteinander vergleicht.

Der HeinZ

2016-05-02, 06:53:56

Interessanterweise scheinen die Schwankungen bei dir unter SSE4.1 am geringsten und unter SSE3 am höchsten zu sein wenn man mal die 5 Durchgänge miteinander vergleicht.

Meine Schwankungen betragen maximal 2 Sekunden in beide Richtungen,also 4, wobei das natürlich kleiner wird umso schneller die CPU ist.

sakul

2016-05-06, 19:58:31

Ich hab nachgeforscht und möchte einige Dinge klar stellen, nicht das hier was falsch rüber kommt. Der VIA C4650 kann AVX/AVX2 nutzen auch ohne FMA x86.
Aber so wie ich es verstehe nicht besonders effektiv. Dazu möchte ich anmerken das nicht sicher ist ob und warum FMA x86 z.Z. nicht aktiv ist unter Windows beim VIA C4650. Die CPU ist noch neu und es könnte durchaus sein das noch per Windows Patch oder Bios Update nachgeholfen werden muss.
Wie ich es verstehe sind die CPU Feature reservierte-bereiche in der CPU um Rechenoperationen abzukürzen/beschleunigen. SSE und seine Nachfolger verwendet ein 128-Bit-Register in einer Zwei-Operanden-Form also a := a + b was bedeutet das, dass Ergebnis wiederum einer der nächsten Operanden sein muss. AVX wiederum erhöht das 128-Bit-Register auf ein 256 Bit-Register mit Drei-Operanden-SIMD-Befehlsformat. Also c := a + b ein, das Ergebnis zerstört damit nicht mehr notwendigerweise ein Quellregister. Das dem VIA C4650 z.Z. fehlende CPU Feature FMA4 packt da noch einen drauf indem es ein multiplizieren eines wertes ermöglicht. Also Operationen der Form D=A+BxC. Wir alle wissen das man auch ohne multiplizieren zu können rechnen kann, aber nicht besonders effektiv :D

Hier noch einige Quellen.
http://www.3dcenter.org/news/naechster-haswell-vorabtest-bestaetigt-starke-cpu-performance-nur-bei-avx2-fma3

https://de.wikipedia.org/wiki/Streaming_SIMD_Extensions

https://de.wikipedia.org/wiki/FMA_x86

https://de.wikipedia.org/wiki/Advanced_Vector_Extensions

Ich hoffe das da noch was kommt seitens VIA spätestens bei der nächsten CPU Generation. :)

Sonyfreak

2016-05-19, 19:34:30

Mein "neuer" Heimkino-PC:
Intel i7-860 @ 2,8Ghz (Standard)
4x2048MB DDR3-1333 9/9/9/24
Radeon X1800XT @ Standard VGA-Treiber :(
Windows 10 x64

Total Computation Time: 216.686 seconds ( 3.611 minutes )
Start-to-End Wall Time: 227.422 seconds ( 3.790 minutes )

CPU Utilization: 767.78 % + 0.03 % kernel overhead
Multi-core Efficiency: 95.97 % + 0.00 % kernel overhead

Intel i7-860 @ 1,2Ghz (0,85V)

Total Computation Time: 515.203 seconds ( 8.587 minutes )
Start-to-End Wall Time: 537.229 seconds ( 8.954 minutes )

CPU Utilization: 765.28 % + 0.04 % kernel overhead
Multi-core Efficiency: 95.66 % + 0.01 % kernel overhead

Standrechner:
Intel Xeon E3-1230 V3 @ 3,7Ghz
2x4096MB DDR3-2400 11/13/13/35
Geforce GTX 680 2GB @ 1241/3504Mhz
Windows 8.1 x64

Total Computation Time: 60.401 seconds ( 1.007 minutes )
Start-to-End Wall Time: 65.169 seconds ( 1.086 minutes )

CPU Utilization: 773.32 % + 0.18 % kernel overhead
Multi-core Efficiency: 96.66 % + 0.02 % kernel overhead

mfg.

Sonyfreak

The_Invisible

2016-05-20, 08:04:50

6700k @ default
32GB DDR4 2666 Cl15
Ubuntu Linux 16.04 x64

kruemelmonster

2016-06-04, 19:25:24

@The_Invisible:

Der Kernel Overhead bei deinem Linux System ist interessant zu sehen, bestätigt er doch die Aussage des y-c Autors dass unter Windows die Threadverwaltung einfach besser=schneller läuft:

For 5 billion digits on a Core i7 4770K (4-cores/8-threads), the parallel speedup is 4.24x on Windows and 4.07 on Linux. The exact reason for this is unknown. But there is a lot of variation in Linux depending on the parallel framework and whether the binary is dynamically vs. statically linked. 4.07x is the best that could be achieved. Most other options are significantly worse. Furthermore, nothing seems be able to match the efficiency of the Windows thread pool.

Nichtsdestotrotz ist dein Skylake i7 @ default mehr als doppelt so schnell wie mein Sandy i7 @ 4.5 GHz. :redface: Könntest du nochmal einen Durchlauf mit dem AVX1 Hina Binary machen?

---

i7 2600k @ 4.5 GHz / 4x 8 GB DDR3 1866 10-10-10-30-2T / ASUS P8Z68-V Pro / Win10 Build 14352

0,5 Mrd Stellen:

Total Computation Time: 95.535 sec
CPU Utilization: 762.04%
Multi-core Efficiency: 95.25%

http://www.forum-3dcenter.org/vbulletin/attachment.php?attachmentid=56184&stc=1&d=1465060608

5 Mrd Stellen: (um das frische Upgrade von 16 auf 32 GB mal zu fordern)

Total Computation Time: 1398.697 sec
CPU Utilization: 781.74%
Multi-core Efficiency: 97.72%

http://www.forum-3dcenter.org/vbulletin/attachment.php?attachmentid=56185&stc=1&d=1465060608

sakul

2017-03-17, 22:29:44

Current Release:
Windows: Version 0.7.2 Build 9468 (Released: March 14, 2017)
Linux : Version 0.7.2 Build 9468 (Released: March 14, 2017)
"new binary specifically optimized for AMD's Ryzen 7 processors."

Vielleicht kann das ja jemand mit entsprechender Hardware mal testen :)

Download-Link: http://www.numberworld.org/y-cruncher/

Schlammsau

2017-03-17, 22:44:40

Ryzen 1700 @ Default (65W TDP)
16GB Dual Channel @ 2666Mhz
Windows 10 x64

0->1->5

Total Computation Time: 48.077 seconds ( 0.801 minutes )
Start-to-End Wall Time: 60.894 seconds ( 1.015 minutes )

CPU Utilization: 1503.64 % + 1.04 % kernel overhead
Multi-core Efficiency: 93.98 % + 0.06 % kernel overhead

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.2.9468 (Windows/17-ZD1 ~ Yukina)
Processor(s): AMD Ryzen 7 1700 Eight-Core Processor
Topology: 16 threads / 8 cores / 1 socket / 1 NUMA node
Physical Memory: 17,179,869,184 (16.0 GiB)
CPU Base Frequency: 2,994,370,687 Hz

Achill

2017-03-17, 23:32:01

Hmm, finde da schmeckt etwas den Ryzen nicht - Werte scheinen zu niedrig zu sein:

6850k@4.4Ghz / UC@3.6Ghz / Win10

Total Computation Time: 33.419 seconds ( 0.557 minutes )
Start-to-End Wall Time: 37.521 seconds ( 0.625 minutes )

CPU Utilization: 1023.18 % + 0.19 % kernel overhead
Multi-core Efficiency: 85.26 % + 0.02 % kernel overhead

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.2.9468 (Windows/14-BDW ~ Kurumi)
Processor(s): Intel(R) Core(TM) i7-6850K CPU @ 3.60GHz
Topology: 12 threads / 6 cores / 1 socket / 1 NUMA node
Physical Memory: 34,359,738,368 (32.0 GiB)
CPU Base Frequency: 3,600,016,064 Hz

Schlammsau

2017-03-18, 08:23:38

Ryzen 1700 @ Default (65W TDP)
16GB Dual Channel @ 2666Mhz
Windows 10 x64

0->1->5

Total Computation Time: 48.077 seconds ( 0.801 minutes )
Start-to-End Wall Time: 60.894 seconds ( 1.015 minutes )

CPU Utilization: 1503.64 % + 1.04 % kernel overhead
Multi-core Efficiency: 93.98 % + 0.06 % kernel overhead

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.2.9468 (Windows/17-ZD1 ~ Yukina)
Processor(s): AMD Ryzen 7 1700 Eight-Core Processor
Topology: 16 threads / 8 cores / 1 socket / 1 NUMA node
Physical Memory: 17,179,869,184 (16.0 GiB)
CPU Base Frequency: 2,994,370,687 Hz

Ryzen 1700 @ Default (65W TDP)
16GB Dual Channel @ 2666Mhz
Windows 10 x64

0->1->5

Energiesparprofil "Höchstleistung"
Total Computation Time: 46.697 seconds ( 0.778 minutes )
Start-to-End Wall Time: 60.423 seconds ( 1.007 minutes )

CPU Utilization: 1541.15 % + 0.47 % kernel overhead
Multi-core Efficiency: 96.32 % + 0.03 % kernel overhead

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.2.9468 (Windows/17-ZD1 ~ Yukina)
Processor(s): AMD Ryzen 7 1700 Eight-Core Processor
Topology: 16 threads / 8 cores / 1 socket / 1 NUMA node
Physical Memory: 17,179,869,184 (16.0 GiB)
CPU Base Frequency: 2,994,390,336 Hz

BlackArchon

2017-03-18, 09:17:50

Hmm, finde da schmeckt etwas den Ryzen nicht - Werte scheinen zu niedrig zu sein:
...
Weil AVX auch bei Zen immer noch langsam ist: http://www.numberworld.org/y-cruncher/faq.html#amd

atopisch

2017-03-18, 10:13:31

Core i7-4790K@4.6 Cache@4.3

2 x 8GB RAM@2000 10-12-12-31

Total Computation Time: 50.907 seconds ( 0.848 minutes )
Start-to-End Wall Time: 54.470 seconds ( 0.908 minutes )

CPU Utilization: 733.26 % + 0.03 % kernel overhead
Multi-core Efficiency: 91.66 % + 0.00 % kernel overhead

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.2.9468 (Windows/13-HSW ~ Airi)
Processor(s): Intel(R) Core(TM) i7-4790K CPU @ 4.00GHz
Topology: 8 threads / 4 cores / 1 socket / 1 NUMA node
Physical Memory: 17,179,869,184 (16.0 GiB)
CPU Base Frequency: 4,000,083,936 Hz

sakul

2017-03-18, 11:23:50

Der Bench ist recht konstant nach fast 1 Jahr, ich habe mal die Ergebnisse der Vorgänger Version mit dazu gepackt.

TerrorZivi

2017-03-18, 14:01:28

Ryzen 1700 @ Default
32GB Dual Channel @ 2666Mhz CL16
Windows 10 x64

0->1->5

Energiesparprofil "Höchstleistung"

Start Date: Sat Mar 18 13:03:05 2017
End Date: Sat Mar 18 13:03:57 2017

Total Computation Time: 47.634 seconds
Start-to-End Wall Time: 51.716 seconds

CPU Utilization: 1483.89 % + 0.66 % kernel overhead
Multi-core Efficiency: 92.74 % + 0.04 % kernel overhead

Ryzen 1700 @ 3.8GHz
32GB Dual Channel @ 2666Mhz CL16
Windows 10 x64

0->1->5

Energiesparprofil "Höchstleistung"

Start Date: Sat Mar 18 13:54:00 2017
End Date: Sat Mar 18 13:54:44 2017

Total Computation Time: 40.802 seconds
Start-to-End Wall Time: 44.468 seconds

CPU Utilization: 1498.15 % + 0.80 % kernel overhead
Multi-core Efficiency: 93.63 % + 0.05 % kernel overhead

Tyrann

2017-03-18, 15:07:10

2600k@4,4GHz

https://picload.org/image/rlidopll/unbenannt.png

gmb

2017-03-18, 17:32:07

Ryzen 1700 @ Default
32GB Dual Channel @ 2666Mhz CL16
Windows 10 x64

Wie schaut es ohne AVX2 aus, mit der Hina.exe? Zen scheint nicht viel davon zu profitieren.

TerrorZivi

2017-03-18, 18:07:52

R7 @ 3.8GHZ

Yukina / ZD1

Total Computation Time: 40.809 seconds
Start-to-End Wall Time: 44.574 seconds

CPU Utilization: 1503.62 % + 0.69 % kernel overhead
Multi-core Efficiency: 93.98 % + 0.04 % kernel overhead

Kasumi / A64

Total Computation Time: 62.692 seconds
Start-to-End Wall Time: 67.237 seconds

CPU Utilization: 1500.18 % + 1.00 % kernel overhead
Multi-core Efficiency: 93.76 % + 0.06 % kernel overhead

Ushio / Nehalem

Total Computation Time: 56.363 seconds
Start-to-End Wall Time: 61.122 seconds

CPU Utilization: 1524.47 % + 0.53 % kernel overhead
Multi-core Efficiency: 95.28 % + 0.03 % kernel overhead

Hina / SNB

Total Computation Time: 57.244 seconds
Start-to-End Wall Time: 62.045 seconds

CPU Utilization: 1518.68 % + 0.63 % kernel overhead
Multi-core Efficiency: 94.92 % + 0.04 % kernel overhead

Airi / Haswell

Total Computation Time: 43.024 seconds
Start-to-End Wall Time: 46.656 seconds

CPU Utilization: 1507.70 % + 0.65 % kernel overhead
Multi-core Efficiency: 94.23 % + 0.04 % kernel overhead

Kurumi / Broadwell

Total Computation Time: 42.616 seconds
Start-to-End Wall Time: 46.338 seconds

CPU Utilization: 1511.10 % + 0.99 % kernel overhead
Multi-core Efficiency: 94.44 % + 0.06 % kernel overhead

atopisch

2017-03-20, 17:22:18

Core i7-3667U boostet die meiste Zeit auf 3.0 Ghz.

Total Computation Time: 286.599 seconds ( 4.777 minutes )
Start-to-End Wall Time: 310.633 seconds ( 5.177 minutes )

CPU Utilization: 385.15 % + 0.03 % kernel overhead
Multi-core Efficiency: 96.29 % + 0.01 % kernel overhead

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.2.9468 (Windows/11-SNB ~ Hina)
Processor(s): Intel(R) Core(TM) i7-3667U CPU @ 2.00GHz
Topology: 4 threads / 2 cores / 1 socket / 1 NUMA node
Physical Memory: 8,589,934,592 (8.00 GiB)
CPU Base Frequency: 2,494,443,600 Hz

Core i3-6100 startet mit 3,7GHz wird dann aber durch die TDP auf 3,1-3,2GHz begrenzt.

Total Computation Time: 116.446 seconds ( 1.941 minutes )
Start-to-End Wall Time: 123.053 seconds ( 2.051 minutes )

CPU Utilization: 385.63 % + 0.07 % kernel overhead
Multi-core Efficiency: 96.41 % + 0.02 % kernel overhead

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.1.9465 (Windows - x64 ADX ~ Kurumi)
Processor(s): Intel(R) Core(TM) i3-6100 CPU @ 3.70GHz
Topology: 4 threads / 2 cores / 1 socket / 1 NUMA node
Physical Memory: 8,589,934,592 (8.00 GiB)
CPU Base Frequency: 3,696,105,567 Hz

Tralalak

2017-03-25, 13:22:16

VIA QuadCore E C4650 2.0GHz (Isaiah - CNR, 4C/4T, 2MB L2 cache)

SSE4.1
http://i669.photobucket.com/albums/vv53/Artthurko/y_cruncher_SSE4_1_%20C4650_zpsek3dfbss.jpg (http://s669.photobucket.com/user/Artthurko/media/y_cruncher_SSE4_1_%20C4650_zpsek3dfbss.jpg.html)

x64 SSE4.1 - Ushio vs x64 AVX - Hina

Computation Time: 675.207 seconds vs 745.754 seconds (+10,45% fur SSE4.1)
Total Time: 703.041 seconds vs 774.904 seconds (+10,22% fur SSE4.1)

:eek::

VIA QuadCore C4650@2.0GHz (AVX)
Program: y-cruncher v0.7.2 Build 9468
Tuning: 11-SNB ~ Hina
Operating System: Windows 10.0 Build 14393

Total Computation Time: 587.516 seconds
Start-to-End Wall Time: 619.317 seconds

http://i669.photobucket.com/albums/vv53/Artthurko/VIA%20y_cruncher_v_0_7_2_build_9468_zpswuzbee7y.jpg (http://s669.photobucket.com/user/Artthurko/media/VIA%20y_cruncher_v_0_7_2_build_9468_zpswuzbee7y.jpg.html)

vs

VIA QuadCore C4650@2.0GHz (SSE4.1)
Program: y-cruncher v0.7.2 Build 9468
Tuning: 08-NHM ~ Ushio
Operating System: Windows 10.0 Build 14393

Total Computation Time: 601.326 seconds
Start-to-End Wall Time: 629.501 seconds

http://i669.photobucket.com/albums/vv53/Artthurko/VIA%20y_cruncher_v_0_7_2_build_9468_Ushio_zpsm3r5llo9.jpg (http://s669.photobucket.com/user/Artthurko/media/VIA%20y_cruncher_v_0_7_2_build_9468_Ushio_zpsm3r5llo9.jpg.html)

:up:

Holgi

2017-03-26, 10:06:33

AMD FX-8320E @ stock 8GB Ram

Tech_FREAK_2000|GS

2017-04-02, 16:08:28

Intel Xeon Phi 7210

Start Time: Sun Apr 2 16:03:07 2017
End Time: Sun Apr 2 16:04:09 2017

Total Computation Time: 54.424 seconds ( 0.907 minutes )
Start-to-End Wall Time: 61.472 seconds ( 1.025 minutes )

CPU Utilization: 16406.67 % + 855.63 % kernel overhead
Multi-core Efficiency: 64.09 % + 3.34 % kernel overhead

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.2.9468 (Linux/14-BDW ~ Kurumi)
Processor(s): Intel(R) Xeon Phi(TM) CPU 7210 @ 1.30GHz
Topology: 256 threads / 64 cores / 1 socket / 2 NUMA nodes
Usable Memory: 117,955,248,128 ( 110 GiB)
CPU Base Frequency: 1,300,007,488 Hz

Validation File: Pi - 20170402-160409.txt

BlackArchon

2017-04-02, 17:26:44

Intel Xeon Phi 7210
...Du, das solltest du mal dem Autor schicken (http://www.numberworld.org/y-cruncher/#Contact) - der findet das vielleicht sehr interessant und will noch mehr sehen. :)

Rein von der Performance her ist das aber leider gar nicht mal so toll - 500m bekommt mein i7-5775C@3,8 GHz auch in 56 Sekunden hin.

oOOMadCatOOo

2017-04-02, 18:22:22

6900k@4,4Ghz
UC@3.5Ghz
DDR4-3200@14-14-14-34

Total Computation Time: 25.088 seconds
Start-to-End Wall Time: 27.029 seconds

CPU Utilization: 1446.48 % + 1.18 % kernel overhead
Multi-core Efficiency: 90.40 % + 0.07 % kernel overhead

Benchmark Validation File - DO NOT MODIFY! If you do it will fail validation.

