Smartphone vs Desktop challenge
Question is whether Stockfish 7 on LG G3 will beat Houdini 4 Pro on Pentium E5200.
LG G3 is capable for about 1,400 Knp/s
Pentium E2000 is in the 2,000 range for Stockfish/Komodo and fairly in the 3,000 range for semi-obsolete H4 Pro.
benchmark new smartphones: (Old Thread)
Moderators: hgm, Rebel, chrisw
-
- Posts: 2821
- Joined: Fri Sep 25, 2015 9:38 pm
- Location: Sortland, Norway
-
- Posts: 18748
- Joined: Thu Mar 09, 2006 6:40 pm
- Location: US of Europe, germany
- Full name: Thorsten Czub
Re: Budget phone
S7 after 2', default hash size, 2927.Lion wrote:And what about the Samsung galaxy s7 ?
Began with 3600 but decreased after a while to this number.
What seems like a fairy tale today may be reality tomorrow.
Here we have a fairy tale of the day after tomorrow....
Here we have a fairy tale of the day after tomorrow....
-
- Posts: 2949
- Joined: Mon May 05, 2008 12:16 pm
- Location: Bordeaux (France)
- Full name: Julien Marcel
Re: benchmark new smartphones:
Here comes the updated charts.
The Galaxy S7 Edge is the European version, with the new Exynos. I set Stockfish to 8 threads, gave it 2GB of hash and let it run for one minute.
I'd be curious to know the bench results of the American version, with the Snapdragon. It should be faster than the Exynos, I believe.
The Galaxy S7 Edge is the European version, with the new Exynos. I set Stockfish to 8 threads, gave it 2GB of hash and let it run for one minute.
I'd be curious to know the bench results of the American version, with the Snapdragon. It should be faster than the Exynos, I believe.
Code: Select all
PC mit i5-3550 (4 cores @3.9 Ghz) 6.332.000
PC mit i7-4700mq ( @2.4 Ghz) 5.492.000
Samsung S7 Edge (Exynos, 8 cores 64 bits) 3.036.000 < NEW
Samsung S6 Edge + (8 cores 64 Bit Exynos) 2.505.000
Samsung Galaxy Note 5 2.500.000 < NEW
iPad Pro (A9X, 2 cores @2.26 Ghz 64 bits) 2.480.000
Samsung S6 (8 cores 64 Bit Exynos) 2.042.000
iPhone 6s 2.024.000
Ipad Air 2 (3 cores Apple A8X + M8 64 bits 1.5 Ghz) 1.970.000
Xiaomi Redmi Note2 (MTK6795 Helio x10) 1.940.000
Lenovo Vibe X2 (8 cores MTK6595m 2.0 Ghz) 1.851.000
Cube T9 (8 cores 2.0Ghz ) 1.837.000
Samsung Note4 (Exynos 5433 8 cores 1.9/1.3 Ghz 64Bit) 1.520.000
LG G3 1.400.000 < NEW
Xiaomi MiPad (4 cores Tegra K1 32 bits) 1.357.000
Huawei Ascend Mate 7 (8 cores Kirin 925 1.8 Ghz) 1.293.000
iPad Mini 4 (2 cores @1.5 GHz, 64 bits) 1.290.000
IPhone 6 (2 cores Apple A8 64-bits 1,38 GHz) 1.270.000
Huawei Honor 6 (8 cores Kirin 920 1.7 Ghz) 1.258.000
One plus two (8 cores 810 64Bit) 1.242.000
Teclast P98HD (8 cores MTK8392 2 Ghz) 1.241.000
ELephone P8 (8 cores MTK6592 1,7 Ghz) 1.240.000
TCL Idol X+ S960T ( 8 cores 2.0 GHz) 1.226.000
Ipad Air (2 cores Apple A7 64 bits 1.4 Ghz) 1.218.000
Onda V989 (8 cores A80T 2 Ghz) 1.185.000
Iocean X8 (8 cores MTK6592 1.7GHz) 1.163.000
Iphone 5s (2 64bit cores 1.3 ghz) 1.152.000
Efox Smart E5 (8 Cores MTK6592 1,7GHz) 1 138.000
Jiayu G4S (8 cores MTK6592 1,7GHz) 1.132.000
iPad Mini 2 (2 cores Apple A7 64 bits 1.3 GHz) 1.128.000
Cube Talk 9x (8 cores MTK8392 1.7 Ghz) 1.124.000
TCL Idol X+ S960T ( 8 cores 2.0 GHz) 1.112.000
PIPO P1 (4 cores RK3288 1.8 Ghz) 1.108.000
Goophone M8 (8 cores MTK8392 1.7 Ghz) 1.100.000
