benchmark new smartphones:

Discussion of anything and everything relating to chess playing software and machines.

Moderators: hgm, Rebel, chrisw

royb
Posts: 546
Joined: Thu Mar 09, 2006 12:53 am

Re: benchmark new smartphones:

Post by royb »

Jhoravi wrote:
kinderchocolate wrote:iPhone 7 Plus - 2556.2kN/s
iPhone 7 has 4 cores. Does it mean only 2 cores can be seen at a time?
The article I read (cannot remember where now, sorry) said that the iPhone 7 has 2 fast cores and 2 slow cores. The slow cores are for handling routine background stuff that do not require a fast core to accomplish. That allows those functions to run without consuming much battery power.
Jhoravi
Posts: 291
Joined: Wed May 08, 2013 6:49 am

Re: benchmark new smartphones:

Post by Jhoravi »

royb wrote:
Jhoravi wrote:
kinderchocolate wrote:iPhone 7 Plus - 2556.2kN/s
iPhone 7 has 4 cores. Does it mean only 2 cores can be seen at a time?
The article I read (cannot remember where now, sorry) said that the iPhone 7 has 2 fast cores and 2 slow cores. The slow cores are for handling routine background stuff that do not require a fast core to accomplish. That allows those functions to run without consuming much battery power.
That's the same philosophy as QuadCore Snapdragon 820. It has 2 fast cores and 2 slow cores yet Droidfish can use all 4 cores. Maybe iOS is less tolerant in that regard
Werewolf
Posts: 1848
Joined: Thu Sep 18, 2008 10:24 pm

Re: benchmark new smartphones:

Post by Werewolf »

Everyone should be amazed by the speed of the iPhone 7. 2500 Kn/s on only two cores is far more impressive that the same nps on an 8 core phone.

Also consider this: I think the iPhone Stockfish is Stockfish 6 (correct me if I'm wrong people). I tested Stockfish 6 on my Surface Pro 4 - which is a dual core Skylake processor @ 3.2 GHz - and it also gets around 2500 Kn/s.

So what we're saying here - for chess - is that the iPhone 7 is as fast as a dual core Skylake @ 3.2 Ghz.

Considering the iPhone 7 surely runs at a lower clockspeed - I am blown away by this. :shock:
User avatar
Laskos
Posts: 10948
Joined: Wed Jul 26, 2006 10:21 pm
Full name: Kai Laskos

Re: benchmark new smartphones:

Post by Laskos »

Werewolf wrote:Everyone should be amazed by the speed of the iPhone 7. 2500 Kn/s on only two cores is far more impressive that the same nps on an 8 core phone.

Also consider this: I think the iPhone Stockfish is Stockfish 6 (correct me if I'm wrong people). I tested Stockfish 6 on my Surface Pro 4 - which is a dual core Skylake processor @ 3.2 GHz - and it also gets around 2500 Kn/s.

So what we're saying here - for chess - is that the iPhone 7 is as fast as a dual core Skylake @ 3.2 Ghz.

Considering the iPhone 7 surely runs at a lower clockspeed - I am blown away by this. :shock:
And likely consumes less power. Amazing indeed.
User avatar
Eelco de Groot
Posts: 4596
Joined: Sun Mar 12, 2006 2:40 am
Full name:   

Re: benchmark new smartphones:

Post by Eelco de Groot »

2 cores means less heat I suppose. The compartment is sealed so I was thinking, does not the air inside heat up? There seems to be something like a barometric vent, I have not investigated. But I could not find much about any cooling mechanisms they use for these phones, where Samsungs s7 has a heatpipe. Not that it much will help if the s7 battery overheats or explodes... With i7 it seems you have to watch out for hissing sounds when under load (or loading an app?), nobody really knows what it is exactly Apple's won't officially comment but the person who mentioned it first got a new one. If something inside or near near the A10 starts vibrating, that could be bad for the thermal paste I suppose, especially in the long run?
UnstoppableDrew

It’s full of dream snakes. You need an empty mirrorcatch box, a Clay Man, some supplies, and a couple Foxfire candles to make a serpent trap, then you can trap them and get rid of them.
Posted on Sep 19, 2016 | 9:30 AM
DJ CERLA

Not the first time it happens on first-batch iPhone releases, it happened on the iPhone 5 for example.

It’s the RF shield of the DAC misaligned, so the processor leaks radio waves into the loudspeakers. Apple is exchanging the defective units.
Posted on Sep 18, 2016 | 4:59 PM
Debugging is twice as hard as writing the code in the first
place. Therefore, if you write the code as cleverly as possible, you
are, by definition, not smart enough to debug it.
-- Brian W. Kernighan
h1a8
Posts: 512
Joined: Fri Jun 04, 2010 7:23 am

Re: benchmark new smartphones:

Post by h1a8 »

Werewolf wrote:Everyone should be amazed by the speed of the iPhone 7. 2500 Kn/s on only two cores is far more impressive that the same nps on an 8 core phone.

Also consider this: I think the iPhone Stockfish is Stockfish 6 (correct me if I'm wrong people). I tested Stockfish 6 on my Surface Pro 4 - which is a dual core Skylake processor @ 3.2 GHz - and it also gets around 2500 Kn/s.

So what we're saying here - for chess - is that the iPhone 7 is as fast as a dual core Skylake @ 3.2 Ghz.

Considering the iPhone 7 surely runs at a lower clockspeed - I am blown away by this. :shock:
wait a minute. I thought it used 4 cores. Why is it only using 2 cores and why is it advertised as 4 cores?


One last question: it two phones achieve 2500kn/s on a certain chess app and engine but one uses 2 core and the other uses 4 core then which is stronger?
kinderchocolate
Posts: 454
Joined: Mon Nov 01, 2010 6:55 am
Full name: Ted Wong

Re: benchmark new smartphones:

Post by kinderchocolate »

Guys. I have no idea how many cores the phone was using. All I saw was the NPS number. There's a possibility that not all the cores were used.
Werewolf
Posts: 1848
Joined: Thu Sep 18, 2008 10:24 pm

Re: benchmark new smartphones:

Post by Werewolf »

@ Leon
I think it has two "BIG" cores (i.e. fast cores which are high performance but also power hungry) and two "little" cores (i.e. slow cores which can run background processes and sip little power).

If two engines produce the same nps and one does it on two cores and the other uses 4, then the one with 2 is stronger. The reason is search efficiency gets worse as more cores are added.
NPS by itself, without reference to the number of cores used, is fairly meaningless.
Last edited by Werewolf on Thu Sep 29, 2016 10:45 am, edited 3 times in total.
Werewolf
Posts: 1848
Joined: Thu Sep 18, 2008 10:24 pm

Re: benchmark new smartphones:

Post by Werewolf »

kinderchocolate wrote:Guys. I have no idea how many cores the phone was using. All I saw was the NPS number. There's a possibility that not all the cores were used.
Do you know when we'll see a nps counter on Smallfish?
kinderchocolate
Posts: 454
Joined: Mon Nov 01, 2010 6:55 am
Full name: Ted Wong

Re: benchmark new smartphones:

Post by kinderchocolate »

Werewolf wrote:
kinderchocolate wrote:Guys. I have no idea how many cores the phone was using. All I saw was the NPS number. There's a possibility that not all the cores were used.
Do you know when we'll see a nps counter on Smallfish?
Carl, I don't have a plan to support NPS counter. We'll should stick with the Stockfish app.