Validation Version: 1.3

Program: y-cruncher v0.7.2 Build 9468
Tuning: 14-BDW ~ Kurumi

User: None Specified - You can edit this in "Username.txt".

Operating System: Windows 10.0 Build 14393

Processor(s):
Name: Intel(R) Core(TM) i7-6900K CPU @ 3.20GHz
Logical Cores: 16
Physical Cores: 8
Sockets: 1
NUMA Nodes: 1
Base Frequency: 3,200,000,479 Hz

Motherboard:
Manufacturer: ASUSTeK COMPUTER INC.
Model: RAMPAGE V EXTREME
Version: Rev 1.xx
Serial Number: Suppressed - Personally identifiable information is opt-in only.

Memory:
Usable Memory: 34,267,688,960 (31.9 GiB)
Total Memory: 34,359,738,368 (32.0 GiB)
DIMM: 8.00 GiB - G-Skill - F4-3200C14-8GTZSW
DIMM: 8.00 GiB - G-Skill - F4-3200C14-8GTZSW
DIMM: 8.00 GiB - G-Skill - F4-3200C14-8GTZSW
DIMM: 8.00 GiB - G-Skill - F4-3200C14-8GTZSW

Constant: Pi
Algorithm: Chudnovsky Formula
Decimal Digits: 500,000,000
Hexadecimal Digits: Disabled
Computation Mode: Ram Only
Threading Mode: Push Pool -> 16 / ? (randomization on)
Working Memory: 2,794,382,664 (2.60 GiB)
Total Memory: 2,873,143,432 (2.68 GiB)

Start Date: Sun Apr 2 18:17:57 2017
End Date: Sun Apr 2 18:18:24 2017

Total Computation Time: 25.088 seconds
Start-to-End Wall Time: 27.029 seconds

CPU Utilization: 1446.48 % + 1.18 % kernel overhead
Multi-core Efficiency: 90.40 % + 0.07 % kernel overhead

Last Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Dec Counts: {49995279,50000437,50011436,49992409,50005121,49990678,49998820,50000320,5000663 2,49998868}

Binary Hash: Floor(bin * 10^dec) mod (2^61 - 1) = 1095036223966448356

Spot Check: Good through 500,000,000
Timer Sanity Check: Passed
Frequency Sanity Check: Disabled in this version of y-cruncher
Reference Clock: TSC
Reference Clock 0: 3,125,001
Reference Clock 1: 181,895,378
Reference Clock 2: 20,305,607
Is Debugger Present: No
Is Contiguous: Yes
ECC Recovered Errors: 0

Event Log:
Sun Apr 2 18:17:57 2017 0.006 Reserving Working Memory
Sun Apr 2 18:17:58 2017 0.602 Reserving Working Memory: 2.60 GiB
Sun Apr 2 18:17:58 2017 0.602 Constructing Twiddle Tables
Sun Apr 2 18:17:58 2017 0.635 Constructing Twiddle Tables: 75.1 MiB
Sun Apr 2 18:17:58 2017 0.636 Begin Computation
Sun Apr 2 18:17:58 2017 0.636 Series: ( 34 ) 0.000%
Sun Apr 2 18:17:58 2017 0.638 Series: ( 33 ) 0.002%
Sun Apr 2 18:17:58 2017 0.639 Series: ( 32 ) 0.003%
Sun Apr 2 18:17:58 2017 0.639 Series: ( 31 ) 0.004%
Sun Apr 2 18:17:58 2017 0.640 Series: ( 30 ) 0.006%
Sun Apr 2 18:17:58 2017 0.640 Series: ( 29 ) 0.008%
Sun Apr 2 18:17:58 2017 0.641 Series: ( 28 ) 0.011%
Sun Apr 2 18:17:58 2017 0.642 Series: ( 27 ) 0.015%
Sun Apr 2 18:17:58 2017 0.644 Series: ( 26 ) 0.021%
Sun Apr 2 18:17:58 2017 0.646 Series: ( 25 ) 0.028%
Sun Apr 2 18:17:58 2017 0.648 Series: ( 24 ) 0.039%
Sun Apr 2 18:17:58 2017 0.651 Series: ( 23 ) 0.053%
Sun Apr 2 18:17:58 2017 0.655 Series: ( 22 ) 0.072%
Sun Apr 2 18:17:58 2017 0.660 Series: ( 21 ) 0.099%
Sun Apr 2 18:17:58 2017 0.665 Series: ( 20 ) 0.135%
Sun Apr 2 18:17:58 2017 0.673 Series: ( 19 ) 0.184%
Sun Apr 2 18:17:58 2017 0.683 Series: ( 18 ) 0.252%
Sun Apr 2 18:17:58 2017 0.696 Series: ( 17 ) 0.344%
Sun Apr 2 18:17:58 2017 0.712 Series: ( 16 ) 0.471%
Sun Apr 2 18:17:58 2017 0.735 Series: ( 15 ) 0.643%
Sun Apr 2 18:17:58 2017 0.765 Series: ( 14 ) 0.879%
Sun Apr 2 18:17:58 2017 0.810 Series: ( 13 ) 1.202%
Sun Apr 2 18:17:58 2017 0.882 Series: ( 12 ) 1.643%
Sun Apr 2 18:17:58 2017 0.984 Series: ( 11 ) 2.246%
Sun Apr 2 18:17:58 2017 1.118 Series: ( 10 ) 3.070%
Sun Apr 2 18:17:59 2017 1.303 Series: ( 9 ) 4.196%
Sun Apr 2 18:17:59 2017 1.558 Series: ( 8 ) 5.738%
Sun Apr 2 18:17:59 2017 1.935 Series: ( 7 ) 7.846%
Sun Apr 2 18:18:00 2017 2.470 Series: ( 6 ) 10.732%
Sun Apr 2 18:18:01 2017 3.198 Series: ( 5 ) 14.685%
Sun Apr 2 18:18:02 2017 4.277 Series: ( 4 ) 20.104%
Sun Apr 2 18:18:03 2017 5.818 Series: ( 3 ) 27.543%
Sun Apr 2 18:18:05 2017 7.965 Series: ( 2 ) 37.778%
Sun Apr 2 18:18:08 2017 10.908 Series: ( 1 ) 51.913%
Sun Apr 2 18:18:12 2017 14.993 Series: ( 0 ) 71.591%
Sun Apr 2 18:18:19 2017 21.186 Finishing Series
Sun Apr 2 18:18:19 2017 21.265 Division
Sun Apr 2 18:18:20 2017 22.440 InvSqrt
Sun Apr 2 18:18:21 2017 23.313 Final Multiply
Sun Apr 2 18:18:21 2017 23.844 Base Converting
Sun Apr 2 18:18:23 2017 25.726 Writing Decimal Digits
Sun Apr 2 18:18:24 2017 26.334 Verifying Base Conversion
Sun Apr 2 18:18:24 2017 27.029 End Computation

----

Checksum0: 6682065a7d45db02381652b78e577ec2334171701bb0e1b2f01039ac9327c4ce3f10f55ddf6aa05d 9b47d75a7df43f6e518c875ec848f8857f6dfb4fd094c53b
Checksum1: c21ed04a9d576f3309d2c46721995a7e5be372dc10d44f6cad808f49ca239a46e89e1fa162dda9e6 ff96f346ef4426aef93cc094f07dec344742244f62e9360d

Tech_FREAK_2000|GS

2017-04-02, 19:01:29

Du, das solltest du mal dem Autor schicken (http://www.numberworld.org/y-cruncher/#Contact
) - der findet das vielleicht sehr interessant und will noch mehr sehen. :)

Rein von der Performance her ist das aber leider gar nicht mal so toll - 500m bekommt mein i7-5775C@3,8 GHz auch in 56 Sekunden hin.

Ich bin da etwas "spät" dran, er hat das schon mit einem KNL System getestet.

Academia:
Is there a version that can use the GPU?
[...]
But before we slam the door on GPUs, it's worth mentioning the Xeon Phi processor line. While these aren't exactly GPUs, they are still massively parallelized and have large SIMD vectors. Preliminary benchmarks on Knights Landing are somewhat disappointing even with the AVX512 binaries. But it's difficult to draw any conclusions without access to the hardware and without the ability to tune the program for the hardware.
[...]

Quelle:
http://www.numberworld.org/y-cruncher/faq.html#gpu

Hier noch der Link auf die News mit den Ergebnissen:
http://www.numberworld.org/y-cruncher/news.html#2016_10_10

atopisch

2017-04-18, 17:10:42

Core i7-6600U mit 15 Watt konfigurierter TDP. Boostet zwischen 2600 MHz und 2700 MHz. Er fängt mit 3000 MHz an und hat damit eine kurzfristige TDP von 20 Watt. Schon im Single Thread Modus boostet er Dank der TDP von 15 Watt nur zwischen 3000 MHz und 3200 MHz anstatt der maximalen 3400 MHz.

Total Computation Time: 121.241 seconds ( 2.021 minutes )
Start-to-End Wall Time: 128.108 seconds ( 2.135 minutes )

CPU Utilization: 390.19 % + 0.04 % kernel overhead
Multi-core Efficiency: 97.55 % + 0.01 % kernel overhead

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.2.9468 (Windows/14-BDW ~ Kurumi)
Processor(s): Intel(R) Core(TM) i7-6600U CPU @ 2.60GHz
Topology: 4 threads / 2 cores / 1 socket / 1 NUMA node
Physical Memory: 17,179,869,184 (16.0 GiB)
CPU Base Frequency: 2,808,461,792 Hz

Validation File: Pi - 20170418-165955.txt

kruemelmonster

2017-07-07, 00:22:21

i7 7800X @ 4.5 Core / 4.4 AVX / 3.0 Uncore / 2x 8 GB DDR4 3000 CL15

Total Computation Time: 36.229 seconds ( 0.604 minutes )
Start-to-End Wall Time: 38.416 seconds ( 0.640 minutes )

CPU Utilization: 1005.94 % + 5.78 % kernel overhead
Multi-core Efficiency: 83.83 % + 0.48 % kernel overhead

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.2.9469 (Windows/14-BDW ~ Kurumi)
Processor(s): Intel(R) Core(TM) i7-7800X CPU @ 3.50GHz
Topology: 12 threads / 6 cores / 1 socket / 1 NUMA node
Physical Memory: 17,179,869,184 (16.0 GiB)
CPU Base Frequency: 3,503,989,983 Hz

IchoTolot

2017-07-07, 00:45:00

7700K Default 32 GB DDR4-3000 CL15-17-17-35 1T

Benchmark Validation File - DO NOT MODIFY! If you do it will fail validation.

Validation Version: 1.3

Program: y-cruncher v0.7.2 Build 9469
Tuning: 14-BDW ~ Kurumi

User: None Specified - You can edit this in "Username.txt".

Operating System: Windows 10.0 Build 15063

Processor(s):
Name: Intel(R) Core(TM) i7-7700K CPU @ 4.20GHz
Logical Cores: 8
Physical Cores: 4
Sockets: 1
NUMA Nodes: 1
Base Frequency: 4,200,001,408 Hz

Motherboard:
Manufacturer: ASUSTeK COMPUTER INC.
Model: PRIME Z270-P
Version: Rev X.0x
Serial Number: Suppressed - Personally identifiable information is opt-in only.

Memory:
Usable Memory: 34,227,044,352 (31.9 GiB)
Total Memory: 34,359,738,368 (32.0 GiB)
DIMM: 8.00 GiB - Corsair - CMK16GX4M2B3000C15
DIMM: 8.00 GiB - Corsair - CMK16GX4M2B3000C15
DIMM: 8.00 GiB - Corsair - CMK16GX4M2B3000C15
DIMM: 8.00 GiB - Corsair - CMK16GX4M2B3000C15

Constant: Pi
Algorithm: Chudnovsky Formula
Decimal Digits: 500,000,000
Hexadecimal Digits: Disabled
Computation Mode: Ram Only
Threading Mode: Push Pool -> 8 / ? (randomization on)
Working Memory: 2,581,913,416 (2.40 GiB)
Total Memory: 2,660,674,184 (2.48 GiB)

Start Date: Fri Jul 7 00:41:08 2017
End Date: Fri Jul 7 00:41:51 2017

Total Computation Time: 38.937 seconds
Start-to-End Wall Time: 42.530 seconds

CPU Utilization: 764.41 % + 0.40 % kernel overhead
Multi-core Efficiency: 95.55 % + 0.05 % kernel overhead

Last Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Dec Counts: {49995279,50000437,50011436,49992409,50005121,49990678,49998820,50000320,5000663 2,49998868}

Binary Hash: Floor(bin * 10^dec) mod (2^61 - 1) = 1095036223966448356

Spot Check: Good through 500,000,000
Timer Sanity Check: Passed
Frequency Sanity Check: Disabled in this version of y-cruncher
Reference Clock: TSC
Reference Clock 0: 4,101,568
Reference Clock 1: 173,774,932
Reference Clock 2: 20,365,520
Is Debugger Present: No
Is Contiguous: Yes
ECC Recovered Errors: 0

Event Log:
Fri Jul 7 00:41:08 2017 0.003 Reserving Working Memory
Fri Jul 7 00:41:09 2017 0.146 Reserving Working Memory: 2.41 GiB (locked, 2.00 MiB pages)
Fri Jul 7 00:41:09 2017 0.146 Constructing Twiddle Tables
Fri Jul 7 00:41:09 2017 0.166 Constructing Twiddle Tables: 75.1 MiB (locked, 2.00 MiB pages)
Fri Jul 7 00:41:09 2017 0.166 Begin Computation
Fri Jul 7 00:41:09 2017 0.167 Series: ( 34 ) 0.000%
Fri Jul 7 00:41:09 2017 0.169 Series: ( 33 ) 0.002%
Fri Jul 7 00:41:09 2017 0.169 Series: ( 32 ) 0.003%
Fri Jul 7 00:41:09 2017 0.169 Series: ( 31 ) 0.004%
Fri Jul 7 00:41:09 2017 0.170 Series: ( 30 ) 0.006%
Fri Jul 7 00:41:09 2017 0.170 Series: ( 29 ) 0.008%
Fri Jul 7 00:41:09 2017 0.171 Series: ( 28 ) 0.011%
Fri Jul 7 00:41:09 2017 0.172 Series: ( 27 ) 0.015%
Fri Jul 7 00:41:09 2017 0.173 Series: ( 26 ) 0.021%
Fri Jul 7 00:41:09 2017 0.175 Series: ( 25 ) 0.028%
Fri Jul 7 00:41:09 2017 0.177 Series: ( 24 ) 0.039%
Fri Jul 7 00:41:09 2017 0.180 Series: ( 23 ) 0.053%
Fri Jul 7 00:41:09 2017 0.185 Series: ( 22 ) 0.072%
Fri Jul 7 00:41:09 2017 0.191 Series: ( 21 ) 0.099%
Fri Jul 7 00:41:09 2017 0.199 Series: ( 20 ) 0.135%
Fri Jul 7 00:41:09 2017 0.212 Series: ( 19 ) 0.184%
Fri Jul 7 00:41:09 2017 0.226 Series: ( 18 ) 0.252%
Fri Jul 7 00:41:09 2017 0.244 Series: ( 17 ) 0.344%
Fri Jul 7 00:41:09 2017 0.268 Series: ( 16 ) 0.471%
Fri Jul 7 00:41:09 2017 0.304 Series: ( 15 ) 0.643%
Fri Jul 7 00:41:09 2017 0.355 Series: ( 14 ) 0.879%
Fri Jul 7 00:41:09 2017 0.427 Series: ( 13 ) 1.202%
Fri Jul 7 00:41:09 2017 0.523 Series: ( 12 ) 1.643%
Fri Jul 7 00:41:09 2017 0.663 Series: ( 11 ) 2.246%
Fri Jul 7 00:41:09 2017 0.862 Series: ( 10 ) 3.070%
Fri Jul 7 00:41:09 2017 1.138 Series: ( 9 ) 4.196%
Fri Jul 7 00:41:10 2017 1.607 Series: ( 8 ) 5.738%
Fri Jul 7 00:41:11 2017 2.226 Series: ( 7 ) 7.846%
Fri Jul 7 00:41:11 2017 3.042 Series: ( 6 ) 10.732%
Fri Jul 7 00:41:13 2017 4.177 Series: ( 5 ) 14.685%
Fri Jul 7 00:41:14 2017 5.842 Series: ( 4 ) 20.104%
Fri Jul 7 00:41:17 2017 8.270 Series: ( 3 ) 27.543%
Fri Jul 7 00:41:20 2017 11.693 Series: ( 2 ) 37.778%
Fri Jul 7 00:41:25 2017 16.258 Series: ( 1 ) 51.913%
Fri Jul 7 00:41:31 2017 22.768 Series: ( 0 ) 71.591%
Fri Jul 7 00:41:41 2017 32.606 Finishing Series
Fri Jul 7 00:41:41 2017 32.677 Division
Fri Jul 7 00:41:43 2017 34.462 InvSqrt
Fri Jul 7 00:41:44 2017 35.563 Final Multiply
Fri Jul 7 00:41:45 2017 36.316 Base Converting
Fri Jul 7 00:41:47 2017 39.105 Writing Decimal Digits
Fri Jul 7 00:41:50 2017 41.373 Verifying Base Conversion
Fri Jul 7 00:41:51 2017 42.530 End Computation