Zopo ZP998 (8 cores MTK6592 1.7 GHz ) 1.100.000
Coolpad F1 (8 cores MTK6592 1.7 GHz) 1.087.000
Star Ulefone U9592 (8 cores 1.7 Ghz) 1.080.000
Motorola X play (8 cores 615 but only 32bit OS) 1.077.000
Teclast P90HD (4 cores RK3288 1.8 Ghz) 1.072.000
THL 5000 (8 cores MTK6592 2.0 Ghz) 1.069.000
ASUS Transformer TF701t (4 cores ) 1.054.000
Elephone P2000 (8 cores MTK6592 1.7 Ghz) 1.037.000
Pipo T9 (8 cores MTK6592 1.7 Ghz) 1.021.000
Samsung Note10.1 2014 (4cores exynos) 1.014.000
Lenovo Miix 2 10 (4 cores, x86 Atom Bay) 915.000
Pipo M9pro (4 cores RK3188 1.6 Ghz) 809.000
Oneplus One (4 cores Snapdragon S801 2.5 Ghz) 784.000
Samsung Galaxy Note2 (4 cores Exynos 4412 1.6 GHz) 714.000
Samsung Galaxy Note 8.0 (4 cores Exynos 4412 1.6 GHz) 714.000
Sony Xperia Z3 (4 cores Snapdragon S801 2.5 Ghz) 713.000
Xiaomi Mi3 (4 cores Snapdragon S801 2.26 Ghz) 711.000
Xiaomi Mi4 (4 cores Snapdragon S801 2.5 Ghz) 707.000
ASUS Transformer TF300T (4 cores) 661.000
HTC One M8 (4 cores Snapdragon S801 2.26 Ghz) 650.000
Samsung Galaxy Note 3 (4 cores Snapdragon S800 2.3 GHz) 648.000
Asus memopad 10.1 (4 cores RK3188 1.6 GHz) 644.000
One Plus One 643.000
Samsung Galaxy S5 (4 cores Snapdragon S801 2.5 Ghz) 633.000
LG G3 (4 cores Snapdragon S801 2.5 Ghz) 613.000
Sony Xperia Z1 (4 cores Snapdragon S800 2.2 Ghz) 602.000
Asus Infinity tf700 (4 cores) 590.000
Note 3 (4 cores) 581.000
Galaxy S3 (4 cores) 574.000
Cubot One (4 core MTK 6589T@ 4x1.5Ghz) 568.000
BQ Aquaris 5.7 5.7 (4 cores MTK6589T 1.5 Ghz) 566.000
LG G2 556.000
Pomp c6 (4 cores MT6589T) 553.000
Jiayu G3ST (4 cores MTK6589T 1,5 Ghz) 548.000
Acer Liquid S1 (4 cores MTK6589T 1.5 Ghz) 545.000
Nexus 7 Wifi (Grouper) (4 cores Tegra 4 1,3 GHz) 545.000
Zopo ZP700 (4 cores MTK6582 1,3 GHz) 536.000
Timmy T1 (4 cores MT6589T 1.5 GHz) 529.000
Pipo max M9 (4x cortex a9 1.6 ghz) 526.000
LG Optimus 4xHD (4 cores) 521.000
ZTE geek v975 (2+2HT intel atom) 511.000
iPad4 510.000
Nexus 10 (2 cores) 510.000
Google Nexus 5 (4 cores) 508.000
Asus Zenfone 6 (2 cores + Hyperthread Intel z2580) 497.000
Amoi N828 (4 cores MTK6589 @ 4x1,2GHz) 493.000
iPhone 5 (2 cores) 476.800
HTC one X tegra3 (4 cores) 470.000
Motorola G (4 cores) 460.000
google nexus 7 tablet pc (4 cores) 457.000
SamsungGalaxy S4(1.9Ghz,4 cores,1GBhash) 450.000
Asus Transformer Prime (4 threads) 440.435
Motorola G (2014) 4 cores 439.000
HTC one 438.000
Huawei P6 (4 cores K3V2E 1.5 Ghz) 427.000
Tablet HP 7.1 1201 (A7 Quad Core 1,0 Ghz) 410.000
Meizu MX3 (8 cores Exynos 5410) 410.000
Huawei P6 (Hi-SiliconK3V2 4x1.5) 405.000
Google Nexus4 (4 cores) 400.000
Xiaomi Mi2 386.000
Sony Xperia Z (4 cores) 376.000
B&N Nook HD+ (2 cores TI OMAP 4470 1,5 GHz) 371.000
Oppo Find 5 368.000
Dell Latitude (Core2duo T7600, 2.3 Ghz) 366.000
Samsung Galaxy 3 (2 core) 333.567
Galaxy Note 329.000
Raspberry Pi 2 (4 cores @ 900 MHz) 325.000
Trekstor Surftab 305.000
iPad mini 277.500
iPad3 277.000
Mbx Dongle Board g02 (2 cores AML8726-MX 1,2 GHz) 276.000
Ipad2 (2 cores) 274.000
Motorola Razr i (2 cores hyperthread) 271.000
Sony xperia S (2 cores) 259.000
Samsung Galaxy Nexus (2 cores TI OMAP 4460 1,2 GHz) 256.000
Tablet Rockchip RK3066 2core @1.6Ghz 250.000
Samsung Galaxy S2 253.000
Motorola X 253.000
Motorola Razr (Slimkat Android 4.4.2) 250.000
iPhone 4S (Apple A5) 225.500
Lenovo A660 (2 cores) 222.000
Advent Vega Tegra2 220.500
Sony Tablet S 218.000
Motorola Razr xt910 (2 cores) 216.000
Motorola Razr HD 212.000
LG Optimus Speed P990 (2 cores) 200.000
HTC one S qualcomm s4 (2 cores) 200.000
Sony Xperia P (2 cores) 196.000
Samsung Galaxy SIII 1.5GHz (2 Cores) 189.867
Motorola Razr i (1 core) 186.000
Nuu Nu1 (qualcom dualcore 1.7 Ghz) 142.000
samsung epic 141.000
HTC Flyer, 1.5 Ghz 140.000
Advent Vega Tablet (2 cores) 137.126
Dell Streak 133.000
Sony Xperia P (2 cores) 112.000
Samsung Vibrant 111.000
Samsung Galaxy Tab 108.500
LG Optimus 2x 102.000
HTC HD2 1 Ghz 1 core 94.000
HTC Desire S 90.000
Sony Xperia Ray 85.126
HTC Desire 84.000
iPhone 4 80.000
ipod touch 4 78.000
samsung galaxy s 70.000
7-inch Barnes and Noble Color 62.500
Sony PRS-T1 ebook-reader 53.817
iPhone 3GS 51.000
HTC Wildfire S 31.000
Android phone Qualcomm 600MHz (1 core) 25.750
Ipod touch 2nd gen 16.500
Palm Pre oc. 1Ghz (Webos1.4.5) 16.000
ZT-180 10,2" Pad 15.345
Palm Pre oc. 800mhz (Webos1.4.5) 13.000
APAD Rockchip 600mhz (android1.5) 10.000
Palm Pre 500mhz (Webos1.4.5) 8.000
"The only good bug is a dead bug." (Don Dailey)
[Blog: http://tinyurl.com/predateur ] [Facebook: http://tinyurl.com/fbpredateur ] [MacEngines: http://tinyurl.com/macengines ]
[Blog: http://tinyurl.com/predateur ] [Facebook: http://tinyurl.com/fbpredateur ] [MacEngines: http://tinyurl.com/macengines ]
-
- Posts: 18748
- Joined: Thu Mar 09, 2006 6:40 pm
- Location: US of Europe, germany
- Full name: Thorsten Czub
Re: benchmark new smartphones:
I don't think it is good to Change the hash size.
We already have problems enough with the different stockfish versions over a period of time, by changing hash you change another parameter.
Increasing hash, and decreasing time of measurement for the benchmark both
Advantages the engine, but what is it worth for ?
You have 3036 and I have 2927.
So it's not a big change overall.
We already have problems enough with the different stockfish versions over a period of time, by changing hash you change another parameter.
Increasing hash, and decreasing time of measurement for the benchmark both
Advantages the engine, but what is it worth for ?
You have 3036 and I have 2927.
So it's not a big change overall.
What seems like a fairy tale today may be reality tomorrow.
Here we have a fairy tale of the day after tomorrow....
Here we have a fairy tale of the day after tomorrow....
-
- Posts: 710
- Joined: Sat Dec 06, 2014 1:53 pm
Re: Budget phone
CCRL 40/40: +6−44=70, which is -114 elo H4 vs SF7Nordlandia wrote:Smartphone vs Desktop challenge
Question is whether Stockfish 7 on LG G3 will beat Houdini 4 Pro on Pentium E5200.
LG G3 is capable for about 1,400 Knp/s
Pentium E2000 is in the 2,000 range for Stockfish/Komodo and fairly in the 3,000 range for semi-obsolete H4 Pro.
this amount of ELO can be compensated about 4x time/speed, so I estimate H4 need CPU capable of SF7 @ 5 600 Knp/s to draw against SF7@LG_G3
With 1.5x speed advantage I predict compensation of 40elo, which still gives +75 elo advantage for SF7@LG_G3
P.S. another factor: H4 @ PC is capable of Syzygy-6, SF7@LG_G3 practically support only Syzygy-5. Have no idea how this can influence elo.