----

Checksum0: 0bc1bbb7d3457698075389ab8aafd5d25b0aa59e30d45f72c483d40a93fdbb0681eaf6af43e43f1d a0faa252b116a8a20b7fcc88ddca220113480d1ecc2d3cd5
Checksum1: da73134e13c431f677616599ed7495f7d8e6beeecf1d173ce0b7551e67ca3b27d27d04a3a88ea857 edcdceb54284fce8208cc13b1a70abc218eeb59218e9f9ff

BlackArchon

2017-07-07, 08:23:50

i7 7800X @ 4.5 Core / 4.4 AVX / 3.0 Uncore / 2x 8 GB DDR4 3000 CL15

Total Computation Time: 36.229 seconds ( 0.604 minutes )
Start-to-End Wall Time: 38.416 seconds ( 0.640 minutes )

CPU Utilization: 1005.94 % + 5.78 % kernel overhead
Multi-core Efficiency: 83.83 % + 0.48 % kernel overhead

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.2.9469 (Windows/14-BDW ~ Kurumi)
Processor(s): Intel(R) Core(TM) i7-7800X CPU @ 3.50GHz
Topology: 12 threads / 6 cores / 1 socket / 1 NUMA node
Physical Memory: 17,179,869,184 (16.0 GiB)
CPU Base Frequency: 3,503,989,983 Hz
Wird Zeit, dass der Autor von y-Cruncher seine AVX512-Version fertigstellt, da geht bestimmt noch einiges.

Edit:
Er hat gerade eine AVX512-Version mitsamt einigen Erklärungen dazu auf http://www.numberworld.org/y-cruncher/ gepostet!

kruemelmonster

2017-07-07, 17:49:24

Er hat gerade eine AVX512-Version mitsamt einigen Erklärungen dazu auf http://www.numberworld.org/y-cruncher/ gepostet!

Erster Durchlauf mit nur 4,5 GHz Core / 4,2 AVX / 3,0 Uncore, mit der bisherigen Spannung und AVX@4,4 hat der Rechner direkt einen BSOD gebracht.
Die Leistungsaufnahme lag während des Tests zwischen 120 und 150 Watt bei einem Powertarget von 165w long / 180w short.

Total Computation Time: 32.819 seconds ( 0.547 minutes )
Start-to-End Wall Time: 34.736 seconds ( 0.579 minutes )

CPU Utilization: 952.52 % + 1.19 % kernel overhead
Multi-core Efficiency: 79.38 % + 0.10 % kernel overhead

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.3.9471 (Windows/17-SKX ~ Kotori)
Processor(s): Intel(R) Core(TM) i7-7800X CPU @ 3.50GHz
Topology: 12 threads / 6 cores / 1 socket / 1 NUMA node
Physical Memory: 17,179,869,184 (16.0 GiB)
CPU Base Frequency: 3,504,002,431 Hz

BlackArchon

2017-07-07, 18:17:40

Erster Durchlauf mit nur 4,5 GHz Core / 4,2 AVX / 3,0 Uncore, mit der bisherigen Spannung und AVX@4,4 hat der Rechner direkt einen BSOD gebracht.
Die Leistungsaufnahme lag während des Tests zwischen 120 und 150 Watt bei einem Powertarget von 165w long / 180w short.
...
Ich glaube, der Autor würde sich über ein paar Werte mit verschiedenen Testgrößen freuen. :)

oOOMadCatOOo

2017-07-12, 20:53:55

i7 7900X @ 4.5 Core / 4.2 AVX / 3.2 Uncore / DDR4 2666 CL14

Total Computation Time: 20.125 seconds
Start-to-End Wall Time: 21.914 seconds

CPU Utilization: 1684.82 % + 2.41 % kernel overhead
Multi-core Efficiency: 84.24 % + 0.12 % kernel overhead

Last Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Program: y-cruncher v0.7.3 Build 9471

atopisch

2017-08-03, 22:10:13

Ryzen 5 1600@3800MHz 16GB RAM@3200MHz 14-14-14-28-1T

Total Computation Time: 53.326 seconds ( 0.889 minutes )
Start-to-End Wall Time: 57.053 seconds ( 0.951 minutes )

CPU Utilization: 1026.41 % + 0.23 % kernel overhead
Multi-core Efficiency: 85.53 % + 0.02 % kernel overhead

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.3.9472 (Windows/17-ZD1 ~ Yukina)
Processor(s): AMD Ryzen 5 1600 Six-Core Processor
Topology: 12 threads / 6 cores / 1 socket / 1 NUMA node
Physical Memory: 17,179,869,184 (16.0 GiB)
CPU Base Frequency: 3,800,195,295 Hz

IchoTolot

2017-08-03, 22:43:33

i7 7700K 4.8 Ghz

Benchmark Validation File - DO NOT MODIFY! If you do it will fail validation.

Validation Version: 1.3

Program: y-cruncher v0.7.3 Build 9472
Tuning: 14-BDW ~ Kurumi

User: None Specified - You can edit this in "Username.txt".

Operating System: Windows 10.0 Build 15063

Processor(s):
Name: Intel(R) Core(TM) i7-7700K CPU @ 4.20GHz
Logical Cores: 8
Physical Cores: 4
Sockets: 1
NUMA Nodes: 1
Base Frequency: 4,200,006,720 Hz

Motherboard:
Manufacturer: ASUSTeK COMPUTER INC.
Model: PRIME Z270-P
Version: Rev X.0x
Serial Number: Suppressed - Personally identifiable information is opt-in only.

Memory:
Usable Memory: 34,226,913,280 (31.9 GiB)
Total Memory: 34,359,738,368 (32.0 GiB)
DIMM: 8.00 GiB - Corsair - CMK16GX4M2B3000C15
DIMM: 8.00 GiB - Corsair - CMK16GX4M2B3000C15
DIMM: 8.00 GiB - Corsair - CMK16GX4M2B3000C15
DIMM: 8.00 GiB - Corsair - CMK16GX4M2B3000C15

Constant: Pi
Algorithm: Chudnovsky Formula
Decimal Digits: 500,000,000
Hexadecimal Digits: Disabled
Computation Mode: Ram Only
Threading Mode: Push Pool -> 8 / ? (randomization on)
Working Memory: 2,581,912,616 (2.40 GiB)
Total Memory: 2,660,671,848 (2.48 GiB)

Start Date: Thu Aug 3 22:40:33 2017
End Date: Thu Aug 3 22:41:12 2017

Total Computation Time: 36.011 seconds
Start-to-End Wall Time: 39.108 seconds

CPU Utilization: 768.77 % + 0.04 % kernel overhead
Multi-core Efficiency: 96.10 % + 0.01 % kernel overhead

Last Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Dec Counts: {49995279,50000437,50011436,49992409,50005121,49990678,49998820,50000320,5000663 2,49998868}

Binary Hash: Floor(bin * 10^dec) mod (2^61 - 1) = 1095036223966448356

Spot Check: Good through 500,000,000
Timer Sanity Check: Passed
Frequency Sanity Check: Disabled in this version of y-cruncher
Reference Clock: TSC
Reference Clock 0: 4,101,568
Reference Clock 1: 189,828,916
Reference Clock 2: 22,310,444
Is Debugger Present: No
Is Contiguous: Yes
ECC Recovered Errors: 0

Lehdro

2017-08-04, 23:03:15

R7 1800X @ 4,04 GHz
Benchmark Validation File - DO NOT MODIFY! If you do it will fail validation.

Validation Version: 1.3

Program: y-cruncher v0.7.3 Build 9472
Tuning: 17-ZD1 ~ Yukina

User: None Specified - You can edit this in "Username.txt".

Operating System: Windows 10.0 Build 15063

Processor(s):
Name: AMD Ryzen 7 1800X Eight-Core Processor
Logical Cores: 16
Physical Cores: 8
Sockets: 1
NUMA Nodes: 1
Base Frequency: 4,042,410,559 Hz

Motherboard:
Manufacturer: ASUSTeK COMPUTER INC.
Model: PRIME X370-PRO
Version: Rev X.0x
Serial Number: Suppressed - Personally identifiable information is opt-in only.

Memory:
Usable Memory: 34,289,782,784 (31.9 GiB)
Total Memory: 34,359,738,368 (32.0 GiB)
DIMM: 16.0 GiB - Unknown - F4-3400C16-16GVR
DIMM: 16.0 GiB - Unknown - F4-3400C16-16GVR

Constant: Pi
Algorithm: Chudnovsky Formula
Decimal Digits: 500,000,000
Hexadecimal Digits: Disabled
Computation Mode: Ram Only
Threading Mode: Push Pool -> 16 / ? (randomization on)
Working Memory: 2,774,961,704 (2.58 GiB)
Total Memory: 2,852,729,704 (2.66 GiB)

Start Date: Fri Aug 4 22:57:21 2017
End Date: Fri Aug 4 22:58:04 2017

Total Computation Time: 36.467 seconds
Start-to-End Wall Time: 42.758 seconds

CPU Utilization: 1529.18 % + 0.60 % kernel overhead
Multi-core Efficiency: 95.57 % + 0.04 % kernel overhead

Last Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Dec Counts: {49995279,50000437,50011436,49992409,50005121,49990678,49998820,50000320,5000663 2,49998868}

Binary Hash: Floor(bin * 10^dec) mod (2^61 - 1) = 1095036223966448356

Spot Check: Good through 500,000,000
Timer Sanity Check: Passed
Frequency Sanity Check: Disabled in this version of y-cruncher
Reference Clock: TSC
Reference Clock 0: 3,947,669
Reference Clock 1: 108,902,316
Reference Clock 2: 28,734,236
Is Debugger Present: No
Is Contiguous: Yes
ECC Recovered Errors: 0

Athlonxp

2017-10-11, 10:31:54

Version 0.7.3 Build 9475 (Released: September 14, 2017)

http://www.numberworld.org/y-cruncher/

:)

Athlonxp

2017-11-04, 21:32:29

Version 0.7.4 Build 9477 (Released: October 14, 2017)

http://www.numberworld.org/y-cruncher/

:D

atopisch

2017-11-05, 09:37:13

Die neue Version ist etwas schneller. Ryzen 5 1600 @ 3.8GHz, RAM 2 x 8GB 3333 14-14-14-30
Total Computation Time: 50.891 seconds ( 0.848 minutes )
Start-to-End Wall Time: 54.939 seconds ( 0.916 minutes )

CPU Utilization: 1028.54 % + 0.43 % kernel overhead
Multi-core Efficiency: 85.71 % + 0.04 % kernel overhead

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.4.9477 (Windows/17-ZD1 ~ Yukina)
Processor(s): AMD Ryzen 5 1600 Six-Core Processor
Topology: 12 threads / 6 cores / 1 socket / 1 NUMA node
Physical Memory: 17,179,869,184 (16.0 GiB)
CPU Base Frequency: 3,792,935,456 Hz

IchoTolot

2017-11-05, 12:19:03

Total Computation Time: 34.200 seconds ( 0.570 minutes )
Start-to-End Wall Time: 37.482 seconds ( 0.625 minutes )

CPU Utilization: 779.57 % + 0.09 % kernel overhead
Multi-core Efficiency: 97.45 % + 0.01 % kernel overhead

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.4.9477 (Windows/14-BDW ~ Kurumi)
Processor(s): Intel(R) Core(TM) i7-7700K CPU @ 4.20GHz
Topology: 8 threads / 4 cores / 1 socket / 1 NUMA node
Physical Memory: 34,359,738,368 (32.0 GiB)
CPU Base Frequency: 4,200,000,943 Hz

Annator

2017-11-09, 18:07:12

8700K@5Ghz/4,5Ghz Uncore 16GB 3200 CL14
Total Computation Time: 39.905 seconds ( 0.665 minutes )
Start-to-End Wall Time: 42.926 seconds ( 0.715 minutes )

CPU Utilization: 1031.55 % + 0.51 % kernel overhead
Multi-core Efficiency: 85.96 % + 0.04 % kernel overhead

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.4.9477 (Windows/14-BDW ~ Kurumi)
Processor(s): Intel(R) Core(TM) i7-8700K CPU @ 3.70GHz
Topology: 12 threads / 6 cores / 1 socket / 1 NUMA node
Physical Memory: 17,179,869,184 (16.0 GiB)
CPU Base Frequency: 3,695,993,503 Hz

oOOMadCatOOo

2017-11-09, 19:07:14

7980XE @ 4.5 GHz
AVX2 @ 4.0GHz
AVX512 @ 3.8 GHz
Uncore @ 3.0Ghz
32GB DDR4-3200 CL14

Total Computation Time: 14.234 seconds
Start-to-End Wall Time: 15.783 seconds

CPU Utilization: 3128.38 % + 9.99 % kernel overhead
Multi-core Efficiency: 86.90 % + 0.28 % kernel overhead

Last Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

BlackArchon

2017-11-09, 19:29:22

7980XE @ 4.5 GHz
AVX2 @ 4.0GHz
AVX512 @ 3.8 GHz
Uncore @ 3.0Ghz
32GB DDR4-3200 CL14

...Ich glaube, Alex Yee würde sich über eine komplette Messreihe für die Benchmark-Seite (http://www.numberworld.org/y-cruncher/#Benchmarks) freuen, wenn du die aktuellste Version von y-cruncher verwendest. Ganz unten auf seiner Seite ist die E-Mail-Adresse von ihm. :)

hq-hq

2018-02-04, 22:42:52

8700k@5.2GHz (1.375V Bios, ~1.34V full load, AVX Offset=0), Uncore@4.9GHz
DDR4@3866MHz 16 16 16 30

500.000.000

Total Computation Time: 23.127 seconds
Start-to-End Wall Time: 26.574 seconds

CPU Utilization: 1107.53 % + 1.15 % kernel overhead
Multi-core Efficiency: 92.29 % + 0.10 % kernel overhead

Last Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Benchmark Validation File - DO NOT MODIFY! If you do, it will fail validation.

Validation Version: 1.3

Program: y-cruncher v0.7.5 Build 9480
Tuning: 14-BDW ~ Kurumi

User: None Specified - You can edit this in "Username.txt".

Operating System: Windows 10.0 Build 16299

Processor(s):
Name: Intel(R) Core(TM) i7-8700K CPU @ 3.70GHz
Logical Cores: 12
Physical Cores: 6
Sockets: 1
NUMA Nodes: 1
Base Frequency: 3,695,996,095 Hz

Motherboard:
Manufacturer: Gigabyte Technology Co., Ltd.
Model: Z370 HD3P-CF
Version: x.x
Serial Number: Suppressed - Personally identifiable information is opt-in only.

Memory:
Usable Memory: 17,123,041,280 (15.9 GiB)
Total Memory: 17,179,869,184 (16.0 GiB)
DIMM: 8.00 GiB - 04CD - F4-4133C19-8GTZC
DIMM: 8.00 GiB - 04CD - F4-4133C19-8GTZC

Constant: Pi
Algorithm: Chudnovsky Formula
Decimal Digits: 500,000,000
Hexadecimal Digits: Disabled
Computation Mode: Ram Only
Threading Mode: Push Pool -> 24 / ? (randomization on)
Working Memory: 2,714,405,288 (2.53 GiB)
Total Memory: 2,805,675,752 (2.61 GiB)

Start Date: Sun Feb 4 22:03:22 2018
End Date: Sun Feb 4 22:03:48 2018

Total Computation Time: 23.167 seconds
Start-to-End Wall Time: 26.624 seconds

CPU Utilization: 1114.81 % + 0.54 % kernel overhead
Multi-core Efficiency: 92.90 % + 0.04 % kernel overhead

Last Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Dec Counts: {49995279,50000437,50011436,49992409,50005121,49990678,49998820,50000320,5000663 2,49998868}

Binary Hash: Floor(bin * 10^dec) mod (2^61 - 1) = 1095036223966448356

Spot Check: Good through 500,000,000
Timer Sanity Check: Passed
Frequency Sanity Check: Disabled in this version of y-cruncher
Reference Clock: TSC
Reference Clock 0: 3,609,378
Reference Clock 1: 205,858,973
Reference Clock 2: 24,087,405
Is Debugger Present: No
Is Contiguous: Yes
ECC Recovered Errors: 0

Event Log:
Sun Feb 4 22:03:22 2018 0.004 Reserving Working Memory
Sun Feb 4 22:03:22 2018 0.293 Reserving Working Memory: 2.53 GiB (locked, spread: 100%/1)
Sun Feb 4 22:03:22 2018 0.293 Constructing Twiddle Tables
Sun Feb 4 22:03:22 2018 0.318 Constructing Twiddle Tables: 88.0 MiB (locked, spread: 100%/1)
Sun Feb 4 22:03:22 2018 0.319 Begin Computation
Sun Feb 4 22:03:22 2018 0.319 Summing Series
Sun Feb 4 22:03:22 2018 0.319 Series: ( 34 ) 0.000%
Sun Feb 4 22:03:22 2018 0.320 Series: ( 33 ) 0.002%
Sun Feb 4 22:03:22 2018 0.320 Series: ( 32 ) 0.003%
Sun Feb 4 22:03:22 2018 0.320 Series: ( 31 ) 0.004%
Sun Feb 4 22:03:22 2018 0.321 Series: ( 30 ) 0.006%
Sun Feb 4 22:03:22 2018 0.321 Series: ( 29 ) 0.008%
Sun Feb 4 22:03:22 2018 0.322 Series: ( 28 ) 0.011%
Sun Feb 4 22:03:22 2018 0.323 Series: ( 27 ) 0.015%
Sun Feb 4 22:03:22 2018 0.324 Series: ( 26 ) 0.021%
Sun Feb 4 22:03:22 2018 0.325 Series: ( 25 ) 0.028%
Sun Feb 4 22:03:22 2018 0.327 Series: ( 24 ) 0.039%
Sun Feb 4 22:03:22 2018 0.330 Series: ( 23 ) 0.053%
Sun Feb 4 22:03:22 2018 0.333 Series: ( 22 ) 0.072%
Sun Feb 4 22:03:22 2018 0.337 Series: ( 21 ) 0.099%
Sun Feb 4 22:03:22 2018 0.342 Series: ( 20 ) 0.135%
Sun Feb 4 22:03:22 2018 0.350 Series: ( 19 ) 0.184%
Sun Feb 4 22:03:22 2018 0.359 Series: ( 18 ) 0.252%
Sun Feb 4 22:03:22 2018 0.371 Series: ( 17 ) 0.344%
Sun Feb 4 22:03:22 2018 0.388 Series: ( 16 ) 0.471%
Sun Feb 4 22:03:22 2018 0.412 Series: ( 15 ) 0.643%
Sun Feb 4 22:03:22 2018 0.445 Series: ( 14 ) 0.879%
Sun Feb 4 22:03:22 2018 0.490 Series: ( 13 ) 1.202%
Sun Feb 4 22:03:22 2018 0.552 Series: ( 12 ) 1.643%
Sun Feb 4 22:03:22 2018 0.643 Series: ( 11 ) 2.246%
Sun Feb 4 22:03:23 2018 0.775 Series: ( 10 ) 3.070%
Sun Feb 4 22:03:23 2018 0.962 Series: ( 9 ) 4.196%
Sun Feb 4 22:03:23 2018 1.223 Series: ( 8 ) 5.738%
Sun Feb 4 22:03:23 2018 1.596 Series: ( 7 ) 7.846%
Sun Feb 4 22:03:24 2018 2.098 Series: ( 6 ) 10.732%
Sun Feb 4 22:03:25 2018 2.793 Series: ( 5 ) 14.685%
Sun Feb 4 22:03:26 2018 3.790 Series: ( 4 ) 20.104%
Sun Feb 4 22:03:27 2018 5.195 Series: ( 3 ) 27.543%
Sun Feb 4 22:03:29 2018 7.136 Series: ( 2 ) 37.778%
Sun Feb 4 22:03:32 2018 9.865 Series: ( 1 ) 51.913%
Sun Feb 4 22:03:35 2018 13.645 Series: ( 0 ) 71.591%
Sun Feb 4 22:03:41 2018 19.272 Finishing Series
Sun Feb 4 22:03:41 2018 19.324 Division
Sun Feb 4 22:03:42 2018 20.573 InvSqrt
Sun Feb 4 22:03:43 2018 21.319 Final Multiply
Sun Feb 4 22:03:44 2018 21.780 Base Converting
Sun Feb 4 22:03:45 2018 23.487 Writing Decimal Digits
Sun Feb 4 22:03:48 2018 26.624 End Computation

----

Checksum0: f976401d9ea8a7a8c802333cc19604c94e6ec9d1e43a65ffa9f6ed3880191330d4cbeadc19d64d09 58362ced732c383971a9c316c8d27b198413112bcbbdb455
Checksum1: 4eb11eed2627a3e7371f0180a843e64e18150c5aa3694c50e03b09e2bc227c984bf54ed81b36c92f f15aa2212e3e8f462e7d1dfdeb991a254831cc185aaa0b79

geht bis 190Watt, manchmal hab ich um mein schwachbrüstiges Z370 HD3P Board Angst :freak:

Temp+Watt 62538 (kann ab 69°C instabil werden, etwa ab Wassertemp 30°C)

@Annator, warum ist deiner so langsam? Vermutlich ist deine CPU ins Powerlimit gekracht und hat sich stark runtergetaktet?

GTX1060User

2018-02-21, 22:38:15

AMD Ryzen 7 1700 @ 3,6GHz
DDR4 3200 @ 2933 MHz, Dual Channel, Single RANK

Mit HT

Total Computation Time: 37.858 seconds ( 0.631 minutes )
Start-to-End Wall Time: 41.581 seconds ( 0.693 minutes )

CPU Utilization: 1558.49 % + 0.29 % kernel overhead
Multi-core Efficiency: 97.41 % + 0.02 % kernel overhead

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Ohne HT

Total Computation Time: 41.244 seconds ( 0.687 minutes )
Start-to-End Wall Time: 44.889 seconds ( 0.748 minutes )

CPU Utilization: 780.71 % + 0.34 % kernel overhead
Multi-core Efficiency: 97.59 % + 0.04 % kernel overhead

Last Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,0000

GTX1060User

2018-02-21, 22:55:09

Bitte Löschen ^^ Doppelpost -.-

Athlonxp

2018-09-05, 19:05:21

Version 0.7.6 Build 9484 (Released: August 28, 2018)

http://www.numberworld.org/y-cruncher/version_history.html

http://www.numberworld.org/y-cruncher/

:)

atopisch

2018-09-06, 21:56:37

Ryzen 5 1600 @ 3.8GHz, RAM 2 x 8GB 3200MHz 14-13-13-13-28
Windows 8.1
Program: y-cruncher v0.7.6 Build 9484
Tuning: 17-ZN1 ~ Yukina

Total Computation Time: 47.070 seconds
Start-to-End Wall Time: 48.986 seconds

CPU Utilization: 1114.58 % + 1.10 % kernel overhead
Multi-core Efficiency: 92.88 % + 0.09 % kernel overhead

Last Decimal Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

IchoTolot

2018-09-06, 22:20:38

Start Time: Thu Sep 6 22:18:32 2018
End Time: Thu Sep 6 22:19:08 2018

Total Computation Time: 33.772 seconds ( 0.563 minutes )
Start-to-End Wall Time: 36.317 seconds ( 0.605 minutes )

CPU Utilization: 772.70 % + 0.23 % kernel overhead
Multi-core Efficiency: 96.59 % + 0.03 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.6.9484 (Windows/14-BDW ~ Kurumi)
Processor(s): Intel(R) Core(TM) i7-7700K CPU @ 4.20GHz
Topology: 8 threads / 4 cores / 1 socket / 1 NUMA node
Physical Memory: 34,359,738,368 (32.0 GiB)
CPU Base Frequency: 4,199,991,343 Hz

Validation File: Pi - 20180906-221909.txt

diedl

2018-09-07, 00:33:32

KODLIX AP42 Intel Apollo Lake N4200 Pentium =(Beelink AP 42)
Pentium N4200

RAM: 4 GiB DDR3 800(1600) MHz 15-15-15-34 1T
Win 10 pro 64 17134

Benchmark Validation File - DO NOT MODIFY! If you do, it will fail validation.

Validation Version: 1.3

Program: y-cruncher v0.7.6 Build 9484
Tuning: 08-NHM ~ Ushio

User: None Specified - You can edit this in "N4200.txt".

Operating System: Windows 10.0 Build 17134

Processor(s):
Name: Intel(R) Pentium(R) CPU N4200 @ 2,4 GHz
Logical Cores: 4
Physical Cores: 4
Sockets: 1
NUMA Nodes: 1
Base Frequency: 1,094,394,255 Hz

Motherboard:
Manufacturer: AMI Corporation
Model: Aptio CRB
Version: Default string
Serial Number: Suppressed - Personally identifiable information is opt-in only.

Memory:
Usable Memory: 4,137,058,304 (3.85 GiB)
Total Memory: 4,294,967,296 (4.00 GiB)
DIMM: 2.00 GiB - 0000 -
DIMM: 2.00 GiB - 0000 -

Constant: Pi
Algorithm: Chudnovsky Formula
Decimal Digits: 500,000,000
Hexadecimal Digits: Disabled
Computation Mode: Ram Only
Threading Mode: Push Pool -> 4 / ? (randomization on)
Working Memory: 2,447,922,576 (2.28 GiB)
Total Memory: 2,746,818,320 (2.56 GiB)

Start Date: Fri Sep 7 00:15:05 2018
End Date: Fri Sep 7 00:21:38 2018

Total Computation Time: 388.047 seconds
Start-to-End Wall Time: 392.899 seconds

CPU Utilization: 382.73 % + 0.45 % kernel overhead
Multi-core Efficiency: 95.68 % + 0.11 % kernel overhead

Last Decimal Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

SHA256-dec(500,000,001 - 500,000,100): 8014546a331d8959a7e3b97c8c46a1728f74193425f7908b99e155c501561b5d

Dec Counts: {49995279,50000437,50011436,49992409,50005121,49990678,49998820,50000320,5000663 2,49998868}

Dec Hash: Floor(x * 10^dec) mod (2^61 - 1) = 1095036223966448356

Spot Check: Good through 500,000,000
Timer Sanity Check: Passed
Frequency Sanity Check: Disabled in this version of y-cruncher
Reference Clock: TSC
Reference Clock 0: 1,068,751
Reference Clock 1: 114,891,970
Reference Clock 2: 779,438
Is Debugger Present: No
Is Contiguous: Yes
ECC Recovered Errors: 0
Colors: Yes

Event Log:
Fri Sep 7 00:15:05 2018 0.042 Working Memory
Fri Sep 7 00:15:07 2018 1.808 Working Memory: 2.28 GiB (locked, spread: 100%/1)
Fri Sep 7 00:15:07 2018 1.809 Twiddle Tables
Fri Sep 7 00:15:07 2018 2.413 Twiddle Tables: 286 MiB (locked, spread: 100%/1)
Fri Sep 7 00:15:07 2018 2.463 Begin Computation
Fri Sep 7 00:15:07 2018 2.488 Summing Series
Fri Sep 7 00:15:07 2018 2.510 Series: A ( 16 ) 0.000%
Fri Sep 7 00:15:08 2018 3.481 Series: A ( 15 ) 0.334%
Fri Sep 7 00:15:09 2018 4.421 Series: E ( 14 ) 0.768%
Fri Sep 7 00:15:10 2018 5.347 Series: E ( 13 ) 1.202%
Fri Sep 7 00:15:11 2018 6.295 Series: E ( 12 ) 1.643%
Fri Sep 7 00:15:13 2018 7.852 Series: E ( 11 ) 2.246%
Fri Sep 7 00:15:15 2018 9.910 Series: E ( 10 ) 3.070%
Fri Sep 7 00:15:17 2018 12.599 Series: E ( 9 ) 4.196%
Fri Sep 7 00:15:21 2018 16.456 Series: E ( 8 ) 5.738%
Fri Sep 7 00:15:27 2018 21.849 Series: E ( 7 ) 7.846%
Fri Sep 7 00:15:34 2018 29.430 Series: E ( 6 ) 10.732%
Fri Sep 7 00:15:45 2018 40.228 Series: E ( 5 ) 14.685%
Fri Sep 7 00:16:01 2018 56.236 Series: E ( 4 ) 20.104%
Fri Sep 7 00:16:25 2018 80.397 Series: E ( 3 ) 27.543%
Fri Sep 7 00:16:59 2018 114.006 Series: E ( 2 ) 37.778%
Fri Sep 7 00:17:44 2018 158.945 Series: E ( 1 ) 51.913%
Fri Sep 7 00:18:46 2018 221.206 Series: E ( 0 ) 71.591%
Fri Sep 7 00:20:23 2018 317.974 Finishing Series
Fri Sep 7 00:20:23 2018 318.229 Division
Fri Sep 7 00:20:41 2018 335.970 InvSqrt
Fri Sep 7 00:20:52 2018 347.398 Final Multiply
Fri Sep 7 00:21:01 2018 355.896 Base Converting
Fri Sep 7 00:21:35 2018 390.544 Writing Decimal Digits
Fri Sep 7 00:21:38 2018 392.882 End Computation

----

Checksum0: 2b139fcca3809d0e45e9b81368ed7f189bfa2af9b627158851d1f2a6c45be01e7fd2aee865637d41 9079d911c6b4bb105641f4ebca48d15d71f4d83c5d5a50ab
Checksum1: e1508fc84e72408c9e0b4ef0f6a25a9321a888401e20370ae1e31ee967f26e8775e32fd8fe84abd1 af024fa30637119d3dee04c18923f54bd04693e7ae4ad228

Athlonxp

2018-10-29, 19:44:21

Version 0.7.6 Build 9487 (Released: October August 14, 2018)

http://www.numberworld.org/y-cruncher/version_history.html

http://www.numberworld.org/y-cruncher/

:)

Tyrann

2018-10-29, 21:11:06

Benchmark Validation File - DO NOT MODIFY! If you do, it will fail validation.

Validation Version: 1.3

Program: y-cruncher v0.7.6 Build 9487
Tuning: 11-SNB ~ Hina

User: None Specified - You can edit this in "Username.txt".

Operating System: Windows 10.0 Build 17134

Processor(s):
Name: Intel(R) Core(TM) i7-2600K CPU @ 3.40GHz
Logical Cores: 8
Physical Cores: 4
Sockets: 1
NUMA Nodes: 1
Base Frequency: 3,392,308,224 Hz

Motherboard:
Manufacturer: ASRock
Model: P67 Extreme4
Version:
Serial Number: Suppressed - Personally identifiable information is opt-in only.

Memory:
Usable Memory: 25,729,372,160 (24.0 GiB)
Total Memory: 25,769,803,776 (24.0 GiB)
DIMM: 4.00 GiB - 8394 - 993995
DIMM: 8.00 GiB - Kingston - 9905403-547.A00LF
DIMM: 4.00 GiB - 8394 - 993995
DIMM: 8.00 GiB - Kingston - 9905403-547.A00LF

Constant: Pi
Algorithm: Chudnovsky Formula
Decimal Digits: 500,000,000
Hexadecimal Digits: Disabled
Computation Mode: Ram Only
Threading Mode: Push Pool -> 8 / ? (randomization on)
Working Memory: 3,158,647,424 (2.94 GiB)
Total Memory: 3,342,666,752 (3.11 GiB)

Start Date: Mon Oct 29 21:08:14 2018
End Date: Mon Oct 29 21:09:55 2018

Total Computation Time: 98.435 seconds
Start-to-End Wall Time: 100.542 seconds

CPU Utilization: 771.96 % + 0.16 % kernel overhead
Multi-core Efficiency: 96.49 % + 0.02 % kernel overhead

Last Decimal Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Armaq

2018-10-29, 23:11:14

Processor(s):
Name: AMD Ryzen 7 2700 Eight-Core Processor
Logical Cores: 16
Physical Cores: 8
Sockets: 1
NUMA Nodes: 1
Base Frequency: 3,917,644,352 Hz

Motherboard:
Manufacturer: ASUSTeK COMPUTER INC.
Model: ROG CROSSHAIR VII HERO
Version: Rev 1.xx
Serial Number: Suppressed - Personally identifiable information is opt-in only.