-
- Posts: 536
- Joined: Thu Mar 09, 2006 12:53 am
Re: benchmark new smartphones:
Julien,
Did you use Droidfish for this result? I have Droidfish with SF 7 as the engine and I get nowhere near what you see. I have the Snapdragon 820-based Galaxy S7 Edge and after one minute with 1 GB of Hash and 4 threads (supposed to be 4 cores on Snapdragon 820), I see this performance in NPS for the starting position: 1096K nodes per second.
I'm wondering if I've got something set up incorrectly with SF 7 that is causing this low a number compared to the result you posted. Yes, your CPU is Exynos 8-core but some have said performance tests have shown that the two are close and the Snapdragon 820 is even a bit faster in some tests.
Roy
Did you use Droidfish for this result? I have Droidfish with SF 7 as the engine and I get nowhere near what you see. I have the Snapdragon 820-based Galaxy S7 Edge and after one minute with 1 GB of Hash and 4 threads (supposed to be 4 cores on Snapdragon 820), I see this performance in NPS for the starting position: 1096K nodes per second.
I'm wondering if I've got something set up incorrectly with SF 7 that is causing this low a number compared to the result you posted. Yes, your CPU is Exynos 8-core but some have said performance tests have shown that the two are close and the Snapdragon 820 is even a bit faster in some tests.
Roy
-
- Posts: 18748
- Joined: Thu Mar 09, 2006 6:40 pm
- Location: US of Europe, germany
- Full name: Thorsten Czub
Re: benchmark new smartphones:
Snapdragon 820 has only 4 cores. Is a hot CPU and I guess exynos has bigger internal cache ?
What seems like a fairy tale today may be reality tomorrow.
Here we have a fairy tale of the day after tomorrow....
Here we have a fairy tale of the day after tomorrow....
-
- Posts: 10948
- Joined: Wed Jul 26, 2006 10:21 pm
- Full name: Kai Laskos
Re: benchmark new smartphones:
My guess is that SF was running on a single core. Snapdragon 820 should perform close or maybe even above Exynos.royb wrote:Julien,
Did you use Droidfish for this result? I have Droidfish with SF 7 as the engine and I get nowhere near what you see. I have the Snapdragon 820-based Galaxy S7 Edge and after one minute with 1 GB of Hash and 4 threads (supposed to be 4 cores on Snapdragon 820), I see this performance in NPS for the starting position: 1096K nodes per second.
I'm wondering if I've got something set up incorrectly with SF 7 that is causing this low a number compared to the result you posted. Yes, your CPU is Exynos 8-core but some have said performance tests have shown that the two are close and the Snapdragon 820 is even a bit faster in some tests.
Roy
-
- Posts: 536
- Joined: Thu Mar 09, 2006 12:53 am
Re: benchmark new smartphones:
Could it be that despite my setting the number of threads to 4, it was still using a single core? I do not know how to tell on the phone what is really going on when running SF 7 on it. Perhaps others with a Snapdragon 820 phone can test it and then we may learn more about this seemingly strange result.Laskos wrote:My guess is that SF was running on a single core. Snapdragon 820 should perform close or maybe even above Exynos.royb wrote:Julien,
Did you use Droidfish for this result? I have Droidfish with SF 7 as the engine and I get nowhere near what you see. I have the Snapdragon 820-based Galaxy S7 Edge and after one minute with 1 GB of Hash and 4 threads (supposed to be 4 cores on Snapdragon 820), I see this performance in NPS for the starting position: 1096K nodes per second.
I'm wondering if I've got something set up incorrectly with SF 7 that is causing this low a number compared to the result you posted. Yes, your CPU is Exynos 8-core but some have said performance tests have shown that the two are close and the Snapdragon 820 is even a bit faster in some tests.
Roy
-
- Posts: 10948
- Joined: Wed Jul 26, 2006 10:21 pm
- Full name: Kai Laskos
Re: benchmark new smartphones:
No way it's 1096K. In fact I hope it's above Exynos.royb wrote:Could it be that despite my setting the number of threads to 4, it was still using a single core? I do not know how to tell on the phone what is really going on when running SF 7 on it. Perhaps others with a Snapdragon 820 phone can test it and then we may learn more about this seemingly strange result.Laskos wrote:My guess is that SF was running on a single core. Snapdragon 820 should perform close or maybe even above Exynos.royb wrote:Julien,
Did you use Droidfish for this result? I have Droidfish with SF 7 as the engine and I get nowhere near what you see. I have the Snapdragon 820-based Galaxy S7 Edge and after one minute with 1 GB of Hash and 4 threads (supposed to be 4 cores on Snapdragon 820), I see this performance in NPS for the starting position: 1096K nodes per second.
I'm wondering if I've got something set up incorrectly with SF 7 that is causing this low a number compared to the result you posted. Yes, your CPU is Exynos 8-core but some have said performance tests have shown that the two are close and the Snapdragon 820 is even a bit faster in some tests.
Roy