Memory:
Usable Memory: 17,102,282,752 (15.9 GiB)
Total Memory: 17,179,869,184 (16.0 GiB)
DIMM: 8.00 GiB - Unknown - F4-3600C16-8GTZR
DIMM: 8.00 GiB - Unknown - F4-3600C16-8GTZR

Constant: Pi
Algorithm: Chudnovsky Formula
Decimal Digits: 500,000,000
Hexadecimal Digits: Disabled
Computation Mode: Ram Only
Threading Mode: Push Pool -> 16 / ? (randomization on)
Working Memory: 2,664,151,440 (2.48 GiB)
Total Memory: 2,792,302,288 (2.60 GiB)

Start Date: Mon Oct 29 23:08:51 2018
End Date: Mon Oct 29 23:09:30 2018

Total Computation Time: 35.438 seconds
Start-to-End Wall Time: 39.559 seconds

CPU Utilization: 1491.31 % + 1.63 % kernel overhead
Multi-core Efficiency: 93.21 % + 0.10 % kernel overhead

Last Decimal Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Frank1974

2018-10-30, 15:33:38

AMD Ryzen 7 2700X@4GHz, Turbo off
DDR4-3200@3000MHz 16-16-16-36-1T
Windows 10 x64, v1803

Processor(s):
Name: AMD Ryzen 7 2700X Eight-Core Processor
Logical Cores: 16
Physical Cores: 8
Sockets: 1
NUMA Nodes: 1
Base Frequency: 3,992,494,208 Hz

Motherboard:
Manufacturer: ASUSTeK COMPUTER INC.
Model: PRIME X370-PRO
Version: Rev X.0x
Serial Number: Suppressed - Personally identifiable information is opt-in only.

Memory:
Usable Memory: 17,108,471,808 (15.9 GiB)
Total Memory: 17,179,869,184 (16.0 GiB)
DIMM: 8.00 GiB - Unknown - F4-3200C16-8GVKB
DIMM: 8.00 GiB - Unknown - F4-3200C16-8GVKB

Constant: Pi
Algorithm: Chudnovsky Formula
Decimal Digits: 500,000,000
Hexadecimal Digits: Disabled
Computation Mode: Ram Only
Threading Mode: Push Pool -> 16 / ? (randomization on)
Working Memory: 2,664,151,440 (2.48 GiB)
Total Memory: 2,792,302,288 (2.60 GiB)

Start Date: Tue Oct 30 15:24:59 2018
End Date: Tue Oct 30 15:25:34 2018

Total Computation Time: 33.193 seconds
Start-to-End Wall Time: 35.024 seconds

CPU Utilization: 1556.87 % + 0.47 % kernel overhead
Multi-core Efficiency: 97.30 % + 0.03 % kernel overhead

Last Decimal Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

mfg
Frank

hq-hq

2019-01-12, 20:07:16

8700k@5.2GHz (1.375V Bios, ~1.34V full load, AVX Offset=0), Uncore@4.9GHz
DDR4@3866MHz 16 16 16 30

500.000.000

Total Computation Time: 23.127 seconds
Start-to-End Wall Time: 26.574 seconds

CPU Utilization: 1107.53 % + 1.15 % kernel overhead
Multi-core Efficiency: 92.29 % + 0.10 % kernel overhead

Last Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Benchmark Validation File - DO NOT MODIFY! If you do, it will fail validation.

Validation Version: 1.3

Program: y-cruncher v0.7.5 Build 9480
Tuning: 14-BDW ~ Kurumi

User: None Specified - You can edit this in "Username.txt".

Operating System: Windows 10.0 Build 16299

Processor(s):
Name: Intel(R) Core(TM) i7-8700K CPU @ 3.70GHz
Logical Cores: 12
Physical Cores: 6
Sockets: 1
NUMA Nodes: 1
Base Frequency: 3,695,996,095 Hz

Motherboard:
Manufacturer: Gigabyte Technology Co., Ltd.
Model: Z370 HD3P-CF
Version: x.x
Serial Number: Suppressed - Personally identifiable information is opt-in only.

Memory:
Usable Memory: 17,123,041,280 (15.9 GiB)
Total Memory: 17,179,869,184 (16.0 GiB)
DIMM: 8.00 GiB - 04CD - F4-4133C19-8GTZC
DIMM: 8.00 GiB - 04CD - F4-4133C19-8GTZC

Constant: Pi
Algorithm: Chudnovsky Formula
Decimal Digits: 500,000,000
Hexadecimal Digits: Disabled
Computation Mode: Ram Only
Threading Mode: Push Pool -> 24 / ? (randomization on)
Working Memory: 2,714,405,288 (2.53 GiB)
Total Memory: 2,805,675,752 (2.61 GiB)

Start Date: Sun Feb 4 22:03:22 2018
End Date: Sun Feb 4 22:03:48 2018

Total Computation Time: 23.167 seconds
Start-to-End Wall Time: 26.624 seconds

CPU Utilization: 1114.81 % + 0.54 % kernel overhead
Multi-core Efficiency: 92.90 % + 0.04 % kernel overhead

Last Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Dec Counts: {49995279,50000437,50011436,49992409,50005121,49990678,49998820,50000320,5000663 2,49998868}

Binary Hash: Floor(bin * 10^dec) mod (2^61 - 1) = 1095036223966448356

Spot Check: Good through 500,000,000
Timer Sanity Check: Passed
Frequency Sanity Check: Disabled in this version of y-cruncher
Reference Clock: TSC
Reference Clock 0: 3,609,378
Reference Clock 1: 205,858,973
Reference Clock 2: 24,087,405
Is Debugger Present: No
Is Contiguous: Yes
ECC Recovered Errors: 0

Event Log:
Sun Feb 4 22:03:22 2018 0.004 Reserving Working Memory
Sun Feb 4 22:03:22 2018 0.293 Reserving Working Memory: 2.53 GiB (locked, spread: 100%/1)
Sun Feb 4 22:03:22 2018 0.293 Constructing Twiddle Tables
Sun Feb 4 22:03:22 2018 0.318 Constructing Twiddle Tables: 88.0 MiB (locked, spread: 100%/1)
Sun Feb 4 22:03:22 2018 0.319 Begin Computation
Sun Feb 4 22:03:22 2018 0.319 Summing Series
Sun Feb 4 22:03:22 2018 0.319 Series: ( 34 ) 0.000%
Sun Feb 4 22:03:22 2018 0.320 Series: ( 33 ) 0.002%
Sun Feb 4 22:03:22 2018 0.320 Series: ( 32 ) 0.003%
Sun Feb 4 22:03:22 2018 0.320 Series: ( 31 ) 0.004%
Sun Feb 4 22:03:22 2018 0.321 Series: ( 30 ) 0.006%
Sun Feb 4 22:03:22 2018 0.321 Series: ( 29 ) 0.008%
Sun Feb 4 22:03:22 2018 0.322 Series: ( 28 ) 0.011%
Sun Feb 4 22:03:22 2018 0.323 Series: ( 27 ) 0.015%
Sun Feb 4 22:03:22 2018 0.324 Series: ( 26 ) 0.021%
Sun Feb 4 22:03:22 2018 0.325 Series: ( 25 ) 0.028%
Sun Feb 4 22:03:22 2018 0.327 Series: ( 24 ) 0.039%
Sun Feb 4 22:03:22 2018 0.330 Series: ( 23 ) 0.053%
Sun Feb 4 22:03:22 2018 0.333 Series: ( 22 ) 0.072%
Sun Feb 4 22:03:22 2018 0.337 Series: ( 21 ) 0.099%
Sun Feb 4 22:03:22 2018 0.342 Series: ( 20 ) 0.135%
Sun Feb 4 22:03:22 2018 0.350 Series: ( 19 ) 0.184%
Sun Feb 4 22:03:22 2018 0.359 Series: ( 18 ) 0.252%
Sun Feb 4 22:03:22 2018 0.371 Series: ( 17 ) 0.344%
Sun Feb 4 22:03:22 2018 0.388 Series: ( 16 ) 0.471%
Sun Feb 4 22:03:22 2018 0.412 Series: ( 15 ) 0.643%
Sun Feb 4 22:03:22 2018 0.445 Series: ( 14 ) 0.879%
Sun Feb 4 22:03:22 2018 0.490 Series: ( 13 ) 1.202%
Sun Feb 4 22:03:22 2018 0.552 Series: ( 12 ) 1.643%
Sun Feb 4 22:03:22 2018 0.643 Series: ( 11 ) 2.246%
Sun Feb 4 22:03:23 2018 0.775 Series: ( 10 ) 3.070%
Sun Feb 4 22:03:23 2018 0.962 Series: ( 9 ) 4.196%
Sun Feb 4 22:03:23 2018 1.223 Series: ( 8 ) 5.738%
Sun Feb 4 22:03:23 2018 1.596 Series: ( 7 ) 7.846%
Sun Feb 4 22:03:24 2018 2.098 Series: ( 6 ) 10.732%
Sun Feb 4 22:03:25 2018 2.793 Series: ( 5 ) 14.685%
Sun Feb 4 22:03:26 2018 3.790 Series: ( 4 ) 20.104%
Sun Feb 4 22:03:27 2018 5.195 Series: ( 3 ) 27.543%
Sun Feb 4 22:03:29 2018 7.136 Series: ( 2 ) 37.778%
Sun Feb 4 22:03:32 2018 9.865 Series: ( 1 ) 51.913%
Sun Feb 4 22:03:35 2018 13.645 Series: ( 0 ) 71.591%
Sun Feb 4 22:03:41 2018 19.272 Finishing Series
Sun Feb 4 22:03:41 2018 19.324 Division
Sun Feb 4 22:03:42 2018 20.573 InvSqrt
Sun Feb 4 22:03:43 2018 21.319 Final Multiply
Sun Feb 4 22:03:44 2018 21.780 Base Converting
Sun Feb 4 22:03:45 2018 23.487 Writing Decimal Digits
Sun Feb 4 22:03:48 2018 26.624 End Computation

----

Checksum0: f976401d9ea8a7a8c802333cc19604c94e6ec9d1e43a65ffa9f6ed3880191330d4cbeadc19d64d09 58362ced732c383971a9c316c8d27b198413112bcbbdb455
Checksum1: 4eb11eed2627a3e7371f0180a843e64e18150c5aa3694c50e03b09e2bc227c984bf54ed81b36c92f f15aa2212e3e8f462e7d1dfdeb991a254831cc185aaa0b79

geht bis 190Watt, manchmal hab ich um mein schwachbrüstiges Z370 HD3P Board Angst :freak:

Temp+Watt 62538 (kann ab 69°C instabil werden, etwa ab Wassertemp 30°C)

@Annator, warum ist deiner so langsam? Vermutlich ist deine CPU ins Powerlimit gekracht und hat sich stark runtergetaktet?

8700k@5.2GHz, Uncore@4.9GHz DDR4@4133MHz 17 17 17 32

ein klein wenig schneller geworden dank RAM:

Total Computation Time: 22.813 seconds
Start-to-End Wall Time: 24.402 seconds

CPU Utilization: 1117.08 % + 1.23 % kernel overhead
Multi-core Efficiency: 93.09 % + 0.10 % kernel overhead

Last Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Benchmark Validation File - DO NOT MODIFY! If you do, it will fail validation.

Validation Version: 1.3

Program: y-cruncher v0.7.5 Build 9480
Tuning: 14-BDW ~ Kurumi

User: None Specified - You can edit this in "Username.txt".

Operating System: Windows 10.0 Build 17134

Processor(s):
Name: Intel(R) Core(TM) i7-8700K CPU @ 3.70GHz
Logical Cores: 12
Physical Cores: 6
Sockets: 1
NUMA Nodes: 1
Base Frequency: 3,695,995,072 Hz

Motherboard:
Manufacturer: ASRock
Model: Z370 Extreme4
Version:
Serial Number: Suppressed - Personally identifiable information is opt-in only.

Memory:
Usable Memory: 17,105,649,664 (15.9 GiB)
Total Memory: 17,179,869,184 (16.0 GiB)
DIMM: 8.00 GiB - 04CD - F4-4133C19-8GTZC
DIMM: 8.00 GiB - 04CD - F4-4133C19-8GTZC

Constant: Pi
Algorithm: Chudnovsky Formula
Decimal Digits: 500,000,000
Hexadecimal Digits: Disabled
Computation Mode: Ram Only
Threading Mode: Push Pool -> 24 / ? (randomization on)
Working Memory: 2,714,405,288 (2.53 GiB)
Total Memory: 2,805,675,752 (2.61 GiB)

Start Date: Sat Jan 12 19:58:53 2019
End Date: Sat Jan 12 19:59:17 2019

Total Computation Time: 22.813 seconds
Start-to-End Wall Time: 24.402 seconds

CPU Utilization: 1117.08 % + 1.23 % kernel overhead
Multi-core Efficiency: 93.09 % + 0.10 % kernel overhead

Last Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Dec Counts: {49995279,50000437,50011436,49992409,50005121,49990678,49998820,50000320,5000663 2,49998868}

Binary Hash: Floor(bin * 10^dec) mod (2^61 - 1) = 1095036223966448356

Spot Check: Good through 500,000,000
Timer Sanity Check: Passed
Frequency Sanity Check: Disabled in this version of y-cruncher
Reference Clock: TSC
Reference Clock 0: 3,609,376
Reference Clock 1: 203,617,719
Reference Clock 2: 24,024,640
Is Debugger Present: No
Is Contiguous: Yes
ECC Recovered Errors: 0

Event Log:
Sat Jan 12 19:58:53 2019 0.005 Reserving Working Memory
Sat Jan 12 19:58:53 2019 0.493 Reserving Working Memory: 2.53 GiB (locked, spread: 100%/1)
Sat Jan 12 19:58:53 2019 0.493 Constructing Twiddle Tables
Sat Jan 12 19:58:53 2019 0.527 Constructing Twiddle Tables: 88.0 MiB (locked, spread: 100%/1)
Sat Jan 12 19:58:53 2019 0.527 Begin Computation
Sat Jan 12 19:58:53 2019 0.527 Summing Series
Sat Jan 12 19:58:53 2019 0.527 Series: ( 34 ) 0.000%
Sat Jan 12 19:58:53 2019 0.528 Series: ( 33 ) 0.002%
Sat Jan 12 19:58:53 2019 0.528 Series: ( 32 ) 0.003%
Sat Jan 12 19:58:53 2019 0.529 Series: ( 31 ) 0.004%
Sat Jan 12 19:58:53 2019 0.529 Series: ( 30 ) 0.006%
Sat Jan 12 19:58:53 2019 0.529 Series: ( 29 ) 0.008%
Sat Jan 12 19:58:53 2019 0.530 Series: ( 28 ) 0.011%
Sat Jan 12 19:58:53 2019 0.531 Series: ( 27 ) 0.015%
Sat Jan 12 19:58:53 2019 0.532 Series: ( 26 ) 0.021%
Sat Jan 12 19:58:53 2019 0.533 Series: ( 25 ) 0.028%
Sat Jan 12 19:58:53 2019 0.535 Series: ( 24 ) 0.039%
Sat Jan 12 19:58:53 2019 0.537 Series: ( 23 ) 0.053%
Sat Jan 12 19:58:53 2019 0.540 Series: ( 22 ) 0.072%
Sat Jan 12 19:58:53 2019 0.544 Series: ( 21 ) 0.099%
Sat Jan 12 19:58:53 2019 0.549 Series: ( 20 ) 0.135%
Sat Jan 12 19:58:53 2019 0.555 Series: ( 19 ) 0.184%
Sat Jan 12 19:58:53 2019 0.563 Series: ( 18 ) 0.252%
Sat Jan 12 19:58:53 2019 0.575 Series: ( 17 ) 0.344%
Sat Jan 12 19:58:53 2019 0.591 Series: ( 16 ) 0.471%
Sat Jan 12 19:58:53 2019 0.613 Series: ( 15 ) 0.643%
Sat Jan 12 19:58:53 2019 0.646 Series: ( 14 ) 0.879%
Sat Jan 12 19:58:53 2019 0.691 Series: ( 13 ) 1.202%
Sat Jan 12 19:58:53 2019 0.753 Series: ( 12 ) 1.643%
Sat Jan 12 19:58:54 2019 0.844 Series: ( 11 ) 2.246%
Sat Jan 12 19:58:54 2019 0.976 Series: ( 10 ) 3.070%
Sat Jan 12 19:58:54 2019 1.159 Series: ( 9 ) 4.196%
Sat Jan 12 19:58:54 2019 1.420 Series: ( 8 ) 5.738%
Sat Jan 12 19:58:54 2019 1.789 Series: ( 7 ) 7.846%
Sat Jan 12 19:58:55 2019 2.286 Series: ( 6 ) 10.732%
Sat Jan 12 19:58:56 2019 2.970 Series: ( 5 ) 14.685%
Sat Jan 12 19:58:57 2019 3.951 Series: ( 4 ) 20.104%
Sat Jan 12 19:58:58 2019 5.339 Series: ( 3 ) 27.543%
Sat Jan 12 19:59:00 2019 7.250 Series: ( 2 ) 37.778%
Sat Jan 12 19:59:03 2019 9.939 Series: ( 1 ) 51.913%
Sat Jan 12 19:59:06 2019 13.660 Series: ( 0 ) 71.591%
Sat Jan 12 19:59:12 2019 19.227 Finishing Series
Sat Jan 12 19:59:12 2019 19.276 Division
Sat Jan 12 19:59:13 2019 20.477 InvSqrt
Sat Jan 12 19:59:14 2019 21.199 Final Multiply
Sat Jan 12 19:59:14 2019 21.656 Base Converting
Sat Jan 12 19:59:16 2019 23.342 Writing Decimal Digits
Sat Jan 12 19:59:17 2019 24.401 End Computation

----

Checksum0: becd9dbf5390586535571d0c526e8c8774fb46e3fded37bb0170b4656145142335c52c0f12e27664 86882ca5500e3503e0789f3ff24696a6c6dc47fb0a414d64
Checksum1: b5f82b22b7647816a56e7ed8858f26ba19729fe51dd85e62cf1f0e2ac3fd73d3fdf99a4dc8f5ae3a 1c8892f05e9c4b34dcc937c77c7ecccea15e9fba7b8ab88d

die neueste Version vom 10.01.2019 ist noch einen Tick schneller

Total Computation Time: 22.377 seconds
Start-to-End Wall Time: 23.838 seconds

CPU Utilization: 1122.19 % + 0.84 % kernel overhead
Multi-core Efficiency: 93.52 % + 0.07 % kernel overhead

Last Decimal Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Benchmark Validation File - DO NOT MODIFY! If you do, it will fail validation.

Validation Version: 1.3

Program: y-cruncher v0.7.7 Build 9494
Tuning: 14-BDW ~ Kurumi

User: hq-hq

Operating System: Windows 10.0 Build 17134

Processor(s):
Name: Intel(R) Core(TM) i7-8700K CPU @ 3.70GHz
Logical Cores: 12
Physical Cores: 6
Sockets: 1
NUMA Nodes: 1
Base Frequency: 3,696,007,488 Hz

Motherboard:
Manufacturer: ASRock
Model: Z370 Extreme4
Version:
Serial Number: Suppressed - Personally identifiable information is opt-in only.

Memory:
Usable Memory: 17,105,649,664 (15.9 GiB)
Total Memory: 17,179,869,184 (16.0 GiB)
DIMM: 8.00 GiB - 04CD - F4-4133C19-8GTZC
DIMM: 8.00 GiB - 04CD - F4-4133C19-8GTZC

Constant: Pi
Algorithm: Chudnovsky (1989)
Decimal Digits: 500,000,000
Hexadecimal Digits: Disabled
Computation Mode: Ram Only
Threading Mode: Push Pool -> 24 / ? (randomization on)
Working Memory: 2,717,108,840 (2.53 GiB)
Total Memory: 2,819,282,856 (2.63 GiB)

Configuration Dump:
{
Constant : {
Constant : "pi"
Algorithm : "chudnovsky"
}
ComputeSize : {
DecimalDigits : 500000000
EnableHexDigits : "false"
}
Output : {
Path : ""
OutputEnable : "true"
DigitsPerFile : 0
}
OutputVerify : "false"
Mode : "ram"
Parallelism : {
TaskDecomposition : 24
Framework : "pushpool"
WorkerThreads : 0
Randomization : "true"
}
Allocator : {
Allocator : "mmap"
LargePages : "attempt"
LockedPages : "attempt"
}
}

Start Date: Sat Jan 12 20:26:33 2019
End Date: Sat Jan 12 20:26:56 2019

Total Computation Time: 22.377 seconds
Start-to-End Wall Time: 23.838 seconds

CPU Utilization: 1122.19 % + 0.84 % kernel overhead
Multi-core Efficiency: 93.52 % + 0.07 % kernel overhead

Last Decimal Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

SHA256-dec(500,000,001 - 500,000,100): 8014546a331d8959a7e3b97c8c46a1728f74193425f7908b99e155c501561b5d

Dec Counts: {49995279,50000437,50011436,49992409,50005121,49990678,49998820,50000320,5000663 2,49998868}

Dec Hash: Floor(|x| * 10^dec) mod (2^61 - 1) = 1095036223966448356

Spot Check: Good through 500,000,000
Timer Sanity Check: Passed
Frequency Sanity Check: Disabled in this version of y-cruncher
Reference Clock: TSC
Reference Clock 0: 3,609,382
Reference Clock 1: 203,603,621
Reference Clock 2: 24,389,008
Is Debugger Present: No
Is Contiguous: Yes
ECC Recovered Errors: 0
Colors: Yes

Event Log:
Sat Jan 12 20:26:33 2019 0.006 Working Memory
Sat Jan 12 20:26:33 2019 0.510 Working Memory: 2.53 GiB (locked, spread: 100%/1)
Sat Jan 12 20:26:33 2019 0.510 Twiddle Tables
Sat Jan 12 20:26:33 2019 0.544 Twiddle Tables: 98.0 MiB (locked, spread: 100%/1)
Sat Jan 12 20:26:33 2019 0.545 Begin Computation
Sat Jan 12 20:26:33 2019 0.545 Series CommonP2B3... 35,256,847 terms (Expansion Factor = 2.636)
Sat Jan 12 20:26:33 2019 0.545 Series: A ( 12 ) 0.000%
Sat Jan 12 20:26:33 2019 0.694 Series: A ( 11 ) 1.231%
Sat Jan 12 20:26:33 2019 0.906 Series: E ( 10 ) 2.713%
Sat Jan 12 20:26:34 2019 1.134 Series: E ( 9 ) 4.196%
Sat Jan 12 20:26:34 2019 1.387 Series: E ( 8 ) 5.738%
Sat Jan 12 20:26:34 2019 1.754 Series: E ( 7 ) 7.846%
Sat Jan 12 20:26:35 2019 2.249 Series: E ( 6 ) 10.732%
Sat Jan 12 20:26:35 2019 2.915 Series: E ( 5 ) 14.685%
Sat Jan 12 20:26:36 2019 3.884 Series: E ( 4 ) 20.104%
Sat Jan 12 20:26:38 2019 5.283 Series: E ( 3 ) 27.543%
Sat Jan 12 20:26:40 2019 7.216 Series: E ( 2 ) 37.778%
Sat Jan 12 20:26:42 2019 9.757 Series: E ( 1 ) 51.913%
Sat Jan 12 20:26:46 2019 13.353 Series: E ( 0 ) 71.591%
Sat Jan 12 20:26:51 2019 18.772 Finishing Series
Sat Jan 12 20:26:51 2019 18.821 Large Division
Sat Jan 12 20:26:53 2019 20.003 InvSqrt(10005)...
Sat Jan 12 20:26:53 2019 20.761 Large Multiply
Sat Jan 12 20:26:54 2019 21.222 Base Converting
Sat Jan 12 20:26:55 2019 22.923 Writing Decimal Digits
Sat Jan 12 20:26:56 2019 23.838 End Computation

----

Checksum0: 48865271e3e4518c8c20648af1b79ac9cb9bd80cc8565456539002fdd2bacb8f22aee98bd8cd7f74 7423406cf97068ddd9ddb5bb952585058d09cb64cb09ab4d
Checksum1: 494325e32bb53dca2b58c153eb481556172eef4a8276da41c6b4b586cf46ae33b4f0f8cd9b85e0da 93f8946b364878ec03a2ae73942a5801e1b5e50fc8e4007b

Darkman.X

2019-01-12, 22:05:50

Keine Ahnung wie vergleichbar die Versionen untereinander sind.

Damals (Version 0.6.9.9464):

i7-5930K @ 4 GHz
4 x 4 GiB DDR4-2666 (15-15-15-35-2T-1.2V)

Computation Time: 42.783 seconds
Total Time: 47.097 seconds

CPU Utilization: 1026.7 %
Multi-core Efficiency: 85.5586 %

Heute:
i9-9900K @ Stock (4,7 GHz All-Core) ; AVX-Offset=0
4 x 8 GiB DDR4-3600 (16-16-16-36-2T)

Computation Time: 19.863 seconds
Total Time: 21.314 seconds

CPU Utilization: 1569.47 %
Multi-core Efficiency: 98.09 %

Benchmark Validation File - DO NOT MODIFY! If you do, it will fail validation.

Validation Version: 1.3

Program: y-cruncher v0.7.7 Build 9494
Tuning: 14-BDW ~ Kurumi

User: Darkman.X (3DCenter-Forum)

Operating System: Windows 10.0 Build 17763

Processor(s):
Name: Intel(R) Core(TM) i9-9900K CPU @ 3.60GHz
Logical Cores: 16
Physical Cores: 8
Sockets: 1
NUMA Nodes: 1
Base Frequency: 3,600,012,224 Hz

Motherboard:
Manufacturer: ASUSTeK COMPUTER INC.
Model: ROG MAXIMUS XI HERO
Version: Rev 1.xx
Serial Number: Suppressed - Personally identifiable information is opt-in only.

Memory:
Usable Memory: 34,272,702,464 (31.9 GiB)
Total Memory: 34,359,738,368 (32.0 GiB)
DIMM: 8.00 GiB - G-Skill - F4-3600C16-8GTZR
DIMM: 8.00 GiB - G-Skill - F4-3600C16-8GTZR
DIMM: 8.00 GiB - G-Skill - F4-3600C16-8GTZR
DIMM: 8.00 GiB - G-Skill - F4-3600C16-8GTZR

Constant: Pi
Algorithm: Chudnovsky (1989)
Decimal Digits: 500,000,000
Hexadecimal Digits: Disabled
Computation Mode: Ram Only
Threading Mode: Push Pool -> 16 / ? (randomization on)
Working Memory: 2,657,207,184 (2.47 GiB)
Total Memory: 2,759,381,200 (2.57 GiB)

Configuration Dump:
{
Constant : {
Constant : "pi"
Algorithm : "chudnovsky"
}
ComputeSize : {
DecimalDigits : 500000000
EnableHexDigits : "false"
}
Output : {
Path : ""
OutputEnable : "true"
DigitsPerFile : 0
}
OutputVerify : "false"
Mode : "ram"
Parallelism : {
TaskDecomposition : 16
Framework : "pushpool"
WorkerThreads : 0
Randomization : "true"
}
Allocator : {
Allocator : "mmap"
LargePages : "attempt"
LockedPages : "attempt"
}
}

Start Date: Sat Jan 12 23:26:06 2019
End Date: Sat Jan 12 23:26:27 2019

Total Computation Time: 19.863 seconds
Start-to-End Wall Time: 21.314 seconds

CPU Utilization: 1569.47 % + 0.47 % kernel overhead
Multi-core Efficiency: 98.09 % + 0.03 % kernel overhead

Last Decimal Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

SHA256-dec(500,000,001 - 500,000,100): 8014546a331d8959a7e3b97c8c46a1728f74193425f7908b99e155c501561b5d

Dec Counts: {49995279,50000437,50011436,49992409,50005121,49990678,49998820,50000320,5000663 2,49998868}

Dec Hash: Floor(|x| * 10^dec) mod (2^61 - 1) = 1095036223966448356

Spot Check: Good through 500,000,000
Timer Sanity Check: Passed
Frequency Sanity Check: Disabled in this version of y-cruncher
Reference Clock:
Reference Clock 0: 10,000,000
Reference Clock 1: 186,061,245
Reference Clock 2: 22,417,068
Is Debugger Present: No
Is Contiguous: Yes
ECC Recovered Errors: 0
Colors: Yes

Event Log:
Sat Jan 12 23:26:06 2019 0.009 Working Memory
Sat Jan 12 23:26:06 2019 0.332 Working Memory: 2.48 GiB (locked, 2.00 MiB pages, spread: 100%/1)
Sat Jan 12 23:26:06 2019 0.333 Twiddle Tables
Sat Jan 12 23:26:06 2019 0.361 Twiddle Tables: 98.0 MiB (locked, 2.00 MiB pages, spread: 100%/1)
Sat Jan 12 23:26:06 2019 0.361 Begin Computation
Sat Jan 12 23:26:06 2019 0.362 Series CommonP2B3... 35,256,847 terms (Expansion Factor = 2.636)
Sat Jan 12 23:26:06 2019 0.362 Series: A ( 15 ) 0.000%
Sat Jan 12 23:26:06 2019 0.366 Series: A ( 14 ) 0.023%
Sat Jan 12 23:26:06 2019 0.443 Series: A ( 13 ) 0.763%
Sat Jan 12 23:26:06 2019 0.529 Series: E ( 12 ) 1.504%
Sat Jan 12 23:26:06 2019 0.620 Series: E ( 11 ) 2.246%
Sat Jan 12 23:26:06 2019 0.727 Series: E ( 10 ) 3.070%
Sat Jan 12 23:26:07 2019 0.877 Series: E ( 9 ) 4.196%
Sat Jan 12 23:26:07 2019 1.088 Series: E ( 8 ) 5.738%
Sat Jan 12 23:26:07 2019 1.387 Series: E ( 7 ) 7.846%
Sat Jan 12 23:26:08 2019 1.803 Series: E ( 6 ) 10.732%
Sat Jan 12 23:26:08 2019 2.378 Series: E ( 5 ) 14.685%
Sat Jan 12 23:26:09 2019 3.234 Series: E ( 4 ) 20.104%
Sat Jan 12 23:26:10 2019 4.436 Series: E ( 3 ) 27.543%
Sat Jan 12 23:26:12 2019 6.118 Series: E ( 2 ) 37.778%
Sat Jan 12 23:26:14 2019 8.347 Series: E ( 1 ) 51.913%
Sat Jan 12 23:26:17 2019 11.552 Series: E ( 0 ) 71.591%
Sat Jan 12 23:26:22 2019 16.357 Finishing Series
Sat Jan 12 23:26:22 2019 16.414 Large Division
Sat Jan 12 23:26:23 2019 17.541 InvSqrt(10005)...
Sat Jan 12 23:26:24 2019 18.268 Large Multiply
Sat Jan 12 23:26:24 2019 18.699 Base Converting
Sat Jan 12 23:26:26 2019 20.227 Writing Decimal Digits
Sat Jan 12 23:26:27 2019 21.313 End Computation

----

Checksum0: 603f4adb0062529700ab2d40c2c1cfcce59e5153c3ef27e59a7ea344243efb19d55fffba8433c713 b86f46e02275c18a4f3594a1f91f5d1ee6b6da132edccc0c
Checksum1: 2318a2f021bd4cb040afd331363e38d6a9b0c6efa66d22e30d193d3b40d885baf4b2bf57f79e8e26 0295c2f1dfa0ff325b216760ca2850b71155c5d300314e40

Athlonxp

2019-01-28, 21:22:35

January 23, 2019 v0.7.7.9495

Windows + Linux

Fixes:

Partial work-around for system error code (1453) which may happen while writing digits at the end of a large computation on systems with very little memory.
Improved error message for error code 1453 to hint at possible low memory situation.
The Gamma(1/4) digit file should now properly decompress on non-English locales.
Errors when loading custom formula files are now handled more consistently.
Error messages from simultaneous swap file errors will not overlap as badly as before.

Thanks to 鲍东方 for reporting several of these.

http://www.numberworld.org/y-cruncher/

:)

Athlonxp

2019-03-02, 10:58:14

Version 0.7.7 Build 9498 (Released: February 24, 2019)

February 24, 2019 v0.7.7.9498

Windows + Linux

Fixes:

P2 - Fixed a regression in v0.7.7.9497 where one of the many bugfixes triggered a compiler optimizer bug in VS2015 that would sometimes cause the relevant binaries to incorrectly calculate memory sizes. This is significant because it had a small potential to produce a computation plan that could not be finished. Bugs like this are normally caught during the extensive QA testing phase prior to a feature release. But these tests are not rerun for patch releases.
P4 - Fixed a crash in some low memory situations involving the swap files.
P4 - Fixed some issues with the RAID-3 functionality.
P5 - When the program crashes on mulitple threads simultaneously, the error and mini-dump messages are no longer overlapping.
P5 - Fixed multiple minor UI bugs.
P5 - The time limit in the stress-tester has been capped to 1 million seconds.
P3 - Fixed an alignment issue in some internal functions.
P5 - Fixed a couple minor UI bugs in the core selector menu of the stress tester.
P5 - Fixed a bug in the I/O benchmark when the bytes/seek is greater than the working memory.
P5 - Fixed a minor UI bug in the Digit Viewer.
P5 - Fixed an issue with running a stress-test from a configuration file with invalid core numbers.
P5 - Fixed an issue where custom formula labels weren't properly being sanitized.

February 16, 2019 v0.7.7.9497

Windows + Linux

Fixes:

P3 - Fixed an issue where a short number can error the program. This is only possible to hit from the custom formulas.
P5 - Fixed an out-of-date warning for extremely slow series.
P5 - Fixed a bug in the Euler-Mascheroni Constant that may cause it to display an incorrect value for the disk usage.
P5 - The length limit for custom formula strings now counts Unicode code points instead of UTF-8 code-units.
P4 - When running a swap mode computation from the command line, the "bytes/seek" parameter wouldn't auto-update when the swap configuration is set.
P5 - Fixed an issue where certain invalid UTF-8 sequences will cause y-cruncher to hang.
P3 - Fixed some more BufferTooSmallException errors in the custom formulas.
P3 - Fixed a spurious error in Newton Method implementations that can only be hit with custom formulas.
P3 - Fixed an issue with SeriesBinaryBBP for large power coefficients.
P4 - Fixed a bug in the RAID-3 quick configure.

February 2, 2019 v0.7.7.9496

Windows + Linux

Fixes:

P5 - Removed some extraneous warnings for unusual series and extremely large computations.
P4 - Fixed a crash in the I/O benchmark when using a very small amount of memory.
P3 - Fixed a bug in the custom formulas that can cause a BufferTooSmallException.

http://www.numberworld.org/y-cruncher

;)

Athlonxp

2019-03-26, 17:24:21

Version 0.7.7 Build 9499 (Released: October March 10, 2019)

March 10, 2019 v0.7.7.9499

Windows + Linux

Fixes:

P5 - Removed an outdated message about a million digits being the minimum.
P3 - Fixed an issue with the RAID3 after marking a drive as failed.
P4 - Fixed an issue where the program cannot immediately recover from a drive failure in RAID3 while renaming checkpoint files.
P5 - Fixed some incorrect error messages for certain file IO errors.
P4 - Fixed a crash in the I/O benchmark when using a large task decomposition for some situations.
P3 - Fixed an issue in the BBP digit extractor with a very large number of threads.
P5 - Fixed some issues with loading invalid configuration files.
P3 - Fixed a corner-case bug for some Newton's Method iterations.
P5 - Fixed a minor bug with invalid input handling for command line arguments.
P3 - Fixed a crash in Swap Mode for some custom formulas.
P5 - The year for the Chudnovsky formula has been changed to 1988. The original year (1989) was the wrong year.
P5 - Fixed a typo in Ramanujan's formula for Pi.
P4 - Fixed an issue where some swap mode computations over-estimate their required disk usage.
P3 - Fixed an issue where some custom formula functions use more disk than they are supposed to in Swap Mode.

鲍东方 found all but the last 5 on this list.

Other:

Added support for a new syntax for the custom formula Scope function that preserves ordering through JSON serialization.

http://www.numberworld.org/y-cruncher

;)

atopisch

2019-07-17, 21:35:22

Ryzen 7 3700X ohne Turbo @3.6GHz 2x8GB RAM@3200Mhz CL14

Total Computation Time: 23.451 seconds ( 0.391 minutes )
Start-to-End Wall Time: 24.704 seconds ( 0.412 minutes )

CPU Utilization: 1461.62 % + 0.40 % kernel overhead
Multi-core Efficiency: 91.35 % + 0.02 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.7.9501 (Windows/17-ZN1 ~ Yukina)
Processor(s): AMD Ryzen 7 3700X 8-Core Processor
Topology: 16 threads / 8 cores / 1 socket / 1 NUMA node
Physical Memory: 17,179,869,184 (16.0 GiB)
CPU Base Frequency: 3,593,349,389 Hz

Tralalak

2020-04-18, 12:52:58

AMD FX-8300 3.3GHz @ Turbo ON and 2x 8GB DDR3 dual-channel

https://i.imgur.com/EYkU9bp.jpg

Achill

2020-04-19, 00:16:06

3900X@Defaults mit PBO=off und DDR4-3733@16-16-16-16-32-48-294-CR1 @1.45V

Jemand eine Ahnung wie man den "kernel overhead" einordnen soll und warum dieser bei mir so hoch ist?

Start Time: Sun Apr 19 00:13:54 2020
End Time: Sun Apr 19 00:14:10 2020

Total Computation Time: 14.790 seconds ( 0.246 minutes )
Start-to-End Wall Time: 15.431 seconds ( 0.257 minutes )

CPU Utilization: 2135.42 % + 6.66 % kernel overhead
Multi-core Efficiency: 88.98 % + 0.28 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.8.9506 (Windows/19-ZN2 ~ Kagari)
Processor(s): AMD Ryzen 9 3900X 12-Core Processor
Topology: 24 threads / 12 cores / 1 socket / 1 NUMA node
Physical Memory: 34,359,738,368 (32.0 GiB)
CPU Base Frequency: 3,800,015,808 Hz

atopisch

2020-04-19, 08:28:22

@Achill: Wird wohl je höher ausfallen, je mehr Kerne im Spiel sind.

Mit der aktuellen Version 0.7.8.9506 wird eine neue Version für Zen2 genutzt: 19-ZN2 ~ Kagari.

Mit der 0.7.8.9503 hat er 17-ZN1 ~ Yukina genutzt. Damit war ich bei:

Total Computation Time: 19.121 seconds
Start-to-End Wall Time: 20.198 seconds

CPU Utilization: 1538.81 % + 1.96 % kernel overhead
Multi-core Efficiency: 96.18 % + 0.12 % kernel overhead

Start Time: Sun Apr 19 08:22:54 2020
End Time: Sun Apr 19 08:23:13 2020

Total Computation Time: 18.480 seconds ( 0.308 minutes )
Start-to-End Wall Time: 19.606 seconds ( 0.327 minutes )

CPU Utilization: 1547.63 % + 2.71 % kernel overhead
Multi-core Efficiency: 96.73 % + 0.17 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.8.9506 (Windows/19-ZN2 ~ Kagari)
Processor(s): AMD Ryzen 7 3700X 8-Core Processor
Topology: 16 threads / 8 cores / 1 socket / 1 NUMA node
Physical Memory: 17,179,869,184 (16.0 GiB)
CPU Base Frequency: 4,000,234,127 Hz

Tralalak

2020-04-19, 10:35:10

Intel Core i5 1035G1 and 1x 8GB SO-DIMM DDR4

https://i.imgur.com/xYGpFjL.jpg

Tralalak

2020-04-21, 16:51:58

Intel Core i5-1035G1 @ 1.00GHz and 16GB (2x 8GB) SO-DIMM DDR4

https://i.imgur.com/xkVCSqI.jpg

hq-hq

2021-01-10, 22:36:40

5800x 105Watt TDP, Curve -30, FCLK 1933MHz, RAM 3866MHz Cl 15 16 16 32

Start Date: Sun Jan 10 22:16:50 2021
End Date: Sun Jan 10 22:17:06 2021

Total Computation Time: 15.524 seconds
Start-to-End Wall Time: 16.073 seconds

CPU Utilization: 1561.17 % + 1.51 % kernel overhead
Multi-core Efficiency: 97.57 % + 0.09 % kernel overhead

Last Decimal Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

mit Curve so 80°C ohne Curve geht die CPU bis 90°C hoch und ist etwas langsamer dafür ist der Takt konstanter bei ca. 4475MHz, mit -30Curve zappelt der wie blöde

Start Date: Sun Jan 10 22:22:52 2021
End Date: Sun Jan 10 22:23:09 2021

Total Computation Time: 15.987 seconds
Start-to-End Wall Time: 16.552 seconds

CPU Utilization: 1560.30 % + 1.76 % kernel overhead
Multi-core Efficiency: 97.52 % + 0.11 % kernel overhead

Last Decimal Digits:
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

labecula

2021-01-11, 14:10:18

Jetzt würde ich ja schon gerne mal einen Apple M1 daran nativ ackern lassen wollen. Nur mal um zu sehen wie er abseits der App-Norm zurecht kommt und es bringt... oder eben nicht.

Nuon

2021-01-11, 20:04:36

R9 5900X@default, 32GB3200@3600 18-21-21-39, kagari.exe
Start Time: Mon Jan 11 19:51:54 2021
End Time: Mon Jan 11 19:52:10 2021

Total Computation Time: 14.615 seconds ( 0.244 minutes )
Start-to-End Wall Time: 15.288 seconds ( 0.255 minutes )

CPU Utilization: 2213.65 % + 12.08 % kernel overhead
Multi-core Efficiency: 92.24 % + 0.50 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000
der kernel overhead ist bei mir ganz schön groß :eek:

Achill

2021-01-14, 10:25:33

Neu:

Ryzen 5950X, PBO@142W PPT, IF@1866MHz, Curve.Opt per Core von 0 bis -15
DDR4-3733@16-17-16-16-34-50-485-CR1 @1.37

Start Time: Thu Jan 14 10:22:32 2021
End Time: Thu Jan 14 10:22:45 2021

Total Computation Time: 12.186 seconds ( 0.203 minutes )
Start-to-End Wall Time: 12.748 seconds ( 0.212 minutes )

CPU Utilization: 3049.55 % + 7.95 % kernel overhead
Multi-core Efficiency: 95.30 % + 0.25 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.8.9507 (Windows/19-ZN2 ~ Kagari)
Processor(s): AMD Ryzen 9 5950X 16-Core Processor
Topology: 32 threads / 16 cores / 1 socket / 1 NUMA node
Physical Memory: 34,359,738,368 (32.0 GiB)
CPU Base Frequency: 3,400,034,271 Hz

Alt:
3900X@Defaults mit PBO=off und DDR4-3733@16-16-16-16-32-48-294-CR1 @1.45V

Jemand eine Ahnung wie man den "kernel overhead" einordnen soll und warum dieser bei mir so hoch ist?

Start Time: Sun Apr 19 00:13:54 2020
End Time: Sun Apr 19 00:14:10 2020

Total Computation Time: 14.790 seconds ( 0.246 minutes )
Start-to-End Wall Time: 15.431 seconds ( 0.257 minutes )

CPU Utilization: 2135.42 % + 6.66 % kernel overhead
Multi-core Efficiency: 88.98 % + 0.28 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.8.9506 (Windows/19-ZN2 ~ Kagari)
Processor(s): AMD Ryzen 9 3900X 12-Core Processor
Topology: 24 threads / 12 cores / 1 socket / 1 NUMA node
Physical Memory: 34,359,738,368 (32.0 GiB)
CPU Base Frequency: 3,800,015,808 Hz

Tyrann

2022-01-30, 21:19:30

i7-4765T @ 3GHz
16GB DDR3 1600MHz
kernel 5.16.0-arch1-1

https://www.forum-3dcenter.org/vbulletin/attachment.php?attachmentid=78257&stc=1&d=1643573834

Ryzen 5 3600
https://www.forum-3dcenter.org/vbulletin/attachment.php?attachmentid=78258&stc=1&d=1643576482

BeetleatWar1977

2022-01-30, 22:11:16

Neu:

Ryzen 5950X, PBO@142W PPT, IF@1866MHz, Curve.Opt per Core von 0 bis -15
DDR4-3733@16-17-16-16-34-50-485-CR1 @1.37

Start Time: Thu Jan 14 10:22:32 2021
End Time: Thu Jan 14 10:22:45 2021

Total Computation Time: 12.186 seconds ( 0.203 minutes )
Start-to-End Wall Time: 12.748 seconds ( 0.212 minutes )

CPU Utilization: 3049.55 % + 7.95 % kernel overhead
Multi-core Efficiency: 95.30 % + 0.25 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.8.9507 (Windows/19-ZN2 ~ Kagari)
Processor(s): AMD Ryzen 9 5950X 16-Core Processor
Topology: 32 threads / 16 cores / 1 socket / 1 NUMA node
Physical Memory: 34,359,738,368 (32.0 GiB)
CPU Base Frequency: 3,400,034,271 Hz

Alt:

Ich hätte gedacht der Abstand ist größer......

Begin Computation:

Series CommonP2B3... 35,256,847 terms (Expansion Factor = 2.636)
Time: 10.665 seconds ( 0.178 minutes )
Large Division...
Time: 0.604 seconds ( 0.010 minutes )
InvSqrt(10005)...
Time: 0.400 seconds ( 0.007 minutes )
Large Multiply...
Time: 0.250 seconds ( 0.004 minutes )

Pi: 11.924 seconds ( 0.199 minutes )

Base Converting:
Time: 0.876 seconds ( 0.015 minutes )
Writing Decimal Digits:
Time: 0.327 seconds ( 0.005 minutes )

Start Time: Sun Jan 30 22:08:11 2022
End Time: Sun Jan 30 22:08:25 2022

Total Computation Time: 12.801 seconds ( 0.213 minutes )
Start-to-End Wall Time: 13.930 seconds ( 0.232 minutes )

CPU Utilization: 2024.19 % + 49.19 % kernel overhead
Multi-core Efficiency: 84.34 % + 2.05 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.8.9507 (Windows/19-ZN2 ~ Kagari)
Processor(s): AMD Ryzen 9 5900X 12-Core Processor
Topology: 24 threads / 12 cores / 1 socket / 1 NUMA node
Physical Memory: 34,359,738,368 (32.0 GiB)
CPU Base Frequency: 3,700,047,952 Hz

Athlonxp

2022-03-14, 11:23:47

Version 0.7.9 Build 9509 (Released: March 14, 2022)

Changes:

Added 20-ZN3, a new binary tuned for AMD Zen 3. Depending on your system and configuration, it may or may not actually be faster than 18-ZN2. You will have to experiment.

The 18-CNL binary has now been retuned for Intel Tiger Lake. It will still run on Cannon Lake since it doesn't use any new instructions.

The menu and configurations for digit output have been revamped to allow for more output formats in the future. For now, the only new setting is that you can enable/disable the use of raw I/O for digit output.

Fixed an issue in an upcoming version of Windows where multiple processor groups can be assigned to the same NUMA node.

Removed the 00-x86 binary as it is well outdated and bloating the download sizes.

All binaries have been retuned to reduce memory footprint at the cost of more computation. Performance changes can be in either direction (better or worse).

Compilers and libraries have been fast-forward by 2 years since this project went on hiatus.

This release has only been lightly tested.

http://www.numberworld.org/y-cruncher/

:D

Athlonxp

2022-06-20, 00:53:22

Version 0.7.9 Build 9510 (Released: June 19, 2022)

Fixes:

Fixed the SFT stress-test not being invokable from the command line.
Fixed config saving not working.
Computation limit has been increased to 200 trillion digits.
Spot-check files have been updated with the latest records.
Added a new custom formula for Catalan's constant by Jorge Zuniga.
20-ZN3 is no longer automatically selected due to unexpectedly poor tuning.

http://www.numberworld.org/y-cruncher

:D

Athlonxp

2022-09-01, 12:00:53

Version 0.7.10 Build 9513 (Released: August 31, 2022)

Windows + Linux
New Features:

Added 22-ZN4, a new binary optimized for AMD Zen4 with AVX512.
This 18-CNL and 22-ZN4 Linux binaries in this release have not been tested.

http://www.numberworld.org/y-cruncher

:D

Achill

2022-09-01, 12:42:35

Version 0.7.10 Build 9513 (Released: August 31, 2022)

http://www.numberworld.org/y-cruncher

:D

Für den 5800X3D wird leider automatisch die Zen2 binary gewählt (19-ZN2 ~ Kagari.exe) .. :/

SC:
Total Computation Time: 123.701 seconds ( 2.062 minutes )
Start-to-End Wall Time: 124.432 seconds ( 2.074 minutes )

Total Computation Time: 123.701 seconds ( 2.062 minutes )
Start-to-End Wall Time: 124.432 seconds ( 2.074 minutes )

CPU Utilization: 99.86 % + 0.00 % kernel overhead
Multi-core Efficiency: 6.24 % + 0.00 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.10.9513 (Windows/19-ZN2 ~ Kagari)
Processor(s): AMD Ryzen 7 5800X3D 8-Core Processor
Topology: 16 threads / 8 cores / 1 socket / 1 NUMA node
Physical Memory: 68,719,476,736 (64.0 GiB)
CPU Base Frequency: 3,400,008,160 Hz

---

MC:
Total Computation Time: 16.301 seconds ( 0.272 minutes )
Start-to-End Wall Time: 16.810 seconds ( 0.280 minutes )

Total Computation Time: 16.301 seconds ( 0.272 minutes )
Start-to-End Wall Time: 16.810 seconds ( 0.280 minutes )

CPU Utilization: 1530.12 % + 1.15 % kernel overhead
Multi-core Efficiency: 95.63 % + 0.07 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.10.9513 (Windows/19-ZN2 ~ Kagari)
Processor(s): AMD Ryzen 7 5800X3D 8-Core Processor
Topology: 16 threads / 8 cores / 1 socket / 1 NUMA node
Physical Memory: 68,719,476,736 (64.0 GiB)
CPU Base Frequency: 3,400,010,336 Hz

---

Mit der Zen3 binary (20-ZN3 ~ Yuzuki.exe) ist das Ergebnis:

MC:
Total Computation Time: 15.870 seconds ( 0.265 minutes )
Start-to-End Wall Time: 16.392 seconds ( 0.273 minutes )

Total Computation Time: 15.870 seconds ( 0.265 minutes )
Start-to-End Wall Time: 16.392 seconds ( 0.273 minutes )

CPU Utilization: 1526.83 % + 0.69 % kernel overhead
Multi-core Efficiency: 95.43 % + 0.04 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.10.9513 (Windows/20-ZN3 ~ Yuzuki)
Processor(s): AMD Ryzen 7 5800X3D 8-Core Processor
Topology: 16 threads / 8 cores / 1 socket / 1 NUMA node
Physical Memory: 68,719,476,736 (64.0 GiB)
CPU Base Frequency: 3,400,004,896 Hz

Saugbär

2022-09-02, 16:45:31

Der 5800X3D enttäuscht gerade im SC Test ein wenig.
Ein 7800X3D mit AVX512-(F/CD/VL/BW/DQ/IFMA/VBMI/VBMI2/GFNI)könnte das Blatt jedoch wenden.

11th Gen Intel(R) Core(TM) i7-11800H
SC:
Total Computation Time: 91.191 seconds ( 1.520 minutes )
Start-to-End Wall Time: 92.195 seconds ( 1.537 minutes )

Start Time: Fri Sep 2 15:55:36 2022
End Time: Fri Sep 2 15:57:09 2022

Total Computation Time: 91.191 seconds ( 1.520 minutes )
Start-to-End Wall Time: 92.195 seconds ( 1.537 minutes )

CPU Utilization: 99.88 % + 0.00 % kernel overhead
Multi-core Efficiency: 6.24 % + 0.00 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.10.9513 (Windows/18-CNL ~ Shinoa)
Processor(s): 11th Gen Intel(R) Core(TM) i7-11800H @ 2.30GHz
Topology: 16 threads / 8 cores / 1 socket / 1 NUMA node
Physical Memory: 34,359,738,368 (32.0 GiB)
CPU Base Frequency: 2,304,005,728 Hz

MC:
Total Computation Time: 16.849 seconds ( 0.281 minutes )
Start-to-End Wall Time: 17.564 seconds ( 0.293 minutes )

Start Time: Fri Sep 2 16:05:17 2022
End Time: Fri Sep 2 16:05:34 2022

Total Computation Time: 16.849 seconds ( 0.281 minutes )
Start-to-End Wall Time: 17.564 seconds ( 0.293 minutes )

CPU Utilization: 1507.44 % + 2.87 % kernel overhead
Multi-core Efficiency: 94.22 % + 0.18 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.7.10.9513 (Windows/18-CNL ~ Shinoa)
Processor(s): 11th Gen Intel(R) Core(TM) i7-11800H @ 2.30GHz
Topology: 16 threads / 8 cores / 1 socket / 1 NUMA node
Physical Memory: 34,359,738,368 (32.0 GiB)
CPU Base Frequency: 2,304,008,096 Hz

Athlonxp

2023-09-22, 13:47:45

Version 0.8.2 Build 9523 (Released: September 21, 2023)

Fixed detection of newer instructions sets like APX and AVX10.

This bug has no functional effect on the program since y-cruncher does not use these newer instruction sets yet.

http://www.numberworld.org/y-cruncher

:D

GaryX

2023-09-22, 16:13:08

5950x default, Ram @3800mhz Cl 16-22-22-43 1T

Total Computation Time: 113.419 seconds ( 1.890 minutes )
Start-to-End Wall Time: 114.119 seconds ( 1.902 minutes )

CPU Utilization: 99.99 % + 0.00 % kernel overhead
Multi-core Efficiency: 3.12 % + 0.00 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.8.2.9523 (Windows/19-ZN2 ~ Kagari)
Processor(s): AMD Ryzen 9 5950X 16-Core Processor
Topology: 32 threads / 16 cores / 1 socket / 1 NUMA node
Physical Memory: 68,719,476,736 (64.0 GiB)
CPU Base Frequency: 3,400,022,848 Hz

Total Computation Time: 11.494 seconds ( 0.192 minutes )
Start-to-End Wall Time: 11.950 seconds ( 0.199 minutes )

CPU Utilization: 3039.10 % + 5.03 % kernel overhead
Multi-core Efficiency: 94.97 % + 0.16 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.8.2.9523 (Windows/19-ZN2 ~ Kagari)
Processor(s): AMD Ryzen 9 5950X 16-Core Processor
Topology: 32 threads / 16 cores / 1 socket / 1 NUMA node
Physical Memory: 68,719,476,736 (64.0 GiB)
CPU Base Frequency: 3,400,012,512 Hz

Athlonxp

2023-12-07, 12:19:43

Version 0.8.3 Build 9531 (Released: December 5, 2023)

Release Date Version Changes
December 5, 2023 v0.8.3.9531

Windows + Linux Bug Fixes:
Fixed an issue that prevented the program from working on Windows 7.
Fixed a potentially serious issue that may cause incorrect computation*.
*This is caused by a bug in the parallel carry propagation for the VT3 and N63 algorithms. While the issue has never appeared in actual computations or even internal regression tests, it was found while refactoring the relevant code for v0.8.4.

The fix for v0.8.3 is to disable the parallelism with a proper fix coming in v0.8.4. Performance impact should be negligible as it only becomes performance critical during pathological carryout which is extremely rare and does not happen for regular Pi benchmarks.

December 2, 2023 v0.8.3.9530

Windows + Linux
Part 3 of the ongoing rewrites.

As with v0.8.2, this release has major intrusive changes to swap mode. If you will be attempting a long running computation (such as a Pi record), it is strongly recommended to test things at scale before attempting the full computation. This version makes major changes to the software raid and the checkpoint restart - both of which are critical to world record attempts.

There are no changes in this release that are expected to affect competitive benchmarking or hardware reviews. The performance of in-memory Pi computations remains unchanged from v0.8.2 and thus benchmarks can be compared across versions.

Math Changes:

Added two new fastest formulas for Zeta(3) by Jorge Zuniga.
Added a new 2nd fastest formula for Catalan's constant by Jorge Zuniga.
Added two new formulas for Lemniscate by Jorge Zuniga.
Lots of new custom formulas! Zeta(5), Gamma(1/3), and Gamma(1/4) have new pairs of fastest formulas.
InvNthRoot for custom formulas is now faster if the input is a small integer.
Removed all old formulas for Zeta(3).
Removed all old formulas for Catalan's constant except for Pilehood-short.
Removed the ArcSinlemn-based formulas for Lemniscate by Gauss and Sebah.
Removed ArcSinlemn() from the custom formulas.
Infrastructure Changes:

Removed the VST algorithm.
Binaries are now smaller due to the removal of nearly 250,000 lines of code. (consisting of the HNT, N32, N64, VST, and C17 algorithms)
The Disk Raid 0 framework for swap mode now has optimizations for SSDs.
The Disk Raid 0 framework now supports I/O parallelism - including between reads and writes. This can increase utilization of storage devices with independent read and write channels.
Removed the legacy RAID 0+3 framework.
On Windows, swap files are now read-protected to non-adminstrators to reduce the risk of leaking raw device data from SetFileValidData().
Swap mode now supports keeping multiple checkpoints in a zero-overhead manner. If a new checkpoint contains all the files from an older checkpoint, that older checkpoint will not be deleted yet. This means there can be multiple resume points should be the program get interrupted. If the latest checkpoint doesn't work, you may be able to resume from an older checkpoint if it's available.
The guide for swap mode has been updated to reflect the new changes.

Bug Fixes:

Untested fix for an issue in Linux where thread-affinities may not always work.
Fixed an issue where base conversion can fail for certain "short" numbers.
October 13, 2023 v0.8.2.9524

Windows + Linux
Fixed a serious bug in swap mode where a large multiplication with a lot of memory may fail.

http://www.numberworld.org/y-cruncher/version_history.html

:D

Darkman.X

2023-12-07, 18:35:59

Hahahaha, your *modern* Intel chip doesn't have AVX512. Too bad...

Ich fühle mich gemobbt :frown:

-----------------------------------------------------------------------

i9-14900K @ Stock & AVX-Offset = 0
DDR5-6400 ; 32-40-40-84-2T

SC:
Total Computation Time: 81.239 seconds ( 1.354 minutes )
Start-to-End Wall Time: 81.715 seconds ( 1.362 minutes )
Start Time: Thu Dec 7 18:30:13 2023
End Time: Thu Dec 7 18:31:34 2023

Total Computation Time: 81.239 seconds ( 1.354 minutes )
Start-to-End Wall Time: 81.715 seconds ( 1.362 minutes )

CPU Utilization: 26.85 % + 0.02 % kernel overhead
Multi-core Efficiency: 0.84 % + 0.00 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.8.3.9531 (Windows/14-BDW ~ Kurumi)
Processor(s): Intel(R) Core(TM) i9-14900K
Topology: 32 threads / 24 cores / 1 socket / 1 NUMA node
Physical Memory: 68,719,476,736 (64.0 GiB)
CPU Base Frequency: 3,187,215,471 Hz

MC:
Total Computation Time: 8.239 seconds ( 0.137 minutes )
Start-to-End Wall Time: 8.566 seconds ( 0.143 minutes )
Start Time: Thu Dec 7 18:28:14 2023
End Time: Thu Dec 7 18:28:23 2023

Total Computation Time: 8.239 seconds ( 0.137 minutes )
Start-to-End Wall Time: 8.566 seconds ( 0.143 minutes )

CPU Utilization: 1352.43 % + 1.52 % kernel overhead
Multi-core Efficiency: 42.26 % + 0.05 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.8.3.9531 (Windows/14-BDW ~ Kurumi)
Processor(s): Intel(R) Core(TM) i9-14900K
Topology: 32 threads / 24 cores / 1 socket / 1 NUMA node
Physical Memory: 68,719,476,736 (64.0 GiB)
CPU Base Frequency: 3,187,219,728 Hz

MORPHiNE

2023-12-07, 19:47:04

Tuning: Windows/22-ZN4 ~ Kizuna - Zen 4 Raphael (x64 AVX512-GFNI)

Version: 0.8.3.9531 (Windows/22-ZN4 ~ Kizuna)
Processor(s): AMD Ryzen 9 7950X 16-Core Processor
Topology: 32 threads / 16 cores / 1 socket / 1 NUMA node
Physical Memory: 68,719,476,736 (64.0 GiB)
CPU Base Frequency: 4,491,480,960 Hz

CO -30
PPT 230W
PBO +100
DDR5-6000 CL32-38-38-38-96-1T

SC 500M:

Total Computation Time: 70.244 seconds ( 1.171 minutes )
Start-to-End Wall Time: 70.909 seconds ( 1.182 minutes )

CPU Utilization: 98.12 % + 0.00 % kernel overhead
Multi-core Efficiency: 3.07 % + 0.00 % kernel overhead

MC 500M:

Total Computation Time: 7.394 seconds ( 0.123 minutes )
Start-to-End Wall Time: 7.730 seconds ( 0.129 minutes )

CPU Utilization: 1003.73 % + 1.48 % kernel overhead
Multi-core Efficiency: 31.37 % + 0.05 % kernel overhead

Nuon

2023-12-07, 21:23:18

Version: 0.8.3.9531 (Windows/19-ZN2 ~ Kagari)
Processor(s): AMD Ryzen 9 5900X 12-Core Processor
Topology: 24 threads / 12 cores / 1 socket / 1 NUMA node
Physical Memory: 34,359,738,368 (32.0 GiB)
CPU Base Frequency: 3,693,071,232 Hz

PPT 87W
DDR4 3200

SC 500M:

Total Computation Time: 116.489 seconds ( 1.941 minutes )
Start-to-End Wall Time: 117.149 seconds ( 1.952 minutes )

CPU Utilization: 99.71 % + 0.00 % kernel overhead
Multi-core Efficiency: 4.15 % + 0.00 % kernel overhead

MC 500M:

Total Computation Time: 15.124 seconds ( 0.252 minutes )
Start-to-End Wall Time: 15.581 seconds ( 0.260 minutes )

CPU Utilization: 1506.03 % + 0.93 % kernel overhead
Multi-core Efficiency: 62.75 % + 0.04 % kernel overhead

PPT 142W
CO -24
DDR4 3200

SC 500M:

Total Computation Time: 113.824 seconds ( 1.897 minutes )
Start-to-End Wall Time: 114.494 seconds ( 1.908 minutes )

CPU Utilization: 99.61 % + 0.00 % kernel overhead
Multi-core Efficiency: 4.15 % + 0.00 % kernel overhead

MC 500M:

Total Computation Time: 12.998 seconds ( 0.217 minutes )
Start-to-End Wall Time: 13.452 seconds ( 0.224 minutes )

CPU Utilization: 1423.74 % + 0.48 % kernel overhead
Multi-core Efficiency: 59.32 % + 0.02 % kernel overhead

Saugbär

2023-12-23, 23:31:07

Version: 0.8.3.9532 (Windows/18-CNL ~ Shinoa)
Processor(s): 11th Gen Intel(R) Core(TM) i7-11800H @ 2.30GHz
Topology: 16 threads / 8 cores / 1 socket / 1 NUMA node
Physical Memory: 34,359,738,368 (32.0 GiB)
CPU Base Frequency: 2,304,029,184 Hz

SC 500M:
Total Computation Time: 90.641 seconds ( 1.511 minutes )
Start-to-End Wall Time: 91.604 seconds ( 1.527 minutes )

CPU Utilization: 99.90 % + 0.00 % kernel overhead
Multi-core Efficiency: 6.24 % + 0.00 % kernel overhead

MC 500M:
Total Computation Time: 14.989 seconds ( 0.250 minutes )
Start-to-End Wall Time: 15.610 seconds ( 0.260 minutes )

CPU Utilization: 1416.22 % + 7.51 % kernel overhead
Multi-core Efficiency: 88.51 % + 0.47 % kernel overhead

Hahahaha, your *modern* Intel chip doesn't have AVX512. Too bad...

Gehört damit meine CPU zum Alteisen?

Phlox

2023-12-28, 12:37:08

mal mein Notebook :)

SC:

Total Computation Time: 183.788 seconds ( 3.063 minutes )
Start-to-End Wall Time: 185.166 seconds ( 3.086 minutes )

CPU Utilization: 98.27 % + 0.03 % kernel overhead
Multi-core Efficiency: 6.14 % + 0.00 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.8.3.9532 (Windows/19-ZN2 ~ Kagari)
Processor(s): AMD Ryzen 7 PRO 6850H with Radeon Graphics
Topology: 16 threads / 8 cores / 1 socket / 1 NUMA node
Physical Memory: 51,539,607,552 (48.0 GiB)
CPU Base Frequency: 3,194,145,280 Hz

MC:
Total Computation Time: 25.110 seconds ( 0.419 minutes )
Start-to-End Wall Time: 26.427 seconds ( 0.440 minutes )

CPU Utilization: 1315.87 % + 8.09 % kernel overhead
Multi-core Efficiency: 82.24 % + 0.51 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.8.3.9532 (Windows/19-ZN2 ~ Kagari)
Processor(s): AMD Ryzen 7 PRO 6850H with Radeon Graphics
Topology: 16 threads / 8 cores / 1 socket / 1 NUMA node
Physical Memory: 51,539,607,552 (48.0 GiB)
CPU Base Frequency: 3,194,138,112 Hz

Achill

2023-12-28, 13:30:58

Gute Idee, hab mein HP Firefly G10 auch mal vermessen:

SC - 500M

Start Time: Thu Dec 28 13:21:49 2023
End Time: Thu Dec 28 13:23:11 2023

Total Computation Time: 81.165 seconds ( 1.353 minutes )
Start-to-End Wall Time: 81.954 seconds ( 1.366 minutes )

CPU Utilization: 99.89 % + 0.00 % kernel overhead
Multi-core Efficiency: 6.24 % + 0.00 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.8.3.9531 (Linux/22-ZN4 ~ Kizuna)
Processor(s): AMD Ryzen 7 PRO 7840HS w/ Radeon 780M Graphics
Topology: 16 threads / 8 cores / 1 socket / 1 NUMA node
Usable Memory: 32,893,464,576 (30.6 GiB)
CPU Base Frequency: 3,793,105,296 Hz

Validation File: Pi - 20231228-132311.txt

---

MC - 500M

Start Time: Thu Dec 28 13:25:03 2023
End Time: Thu Dec 28 13:25:17 2023

Total Computation Time: 14.357 seconds ( 0.239 minutes )
Start-to-End Wall Time: 14.810 seconds ( 0.247 minutes )

CPU Utilization: 1461.82 % + 4.32 % kernel overhead
Multi-core Efficiency: 91.36 % + 0.27 % kernel overhead

Last Decimal Digits: Pi
3896531789 0364496761 5664275325 5483742003 7847987772 : 499,999,950
5002477883 0364214864 5906800532 7052368734 3293261427 : 500,000,000

Spot Check: Good through 500,000,000

Version: 0.8.3.9531 (Linux/22-ZN4 ~ Kizuna)
Processor(s): AMD Ryzen 7 PRO 7840HS w/ Radeon 780M Graphics
Topology: 16 threads / 8 cores / 1 socket / 1 NUMA node
Usable Memory: 32,893,464,576 (30.6 GiB)
CPU Base Frequency: 3,792,975,168 Hz

Validation File: Pi - 20231228-132517.txt

---

[..]
Gehört damit meine CPU zum Alteisen?

Jain, bei y-cruncher (wie auch anderen Benchmarks) muss man wissen bzw. eigentlich beim Benchmark mit beschrieben sein, was gemessen wird und was ggf. mit Einfluss haben kann. Bei y-cruncher ist es die Memory Bandbreite mit von starker Relevanz (und Caches können nicht helfen, weil das Dataset schon zu groß ist). Da neue CPUs i.d.R. auch schnelleren RAM unterstützen, muss diese nicht unbedingt auch im gleichen Maßen schneller Rechnen sondern ggf. war vorher schon der Vorgänger Bandbreiten limitiert. Die neuen AMD & Intel CPUs machen hier ggf. einfach solch straken Sprünge, weil diese mit DDR5 daher kommen und dieser mehr Bandbreite bietet ...

Siehe:

Because of the memory-intensive nature of computing Pi and other constants, y-cruncher needs a lot of memory bandwidth to perform well. In fact, the program has been noticably memory bound on nearly all high-end desktops since 2012 as well as the majority of multi-socket systems since at least 2006.

Saugbär

2024-02-27, 04:31:28

Neue Version: 0.8.4.9538
Ich vermute mal, die Optimierungen von Windows 10 zeigen Wirkung.
Selbst der Windows Explorer ist beim Kopiren von großen daten Schneller geworden.

Version: 0.8.4.9538 (Windows/18-CNL ~ Shinoa)
Processor(s): 11th Gen Intel(R) Core(TM) i7-11800H @ 2.30GHz
Topology: 16 threads / 8 cores / 1 socket / 1 NUMA node
Physical Memory: 34,359,738,368 (32.0 GiB)
CPU Base Frequency: 2,304,018,112 Hz

SC 500
Total Computation Time: 81.033 seconds ( 1.351 minutes )
Start-to-End Wall Time: 82.019 seconds ( 1.367 minutes )

CPU Utilization: 99.84 % + 0.02 % kernel overhead
Multi-core Efficiency: 6.24 % + 0.00 % kernel overhead
MC 500
Total Computation Time: 13.861 seconds ( 0.231 minutes )
Start-to-End Wall Time: 14.537 seconds ( 0.242 minutes )

CPU Utilization: 1515.46 % + 2.14 % kernel overhead
Multi-core Efficiency: 94.72 % + 0.13 % kernel overhead

Vergleich